| 1 245 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash: Hash algorithms under the crypto API * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_HASH_H #define _CRYPTO_HASH_H #include <linux/atomic.h> #include <linux/crypto.h> #include <linux/string.h> struct crypto_ahash; /** * DOC: Message Digest Algorithm Definitions * * These data structures define modular message digest algorithm * implementations, managed via crypto_register_ahash(), * crypto_register_shash(), crypto_unregister_ahash() and * crypto_unregister_shash(). */ /* * struct hash_alg_common - define properties of message digest * @digestsize: Size of the result of the transformation. A buffer of this size * must be available to the @final and @finup calls, so they can * store the resulting hash into it. For various predefined sizes, * search include/crypto/ using * git grep _DIGEST_SIZE include/crypto. * @statesize: Size of the block for partial state of the transformation. A * buffer of this size must be passed to the @export function as it * will save the partial state of the transformation into it. On the * other side, the @import function will load the state from a * buffer of this size as well. * @base: Start of data structure of cipher algorithm. The common data * structure of crypto_alg contains information common to all ciphers. * The hash_alg_common data structure now adds the hash-specific * information. */ #define HASH_ALG_COMMON { \ unsigned int digestsize; \ unsigned int statesize; \ \ struct crypto_alg base; \ } struct hash_alg_common HASH_ALG_COMMON; struct ahash_request { struct crypto_async_request base; unsigned int nbytes; struct scatterlist *src; u8 *result; /* This field may only be used by the ahash API code. */ void *priv; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct ahash_alg - asynchronous message digest definition * @init: **[mandatory]** Initialize the transformation context. Intended only to initialize the * state of the HASH transformation at the beginning. This shall fill in * the internal structures used during the entire duration of the whole * transformation. No data processing happens at this point. Driver code * implementation must not use req->result. * @update: **[mandatory]** Push a chunk of data into the driver for transformation. This * function actually pushes blocks of data from upper layers into the * driver, which then passes those to the hardware as seen fit. This * function must not finalize the HASH transformation by calculating the * final message digest as this only adds more data into the * transformation. This function shall not modify the transformation * context, as this function may be called in parallel with the same * transformation object. Data processing can happen synchronously * [SHASH] or asynchronously [AHASH] at this point. Driver must not use * req->result. * @final: **[mandatory]** Retrieve result from the driver. This function finalizes the * transformation and retrieves the resulting hash from the driver and * pushes it back to upper layers. No data processing happens at this * point unless hardware requires it to finish the transformation * (then the data buffered by the device driver is processed). * @finup: **[optional]** Combination of @update and @final. This function is effectively a * combination of @update and @final calls issued in sequence. As some * hardware cannot do @update and @final separately, this callback was * added to allow such hardware to be used at least by IPsec. Data * processing can happen synchronously [SHASH] or asynchronously [AHASH] * at this point. * @digest: Combination of @init and @update and @final. This function * effectively behaves as the entire chain of operations, @init, * @update and @final issued in sequence. Just like @finup, this was * added for hardware which cannot do even the @finup, but can only do * the whole transformation in one run. Data processing can happen * synchronously [SHASH] or asynchronously [AHASH] at this point. * @setkey: Set optional key used by the hashing algorithm. Intended to push * optional key used by the hashing algorithm from upper layers into * the driver. This function can store the key in the transformation * context or can outright program it into the hardware. In the former * case, one must be careful to program the key into the hardware at * appropriate time and one must be careful that .setkey() can be * called multiple times during the existence of the transformation * object. Not all hashing algorithms do implement this function as it * is only needed for keyed message digests. SHAx/MDx/CRCx do NOT * implement this function. HMAC(MDx)/HMAC(SHAx)/CMAC(AES) do implement * this function. This function must be called before any other of the * @init, @update, @final, @finup, @digest is called. No data * processing happens at this point. * @export: Export partial state of the transformation. This function dumps the * entire state of the ongoing transformation into a provided block of * data so it can be @import 'ed back later on. This is useful in case * you want to save partial result of the transformation after * processing certain amount of data and reload this partial result * multiple times later on for multiple re-use. No data processing * happens at this point. Driver must not use req->result. * @import: Import partial state of the transformation. This function loads the * entire state of the ongoing transformation from a provided block of * data so the transformation can continue from this point onward. No * data processing happens at this point. Driver must not use * req->result. * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @clone_tfm: Copy transform into new object, may allocate memory. * @halg: see struct hash_alg_common */ struct ahash_alg { int (*init)(struct ahash_request *req); int (*update)(struct ahash_request *req); int (*final)(struct ahash_request *req); int (*finup)(struct ahash_request *req); int (*digest)(struct ahash_request *req); int (*export)(struct ahash_request *req, void *out); int (*import)(struct ahash_request *req, const void *in); int (*setkey)(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_ahash *tfm); void (*exit_tfm)(struct crypto_ahash *tfm); int (*clone_tfm)(struct crypto_ahash *dst, struct crypto_ahash *src); struct hash_alg_common halg; }; struct shash_desc { struct crypto_shash *tfm; void *__ctx[] __aligned(ARCH_SLAB_MINALIGN); }; #define HASH_MAX_DIGESTSIZE 64 /* * Worst case is hmac(sha3-224-generic). Its context is a nested 'shash_desc' * containing a 'struct sha3_state'. */ #define HASH_MAX_DESCSIZE (sizeof(struct shash_desc) + 360) #define SHASH_DESC_ON_STACK(shash, ctx) \ char __##shash##_desc[sizeof(struct shash_desc) + HASH_MAX_DESCSIZE] \ __aligned(__alignof__(struct shash_desc)); \ struct shash_desc *shash = (struct shash_desc *)__##shash##_desc /** * struct shash_alg - synchronous message digest definition * @init: see struct ahash_alg * @update: see struct ahash_alg * @final: see struct ahash_alg * @finup: see struct ahash_alg * @digest: see struct ahash_alg * @export: see struct ahash_alg * @import: see struct ahash_alg * @setkey: see struct ahash_alg * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @clone_tfm: Copy transform into new object, may allocate memory. * @descsize: Size of the operational state for the message digest. This state * size is the memory size that needs to be allocated for * shash_desc.__ctx * @halg: see struct hash_alg_common * @HASH_ALG_COMMON: see struct hash_alg_common */ struct shash_alg { int (*init)(struct shash_desc *desc); int (*update)(struct shash_desc *desc, const u8 *data, unsigned int len); int (*final)(struct shash_desc *desc, u8 *out); int (*finup)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*digest)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*export)(struct shash_desc *desc, void *out); int (*import)(struct shash_desc *desc, const void *in); int (*setkey)(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_shash *tfm); void (*exit_tfm)(struct crypto_shash *tfm); int (*clone_tfm)(struct crypto_shash *dst, struct crypto_shash *src); unsigned int descsize; union { struct HASH_ALG_COMMON; struct hash_alg_common halg; }; }; #undef HASH_ALG_COMMON struct crypto_ahash { bool using_shash; /* Underlying algorithm is shash, not ahash */ unsigned int statesize; unsigned int reqsize; struct crypto_tfm base; }; struct crypto_shash { unsigned int descsize; struct crypto_tfm base; }; /** * DOC: Asynchronous Message Digest API * * The asynchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_AHASH (listed as type "ahash" in /proc/crypto) * * The asynchronous cipher operation discussion provided for the * CRYPTO_ALG_TYPE_SKCIPHER API applies here as well. */ static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_ahash, base); } /** * crypto_alloc_ahash() - allocate ahash cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for an ahash. The returned struct * crypto_ahash is the cipher handle that is required for any subsequent * API invocation for that ahash. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type, u32 mask); struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *tfm); static inline struct crypto_tfm *crypto_ahash_tfm(struct crypto_ahash *tfm) { return &tfm->base; } /** * crypto_free_ahash() - zeroize and free the ahash handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_ahash(struct crypto_ahash *tfm) { crypto_destroy_tfm(tfm, crypto_ahash_tfm(tfm)); } /** * crypto_has_ahash() - Search for the availability of an ahash. * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash * @type: specifies the type of the ahash * @mask: specifies the mask for the ahash * * Return: true when the ahash is known to the kernel crypto API; false * otherwise */ int crypto_has_ahash(const char *alg_name, u32 type, u32 mask); static inline const char *crypto_ahash_alg_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_name(crypto_ahash_tfm(tfm)); } static inline const char *crypto_ahash_driver_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm)); } /** * crypto_ahash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_ahash_blocksize(struct crypto_ahash *tfm) { return crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm)); } static inline struct hash_alg_common *__crypto_hash_alg_common( struct crypto_alg *alg) { return container_of(alg, struct hash_alg_common, base); } static inline struct hash_alg_common *crypto_hash_alg_common( struct crypto_ahash *tfm) { return __crypto_hash_alg_common(crypto_ahash_tfm(tfm)->__crt_alg); } /** * crypto_ahash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * * Return: message digest size of cipher */ static inline unsigned int crypto_ahash_digestsize(struct crypto_ahash *tfm) { return crypto_hash_alg_common(tfm)->digestsize; } /** * crypto_ahash_statesize() - obtain size of the ahash state * @tfm: cipher handle * * Return the size of the ahash state. With the crypto_ahash_export() * function, the caller can export the state into a buffer whose size is * defined with this function. * * Return: size of the ahash state */ static inline unsigned int crypto_ahash_statesize(struct crypto_ahash *tfm) { return tfm->statesize; } static inline u32 crypto_ahash_get_flags(struct crypto_ahash *tfm) { return crypto_tfm_get_flags(crypto_ahash_tfm(tfm)); } static inline void crypto_ahash_set_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_ahash_tfm(tfm), flags); } static inline void crypto_ahash_clear_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_ahash_tfm(tfm), flags); } /** * crypto_ahash_reqtfm() - obtain cipher handle from request * @req: asynchronous request handle that contains the reference to the ahash * cipher handle * * Return the ahash cipher handle that is registered with the asynchronous * request handle ahash_request. * * Return: ahash cipher handle */ static inline struct crypto_ahash *crypto_ahash_reqtfm( struct ahash_request *req) { return __crypto_ahash_cast(req->base.tfm); } /** * crypto_ahash_reqsize() - obtain size of the request data structure * @tfm: cipher handle * * Return: size of the request data */ static inline unsigned int crypto_ahash_reqsize(struct crypto_ahash *tfm) { return tfm->reqsize; } static inline void *ahash_request_ctx(struct ahash_request *req) { return req->__ctx; } /** * crypto_ahash_setkey - set key for cipher handle * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the ahash cipher. The cipher * handle must point to a keyed hash in order for this function to succeed. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); /** * crypto_ahash_finup() - update and finalize message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_finup(struct ahash_request *req); /** * crypto_ahash_final() - calculate message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer registered with the ahash_request handle. * * Return: * 0 if the message digest was successfully calculated; * -EINPROGRESS if data is fed into hardware (DMA) or queued for later; * -EBUSY if queue is full and request should be resubmitted later; * other < 0 if an error occurred */ int crypto_ahash_final(struct ahash_request *req); /** * crypto_ahash_digest() - calculate message digest for a buffer * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of crypto_ahash_init, * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_digest(struct ahash_request *req); /** * crypto_ahash_export() - extract current message digest state * @req: reference to the ahash_request handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the ahash_request handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_ahash_statesize()). * * Return: 0 if the export was successful; < 0 if an error occurred */ int crypto_ahash_export(struct ahash_request *req, void *out); /** * crypto_ahash_import() - import message digest state * @req: reference to ahash_request handle the state is imported into * @in: buffer holding the state * * This function imports the hash state into the ahash_request handle from the * input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_ahash_import(struct ahash_request *req, const void *in); /** * crypto_ahash_init() - (re)initialize message digest handle * @req: ahash_request handle that already is initialized with all necessary * data using the ahash_request_* API functions * * The call (re-)initializes the message digest referenced by the ahash_request * handle. Any potentially existing state created by previous operations is * discarded. * * Return: see crypto_ahash_final() */ int crypto_ahash_init(struct ahash_request *req); /** * crypto_ahash_update() - add data to message digest for processing * @req: ahash_request handle that was previously initialized with the * crypto_ahash_init call. * * Updates the message digest state of the &ahash_request handle. The input data * is pointed to by the scatter/gather list registered in the &ahash_request * handle * * Return: see crypto_ahash_final() */ int crypto_ahash_update(struct ahash_request *req); /** * DOC: Asynchronous Hash Request Handle * * The &ahash_request data structure contains all pointers to data * required for the asynchronous cipher operation. This includes the cipher * handle (which can be used by multiple &ahash_request instances), pointer * to plaintext and the message digest output buffer, asynchronous callback * function, etc. It acts as a handle to the ahash_request_* API calls in a * similar way as ahash handle to the crypto_ahash_* API calls. */ /** * ahash_request_set_tfm() - update cipher handle reference in request * @req: request handle to be modified * @tfm: cipher handle that shall be added to the request handle * * Allow the caller to replace the existing ahash handle in the request * data structure with a different one. */ static inline void ahash_request_set_tfm(struct ahash_request *req, struct crypto_ahash *tfm) { req->base.tfm = crypto_ahash_tfm(tfm); } /** * ahash_request_alloc() - allocate request data structure * @tfm: cipher handle to be registered with the request * @gfp: memory allocation flag that is handed to kmalloc by the API call. * * Allocate the request data structure that must be used with the ahash * message digest API calls. During * the allocation, the provided ahash handle * is registered in the request data structure. * * Return: allocated request handle in case of success, or NULL if out of memory */ static inline struct ahash_request *ahash_request_alloc_noprof( struct crypto_ahash *tfm, gfp_t gfp) { struct ahash_request *req; req = kmalloc_noprof(sizeof(struct ahash_request) + crypto_ahash_reqsize(tfm), gfp); if (likely(req)) ahash_request_set_tfm(req, tfm); return req; } #define ahash_request_alloc(...) alloc_hooks(ahash_request_alloc_noprof(__VA_ARGS__)) /** * ahash_request_free() - zeroize and free the request data structure * @req: request data structure cipher handle to be freed */ static inline void ahash_request_free(struct ahash_request *req) { kfree_sensitive(req); } static inline void ahash_request_zero(struct ahash_request *req) { memzero_explicit(req, sizeof(*req) + crypto_ahash_reqsize(crypto_ahash_reqtfm(req))); } static inline struct ahash_request *ahash_request_cast( struct crypto_async_request *req) { return container_of(req, struct ahash_request, base); } /** * ahash_request_set_callback() - set asynchronous callback function * @req: request handle * @flags: specify zero or an ORing of the flags * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and * increase the wait queue beyond the initial maximum size; * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep * @compl: callback function pointer to be registered with the request handle * @data: The data pointer refers to memory that is not used by the kernel * crypto API, but provided to the callback function for it to use. Here, * the caller can provide a reference to memory the callback function can * operate on. As the callback function is invoked asynchronously to the * related functionality, it may need to access data structures of the * related functionality which can be referenced using this pointer. The * callback function can access the memory via the "data" field in the * &crypto_async_request data structure provided to the callback function. * * This function allows setting the callback function that is triggered once * the cipher operation completes. * * The callback function is registered with the &ahash_request handle and * must comply with the following template:: * * void callback_function(struct crypto_async_request *req, int error) */ static inline void ahash_request_set_callback(struct ahash_request *req, u32 flags, crypto_completion_t compl, void *data) { req->base.complete = compl; req->base.data = data; req->base.flags = flags; } /** * ahash_request_set_crypt() - set data buffers * @req: ahash_request handle to be updated * @src: source scatter/gather list * @result: buffer that is filled with the message digest -- the caller must * ensure that the buffer has sufficient space by, for example, calling * crypto_ahash_digestsize() * @nbytes: number of bytes to process from the source scatter/gather list * * By using this call, the caller references the source scatter/gather list. * The source scatter/gather list points to the data the message digest is to * be calculated for. */ static inline void ahash_request_set_crypt(struct ahash_request *req, struct scatterlist *src, u8 *result, unsigned int nbytes) { req->src = src; req->nbytes = nbytes; req->result = result; } /** * DOC: Synchronous Message Digest API * * The synchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_SHASH (listed as type "shash" in /proc/crypto) * * The message digest API is able to maintain state information for the * caller. * * The synchronous message digest API can store user-related context in its * shash_desc request data structure. */ /** * crypto_alloc_shash() - allocate message digest handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * message digest cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for a message digest. The returned &struct * crypto_shash is the cipher handle that is required for any subsequent * API invocation for that message digest. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type, u32 mask); struct crypto_shash *crypto_clone_shash(struct crypto_shash *tfm); int crypto_has_shash(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm) { return &tfm->base; } /** * crypto_free_shash() - zeroize and free the message digest handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_shash(struct crypto_shash *tfm) { crypto_destroy_tfm(tfm, crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_alg_name(struct crypto_shash *tfm) { return crypto_tfm_alg_name(crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_driver_name(struct crypto_shash *tfm) { return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm)); } /** * crypto_shash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_shash_blocksize(struct crypto_shash *tfm) { return crypto_tfm_alg_blocksize(crypto_shash_tfm(tfm)); } static inline struct shash_alg *__crypto_shash_alg(struct crypto_alg *alg) { return container_of(alg, struct shash_alg, base); } static inline struct shash_alg *crypto_shash_alg(struct crypto_shash *tfm) { return __crypto_shash_alg(crypto_shash_tfm(tfm)->__crt_alg); } /** * crypto_shash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * Return: digest size of cipher */ static inline unsigned int crypto_shash_digestsize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->digestsize; } static inline unsigned int crypto_shash_statesize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->statesize; } static inline u32 crypto_shash_get_flags(struct crypto_shash *tfm) { return crypto_tfm_get_flags(crypto_shash_tfm(tfm)); } static inline void crypto_shash_set_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_shash_tfm(tfm), flags); } static inline void crypto_shash_clear_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_shash_tfm(tfm), flags); } /** * crypto_shash_descsize() - obtain the operational state size * @tfm: cipher handle * * The size of the operational state the cipher needs during operation is * returned for the hash referenced with the cipher handle. This size is * required to calculate the memory requirements to allow the caller allocating * sufficient memory for operational state. * * The operational state is defined with struct shash_desc where the size of * that data structure is to be calculated as * sizeof(struct shash_desc) + crypto_shash_descsize(alg) * * Return: size of the operational state */ static inline unsigned int crypto_shash_descsize(struct crypto_shash *tfm) { return tfm->descsize; } static inline void *shash_desc_ctx(struct shash_desc *desc) { return desc->__ctx; } /** * crypto_shash_setkey() - set key for message digest * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the keyed message digest cipher. The * cipher handle must point to a keyed message digest cipher in order for this * function to succeed. * * Context: Any context. * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); /** * crypto_shash_digest() - calculate message digest for buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of crypto_shash_init, * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_tfm_digest() - calculate message digest for buffer * @tfm: hash transformation object * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This is a simplified version of crypto_shash_digest() for users who don't * want to allocate their own hash descriptor (shash_desc). Instead, * crypto_shash_tfm_digest() takes a hash transformation object (crypto_shash) * directly, and it allocates a hash descriptor on the stack internally. * Note that this stack allocation may be fairly large. * * Context: Any context. * Return: 0 on success; < 0 if an error occurred. */ int crypto_shash_tfm_digest(struct crypto_shash *tfm, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_export() - extract operational state for message digest * @desc: reference to the operational state handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the operational state handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_shash_descsize). * * Context: Any context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ int crypto_shash_export(struct shash_desc *desc, void *out); /** * crypto_shash_import() - import operational state * @desc: reference to the operational state handle the state imported into * @in: buffer holding the state * * This function imports the hash state into the operational state handle from * the input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Context: Any context. * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_shash_import(struct shash_desc *desc, const void *in); /** * crypto_shash_init() - (re)initialize message digest * @desc: operational state handle that is already filled * * The call (re-)initializes the message digest referenced by the * operational state handle. Any potentially existing state created by * previous operations is discarded. * * Context: Any context. * Return: 0 if the message digest initialization was successful; < 0 if an * error occurred */ static inline int crypto_shash_init(struct shash_desc *desc) { struct crypto_shash *tfm = desc->tfm; if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return crypto_shash_alg(tfm)->init(desc); } /** * crypto_shash_update() - add data to message digest for processing * @desc: operational state handle that is already initialized * @data: input data to be added to the message digest * @len: length of the input data * * Updates the message digest state of the operational state handle. * * Context: Any context. * Return: 0 if the message digest update was successful; < 0 if an error * occurred */ int crypto_shash_update(struct shash_desc *desc, const u8 *data, unsigned int len); /** * crypto_shash_final() - calculate message digest * @desc: operational state handle that is already filled with data * @out: output buffer filled with the message digest * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer. The caller must ensure that the output buffer is * large enough by using crypto_shash_digestsize. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_final(struct shash_desc *desc, u8 *out); /** * crypto_shash_finup() - calculate message digest of buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate functions. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); static inline void shash_desc_zero(struct shash_desc *desc) { memzero_explicit(desc, sizeof(*desc) + crypto_shash_descsize(desc->tfm)); } #endif /* _CRYPTO_HASH_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 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Trace point definitions for the RDMA Connect Manager. * * Author: Chuck Lever <chuck.lever@oracle.com> * * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rdma_cma #if !defined(_TRACE_RDMA_CMA_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RDMA_CMA_H #include <linux/tracepoint.h> #include <trace/misc/rdma.h> DECLARE_EVENT_CLASS(cma_fsm_class, TP_PROTO( const struct rdma_id_private *id_priv ), TP_ARGS(id_priv), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos ) ); #define DEFINE_CMA_FSM_EVENT(name) \ DEFINE_EVENT(cma_fsm_class, cm_##name, \ TP_PROTO( \ const struct rdma_id_private *id_priv \ ), \ TP_ARGS(id_priv)) DEFINE_CMA_FSM_EVENT(send_rtu); DEFINE_CMA_FSM_EVENT(send_rej); DEFINE_CMA_FSM_EVENT(send_mra); DEFINE_CMA_FSM_EVENT(send_sidr_req); DEFINE_CMA_FSM_EVENT(send_sidr_rep); DEFINE_CMA_FSM_EVENT(disconnect); DEFINE_CMA_FSM_EVENT(sent_drep); DEFINE_CMA_FSM_EVENT(sent_dreq); DEFINE_CMA_FSM_EVENT(id_destroy); TRACE_EVENT(cm_id_attach, TP_PROTO( const struct rdma_id_private *id_priv, const struct ib_device *device ), TP_ARGS(id_priv, device), TP_STRUCT__entry( __field(u32, cm_id) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) __string(devname, device->name) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); __assign_str(devname); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc device=%s", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __get_str(devname) ) ); DECLARE_EVENT_CLASS(cma_qp_class, TP_PROTO( const struct rdma_id_private *id_priv ), TP_ARGS(id_priv), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(u32, qp_num) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->qp_num = id_priv->qp_num; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u qp_num=%u", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, __entry->qp_num ) ); #define DEFINE_CMA_QP_EVENT(name) \ DEFINE_EVENT(cma_qp_class, cm_##name, \ TP_PROTO( \ const struct rdma_id_private *id_priv \ ), \ TP_ARGS(id_priv)) DEFINE_CMA_QP_EVENT(send_req); DEFINE_CMA_QP_EVENT(send_rep); DEFINE_CMA_QP_EVENT(qp_destroy); /* * enum ib_wp_type, from include/rdma/ib_verbs.h */ #define IB_QP_TYPE_LIST \ ib_qp_type(SMI) \ ib_qp_type(GSI) \ ib_qp_type(RC) \ ib_qp_type(UC) \ ib_qp_type(UD) \ ib_qp_type(RAW_IPV6) \ ib_qp_type(RAW_ETHERTYPE) \ ib_qp_type(RAW_PACKET) \ ib_qp_type(XRC_INI) \ ib_qp_type_end(XRC_TGT) #undef ib_qp_type #undef ib_qp_type_end #define ib_qp_type(x) TRACE_DEFINE_ENUM(IB_QPT_##x); #define ib_qp_type_end(x) TRACE_DEFINE_ENUM(IB_QPT_##x); IB_QP_TYPE_LIST #undef ib_qp_type #undef ib_qp_type_end #define ib_qp_type(x) { IB_QPT_##x, #x }, #define ib_qp_type_end(x) { IB_QPT_##x, #x } #define rdma_show_qp_type(x) \ __print_symbolic(x, IB_QP_TYPE_LIST) TRACE_EVENT(cm_qp_create, TP_PROTO( const struct rdma_id_private *id_priv, const struct ib_pd *pd, const struct ib_qp_init_attr *qp_init_attr, int rc ), TP_ARGS(id_priv, pd, qp_init_attr, rc), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, pd_id) __field(u32, tos) __field(u32, qp_num) __field(u32, send_wr) __field(u32, recv_wr) __field(int, rc) __field(unsigned long, qp_type) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->pd_id = pd->res.id; __entry->tos = id_priv->tos; __entry->send_wr = qp_init_attr->cap.max_send_wr; __entry->recv_wr = qp_init_attr->cap.max_recv_wr; __entry->rc = rc; if (!rc) { __entry->qp_num = id_priv->qp_num; __entry->qp_type = id_priv->id.qp_type; } else { __entry->qp_num = 0; __entry->qp_type = 0; } memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u pd.id=%u qp_type=%s" " send_wr=%u recv_wr=%u qp_num=%u rc=%d", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, __entry->pd_id, rdma_show_qp_type(__entry->qp_type), __entry->send_wr, __entry->recv_wr, __entry->qp_num, __entry->rc ) ); TRACE_EVENT(cm_req_handler, TP_PROTO( const struct rdma_id_private *id_priv, int event ), TP_ARGS(id_priv, event), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(unsigned long, event) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->event = event; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s (%lu)", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, rdma_show_ib_cm_event(__entry->event), __entry->event ) ); TRACE_EVENT(cm_event_handler, TP_PROTO( const struct rdma_id_private *id_priv, const struct rdma_cm_event *event ), TP_ARGS(id_priv, event), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(unsigned long, event) __field(int, status) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->event = event->event; __entry->status = event->status; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s (%lu/%d)", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, rdma_show_cm_event(__entry->event), __entry->event, __entry->status ) ); TRACE_EVENT(cm_event_done, TP_PROTO( const struct rdma_id_private *id_priv, const struct rdma_cm_event *event, int result ), TP_ARGS(id_priv, event, result), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(unsigned long, event) __field(int, result) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->event = event->event; __entry->result = result; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s consumer returns %d", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, rdma_show_cm_event(__entry->event), __entry->result ) ); DECLARE_EVENT_CLASS(cma_client_class, TP_PROTO( const struct ib_device *device ), TP_ARGS(device), TP_STRUCT__entry( __string(name, device->name) ), TP_fast_assign( __assign_str(name); ), TP_printk("device name=%s", __get_str(name) ) ); #define DEFINE_CMA_CLIENT_EVENT(name) \ DEFINE_EVENT(cma_client_class, cm_##name, \ TP_PROTO( \ const struct ib_device *device \ ), \ TP_ARGS(device)) DEFINE_CMA_CLIENT_EVENT(add_one); DEFINE_CMA_CLIENT_EVENT(remove_one); #endif /* _TRACE_RDMA_CMA_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE cma_trace #include <trace/define_trace.h> |
| 6263 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM capability #if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CAPABILITY_H #include <linux/cred.h> #include <linux/tracepoint.h> #include <linux/user_namespace.h> /** * cap_capable - called after it's determined if a task has a particular * effective capability * * @cred: The credentials used * @target_ns: The user namespace of the resource being accessed * @capable_ns: The user namespace in which the credential provides the * capability to access the targeted resource. * This will be NULL if ret is not 0. * @cap: The capability to check for * @ret: The return value of the check: 0 if it does, -ve if it does not * * Allows to trace calls to cap_capable in commoncap.c */ TRACE_EVENT(cap_capable, TP_PROTO(const struct cred *cred, struct user_namespace *target_ns, const struct user_namespace *capable_ns, int cap, int ret), TP_ARGS(cred, target_ns, capable_ns, cap, ret), TP_STRUCT__entry( __field(const struct cred *, cred) __field(struct user_namespace *, target_ns) __field(const struct user_namespace *, capable_ns) __field(int, cap) __field(int, ret) ), TP_fast_assign( __entry->cred = cred; __entry->target_ns = target_ns; __entry->capable_ns = ret == 0 ? capable_ns : NULL; __entry->cap = cap; __entry->ret = ret; ), TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d", __entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap, __entry->ret) ); #endif /* _TRACE_CAPABILITY_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 173 174 174 174 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 | // SPDX-License-Identifier: GPL-2.0 /* * bcache sysfs interfaces * * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com> * Copyright 2012 Google, Inc. */ #ifndef NO_BCACHEFS_SYSFS #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" #include "sysfs.h" #include "btree_cache.h" #include "btree_io.h" #include "btree_iter.h" #include "btree_key_cache.h" #include "btree_update.h" #include "btree_update_interior.h" #include "btree_gc.h" #include "buckets.h" #include "clock.h" #include "compress.h" #include "disk_accounting.h" #include "disk_groups.h" #include "ec.h" #include "inode.h" #include "journal.h" #include "journal_reclaim.h" #include "keylist.h" #include "move.h" #include "movinggc.h" #include "nocow_locking.h" #include "opts.h" #include "rebalance.h" #include "replicas.h" #include "super-io.h" #include "tests.h" #include <linux/blkdev.h> #include <linux/sort.h> #include <linux/sched/clock.h> #include "util.h" #define SYSFS_OPS(type) \ const struct sysfs_ops type ## _sysfs_ops = { \ .show = type ## _show, \ .store = type ## _store \ } #define SHOW(fn) \ static ssize_t fn ## _to_text(struct printbuf *, \ struct kobject *, struct attribute *); \ \ static ssize_t fn ## _show(struct kobject *kobj, struct attribute *attr,\ char *buf) \ { \ struct printbuf out = PRINTBUF; \ ssize_t ret = fn ## _to_text(&out, kobj, attr); \ \ if (out.pos && out.buf[out.pos - 1] != '\n') \ prt_newline(&out); \ \ if (!ret && out.allocation_failure) \ ret = -ENOMEM; \ \ if (!ret) { \ ret = min_t(size_t, out.pos, PAGE_SIZE - 1); \ memcpy(buf, out.buf, ret); \ } \ printbuf_exit(&out); \ return bch2_err_class(ret); \ } \ \ static ssize_t fn ## _to_text(struct printbuf *out, struct kobject *kobj,\ struct attribute *attr) #define STORE(fn) \ static ssize_t fn ## _store_inner(struct kobject *, struct attribute *,\ const char *, size_t); \ \ static ssize_t fn ## _store(struct kobject *kobj, struct attribute *attr,\ const char *buf, size_t size) \ { \ return bch2_err_class(fn##_store_inner(kobj, attr, buf, size)); \ } \ \ static ssize_t fn ## _store_inner(struct kobject *kobj, struct attribute *attr,\ const char *buf, size_t size) #define __sysfs_attribute(_name, _mode) \ static struct attribute sysfs_##_name = \ { .name = #_name, .mode = _mode } #define write_attribute(n) __sysfs_attribute(n, 0200) #define read_attribute(n) __sysfs_attribute(n, 0444) #define rw_attribute(n) __sysfs_attribute(n, 0644) #define sysfs_printf(file, fmt, ...) \ do { \ if (attr == &sysfs_ ## file) \ prt_printf(out, fmt "\n", __VA_ARGS__); \ } while (0) #define sysfs_print(file, var) \ do { \ if (attr == &sysfs_ ## file) \ snprint(out, var); \ } while (0) #define sysfs_hprint(file, val) \ do { \ if (attr == &sysfs_ ## file) \ prt_human_readable_s64(out, val); \ } while (0) #define sysfs_strtoul(file, var) \ do { \ if (attr == &sysfs_ ## file) \ return strtoul_safe(buf, var) ?: (ssize_t) size; \ } while (0) #define sysfs_strtoul_clamp(file, var, min, max) \ do { \ if (attr == &sysfs_ ## file) \ return strtoul_safe_clamp(buf, var, min, max) \ ?: (ssize_t) size; \ } while (0) #define strtoul_or_return(cp) \ ({ \ unsigned long _v; \ int _r = kstrtoul(cp, 10, &_v); \ if (_r) \ return _r; \ _v; \ }) write_attribute(trigger_gc); write_attribute(trigger_discards); write_attribute(trigger_invalidates); write_attribute(trigger_journal_flush); write_attribute(trigger_journal_writes); write_attribute(trigger_btree_cache_shrink); write_attribute(trigger_btree_key_cache_shrink); write_attribute(trigger_freelist_wakeup); read_attribute(gc_gens_pos); read_attribute(uuid); read_attribute(minor); read_attribute(flags); read_attribute(bucket_size); read_attribute(first_bucket); read_attribute(nbuckets); rw_attribute(durability); read_attribute(io_done); read_attribute(io_errors); write_attribute(io_errors_reset); read_attribute(io_latency_read); read_attribute(io_latency_write); read_attribute(io_latency_stats_read); read_attribute(io_latency_stats_write); read_attribute(congested); read_attribute(btree_write_stats); read_attribute(btree_cache_size); read_attribute(compression_stats); read_attribute(journal_debug); read_attribute(btree_cache); read_attribute(btree_key_cache); read_attribute(btree_reserve_cache); read_attribute(stripes_heap); read_attribute(open_buckets); read_attribute(open_buckets_partial); read_attribute(write_points); read_attribute(nocow_lock_table); #ifdef BCH_WRITE_REF_DEBUG read_attribute(write_refs); static const char * const bch2_write_refs[] = { #define x(n) #n, BCH_WRITE_REFS() #undef x NULL }; static void bch2_write_refs_to_text(struct printbuf *out, struct bch_fs *c) { bch2_printbuf_tabstop_push(out, 24); for (unsigned i = 0; i < ARRAY_SIZE(c->writes); i++) prt_printf(out, "%s\t%li\n", bch2_write_refs[i], atomic_long_read(&c->writes[i])); } #endif read_attribute(internal_uuid); read_attribute(disk_groups); read_attribute(has_data); read_attribute(alloc_debug); read_attribute(usage_base); #define x(t, n, ...) read_attribute(t); BCH_PERSISTENT_COUNTERS() #undef x rw_attribute(discard); read_attribute(state); rw_attribute(label); read_attribute(copy_gc_wait); sysfs_pd_controller_attribute(rebalance); read_attribute(rebalance_status); read_attribute(new_stripes); read_attribute(io_timers_read); read_attribute(io_timers_write); read_attribute(moving_ctxts); #ifdef CONFIG_BCACHEFS_TESTS write_attribute(perf_test); #endif /* CONFIG_BCACHEFS_TESTS */ #define x(_name) \ static struct attribute sysfs_time_stat_##_name = \ { .name = #_name, .mode = 0644 }; BCH_TIME_STATS() #undef x static size_t bch2_btree_cache_size(struct bch_fs *c) { struct btree_cache *bc = &c->btree_cache; size_t ret = 0; struct btree *b; mutex_lock(&bc->lock); list_for_each_entry(b, &bc->live[0].list, list) ret += btree_buf_bytes(b); list_for_each_entry(b, &bc->live[1].list, list) ret += btree_buf_bytes(b); list_for_each_entry(b, &bc->freeable, list) ret += btree_buf_bytes(b); mutex_unlock(&bc->lock); return ret; } static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c) { prt_str(out, "type"); printbuf_tabstop_push(out, 12); printbuf_tabstop_push(out, 16); printbuf_tabstop_push(out, 16); printbuf_tabstop_push(out, 24); prt_printf(out, "type\tcompressed\runcompressed\raverage extent size\r\n"); for (unsigned i = 1; i < BCH_COMPRESSION_TYPE_NR; i++) { struct disk_accounting_pos a = { .type = BCH_DISK_ACCOUNTING_compression, .compression.type = i, }; struct bpos p = disk_accounting_pos_to_bpos(&a); u64 v[3]; bch2_accounting_mem_read(c, p, v, ARRAY_SIZE(v)); u64 nr_extents = v[0]; u64 sectors_uncompressed = v[1]; u64 sectors_compressed = v[2]; bch2_prt_compression_type(out, i); prt_tab(out); prt_human_readable_u64(out, sectors_compressed << 9); prt_tab_rjust(out); prt_human_readable_u64(out, sectors_uncompressed << 9); prt_tab_rjust(out); prt_human_readable_u64(out, nr_extents ? div64_u64(sectors_uncompressed << 9, nr_extents) : 0); prt_tab_rjust(out); prt_newline(out); } return 0; } static void bch2_gc_gens_pos_to_text(struct printbuf *out, struct bch_fs *c) { bch2_btree_id_to_text(out, c->gc_gens_btree); prt_printf(out, ": "); bch2_bpos_to_text(out, c->gc_gens_pos); prt_printf(out, "\n"); } static void bch2_fs_usage_base_to_text(struct printbuf *out, struct bch_fs *c) { struct bch_fs_usage_base b = {}; acc_u64s_percpu(&b.hidden, &c->usage->hidden, sizeof(b) / sizeof(u64)); prt_printf(out, "hidden:\t\t%llu\n", b.hidden); prt_printf(out, "btree:\t\t%llu\n", b.btree); prt_printf(out, "data:\t\t%llu\n", b.data); prt_printf(out, "cached:\t%llu\n", b.cached); prt_printf(out, "reserved:\t\t%llu\n", b.reserved); prt_printf(out, "nr_inodes:\t%llu\n", b.nr_inodes); } SHOW(bch2_fs) { struct bch_fs *c = container_of(kobj, struct bch_fs, kobj); sysfs_print(minor, c->minor); sysfs_printf(internal_uuid, "%pU", c->sb.uuid.b); if (attr == &sysfs_flags) prt_bitflags(out, bch2_fs_flag_strs, c->flags); sysfs_hprint(btree_cache_size, bch2_btree_cache_size(c)); if (attr == &sysfs_btree_write_stats) bch2_btree_write_stats_to_text(out, c); if (attr == &sysfs_gc_gens_pos) bch2_gc_gens_pos_to_text(out, c); sysfs_pd_controller_show(rebalance, &c->rebalance.pd); /* XXX */ if (attr == &sysfs_copy_gc_wait) bch2_copygc_wait_to_text(out, c); if (attr == &sysfs_rebalance_status) bch2_rebalance_status_to_text(out, c); /* Debugging: */ if (attr == &sysfs_journal_debug) bch2_journal_debug_to_text(out, &c->journal); if (attr == &sysfs_btree_cache) bch2_btree_cache_to_text(out, &c->btree_cache); if (attr == &sysfs_btree_key_cache) bch2_btree_key_cache_to_text(out, &c->btree_key_cache); if (attr == &sysfs_btree_reserve_cache) bch2_btree_reserve_cache_to_text(out, c); if (attr == &sysfs_stripes_heap) bch2_stripes_heap_to_text(out, c); if (attr == &sysfs_open_buckets) bch2_open_buckets_to_text(out, c, NULL); if (attr == &sysfs_open_buckets_partial) bch2_open_buckets_partial_to_text(out, c); if (attr == &sysfs_write_points) bch2_write_points_to_text(out, c); if (attr == &sysfs_compression_stats) bch2_compression_stats_to_text(out, c); if (attr == &sysfs_new_stripes) bch2_new_stripes_to_text(out, c); if (attr == &sysfs_io_timers_read) bch2_io_timers_to_text(out, &c->io_clock[READ]); if (attr == &sysfs_io_timers_write) bch2_io_timers_to_text(out, &c->io_clock[WRITE]); if (attr == &sysfs_moving_ctxts) bch2_fs_moving_ctxts_to_text(out, c); #ifdef BCH_WRITE_REF_DEBUG if (attr == &sysfs_write_refs) bch2_write_refs_to_text(out, c); #endif if (attr == &sysfs_nocow_lock_table) bch2_nocow_locks_to_text(out, &c->nocow_locks); if (attr == &sysfs_disk_groups) bch2_disk_groups_to_text(out, c); if (attr == &sysfs_alloc_debug) bch2_fs_alloc_debug_to_text(out, c); if (attr == &sysfs_usage_base) bch2_fs_usage_base_to_text(out, c); return 0; } STORE(bch2_fs) { struct bch_fs *c = container_of(kobj, struct bch_fs, kobj); sysfs_pd_controller_store(rebalance, &c->rebalance.pd); /* Debugging: */ if (!test_bit(BCH_FS_started, &c->flags)) return -EPERM; /* Debugging: */ if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_sysfs)) return -EROFS; if (attr == &sysfs_trigger_btree_cache_shrink) { struct btree_cache *bc = &c->btree_cache; struct shrink_control sc; sc.gfp_mask = GFP_KERNEL; sc.nr_to_scan = strtoul_or_return(buf); bc->live[0].shrink->scan_objects(bc->live[0].shrink, &sc); } if (attr == &sysfs_trigger_btree_key_cache_shrink) { struct shrink_control sc; sc.gfp_mask = GFP_KERNEL; sc.nr_to_scan = strtoul_or_return(buf); c->btree_key_cache.shrink->scan_objects(c->btree_key_cache.shrink, &sc); } if (attr == &sysfs_trigger_gc) bch2_gc_gens(c); if (attr == &sysfs_trigger_discards) bch2_do_discards(c); if (attr == &sysfs_trigger_invalidates) bch2_do_invalidates(c); if (attr == &sysfs_trigger_journal_flush) { bch2_journal_flush_all_pins(&c->journal); bch2_journal_meta(&c->journal); } if (attr == &sysfs_trigger_journal_writes) bch2_journal_do_writes(&c->journal); if (attr == &sysfs_trigger_freelist_wakeup) closure_wake_up(&c->freelist_wait); #ifdef CONFIG_BCACHEFS_TESTS if (attr == &sysfs_perf_test) { char *tmp = kstrdup(buf, GFP_KERNEL), *p = tmp; char *test = strsep(&p, " \t\n"); char *nr_str = strsep(&p, " \t\n"); char *threads_str = strsep(&p, " \t\n"); unsigned threads; u64 nr; int ret = -EINVAL; if (threads_str && !(ret = kstrtouint(threads_str, 10, &threads)) && !(ret = bch2_strtoull_h(nr_str, &nr))) ret = bch2_btree_perf_test(c, test, nr, threads); kfree(tmp); if (ret) size = ret; } #endif bch2_write_ref_put(c, BCH_WRITE_REF_sysfs); return size; } SYSFS_OPS(bch2_fs); struct attribute *bch2_fs_files[] = { &sysfs_minor, &sysfs_btree_cache_size, &sysfs_btree_write_stats, &sysfs_rebalance_status, &sysfs_compression_stats, #ifdef CONFIG_BCACHEFS_TESTS &sysfs_perf_test, #endif NULL }; /* counters dir */ SHOW(bch2_fs_counters) { struct bch_fs *c = container_of(kobj, struct bch_fs, counters_kobj); u64 counter = 0; u64 counter_since_mount = 0; printbuf_tabstop_push(out, 32); #define x(t, n, f, ...) \ if (attr == &sysfs_##t) { \ counter = percpu_u64_get(&c->counters[BCH_COUNTER_##t]);\ counter_since_mount = counter - c->counters_on_mount[BCH_COUNTER_##t];\ if (f & TYPE_SECTORS) { \ counter <<= 9; \ counter_since_mount <<= 9; \ } \ \ prt_printf(out, "since mount:\t"); \ (f & TYPE_COUNTER) ? prt_u64(out, counter_since_mount) :\ prt_human_readable_u64(out, counter_since_mount); \ prt_newline(out); \ \ prt_printf(out, "since filesystem creation:\t"); \ (f & TYPE_COUNTER) ? prt_u64(out, counter) : \ prt_human_readable_u64(out, counter); \ prt_newline(out); \ } BCH_PERSISTENT_COUNTERS() #undef x return 0; } STORE(bch2_fs_counters) { return 0; } SYSFS_OPS(bch2_fs_counters); struct attribute *bch2_fs_counters_files[] = { #define x(t, ...) \ &sysfs_##t, BCH_PERSISTENT_COUNTERS() #undef x NULL }; /* internal dir - just a wrapper */ SHOW(bch2_fs_internal) { struct bch_fs *c = container_of(kobj, struct bch_fs, internal); return bch2_fs_to_text(out, &c->kobj, attr); } STORE(bch2_fs_internal) { struct bch_fs *c = container_of(kobj, struct bch_fs, internal); return bch2_fs_store(&c->kobj, attr, buf, size); } SYSFS_OPS(bch2_fs_internal); struct attribute *bch2_fs_internal_files[] = { &sysfs_flags, &sysfs_journal_debug, &sysfs_btree_cache, &sysfs_btree_key_cache, &sysfs_btree_reserve_cache, &sysfs_new_stripes, &sysfs_stripes_heap, &sysfs_open_buckets, &sysfs_open_buckets_partial, &sysfs_write_points, #ifdef BCH_WRITE_REF_DEBUG &sysfs_write_refs, #endif &sysfs_nocow_lock_table, &sysfs_io_timers_read, &sysfs_io_timers_write, &sysfs_trigger_gc, &sysfs_trigger_discards, &sysfs_trigger_invalidates, &sysfs_trigger_journal_flush, &sysfs_trigger_journal_writes, &sysfs_trigger_btree_cache_shrink, &sysfs_trigger_btree_key_cache_shrink, &sysfs_trigger_freelist_wakeup, &sysfs_gc_gens_pos, &sysfs_copy_gc_wait, sysfs_pd_controller_files(rebalance), &sysfs_moving_ctxts, &sysfs_internal_uuid, &sysfs_disk_groups, &sysfs_alloc_debug, &sysfs_usage_base, NULL }; /* options */ SHOW(bch2_fs_opts_dir) { struct bch_fs *c = container_of(kobj, struct bch_fs, opts_dir); const struct bch_option *opt = container_of(attr, struct bch_option, attr); int id = opt - bch2_opt_table; u64 v = bch2_opt_get_by_id(&c->opts, id); bch2_opt_to_text(out, c, c->disk_sb.sb, opt, v, OPT_SHOW_FULL_LIST); prt_char(out, '\n'); return 0; } STORE(bch2_fs_opts_dir) { struct bch_fs *c = container_of(kobj, struct bch_fs, opts_dir); const struct bch_option *opt = container_of(attr, struct bch_option, attr); int ret, id = opt - bch2_opt_table; char *tmp; u64 v; /* * We don't need to take c->writes for correctness, but it eliminates an * unsightly error message in the dmesg log when we're RO: */ if (unlikely(!bch2_write_ref_tryget(c, BCH_WRITE_REF_sysfs))) return -EROFS; tmp = kstrdup(buf, GFP_KERNEL); if (!tmp) { ret = -ENOMEM; goto err; } ret = bch2_opt_parse(c, opt, strim(tmp), &v, NULL); kfree(tmp); if (ret < 0) goto err; ret = bch2_opt_check_may_set(c, id, v); if (ret < 0) goto err; bch2_opt_set_sb(c, NULL, opt, v); bch2_opt_set_by_id(&c->opts, id, v); if (v && (id == Opt_background_target || id == Opt_background_compression || (id == Opt_compression && !c->opts.background_compression))) bch2_set_rebalance_needs_scan(c, 0); if (v && id == Opt_rebalance_enabled) rebalance_wakeup(c); if (v && id == Opt_copygc_enabled && c->copygc_thread) wake_up_process(c->copygc_thread); ret = size; err: bch2_write_ref_put(c, BCH_WRITE_REF_sysfs); return ret; } SYSFS_OPS(bch2_fs_opts_dir); struct attribute *bch2_fs_opts_dir_files[] = { NULL }; int bch2_opts_create_sysfs_files(struct kobject *kobj) { const struct bch_option *i; int ret; for (i = bch2_opt_table; i < bch2_opt_table + bch2_opts_nr; i++) { if (!(i->flags & OPT_FS)) continue; ret = sysfs_create_file(kobj, &i->attr); if (ret) return ret; } return 0; } /* time stats */ SHOW(bch2_fs_time_stats) { struct bch_fs *c = container_of(kobj, struct bch_fs, time_stats); #define x(name) \ if (attr == &sysfs_time_stat_##name) \ bch2_time_stats_to_text(out, &c->times[BCH_TIME_##name]); BCH_TIME_STATS() #undef x return 0; } STORE(bch2_fs_time_stats) { struct bch_fs *c = container_of(kobj, struct bch_fs, time_stats); #define x(name) \ if (attr == &sysfs_time_stat_##name) \ bch2_time_stats_reset(&c->times[BCH_TIME_##name]); BCH_TIME_STATS() #undef x return size; } SYSFS_OPS(bch2_fs_time_stats); struct attribute *bch2_fs_time_stats_files[] = { #define x(name) \ &sysfs_time_stat_##name, BCH_TIME_STATS() #undef x NULL }; static const char * const bch2_rw[] = { "read", "write", NULL }; static void dev_io_done_to_text(struct printbuf *out, struct bch_dev *ca) { int rw, i; for (rw = 0; rw < 2; rw++) { prt_printf(out, "%s:\n", bch2_rw[rw]); for (i = 1; i < BCH_DATA_NR; i++) prt_printf(out, "%-12s:%12llu\n", bch2_data_type_str(i), percpu_u64_get(&ca->io_done->sectors[rw][i]) << 9); } } SHOW(bch2_dev) { struct bch_dev *ca = container_of(kobj, struct bch_dev, kobj); struct bch_fs *c = ca->fs; sysfs_printf(uuid, "%pU\n", ca->uuid.b); sysfs_print(bucket_size, bucket_bytes(ca)); sysfs_print(first_bucket, ca->mi.first_bucket); sysfs_print(nbuckets, ca->mi.nbuckets); sysfs_print(durability, ca->mi.durability); sysfs_print(discard, ca->mi.discard); if (attr == &sysfs_label) { if (ca->mi.group) bch2_disk_path_to_text(out, c, ca->mi.group - 1); prt_char(out, '\n'); } if (attr == &sysfs_has_data) { prt_bitflags(out, __bch2_data_types, bch2_dev_has_data(c, ca)); prt_char(out, '\n'); } if (attr == &sysfs_state) { prt_string_option(out, bch2_member_states, ca->mi.state); prt_char(out, '\n'); } if (attr == &sysfs_io_done) dev_io_done_to_text(out, ca); if (attr == &sysfs_io_errors) bch2_dev_io_errors_to_text(out, ca); sysfs_print(io_latency_read, atomic64_read(&ca->cur_latency[READ])); sysfs_print(io_latency_write, atomic64_read(&ca->cur_latency[WRITE])); if (attr == &sysfs_io_latency_stats_read) bch2_time_stats_to_text(out, &ca->io_latency[READ].stats); if (attr == &sysfs_io_latency_stats_write) bch2_time_stats_to_text(out, &ca->io_latency[WRITE].stats); sysfs_printf(congested, "%u%%", clamp(atomic_read(&ca->congested), 0, CONGESTED_MAX) * 100 / CONGESTED_MAX); if (attr == &sysfs_alloc_debug) bch2_dev_alloc_debug_to_text(out, ca); if (attr == &sysfs_open_buckets) bch2_open_buckets_to_text(out, c, ca); return 0; } STORE(bch2_dev) { struct bch_dev *ca = container_of(kobj, struct bch_dev, kobj); struct bch_fs *c = ca->fs; if (attr == &sysfs_discard) { bool v = strtoul_or_return(buf); bch2_opt_set_sb(c, ca, bch2_opt_table + Opt_discard, v); } if (attr == &sysfs_durability) { u64 v = strtoul_or_return(buf); bch2_opt_set_sb(c, ca, bch2_opt_table + Opt_durability, v); } if (attr == &sysfs_label) { char *tmp; int ret; tmp = kstrdup(buf, GFP_KERNEL); if (!tmp) return -ENOMEM; ret = bch2_dev_group_set(c, ca, strim(tmp)); kfree(tmp); if (ret) return ret; } if (attr == &sysfs_io_errors_reset) bch2_dev_errors_reset(ca); return size; } SYSFS_OPS(bch2_dev); struct attribute *bch2_dev_files[] = { &sysfs_uuid, &sysfs_bucket_size, &sysfs_first_bucket, &sysfs_nbuckets, &sysfs_durability, /* settings: */ &sysfs_discard, &sysfs_state, &sysfs_label, &sysfs_has_data, &sysfs_io_done, &sysfs_io_errors, &sysfs_io_errors_reset, &sysfs_io_latency_read, &sysfs_io_latency_write, &sysfs_io_latency_stats_read, &sysfs_io_latency_stats_write, &sysfs_congested, /* debug: */ &sysfs_alloc_debug, &sysfs_open_buckets, NULL }; #endif /* _BCACHEFS_SYSFS_H_ */ |
| 6 2 216 5 13 2 123 120 3 2 1 52 129 26 19 19 12 5 36 25 13 20 11 37 9 8 8 8 26 26 7 7 84 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_EXTENTS_H #define _BCACHEFS_EXTENTS_H #include "bcachefs.h" #include "bkey.h" #include "extents_types.h" struct bch_fs; struct btree_trans; /* extent entries: */ #define extent_entry_last(_e) \ ((typeof(&(_e).v->start[0])) bkey_val_end(_e)) #define entry_to_ptr(_entry) \ ({ \ EBUG_ON((_entry) && !extent_entry_is_ptr(_entry)); \ \ __builtin_choose_expr( \ type_is_exact(_entry, const union bch_extent_entry *), \ (const struct bch_extent_ptr *) (_entry), \ (struct bch_extent_ptr *) (_entry)); \ }) /* downcast, preserves const */ #define to_entry(_entry) \ ({ \ BUILD_BUG_ON(!type_is(_entry, union bch_extent_crc *) && \ !type_is(_entry, struct bch_extent_ptr *) && \ !type_is(_entry, struct bch_extent_stripe_ptr *)); \ \ __builtin_choose_expr( \ (type_is_exact(_entry, const union bch_extent_crc *) || \ type_is_exact(_entry, const struct bch_extent_ptr *) ||\ type_is_exact(_entry, const struct bch_extent_stripe_ptr *)),\ (const union bch_extent_entry *) (_entry), \ (union bch_extent_entry *) (_entry)); \ }) #define extent_entry_next(_entry) \ ((typeof(_entry)) ((void *) (_entry) + extent_entry_bytes(_entry))) #define extent_entry_next_safe(_entry, _end) \ (likely(__extent_entry_type(_entry) < BCH_EXTENT_ENTRY_MAX) \ ? extent_entry_next(_entry) \ : _end) static inline unsigned __extent_entry_type(const union bch_extent_entry *e) { return e->type ? __ffs(e->type) : BCH_EXTENT_ENTRY_MAX; } static inline enum bch_extent_entry_type extent_entry_type(const union bch_extent_entry *e) { int ret = __ffs(e->type); EBUG_ON(ret < 0 || ret >= BCH_EXTENT_ENTRY_MAX); return ret; } static inline size_t extent_entry_bytes(const union bch_extent_entry *entry) { switch (extent_entry_type(entry)) { #define x(f, n) \ case BCH_EXTENT_ENTRY_##f: \ return sizeof(struct bch_extent_##f); BCH_EXTENT_ENTRY_TYPES() #undef x default: BUG(); } } static inline size_t extent_entry_u64s(const union bch_extent_entry *entry) { return extent_entry_bytes(entry) / sizeof(u64); } static inline void __extent_entry_insert(struct bkey_i *k, union bch_extent_entry *dst, union bch_extent_entry *new) { union bch_extent_entry *end = bkey_val_end(bkey_i_to_s(k)); memmove_u64s_up_small((u64 *) dst + extent_entry_u64s(new), dst, (u64 *) end - (u64 *) dst); k->k.u64s += extent_entry_u64s(new); memcpy_u64s_small(dst, new, extent_entry_u64s(new)); } static inline void extent_entry_drop(struct bkey_s k, union bch_extent_entry *entry) { union bch_extent_entry *next = extent_entry_next(entry); /* stripes have ptrs, but their layout doesn't work with this code */ BUG_ON(k.k->type == KEY_TYPE_stripe); memmove_u64s_down(entry, next, (u64 *) bkey_val_end(k) - (u64 *) next); k.k->u64s -= (u64 *) next - (u64 *) entry; } static inline bool extent_entry_is_ptr(const union bch_extent_entry *e) { return __extent_entry_type(e) == BCH_EXTENT_ENTRY_ptr; } static inline bool extent_entry_is_stripe_ptr(const union bch_extent_entry *e) { return __extent_entry_type(e) == BCH_EXTENT_ENTRY_stripe_ptr; } static inline bool extent_entry_is_crc(const union bch_extent_entry *e) { switch (__extent_entry_type(e)) { case BCH_EXTENT_ENTRY_crc32: case BCH_EXTENT_ENTRY_crc64: case BCH_EXTENT_ENTRY_crc128: return true; default: return false; } } union bch_extent_crc { u8 type; struct bch_extent_crc32 crc32; struct bch_extent_crc64 crc64; struct bch_extent_crc128 crc128; }; #define __entry_to_crc(_entry) \ __builtin_choose_expr( \ type_is_exact(_entry, const union bch_extent_entry *), \ (const union bch_extent_crc *) (_entry), \ (union bch_extent_crc *) (_entry)) #define entry_to_crc(_entry) \ ({ \ EBUG_ON((_entry) && !extent_entry_is_crc(_entry)); \ \ __entry_to_crc(_entry); \ }) static inline struct bch_extent_crc_unpacked bch2_extent_crc_unpack(const struct bkey *k, const union bch_extent_crc *crc) { #define common_fields(_crc) \ .csum_type = _crc.csum_type, \ .compression_type = _crc.compression_type, \ .compressed_size = _crc._compressed_size + 1, \ .uncompressed_size = _crc._uncompressed_size + 1, \ .offset = _crc.offset, \ .live_size = k->size if (!crc) return (struct bch_extent_crc_unpacked) { .compressed_size = k->size, .uncompressed_size = k->size, .live_size = k->size, }; switch (extent_entry_type(to_entry(crc))) { case BCH_EXTENT_ENTRY_crc32: { struct bch_extent_crc_unpacked ret = (struct bch_extent_crc_unpacked) { common_fields(crc->crc32), }; *((__le32 *) &ret.csum.lo) = (__le32 __force) crc->crc32.csum; return ret; } case BCH_EXTENT_ENTRY_crc64: { struct bch_extent_crc_unpacked ret = (struct bch_extent_crc_unpacked) { common_fields(crc->crc64), .nonce = crc->crc64.nonce, .csum.lo = (__force __le64) crc->crc64.csum_lo, }; *((__le16 *) &ret.csum.hi) = (__le16 __force) crc->crc64.csum_hi; return ret; } case BCH_EXTENT_ENTRY_crc128: { struct bch_extent_crc_unpacked ret = (struct bch_extent_crc_unpacked) { common_fields(crc->crc128), .nonce = crc->crc128.nonce, .csum = crc->crc128.csum, }; return ret; } default: BUG(); } #undef common_fields } static inline bool crc_is_compressed(struct bch_extent_crc_unpacked crc) { return (crc.compression_type != BCH_COMPRESSION_TYPE_none && crc.compression_type != BCH_COMPRESSION_TYPE_incompressible); } static inline bool crc_is_encoded(struct bch_extent_crc_unpacked crc) { return crc.csum_type != BCH_CSUM_none || crc_is_compressed(crc); } void bch2_extent_crc_unpacked_to_text(struct printbuf *, struct bch_extent_crc_unpacked *); /* bkey_ptrs: generically over any key type that has ptrs */ struct bkey_ptrs_c { const union bch_extent_entry *start; const union bch_extent_entry *end; }; struct bkey_ptrs { union bch_extent_entry *start; union bch_extent_entry *end; }; static inline struct bkey_ptrs_c bch2_bkey_ptrs_c(struct bkey_s_c k) { switch (k.k->type) { case KEY_TYPE_btree_ptr: { struct bkey_s_c_btree_ptr e = bkey_s_c_to_btree_ptr(k); return (struct bkey_ptrs_c) { to_entry(&e.v->start[0]), to_entry(extent_entry_last(e)) }; } case KEY_TYPE_extent: { struct bkey_s_c_extent e = bkey_s_c_to_extent(k); return (struct bkey_ptrs_c) { e.v->start, extent_entry_last(e) }; } case KEY_TYPE_stripe: { struct bkey_s_c_stripe s = bkey_s_c_to_stripe(k); return (struct bkey_ptrs_c) { to_entry(&s.v->ptrs[0]), to_entry(&s.v->ptrs[s.v->nr_blocks]), }; } case KEY_TYPE_reflink_v: { struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(k); return (struct bkey_ptrs_c) { r.v->start, bkey_val_end(r), }; } case KEY_TYPE_btree_ptr_v2: { struct bkey_s_c_btree_ptr_v2 e = bkey_s_c_to_btree_ptr_v2(k); return (struct bkey_ptrs_c) { to_entry(&e.v->start[0]), to_entry(extent_entry_last(e)) }; } default: return (struct bkey_ptrs_c) { NULL, NULL }; } } static inline struct bkey_ptrs bch2_bkey_ptrs(struct bkey_s k) { struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k.s_c); return (struct bkey_ptrs) { (void *) p.start, (void *) p.end }; } #define __bkey_extent_entry_for_each_from(_start, _end, _entry) \ for ((_entry) = (_start); \ (_entry) < (_end); \ (_entry) = extent_entry_next_safe(_entry, _end)) #define __bkey_ptr_next(_ptr, _end) \ ({ \ typeof(_end) _entry; \ \ __bkey_extent_entry_for_each_from(to_entry(_ptr), _end, _entry) \ if (extent_entry_is_ptr(_entry)) \ break; \ \ _entry < (_end) ? entry_to_ptr(_entry) : NULL; \ }) #define bkey_extent_entry_for_each_from(_p, _entry, _start) \ __bkey_extent_entry_for_each_from(_start, (_p).end, _entry) #define bkey_extent_entry_for_each(_p, _entry) \ bkey_extent_entry_for_each_from(_p, _entry, _p.start) #define __bkey_for_each_ptr(_start, _end, _ptr) \ for (typeof(_start) (_ptr) = (_start); \ ((_ptr) = __bkey_ptr_next(_ptr, _end)); \ (_ptr)++) #define bkey_ptr_next(_p, _ptr) \ __bkey_ptr_next(_ptr, (_p).end) #define bkey_for_each_ptr(_p, _ptr) \ __bkey_for_each_ptr(&(_p).start->ptr, (_p).end, _ptr) #define __bkey_ptr_next_decode(_k, _end, _ptr, _entry) \ ({ \ __label__ out; \ \ (_ptr).idx = 0; \ (_ptr).has_ec = false; \ \ __bkey_extent_entry_for_each_from(_entry, _end, _entry) \ switch (__extent_entry_type(_entry)) { \ case BCH_EXTENT_ENTRY_ptr: \ (_ptr).ptr = _entry->ptr; \ goto out; \ case BCH_EXTENT_ENTRY_crc32: \ case BCH_EXTENT_ENTRY_crc64: \ case BCH_EXTENT_ENTRY_crc128: \ (_ptr).crc = bch2_extent_crc_unpack(_k, \ entry_to_crc(_entry)); \ break; \ case BCH_EXTENT_ENTRY_stripe_ptr: \ (_ptr).ec = _entry->stripe_ptr; \ (_ptr).has_ec = true; \ break; \ default: \ /* nothing */ \ break; \ } \ out: \ _entry < (_end); \ }) #define __bkey_for_each_ptr_decode(_k, _start, _end, _ptr, _entry) \ for ((_ptr).crc = bch2_extent_crc_unpack(_k, NULL), \ (_entry) = _start; \ __bkey_ptr_next_decode(_k, _end, _ptr, _entry); \ (_entry) = extent_entry_next_safe(_entry, _end)) #define bkey_for_each_ptr_decode(_k, _p, _ptr, _entry) \ __bkey_for_each_ptr_decode(_k, (_p).start, (_p).end, \ _ptr, _entry) #define bkey_crc_next(_k, _end, _crc, _iter) \ ({ \ __bkey_extent_entry_for_each_from(_iter, _end, _iter) \ if (extent_entry_is_crc(_iter)) { \ (_crc) = bch2_extent_crc_unpack(_k, \ entry_to_crc(_iter)); \ break; \ } \ \ (_iter) < (_end); \ }) #define __bkey_for_each_crc(_k, _start, _end, _crc, _iter) \ for ((_crc) = bch2_extent_crc_unpack(_k, NULL), \ (_iter) = (_start); \ bkey_crc_next(_k, _end, _crc, _iter); \ (_iter) = extent_entry_next(_iter)) #define bkey_for_each_crc(_k, _p, _crc, _iter) \ __bkey_for_each_crc(_k, (_p).start, (_p).end, _crc, _iter) /* Iterate over pointers in KEY_TYPE_extent: */ #define extent_for_each_entry_from(_e, _entry, _start) \ __bkey_extent_entry_for_each_from(_start, \ extent_entry_last(_e), _entry) #define extent_for_each_entry(_e, _entry) \ extent_for_each_entry_from(_e, _entry, (_e).v->start) #define extent_ptr_next(_e, _ptr) \ __bkey_ptr_next(_ptr, extent_entry_last(_e)) #define extent_for_each_ptr(_e, _ptr) \ __bkey_for_each_ptr(&(_e).v->start->ptr, extent_entry_last(_e), _ptr) #define extent_for_each_ptr_decode(_e, _ptr, _entry) \ __bkey_for_each_ptr_decode((_e).k, (_e).v->start, \ extent_entry_last(_e), _ptr, _entry) /* utility code common to all keys with pointers: */ struct bch_dev_io_failures *bch2_dev_io_failures(struct bch_io_failures *, unsigned); void bch2_mark_io_failure(struct bch_io_failures *, struct extent_ptr_decoded *); int bch2_bkey_pick_read_device(struct bch_fs *, struct bkey_s_c, struct bch_io_failures *, struct extent_ptr_decoded *); /* KEY_TYPE_btree_ptr: */ int bch2_btree_ptr_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); void bch2_btree_ptr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_btree_ptr_v2_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); void bch2_btree_ptr_v2_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned, int, struct bkey_s); #define bch2_bkey_ops_btree_ptr ((struct bkey_ops) { \ .key_validate = bch2_btree_ptr_validate, \ .val_to_text = bch2_btree_ptr_to_text, \ .swab = bch2_ptr_swab, \ .trigger = bch2_trigger_extent, \ }) #define bch2_bkey_ops_btree_ptr_v2 ((struct bkey_ops) { \ .key_validate = bch2_btree_ptr_v2_validate, \ .val_to_text = bch2_btree_ptr_v2_to_text, \ .swab = bch2_ptr_swab, \ .compat = bch2_btree_ptr_v2_compat, \ .trigger = bch2_trigger_extent, \ .min_val_size = 40, \ }) /* KEY_TYPE_extent: */ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); #define bch2_bkey_ops_extent ((struct bkey_ops) { \ .key_validate = bch2_bkey_ptrs_validate, \ .val_to_text = bch2_bkey_ptrs_to_text, \ .swab = bch2_ptr_swab, \ .key_normalize = bch2_extent_normalize, \ .key_merge = bch2_extent_merge, \ .trigger = bch2_trigger_extent, \ }) /* KEY_TYPE_reservation: */ int bch2_reservation_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); void bch2_reservation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); #define bch2_bkey_ops_reservation ((struct bkey_ops) { \ .key_validate = bch2_reservation_validate, \ .val_to_text = bch2_reservation_to_text, \ .key_merge = bch2_reservation_merge, \ .trigger = bch2_trigger_reservation, \ .min_val_size = 8, \ }) /* Extent checksum entries: */ bool bch2_can_narrow_extent_crcs(struct bkey_s_c, struct bch_extent_crc_unpacked); bool bch2_bkey_narrow_crcs(struct bkey_i *, struct bch_extent_crc_unpacked); void bch2_extent_crc_append(struct bkey_i *, struct bch_extent_crc_unpacked); /* Generic code for keys with pointers: */ static inline bool bkey_is_btree_ptr(const struct bkey *k) { switch (k->type) { case KEY_TYPE_btree_ptr: case KEY_TYPE_btree_ptr_v2: return true; default: return false; } } static inline bool bkey_extent_is_direct_data(const struct bkey *k) { switch (k->type) { case KEY_TYPE_btree_ptr: case KEY_TYPE_btree_ptr_v2: case KEY_TYPE_extent: case KEY_TYPE_reflink_v: return true; default: return false; } } static inline bool bkey_extent_is_inline_data(const struct bkey *k) { return k->type == KEY_TYPE_inline_data || k->type == KEY_TYPE_indirect_inline_data; } static inline unsigned bkey_inline_data_offset(const struct bkey *k) { switch (k->type) { case KEY_TYPE_inline_data: return sizeof(struct bch_inline_data); case KEY_TYPE_indirect_inline_data: return sizeof(struct bch_indirect_inline_data); default: BUG(); } } static inline unsigned bkey_inline_data_bytes(const struct bkey *k) { return bkey_val_bytes(k) - bkey_inline_data_offset(k); } #define bkey_inline_data_p(_k) (((void *) (_k).v) + bkey_inline_data_offset((_k).k)) static inline bool bkey_extent_is_data(const struct bkey *k) { return bkey_extent_is_direct_data(k) || bkey_extent_is_inline_data(k) || k->type == KEY_TYPE_reflink_p; } /* * Should extent be counted under inode->i_sectors? */ static inline bool bkey_extent_is_allocation(const struct bkey *k) { switch (k->type) { case KEY_TYPE_extent: case KEY_TYPE_reservation: case KEY_TYPE_reflink_p: case KEY_TYPE_reflink_v: case KEY_TYPE_inline_data: case KEY_TYPE_indirect_inline_data: case KEY_TYPE_error: return true; default: return false; } } static inline bool bkey_extent_is_unwritten(struct bkey_s_c k) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(ptrs, ptr) if (ptr->unwritten) return true; return false; } static inline bool bkey_extent_is_reservation(struct bkey_s_c k) { return k.k->type == KEY_TYPE_reservation || bkey_extent_is_unwritten(k); } static inline struct bch_devs_list bch2_bkey_devs(struct bkey_s_c k) { struct bch_devs_list ret = (struct bch_devs_list) { 0 }; struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(p, ptr) ret.data[ret.nr++] = ptr->dev; return ret; } static inline struct bch_devs_list bch2_bkey_dirty_devs(struct bkey_s_c k) { struct bch_devs_list ret = (struct bch_devs_list) { 0 }; struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(p, ptr) if (!ptr->cached) ret.data[ret.nr++] = ptr->dev; return ret; } static inline struct bch_devs_list bch2_bkey_cached_devs(struct bkey_s_c k) { struct bch_devs_list ret = (struct bch_devs_list) { 0 }; struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(p, ptr) if (ptr->cached) ret.data[ret.nr++] = ptr->dev; return ret; } unsigned bch2_bkey_nr_ptrs(struct bkey_s_c); unsigned bch2_bkey_nr_ptrs_allocated(struct bkey_s_c); unsigned bch2_bkey_nr_ptrs_fully_allocated(struct bkey_s_c); bool bch2_bkey_is_incompressible(struct bkey_s_c); unsigned bch2_bkey_sectors_compressed(struct bkey_s_c); unsigned bch2_bkey_replicas(struct bch_fs *, struct bkey_s_c); unsigned bch2_extent_ptr_desired_durability(struct bch_fs *, struct extent_ptr_decoded *); unsigned bch2_extent_ptr_durability(struct bch_fs *, struct extent_ptr_decoded *); unsigned bch2_bkey_durability(struct bch_fs *, struct bkey_s_c); const struct bch_extent_ptr *bch2_bkey_has_device_c(struct bkey_s_c, unsigned); static inline struct bch_extent_ptr *bch2_bkey_has_device(struct bkey_s k, unsigned dev) { return (void *) bch2_bkey_has_device_c(k.s_c, dev); } bool bch2_bkey_has_target(struct bch_fs *, struct bkey_s_c, unsigned); void bch2_bkey_extent_entry_drop(struct bkey_i *, union bch_extent_entry *); static inline void bch2_bkey_append_ptr(struct bkey_i *k, struct bch_extent_ptr ptr) { struct bch_extent_ptr *dest; EBUG_ON(bch2_bkey_has_device(bkey_i_to_s(k), ptr.dev)); switch (k->k.type) { case KEY_TYPE_btree_ptr: case KEY_TYPE_btree_ptr_v2: case KEY_TYPE_extent: EBUG_ON(bkey_val_u64s(&k->k) >= BKEY_EXTENT_VAL_U64s_MAX); ptr.type = 1 << BCH_EXTENT_ENTRY_ptr; dest = (struct bch_extent_ptr *)((void *) &k->v + bkey_val_bytes(&k->k)); *dest = ptr; k->k.u64s++; break; default: BUG(); } } void bch2_extent_ptr_decoded_append(struct bkey_i *, struct extent_ptr_decoded *); void bch2_bkey_drop_ptr_noerror(struct bkey_s, struct bch_extent_ptr *); void bch2_bkey_drop_ptr(struct bkey_s, struct bch_extent_ptr *); void bch2_bkey_drop_device_noerror(struct bkey_s, unsigned); void bch2_bkey_drop_device(struct bkey_s, unsigned); #define bch2_bkey_drop_ptrs_noerror(_k, _ptr, _cond) \ do { \ __label__ _again; \ struct bkey_ptrs _ptrs; \ _again: \ _ptrs = bch2_bkey_ptrs(_k); \ \ bkey_for_each_ptr(_ptrs, _ptr) \ if (_cond) { \ bch2_bkey_drop_ptr_noerror(_k, _ptr); \ goto _again; \ } \ } while (0) #define bch2_bkey_drop_ptrs(_k, _ptr, _cond) \ do { \ __label__ _again; \ struct bkey_ptrs _ptrs; \ _again: \ _ptrs = bch2_bkey_ptrs(_k); \ \ bkey_for_each_ptr(_ptrs, _ptr) \ if (_cond) { \ bch2_bkey_drop_ptr(_k, _ptr); \ goto _again; \ } \ } while (0) bool bch2_bkey_matches_ptr(struct bch_fs *, struct bkey_s_c, struct bch_extent_ptr, u64); bool bch2_extents_match(struct bkey_s_c, struct bkey_s_c); struct bch_extent_ptr * bch2_extent_has_ptr(struct bkey_s_c, struct extent_ptr_decoded, struct bkey_s); void bch2_extent_ptr_set_cached(struct bch_fs *, struct bch_io_opts *, struct bkey_s, struct bch_extent_ptr *); bool bch2_extent_normalize_by_opts(struct bch_fs *, struct bch_io_opts *, struct bkey_s); bool bch2_extent_normalize(struct bch_fs *, struct bkey_s); void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *); void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_bkey_ptrs_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1, struct bch_extent_ptr ptr2) { return (ptr1.cached == ptr2.cached && ptr1.unwritten == ptr2.unwritten && ptr1.offset == ptr2.offset && ptr1.dev == ptr2.dev && ptr1.dev == ptr2.dev); } void bch2_ptr_swab(struct bkey_s); /* Generic extent code: */ enum bch_extent_overlap { BCH_EXTENT_OVERLAP_ALL = 0, BCH_EXTENT_OVERLAP_BACK = 1, BCH_EXTENT_OVERLAP_FRONT = 2, BCH_EXTENT_OVERLAP_MIDDLE = 3, }; /* Returns how k overlaps with m */ static inline enum bch_extent_overlap bch2_extent_overlap(const struct bkey *k, const struct bkey *m) { int cmp1 = bkey_lt(k->p, m->p); int cmp2 = bkey_gt(bkey_start_pos(k), bkey_start_pos(m)); return (cmp1 << 1) + cmp2; } int bch2_cut_front_s(struct bpos, struct bkey_s); int bch2_cut_back_s(struct bpos, struct bkey_s); static inline void bch2_cut_front(struct bpos where, struct bkey_i *k) { bch2_cut_front_s(where, bkey_i_to_s(k)); } static inline void bch2_cut_back(struct bpos where, struct bkey_i *k) { bch2_cut_back_s(where, bkey_i_to_s(k)); } /** * bch_key_resize - adjust size of @k * * bkey_start_offset(k) will be preserved, modifies where the extent ends */ static inline void bch2_key_resize(struct bkey *k, unsigned new_size) { k->p.offset -= k->size; k->p.offset += new_size; k->size = new_size; } #endif /* _BCACHEFS_EXTENTS_H */ |
| 208 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_KSM_H #define __LINUX_KSM_H /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork(). */ #include <linux/bitops.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); /* * To identify zeropages that were mapped by KSM, we reuse the dirty bit * in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when * deduplicating memory. */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) extern atomic_long_t ksm_zero_pages; static inline void ksm_map_zero_page(struct mm_struct *mm) { atomic_long_inc(&ksm_zero_pages); atomic_long_inc(&mm->ksm_zero_pages); } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { atomic_long_dec(&ksm_zero_pages); atomic_long_dec(&mm->ksm_zero_pages); } } static inline long mm_ksm_zero_pages(struct mm_struct *mm) { return atomic_long_read(&mm->ksm_zero_pages); } static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { /* Adding mm to ksm is best effort on fork. */ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) __ksm_enter(mm); } static inline int ksm_execve(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return __ksm_enter(mm); return 0; } static inline void ksm_exit(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) __ksm_exit(mm); } /* * When do_swap_page() first faults in from swap what used to be a KSM page, * no problem, it will be assigned to this vma's anon_vma; but thereafter, * it might be faulted into a different anon_vma (or perhaps to a different * offset in the same anon_vma). do_swap_page() cannot do all the locking * needed to reconstitute a cross-anon_vma KSM page: for now it has to make * a copy, and leave remerging the pages to a later pass of ksmd. * * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr); void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); bool ksm_process_mergeable(struct mm_struct *mm); #else /* !CONFIG_KSM */ static inline void ksm_add_vma(struct vm_area_struct *vma) { } static inline int ksm_disable(struct mm_struct *mm) { return 0; } static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { } static inline int ksm_execve(struct mm_struct *mm) { return 0; } static inline void ksm_exit(struct mm_struct *mm) { } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } static inline void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early) { } #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { return 0; } static inline struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { return folio; } static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old) { } #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ #endif /* __LINUX_KSM_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Symmetric key ciphers. * * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_SKCIPHER_H #define _CRYPTO_INTERNAL_SKCIPHER_H #include <crypto/algapi.h> #include <crypto/internal/cipher.h> #include <crypto/skcipher.h> #include <linux/types.h> /* * Set this if your algorithm is sync but needs a reqsize larger * than MAX_SYNC_SKCIPHER_REQSIZE. * * Reuse bit that is specific to hash algorithms. */ #define CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE CRYPTO_ALG_OPTIONAL_KEY struct aead_request; struct rtattr; struct skcipher_instance { void (*free)(struct skcipher_instance *inst); union { struct { char head[offsetof(struct skcipher_alg, base)]; struct crypto_instance base; } s; struct skcipher_alg alg; }; }; struct lskcipher_instance { void (*free)(struct lskcipher_instance *inst); union { struct { char head[offsetof(struct lskcipher_alg, co.base)]; struct crypto_instance base; } s; struct lskcipher_alg alg; }; }; struct crypto_skcipher_spawn { struct crypto_spawn base; }; struct crypto_lskcipher_spawn { struct crypto_spawn base; }; struct skcipher_walk { union { struct { void *addr; } virt; } src, dst; struct scatter_walk in; unsigned int nbytes; struct scatter_walk out; unsigned int total; u8 *page; u8 *buffer; u8 *oiv; void *iv; unsigned int ivsize; int flags; unsigned int blocksize; unsigned int stride; unsigned int alignmask; }; static inline struct crypto_instance *skcipher_crypto_instance( struct skcipher_instance *inst) { return &inst->s.base; } static inline struct crypto_instance *lskcipher_crypto_instance( struct lskcipher_instance *inst) { return &inst->s.base; } static inline struct skcipher_instance *skcipher_alg_instance( struct crypto_skcipher *skcipher) { return container_of(crypto_skcipher_alg(skcipher), struct skcipher_instance, alg); } static inline struct lskcipher_instance *lskcipher_alg_instance( struct crypto_lskcipher *lskcipher) { return container_of(crypto_lskcipher_alg(lskcipher), struct lskcipher_instance, alg); } static inline void *skcipher_instance_ctx(struct skcipher_instance *inst) { return crypto_instance_ctx(skcipher_crypto_instance(inst)); } static inline void *lskcipher_instance_ctx(struct lskcipher_instance *inst) { return crypto_instance_ctx(lskcipher_crypto_instance(inst)); } static inline void skcipher_request_complete(struct skcipher_request *req, int err) { crypto_request_complete(&req->base, err); } int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); int crypto_grab_lskcipher(struct crypto_lskcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline void crypto_drop_lskcipher(struct crypto_lskcipher_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct lskcipher_alg *crypto_lskcipher_spawn_alg( struct crypto_lskcipher_spawn *spawn) { return container_of(spawn->base.alg, struct lskcipher_alg, co.base); } static inline struct skcipher_alg_common *crypto_spawn_skcipher_alg_common( struct crypto_skcipher_spawn *spawn) { return container_of(spawn->base.alg, struct skcipher_alg_common, base); } static inline struct lskcipher_alg *crypto_spawn_lskcipher_alg( struct crypto_lskcipher_spawn *spawn) { return crypto_lskcipher_spawn_alg(spawn); } static inline struct crypto_skcipher *crypto_spawn_skcipher( struct crypto_skcipher_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline struct crypto_lskcipher *crypto_spawn_lskcipher( struct crypto_lskcipher_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline void crypto_skcipher_set_reqsize( struct crypto_skcipher *skcipher, unsigned int reqsize) { skcipher->reqsize = reqsize; } static inline void crypto_skcipher_set_reqsize_dma( struct crypto_skcipher *skcipher, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); skcipher->reqsize = reqsize; } int crypto_register_skcipher(struct skcipher_alg *alg); void crypto_unregister_skcipher(struct skcipher_alg *alg); int crypto_register_skciphers(struct skcipher_alg *algs, int count); void crypto_unregister_skciphers(struct skcipher_alg *algs, int count); int skcipher_register_instance(struct crypto_template *tmpl, struct skcipher_instance *inst); int crypto_register_lskcipher(struct lskcipher_alg *alg); void crypto_unregister_lskcipher(struct lskcipher_alg *alg); int crypto_register_lskciphers(struct lskcipher_alg *algs, int count); void crypto_unregister_lskciphers(struct lskcipher_alg *algs, int count); int lskcipher_register_instance(struct crypto_template *tmpl, struct lskcipher_instance *inst); int skcipher_walk_done(struct skcipher_walk *walk, int res); int skcipher_walk_virt(struct skcipher_walk *walk, struct skcipher_request *req, bool atomic); int skcipher_walk_aead_encrypt(struct skcipher_walk *walk, struct aead_request *req, bool atomic); int skcipher_walk_aead_decrypt(struct skcipher_walk *walk, struct aead_request *req, bool atomic); static inline void skcipher_walk_abort(struct skcipher_walk *walk) { skcipher_walk_done(walk, -ECANCELED); } static inline void *crypto_skcipher_ctx(struct crypto_skcipher *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline void *crypto_lskcipher_ctx(struct crypto_lskcipher *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline void *crypto_skcipher_ctx_dma(struct crypto_skcipher *tfm) { return crypto_tfm_ctx_dma(&tfm->base); } static inline void *skcipher_request_ctx(struct skcipher_request *req) { return req->__ctx; } static inline void *skcipher_request_ctx_dma(struct skcipher_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(skcipher_request_ctx(req), align); } static inline u32 skcipher_request_flags(struct skcipher_request *req) { return req->base.flags; } /* Helpers for simple block cipher modes of operation */ struct skcipher_ctx_simple { struct crypto_cipher *cipher; /* underlying block cipher */ }; static inline struct crypto_cipher * skcipher_cipher_simple(struct crypto_skcipher *tfm) { struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm); return ctx->cipher; } struct skcipher_instance *skcipher_alloc_instance_simple( struct crypto_template *tmpl, struct rtattr **tb); static inline struct crypto_alg *skcipher_ialg_simple( struct skcipher_instance *inst) { struct crypto_cipher_spawn *spawn = skcipher_instance_ctx(inst); return crypto_spawn_cipher_alg(spawn); } static inline struct crypto_lskcipher *lskcipher_cipher_simple( struct crypto_lskcipher *tfm) { struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm); return *ctx; } struct lskcipher_instance *lskcipher_alloc_instance_simple( struct crypto_template *tmpl, struct rtattr **tb); static inline struct lskcipher_alg *lskcipher_ialg_simple( struct lskcipher_instance *inst) { struct crypto_lskcipher_spawn *spawn = lskcipher_instance_ctx(inst); return crypto_lskcipher_spawn_alg(spawn); } #endif /* _CRYPTO_INTERNAL_SKCIPHER_H */ |
| 1 1 1 78 78 78 78 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 | // SPDX-License-Identifier: GPL-2.0+ /* * 2002-10-15 Posix Clocks & timers * by George Anzinger george@mvista.com * Copyright (C) 2002 2003 by MontaVista Software. * * 2004-06-01 Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug. * Copyright (C) 2004 Boris Hu * * These are all the functions necessary to implement POSIX clocks & timers */ #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/sched/task.h> #include <linux/uaccess.h> #include <linux/list.h> #include <linux/init.h> #include <linux/compiler.h> #include <linux/hash.h> #include <linux/posix-clock.h> #include <linux/posix-timers.h> #include <linux/syscalls.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <linux/export.h> #include <linux/hashtable.h> #include <linux/compat.h> #include <linux/nospec.h> #include <linux/time_namespace.h> #include "timekeeping.h" #include "posix-timers.h" static struct kmem_cache *posix_timers_cache; /* * Timers are managed in a hash table for lockless lookup. The hash key is * constructed from current::signal and the timer ID and the timer is * matched against current::signal and the timer ID when walking the hash * bucket list. * * This allows checkpoint/restore to reconstruct the exact timer IDs for * a process. */ static DEFINE_HASHTABLE(posix_timers_hashtable, 9); static DEFINE_SPINLOCK(hash_lock); static const struct k_clock * const posix_clocks[]; static const struct k_clock *clockid_to_kclock(const clockid_t id); static const struct k_clock clock_realtime, clock_monotonic; /* SIGEV_THREAD_ID cannot share a bit with the other SIGEV values. */ #if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \ ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD)) #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!" #endif static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags); #define lock_timer(tid, flags) \ ({ struct k_itimer *__timr; \ __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags)); \ __timr; \ }) static int hash(struct signal_struct *sig, unsigned int nr) { return hash_32(hash32_ptr(sig) ^ nr, HASH_BITS(posix_timers_hashtable)); } static struct k_itimer *__posix_timers_find(struct hlist_head *head, struct signal_struct *sig, timer_t id) { struct k_itimer *timer; hlist_for_each_entry_rcu(timer, head, t_hash, lockdep_is_held(&hash_lock)) { /* timer->it_signal can be set concurrently */ if ((READ_ONCE(timer->it_signal) == sig) && (timer->it_id == id)) return timer; } return NULL; } static struct k_itimer *posix_timer_by_id(timer_t id) { struct signal_struct *sig = current->signal; struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)]; return __posix_timers_find(head, sig, id); } static int posix_timer_add(struct k_itimer *timer) { struct signal_struct *sig = current->signal; struct hlist_head *head; unsigned int cnt, id; /* * FIXME: Replace this by a per signal struct xarray once there is * a plan to handle the resulting CRIU regression gracefully. */ for (cnt = 0; cnt <= INT_MAX; cnt++) { spin_lock(&hash_lock); id = sig->next_posix_timer_id; /* Write the next ID back. Clamp it to the positive space */ sig->next_posix_timer_id = (id + 1) & INT_MAX; head = &posix_timers_hashtable[hash(sig, id)]; if (!__posix_timers_find(head, sig, id)) { hlist_add_head_rcu(&timer->t_hash, head); spin_unlock(&hash_lock); return id; } spin_unlock(&hash_lock); } /* POSIX return code when no timer ID could be allocated */ return -EAGAIN; } static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) { spin_unlock_irqrestore(&timr->it_lock, flags); } static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_real_ts64(tp); return 0; } static ktime_t posix_get_realtime_ktime(clockid_t which_clock) { return ktime_get_real(); } static int posix_clock_realtime_set(const clockid_t which_clock, const struct timespec64 *tp) { return do_sys_settimeofday64(tp, NULL); } static int posix_clock_realtime_adj(const clockid_t which_clock, struct __kernel_timex *t) { return do_adjtimex(t); } static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_ts64(tp); timens_add_monotonic(tp); return 0; } static ktime_t posix_get_monotonic_ktime(clockid_t which_clock) { return ktime_get(); } static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { ktime_get_raw_ts64(tp); timens_add_monotonic(tp); return 0; } static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp) { ktime_get_coarse_real_ts64(tp); return 0; } static int posix_get_monotonic_coarse(clockid_t which_clock, struct timespec64 *tp) { ktime_get_coarse_ts64(tp); timens_add_monotonic(tp); return 0; } static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *tp) { *tp = ktime_to_timespec64(KTIME_LOW_RES); return 0; } static int posix_get_boottime_timespec(const clockid_t which_clock, struct timespec64 *tp) { ktime_get_boottime_ts64(tp); timens_add_boottime(tp); return 0; } static ktime_t posix_get_boottime_ktime(const clockid_t which_clock) { return ktime_get_boottime(); } static int posix_get_tai_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_clocktai_ts64(tp); return 0; } static ktime_t posix_get_tai_ktime(clockid_t which_clock) { return ktime_get_clocktai(); } static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp) { tp->tv_sec = 0; tp->tv_nsec = hrtimer_resolution; return 0; } static __init int init_posix_timers(void) { posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof(struct k_itimer), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } __initcall(init_posix_timers); /* * The siginfo si_overrun field and the return value of timer_getoverrun(2) * are of type int. Clamp the overrun value to INT_MAX */ static inline int timer_overrun_to_int(struct k_itimer *timr) { if (timr->it_overrun_last > (s64)INT_MAX) return INT_MAX; return (int)timr->it_overrun_last; } static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(), timr->it_interval); hrtimer_restart(timer); } static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr) { guard(spinlock)(&timr->it_lock); /* * Check if the timer is still alive or whether it got modified * since the signal was queued. In either case, don't rearm and * drop the signal. */ if (timr->it_signal_seq != timr->it_sigqueue_seq || WARN_ON_ONCE(!timr->it_signal)) return false; if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) return true; timr->kclock->timer_rearm(timr); timr->it_status = POSIX_TIMER_ARMED; timr->it_overrun_last = timr->it_overrun; timr->it_overrun = -1LL; ++timr->it_signal_seq; info->si_overrun = timer_overrun_to_int(timr); return true; } /* * This function is called from the signal delivery code. It decides * whether the signal should be dropped and rearms interval timers. The * timer can be unconditionally accessed as there is a reference held on * it. */ bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { struct k_itimer *timr = container_of(timer_sigq, struct k_itimer, sigq); bool ret; /* * Release siglock to ensure proper locking order versus * timr::it_lock. Keep interrupts disabled. */ spin_unlock(¤t->sighand->siglock); ret = __posixtimer_deliver_signal(info, timr); /* Drop the reference which was acquired when the signal was queued */ posixtimer_putref(timr); spin_lock(¤t->sighand->siglock); return ret; } void posix_timer_queue_signal(struct k_itimer *timr) { lockdep_assert_held(&timr->it_lock); timr->it_status = timr->it_interval ? POSIX_TIMER_REQUEUE_PENDING : POSIX_TIMER_DISARMED; posixtimer_send_sigqueue(timr); } /* * This function gets called when a POSIX.1b interval timer expires from * the HRTIMER interrupt (soft interrupt on RT kernels). * * Handles CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME and CLOCK_TAI * based timers. */ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer); guard(spinlock_irqsave)(&timr->it_lock); posix_timer_queue_signal(timr); return HRTIMER_NORESTART; } static struct pid *good_sigevent(sigevent_t * event) { struct pid *pid = task_tgid(current); struct task_struct *rtn; switch (event->sigev_notify) { case SIGEV_SIGNAL | SIGEV_THREAD_ID: pid = find_vpid(event->sigev_notify_thread_id); rtn = pid_task(pid, PIDTYPE_PID); if (!rtn || !same_thread_group(rtn, current)) return NULL; fallthrough; case SIGEV_SIGNAL: case SIGEV_THREAD: if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX) return NULL; fallthrough; case SIGEV_NONE: return pid; default: return NULL; } } static struct k_itimer *alloc_posix_timer(void) { struct k_itimer *tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); if (!tmr) return tmr; if (unlikely(!posixtimer_init_sigqueue(&tmr->sigq))) { kmem_cache_free(posix_timers_cache, tmr); return NULL; } rcuref_init(&tmr->rcuref, 1); return tmr; } void posixtimer_free_timer(struct k_itimer *tmr) { put_pid(tmr->it_pid); if (tmr->sigq.ucounts) dec_rlimit_put_ucounts(tmr->sigq.ucounts, UCOUNT_RLIMIT_SIGPENDING); kfree_rcu(tmr, rcu); } static void posix_timer_unhash_and_free(struct k_itimer *tmr) { spin_lock(&hash_lock); hlist_del_rcu(&tmr->t_hash); spin_unlock(&hash_lock); posixtimer_putref(tmr); } static int common_timer_create(struct k_itimer *new_timer) { hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0); return 0; } /* Create a POSIX.1b interval timer. */ static int do_timer_create(clockid_t which_clock, struct sigevent *event, timer_t __user *created_timer_id) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct k_itimer *new_timer; int error, new_timer_id; if (!kc) return -EINVAL; if (!kc->timer_create) return -EOPNOTSUPP; new_timer = alloc_posix_timer(); if (unlikely(!new_timer)) return -EAGAIN; spin_lock_init(&new_timer->it_lock); /* * Add the timer to the hash table. The timer is not yet valid * because new_timer::it_signal is still NULL. The timer id is also * not yet visible to user space. */ new_timer_id = posix_timer_add(new_timer); if (new_timer_id < 0) { posixtimer_free_timer(new_timer); return new_timer_id; } new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; new_timer->kclock = kc; new_timer->it_overrun = -1LL; if (event) { rcu_read_lock(); new_timer->it_pid = get_pid(good_sigevent(event)); rcu_read_unlock(); if (!new_timer->it_pid) { error = -EINVAL; goto out; } new_timer->it_sigev_notify = event->sigev_notify; new_timer->sigq.info.si_signo = event->sigev_signo; new_timer->sigq.info.si_value = event->sigev_value; } else { new_timer->it_sigev_notify = SIGEV_SIGNAL; new_timer->sigq.info.si_signo = SIGALRM; memset(&new_timer->sigq.info.si_value, 0, sizeof(sigval_t)); new_timer->sigq.info.si_value.sival_int = new_timer->it_id; new_timer->it_pid = get_pid(task_tgid(current)); } if (new_timer->it_sigev_notify & SIGEV_THREAD_ID) new_timer->it_pid_type = PIDTYPE_PID; else new_timer->it_pid_type = PIDTYPE_TGID; new_timer->sigq.info.si_tid = new_timer->it_id; new_timer->sigq.info.si_code = SI_TIMER; if (copy_to_user(created_timer_id, &new_timer_id, sizeof (new_timer_id))) { error = -EFAULT; goto out; } /* * After succesful copy out, the timer ID is visible to user space * now but not yet valid because new_timer::signal is still NULL. * * Complete the initialization with the clock specific create * callback. */ error = kc->timer_create(new_timer); if (error) goto out; spin_lock_irq(¤t->sighand->siglock); /* This makes the timer valid in the hash table */ WRITE_ONCE(new_timer->it_signal, current->signal); hlist_add_head(&new_timer->list, ¤t->signal->posix_timers); spin_unlock_irq(¤t->sighand->siglock); /* * After unlocking sighand::siglock @new_timer is subject to * concurrent removal and cannot be touched anymore */ return 0; out: posix_timer_unhash_and_free(new_timer); return error; } SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, struct sigevent __user *, timer_event_spec, timer_t __user *, created_timer_id) { if (timer_event_spec) { sigevent_t event; if (copy_from_user(&event, timer_event_spec, sizeof (event))) return -EFAULT; return do_timer_create(which_clock, &event, created_timer_id); } return do_timer_create(which_clock, NULL, created_timer_id); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, struct compat_sigevent __user *, timer_event_spec, timer_t __user *, created_timer_id) { if (timer_event_spec) { sigevent_t event; if (get_compat_sigevent(&event, timer_event_spec)) return -EFAULT; return do_timer_create(which_clock, &event, created_timer_id); } return do_timer_create(which_clock, NULL, created_timer_id); } #endif static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) { struct k_itimer *timr; /* * timer_t could be any type >= int and we want to make sure any * @timer_id outside positive int range fails lookup. */ if ((unsigned long long)timer_id > INT_MAX) return NULL; /* * The hash lookup and the timers are RCU protected. * * Timers are added to the hash in invalid state where * timr::it_signal == NULL. timer::it_signal is only set after the * rest of the initialization succeeded. * * Timer destruction happens in steps: * 1) Set timr::it_signal to NULL with timr::it_lock held * 2) Release timr::it_lock * 3) Remove from the hash under hash_lock * 4) Put the reference count. * * The reference count might not drop to zero if timr::sigq is * queued. In that case the signal delivery or flush will put the * last reference count. * * When the reference count reaches zero, the timer is scheduled * for RCU removal after the grace period. * * Holding rcu_read_lock() across the lookup ensures that * the timer cannot be freed. * * The lookup validates locklessly that timr::it_signal == * current::it_signal and timr::it_id == @timer_id. timr::it_id * can't change, but timr::it_signal becomes NULL during * destruction. */ rcu_read_lock(); timr = posix_timer_by_id(timer_id); if (timr) { spin_lock_irqsave(&timr->it_lock, *flags); /* * Validate under timr::it_lock that timr::it_signal is * still valid. Pairs with #1 above. */ if (timr->it_signal == current->signal) { rcu_read_unlock(); return timr; } spin_unlock_irqrestore(&timr->it_lock, *flags); } rcu_read_unlock(); return NULL; } static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now) { struct hrtimer *timer = &timr->it.real.timer; return __hrtimer_expires_remaining_adjusted(timer, now); } static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now) { struct hrtimer *timer = &timr->it.real.timer; return hrtimer_forward(timer, now, timr->it_interval); } /* * Get the time remaining on a POSIX.1b interval timer. * * Two issues to handle here: * * 1) The timer has a requeue pending. The return value must appear as * if the timer has been requeued right now. * * 2) The timer is a SIGEV_NONE timer. These timers are never enqueued * into the hrtimer queue and therefore never expired. Emulate expiry * here taking #1 into account. */ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) { const struct k_clock *kc = timr->kclock; ktime_t now, remaining, iv; bool sig_none; sig_none = timr->it_sigev_notify == SIGEV_NONE; iv = timr->it_interval; /* interval timer ? */ if (iv) { cur_setting->it_interval = ktime_to_timespec64(iv); } else if (timr->it_status == POSIX_TIMER_DISARMED) { /* * SIGEV_NONE oneshot timers are never queued and therefore * timr->it_status is always DISARMED. The check below * vs. remaining time will handle this case. * * For all other timers there is nothing to update here, so * return. */ if (!sig_none) return; } now = kc->clock_get_ktime(timr->it_clock); /* * If this is an interval timer and either has requeue pending or * is a SIGEV_NONE timer move the expiry time forward by intervals, * so expiry is > now. */ if (iv && timr->it_status != POSIX_TIMER_ARMED) timr->it_overrun += kc->timer_forward(timr, now); remaining = kc->timer_remaining(timr, now); /* * As @now is retrieved before a possible timer_forward() and * cannot be reevaluated by the compiler @remaining is based on the * same @now value. Therefore @remaining is consistent vs. @now. * * Consequently all interval timers, i.e. @iv > 0, cannot have a * remaining time <= 0 because timer_forward() guarantees to move * them forward so that the next timer expiry is > @now. */ if (remaining <= 0) { /* * A single shot SIGEV_NONE timer must return 0, when it is * expired! Timers which have a real signal delivery mode * must return a remaining time greater than 0 because the * signal has not yet been delivered. */ if (!sig_none) cur_setting->it_value.tv_nsec = 1; } else { cur_setting->it_value = ktime_to_timespec64(remaining); } } static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) { const struct k_clock *kc; struct k_itimer *timr; unsigned long flags; int ret = 0; timr = lock_timer(timer_id, &flags); if (!timr) return -EINVAL; memset(setting, 0, sizeof(*setting)); kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_get)) ret = -EINVAL; else kc->timer_get(timr, setting); unlock_timer(timr, flags); return ret; } /* Get the time remaining on a POSIX.1b interval timer. */ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, struct __kernel_itimerspec __user *, setting) { struct itimerspec64 cur_setting; int ret = do_timer_gettime(timer_id, &cur_setting); if (!ret) { if (put_itimerspec64(&cur_setting, setting)) ret = -EFAULT; } return ret; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id, struct old_itimerspec32 __user *, setting) { struct itimerspec64 cur_setting; int ret = do_timer_gettime(timer_id, &cur_setting); if (!ret) { if (put_old_itimerspec32(&cur_setting, setting)) ret = -EFAULT; } return ret; } #endif /** * sys_timer_getoverrun - Get the number of overruns of a POSIX.1b interval timer * @timer_id: The timer ID which identifies the timer * * The "overrun count" of a timer is one plus the number of expiration * intervals which have elapsed between the first expiry, which queues the * signal and the actual signal delivery. On signal delivery the "overrun * count" is calculated and cached, so it can be returned directly here. * * As this is relative to the last queued signal the returned overrun count * is meaningless outside of the signal delivery path and even there it * does not accurately reflect the current state when user space evaluates * it. * * Returns: * -EINVAL @timer_id is invalid * 1..INT_MAX The number of overruns related to the last delivered signal */ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) { struct k_itimer *timr; unsigned long flags; int overrun; timr = lock_timer(timer_id, &flags); if (!timr) return -EINVAL; overrun = timer_overrun_to_int(timr); unlock_timer(timr, flags); return overrun; } static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct hrtimer *timer = &timr->it.real.timer; enum hrtimer_mode mode; mode = absolute ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL; /* * Posix magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they become CLOCK_MONOTONIC based under the * hood. See hrtimer_init(). Update timr->kclock, so the generic * functions which use timr->kclock->clock_get_*() work. * * Note: it_clock stays unmodified, because the next timer_set() might * use ABSTIME, so it needs to switch back. */ if (timr->it_clock == CLOCK_REALTIME) timr->kclock = absolute ? &clock_realtime : &clock_monotonic; hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); timr->it.real.timer.function = posix_timer_fn; if (!absolute) expires = ktime_add_safe(expires, timer->base->get_time()); hrtimer_set_expires(timer, expires); if (!sigev_none) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } static int common_hrtimer_try_to_cancel(struct k_itimer *timr) { return hrtimer_try_to_cancel(&timr->it.real.timer); } static void common_timer_wait_running(struct k_itimer *timer) { hrtimer_cancel_wait_running(&timer->it.real.timer); } /* * On PREEMPT_RT this prevents priority inversion and a potential livelock * against the ksoftirqd thread in case that ksoftirqd gets preempted while * executing a hrtimer callback. * * See the comments in hrtimer_cancel_wait_running(). For PREEMPT_RT=n this * just results in a cpu_relax(). * * For POSIX CPU timers with CONFIG_POSIX_CPU_TIMERS_TASK_WORK=n this is * just a cpu_relax(). With CONFIG_POSIX_CPU_TIMERS_TASK_WORK=y this * prevents spinning on an eventually scheduled out task and a livelock * when the task which tries to delete or disarm the timer has preempted * the task which runs the expiry in task work context. */ static struct k_itimer *timer_wait_running(struct k_itimer *timer, unsigned long *flags) { const struct k_clock *kc = READ_ONCE(timer->kclock); timer_t timer_id = READ_ONCE(timer->it_id); /* Prevent kfree(timer) after dropping the lock */ rcu_read_lock(); unlock_timer(timer, *flags); /* * kc->timer_wait_running() might drop RCU lock. So @timer * cannot be touched anymore after the function returns! */ if (!WARN_ON_ONCE(!kc->timer_wait_running)) kc->timer_wait_running(timer); rcu_read_unlock(); /* Relock the timer. It might be not longer hashed. */ return lock_timer(timer_id, flags); } /* * Set up the new interval and reset the signal delivery data */ void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting) { if (new_setting->it_value.tv_sec || new_setting->it_value.tv_nsec) timer->it_interval = timespec64_to_ktime(new_setting->it_interval); else timer->it_interval = 0; /* Reset overrun accounting */ timer->it_overrun_last = 0; timer->it_overrun = -1LL; } /* Set a POSIX.1b interval timer. */ int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec64 *new_setting, struct itimerspec64 *old_setting) { const struct k_clock *kc = timr->kclock; bool sigev_none; ktime_t expires; if (old_setting) common_timer_get(timr, old_setting); /* * Careful here. On SMP systems the timer expiry function could be * active and spinning on timr->it_lock. */ if (kc->timer_try_to_cancel(timr) < 0) return TIMER_RETRY; timr->it_status = POSIX_TIMER_DISARMED; posix_timer_set_common(timr, new_setting); /* Keep timer disarmed when it_value is zero */ if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) return 0; expires = timespec64_to_ktime(new_setting->it_value); if (flags & TIMER_ABSTIME) expires = timens_ktime_to_host(timr->it_clock, expires); sigev_none = timr->it_sigev_notify == SIGEV_NONE; kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); if (!sigev_none) timr->it_status = POSIX_TIMER_ARMED; return 0; } static int do_timer_settime(timer_t timer_id, int tmr_flags, struct itimerspec64 *new_spec64, struct itimerspec64 *old_spec64) { const struct k_clock *kc; struct k_itimer *timr; unsigned long flags; int error; if (!timespec64_valid(&new_spec64->it_interval) || !timespec64_valid(&new_spec64->it_value)) return -EINVAL; if (old_spec64) memset(old_spec64, 0, sizeof(*old_spec64)); timr = lock_timer(timer_id, &flags); retry: if (!timr) return -EINVAL; if (old_spec64) old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); /* Prevent signal delivery and rearming. */ timr->it_signal_seq++; kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; else error = kc->timer_set(timr, tmr_flags, new_spec64, old_spec64); if (error == TIMER_RETRY) { // We already got the old time... old_spec64 = NULL; /* Unlocks and relocks the timer if it still exists */ timr = timer_wait_running(timr, &flags); goto retry; } unlock_timer(timr, flags); return error; } /* Set a POSIX.1b interval timer */ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, const struct __kernel_itimerspec __user *, new_setting, struct __kernel_itimerspec __user *, old_setting) { struct itimerspec64 new_spec, old_spec, *rtn; int error = 0; if (!new_setting) return -EINVAL; if (get_itimerspec64(&new_spec, new_setting)) return -EFAULT; rtn = old_setting ? &old_spec : NULL; error = do_timer_settime(timer_id, flags, &new_spec, rtn); if (!error && old_setting) { if (put_itimerspec64(&old_spec, old_setting)) error = -EFAULT; } return error; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE4(timer_settime32, timer_t, timer_id, int, flags, struct old_itimerspec32 __user *, new, struct old_itimerspec32 __user *, old) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old ? &old_spec : NULL; int error = 0; if (!new) return -EINVAL; if (get_old_itimerspec32(&new_spec, new)) return -EFAULT; error = do_timer_settime(timer_id, flags, &new_spec, rtn); if (!error && old) { if (put_old_itimerspec32(&old_spec, old)) error = -EFAULT; } return error; } #endif int common_timer_del(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; if (kc->timer_try_to_cancel(timer) < 0) return TIMER_RETRY; timer->it_status = POSIX_TIMER_DISARMED; return 0; } /* * If the deleted timer is on the ignored list, remove it and * drop the associated reference. */ static inline void posix_timer_cleanup_ignored(struct k_itimer *tmr) { if (!hlist_unhashed(&tmr->ignored_list)) { hlist_del_init(&tmr->ignored_list); posixtimer_putref(tmr); } } static inline int timer_delete_hook(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; /* Prevent signal delivery and rearming. */ timer->it_signal_seq++; if (WARN_ON_ONCE(!kc || !kc->timer_del)) return -EINVAL; return kc->timer_del(timer); } /* Delete a POSIX.1b interval timer. */ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) { struct k_itimer *timer; unsigned long flags; timer = lock_timer(timer_id, &flags); retry_delete: if (!timer) return -EINVAL; if (unlikely(timer_delete_hook(timer) == TIMER_RETRY)) { /* Unlocks and relocks the timer if it still exists */ timer = timer_wait_running(timer, &flags); goto retry_delete; } spin_lock(¤t->sighand->siglock); hlist_del(&timer->list); posix_timer_cleanup_ignored(timer); /* * A concurrent lookup could check timer::it_signal lockless. It * will reevaluate with timer::it_lock held and observe the NULL. * * It must be written with siglock held so that the signal code * observes timer->it_signal == NULL in do_sigaction(SIG_IGN), * which prevents it from moving a pending signal of a deleted * timer to the ignore list. */ WRITE_ONCE(timer->it_signal, NULL); spin_unlock(¤t->sighand->siglock); unlock_timer(timer, flags); posix_timer_unhash_and_free(timer); return 0; } /* * Delete a timer if it is armed, remove it from the hash and schedule it * for RCU freeing. */ static void itimer_delete(struct k_itimer *timer) { unsigned long flags; /* * irqsave is required to make timer_wait_running() work. */ spin_lock_irqsave(&timer->it_lock, flags); retry_delete: /* * Even if the timer is not longer accessible from other tasks * it still might be armed and queued in the underlying timer * mechanism. Worse, that timer mechanism might run the expiry * function concurrently. */ if (timer_delete_hook(timer) == TIMER_RETRY) { /* * Timer is expired concurrently, prevent livelocks * and pointless spinning on RT. * * timer_wait_running() drops timer::it_lock, which opens * the possibility for another task to delete the timer. * * That's not possible here because this is invoked from * do_exit() only for the last thread of the thread group. * So no other task can access and delete that timer. */ if (WARN_ON_ONCE(timer_wait_running(timer, &flags) != timer)) return; goto retry_delete; } hlist_del(&timer->list); posix_timer_cleanup_ignored(timer); /* * Setting timer::it_signal to NULL is technically not required * here as nothing can access the timer anymore legitimately via * the hash table. Set it to NULL nevertheless so that all deletion * paths are consistent. */ WRITE_ONCE(timer->it_signal, NULL); spin_unlock_irqrestore(&timer->it_lock, flags); posix_timer_unhash_and_free(timer); } /* * Invoked from do_exit() when the last thread of a thread group exits. * At that point no other task can access the timers of the dying * task anymore. */ void exit_itimers(struct task_struct *tsk) { struct hlist_head timers; if (hlist_empty(&tsk->signal->posix_timers)) return; /* Protect against concurrent read via /proc/$PID/timers */ spin_lock_irq(&tsk->sighand->siglock); hlist_move_list(&tsk->signal->posix_timers, &timers); spin_unlock_irq(&tsk->sighand->siglock); /* The timers are not longer accessible via tsk::signal */ while (!hlist_empty(&timers)) itimer_delete(hlist_entry(timers.first, struct k_itimer, list)); /* * There should be no timers on the ignored list. itimer_delete() has * mopped them up. */ if (!WARN_ON_ONCE(!hlist_empty(&tsk->signal->ignored_posix_timers))) return; hlist_move_list(&tsk->signal->ignored_posix_timers, &timers); while (!hlist_empty(&timers)) { posix_timer_cleanup_ignored(hlist_entry(timers.first, struct k_itimer, ignored_list)); } } SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, const struct __kernel_timespec __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 new_tp; if (!kc || !kc->clock_set) return -EINVAL; if (get_timespec64(&new_tp, tp)) return -EFAULT; /* * Permission checks have to be done inside the clock specific * setter callback. */ return kc->clock_set(which_clock, &new_tp); } SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, struct __kernel_timespec __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 kernel_tp; int error; if (!kc) return -EINVAL; error = kc->clock_get_timespec(which_clock, &kernel_tp); if (!error && put_timespec64(&kernel_tp, tp)) error = -EFAULT; return error; } int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx) { const struct k_clock *kc = clockid_to_kclock(which_clock); if (!kc) return -EINVAL; if (!kc->clock_adj) return -EOPNOTSUPP; return kc->clock_adj(which_clock, ktx); } SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, struct __kernel_timex __user *, utx) { struct __kernel_timex ktx; int err; if (copy_from_user(&ktx, utx, sizeof(ktx))) return -EFAULT; err = do_clock_adjtime(which_clock, &ktx); if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx))) return -EFAULT; return err; } /** * sys_clock_getres - Get the resolution of a clock * @which_clock: The clock to get the resolution for * @tp: Pointer to a a user space timespec64 for storage * * POSIX defines: * * "The clock_getres() function shall return the resolution of any * clock. Clock resolutions are implementation-defined and cannot be set by * a process. If the argument res is not NULL, the resolution of the * specified clock shall be stored in the location pointed to by res. If * res is NULL, the clock resolution is not returned. If the time argument * of clock_settime() is not a multiple of res, then the value is truncated * to a multiple of res." * * Due to the various hardware constraints the real resolution can vary * wildly and even change during runtime when the underlying devices are * replaced. The kernel also can use hardware devices with different * resolutions for reading the time and for arming timers. * * The kernel therefore deviates from the POSIX spec in various aspects: * * 1) The resolution returned to user space * * For CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME, CLOCK_TAI, * CLOCK_REALTIME_ALARM, CLOCK_BOOTTIME_ALAREM and CLOCK_MONOTONIC_RAW * the kernel differentiates only two cases: * * I) Low resolution mode: * * When high resolution timers are disabled at compile or runtime * the resolution returned is nanoseconds per tick, which represents * the precision at which timers expire. * * II) High resolution mode: * * When high resolution timers are enabled the resolution returned * is always one nanosecond independent of the actual resolution of * the underlying hardware devices. * * For CLOCK_*_ALARM the actual resolution depends on system * state. When system is running the resolution is the same as the * resolution of the other clocks. During suspend the actual * resolution is the resolution of the underlying RTC device which * might be way less precise than the clockevent device used during * running state. * * For CLOCK_REALTIME_COARSE and CLOCK_MONOTONIC_COARSE the resolution * returned is always nanoseconds per tick. * * For CLOCK_PROCESS_CPUTIME and CLOCK_THREAD_CPUTIME the resolution * returned is always one nanosecond under the assumption that the * underlying scheduler clock has a better resolution than nanoseconds * per tick. * * For dynamic POSIX clocks (PTP devices) the resolution returned is * always one nanosecond. * * 2) Affect on sys_clock_settime() * * The kernel does not truncate the time which is handed in to * sys_clock_settime(). The kernel internal timekeeping is always using * nanoseconds precision independent of the clocksource device which is * used to read the time from. The resolution of that device only * affects the presicion of the time returned by sys_clock_gettime(). * * Returns: * 0 Success. @tp contains the resolution * -EINVAL @which_clock is not a valid clock ID * -EFAULT Copying the resolution to @tp faulted * -ENODEV Dynamic POSIX clock is not backed by a device * -EOPNOTSUPP Dynamic POSIX clock does not support getres() */ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct __kernel_timespec __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 rtn_tp; int error; if (!kc) return -EINVAL; error = kc->clock_getres(which_clock, &rtn_tp); if (!error && tp && put_timespec64(&rtn_tp, tp)) error = -EFAULT; return error; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(clock_settime32, clockid_t, which_clock, struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; if (!kc || !kc->clock_set) return -EINVAL; if (get_old_timespec32(&ts, tp)) return -EFAULT; return kc->clock_set(which_clock, &ts); } SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; int err; if (!kc) return -EINVAL; err = kc->clock_get_timespec(which_clock, &ts); if (!err && put_old_timespec32(&ts, tp)) err = -EFAULT; return err; } SYSCALL_DEFINE2(clock_adjtime32, clockid_t, which_clock, struct old_timex32 __user *, utp) { struct __kernel_timex ktx; int err; err = get_old_timex32(&ktx, utp); if (err) return err; err = do_clock_adjtime(which_clock, &ktx); if (err >= 0 && put_old_timex32(utp, &ktx)) return -EFAULT; return err; } SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; int err; if (!kc) return -EINVAL; err = kc->clock_getres(which_clock, &ts); if (!err && tp && put_old_timespec32(&ts, tp)) return -EFAULT; return err; } #endif /* * sys_clock_nanosleep() for CLOCK_REALTIME and CLOCK_TAI */ static int common_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { ktime_t texp = timespec64_to_ktime(*rqtp); return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } /* * sys_clock_nanosleep() for CLOCK_MONOTONIC and CLOCK_BOOTTIME * * Absolute nanosleeps for these clocks are time-namespace adjusted. */ static int common_nsleep_timens(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { ktime_t texp = timespec64_to_ktime(*rqtp); if (flags & TIMER_ABSTIME) texp = timens_ktime_to_host(which_clock, texp); return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, const struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; if (!kc) return -EINVAL; if (!kc->nsleep) return -EOPNOTSUPP; if (get_timespec64(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return kc->nsleep(which_clock, flags, &t); } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; if (!kc) return -EINVAL; if (!kc->nsleep) return -EOPNOTSUPP; if (get_old_timespec32(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return kc->nsleep(which_clock, flags, &t); } #endif static const struct k_clock clock_realtime = { .clock_getres = posix_get_hrtimer_res, .clock_get_timespec = posix_get_realtime_timespec, .clock_get_ktime = posix_get_realtime_ktime, .clock_set = posix_clock_realtime_set, .clock_adj = posix_clock_realtime_adj, .nsleep = common_nsleep, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock clock_monotonic = { .clock_getres = posix_get_hrtimer_res, .clock_get_timespec = posix_get_monotonic_timespec, .clock_get_ktime = posix_get_monotonic_ktime, .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock clock_monotonic_raw = { .clock_getres = posix_get_hrtimer_res, .clock_get_timespec = posix_get_monotonic_raw, }; static const struct k_clock clock_realtime_coarse = { .clock_getres = posix_get_coarse_res, .clock_get_timespec = posix_get_realtime_coarse, }; static const struct k_clock clock_monotonic_coarse = { .clock_getres = posix_get_coarse_res, .clock_get_timespec = posix_get_monotonic_coarse, }; static const struct k_clock clock_tai = { .clock_getres = posix_get_hrtimer_res, .clock_get_ktime = posix_get_tai_ktime, .clock_get_timespec = posix_get_tai_timespec, .nsleep = common_nsleep, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, .clock_get_ktime = posix_get_boottime_ktime, .clock_get_timespec = posix_get_boottime_timespec, .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock * const posix_clocks[] = { [CLOCK_REALTIME] = &clock_realtime, [CLOCK_MONOTONIC] = &clock_monotonic, [CLOCK_PROCESS_CPUTIME_ID] = &clock_process, [CLOCK_THREAD_CPUTIME_ID] = &clock_thread, [CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw, [CLOCK_REALTIME_COARSE] = &clock_realtime_coarse, [CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse, [CLOCK_BOOTTIME] = &clock_boottime, [CLOCK_REALTIME_ALARM] = &alarm_clock, [CLOCK_BOOTTIME_ALARM] = &alarm_clock, [CLOCK_TAI] = &clock_tai, }; static const struct k_clock *clockid_to_kclock(const clockid_t id) { clockid_t idx = id; if (id < 0) { return (id & CLOCKFD_MASK) == CLOCKFD ? &clock_posix_dynamic : &clock_posix_cpu; } if (id >= ARRAY_SIZE(posix_clocks)) return NULL; return posix_clocks[array_index_nospec(idx, ARRAY_SIZE(posix_clocks))]; } |
| 2 6 3 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/fs.h> #include <linux/buffer_head.h> #include "amigaffs.h" #include <linux/mutex.h> #include <linux/workqueue.h> /* Ugly macros make the code more pretty. */ #define AFFS_BLOCK(sb, bh, blk) (AFFS_HEAD(bh)->table[AFFS_SB(sb)->s_hashsize-1-(blk)]) #define AFFS_HEAD(bh) ((struct affs_head *)(bh)->b_data) #define AFFS_TAIL(sb, bh) ((struct affs_tail *)((bh)->b_data+(sb)->s_blocksize-sizeof(struct affs_tail))) #define AFFS_ROOT_HEAD(bh) ((struct affs_root_head *)(bh)->b_data) #define AFFS_ROOT_TAIL(sb, bh) ((struct affs_root_tail *)((bh)->b_data+(sb)->s_blocksize-sizeof(struct affs_root_tail))) #define AFFS_DATA_HEAD(bh) ((struct affs_data_head *)(bh)->b_data) #define AFFS_DATA(bh) (((struct affs_data_head *)(bh)->b_data)->data) #define AFFS_CACHE_SIZE PAGE_SIZE #define AFFS_LC_SIZE (AFFS_CACHE_SIZE/sizeof(u32)/2) #define AFFS_AC_SIZE (AFFS_CACHE_SIZE/sizeof(struct affs_ext_key)/2) #define AFFS_AC_MASK (AFFS_AC_SIZE-1) #define AFFSNAMEMAX 30U struct affs_ext_key { u32 ext; /* idx of the extended block */ u32 key; /* block number */ }; /* * affs fs inode data in memory */ struct affs_inode_info { atomic_t i_opencnt; struct mutex i_link_lock; /* Protects internal inode access. */ struct mutex i_ext_lock; /* Protects internal inode access. */ #define i_hash_lock i_ext_lock u32 i_blkcnt; /* block count */ u32 i_extcnt; /* extended block count */ u32 *i_lc; /* linear cache of extended blocks */ u32 i_lc_size; u32 i_lc_shift; u32 i_lc_mask; struct affs_ext_key *i_ac; /* associative cache of extended blocks */ u32 i_ext_last; /* last accessed extended block */ struct buffer_head *i_ext_bh; /* bh of last extended block */ loff_t mmu_private; u32 i_protect; /* unused attribute bits */ u32 i_lastalloc; /* last allocated block */ int i_pa_cnt; /* number of preallocated blocks */ struct inode vfs_inode; }; /* short cut to get to the affs specific inode data */ static inline struct affs_inode_info *AFFS_I(struct inode *inode) { return container_of(inode, struct affs_inode_info, vfs_inode); } /* * super-block data in memory * * Block numbers are adjusted for their actual size * */ struct affs_bm_info { u32 bm_key; /* Disk block number */ u32 bm_free; /* Free blocks in here */ }; struct affs_sb_info { int s_partition_size; /* Partition size in blocks. */ int s_reserved; /* Number of reserved blocks. */ //u32 s_blksize; /* Initial device blksize */ u32 s_data_blksize; /* size of the data block w/o header */ u32 s_root_block; /* FFS root block number. */ int s_hashsize; /* Size of hash table. */ unsigned long s_flags; /* See below. */ kuid_t s_uid; /* uid to override */ kgid_t s_gid; /* gid to override */ umode_t s_mode; /* mode to override */ struct buffer_head *s_root_bh; /* Cached root block. */ struct mutex s_bmlock; /* Protects bitmap access. */ struct affs_bm_info *s_bitmap; /* Bitmap infos. */ u32 s_bmap_count; /* # of bitmap blocks. */ u32 s_bmap_bits; /* # of bits in one bitmap blocks */ u32 s_last_bmap; struct buffer_head *s_bmap_bh; char *s_prefix; /* Prefix for volumes and assigns. */ char s_volume[32]; /* Volume prefix for absolute symlinks. */ spinlock_t symlink_lock; /* protects the previous two */ struct super_block *sb; /* the VFS superblock object */ int work_queued; /* non-zero delayed work is queued */ struct delayed_work sb_work; /* superblock flush delayed work */ spinlock_t work_lock; /* protects sb_work and work_queued */ struct rcu_head rcu; }; #define AFFS_MOUNT_SF_INTL 0x0001 /* International filesystem. */ #define AFFS_MOUNT_SF_BM_VALID 0x0002 /* Bitmap is valid. */ #define AFFS_MOUNT_SF_IMMUTABLE 0x0004 /* Protection bits cannot be changed */ #define AFFS_MOUNT_SF_QUIET 0x0008 /* chmod errors will be not reported */ #define AFFS_MOUNT_SF_SETUID 0x0010 /* Ignore Amiga uid */ #define AFFS_MOUNT_SF_SETGID 0x0020 /* Ignore Amiga gid */ #define AFFS_MOUNT_SF_SETMODE 0x0040 /* Ignore Amiga protection bits */ #define AFFS_MOUNT_SF_MUFS 0x0100 /* Use MUFS uid/gid mapping */ #define AFFS_MOUNT_SF_OFS 0x0200 /* Old filesystem */ #define AFFS_MOUNT_SF_PREFIX 0x0400 /* Buffer for prefix is allocated */ #define AFFS_MOUNT_SF_VERBOSE 0x0800 /* Talk about fs when mounting */ #define AFFS_MOUNT_SF_NO_TRUNCATE 0x1000 /* Don't truncate filenames */ #define affs_clear_opt(o, opt) (o &= ~AFFS_MOUNT_##opt) #define affs_set_opt(o, opt) (o |= AFFS_MOUNT_##opt) #define affs_test_opt(o, opt) ((o) & AFFS_MOUNT_##opt) /* short cut to get to the affs specific sb data */ static inline struct affs_sb_info *AFFS_SB(struct super_block *sb) { return sb->s_fs_info; } void affs_mark_sb_dirty(struct super_block *sb); /* amigaffs.c */ extern int affs_insert_hash(struct inode *inode, struct buffer_head *bh); extern int affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh); extern int affs_remove_header(struct dentry *dentry); extern u32 affs_checksum_block(struct super_block *sb, struct buffer_head *bh); extern void affs_fix_checksum(struct super_block *sb, struct buffer_head *bh); extern void affs_secs_to_datestamp(time64_t secs, struct affs_date *ds); extern umode_t affs_prot_to_mode(u32 prot); extern void affs_mode_to_prot(struct inode *inode); __printf(3, 4) extern void affs_error(struct super_block *sb, const char *function, const char *fmt, ...); __printf(3, 4) extern void affs_warning(struct super_block *sb, const char *function, const char *fmt, ...); extern bool affs_nofilenametruncate(const struct dentry *dentry); extern int affs_check_name(const unsigned char *name, int len, bool notruncate); extern int affs_copy_name(unsigned char *bstr, struct dentry *dentry); /* bitmap. c */ extern u32 affs_count_free_blocks(struct super_block *s); extern void affs_free_block(struct super_block *sb, u32 block); extern u32 affs_alloc_block(struct inode *inode, u32 goal); extern int affs_init_bitmap(struct super_block *sb, int *flags); extern void affs_free_bitmap(struct super_block *sb); /* namei.c */ extern const struct export_operations affs_export_ops; extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len); extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); extern int affs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool); extern int affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); extern int affs_link(struct dentry *olddentry, struct inode *dir, struct dentry *dentry); extern int affs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname); extern int affs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); /* inode.c */ extern struct inode *affs_new_inode(struct inode *dir); extern int affs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void affs_evict_inode(struct inode *inode); extern struct inode *affs_iget(struct super_block *sb, unsigned long ino); extern int affs_write_inode(struct inode *inode, struct writeback_control *wbc); extern int affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s32 type); /* file.c */ void affs_free_prealloc(struct inode *inode); extern void affs_truncate(struct inode *); int affs_file_fsync(struct file *, loff_t, loff_t, int); /* dir.c */ extern void affs_dir_truncate(struct inode *); /* jump tables */ extern const struct inode_operations affs_file_inode_operations; extern const struct inode_operations affs_dir_inode_operations; extern const struct inode_operations affs_symlink_inode_operations; extern const struct file_operations affs_file_operations; extern const struct file_operations affs_file_operations_ofs; extern const struct file_operations affs_dir_operations; extern const struct address_space_operations affs_symlink_aops; extern const struct address_space_operations affs_aops; extern const struct address_space_operations affs_aops_ofs; extern const struct dentry_operations affs_dentry_operations; extern const struct dentry_operations affs_intl_dentry_operations; static inline bool affs_validblock(struct super_block *sb, int block) { return(block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size); } static inline void affs_set_blocksize(struct super_block *sb, int size) { sb_set_blocksize(sb, size); } static inline struct buffer_head * affs_bread(struct super_block *sb, int block) { pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) return sb_bread(sb, block); return NULL; } static inline struct buffer_head * affs_getblk(struct super_block *sb, int block) { pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) return sb_getblk(sb, block); return NULL; } static inline struct buffer_head * affs_getzeroblk(struct super_block *sb, int block) { struct buffer_head *bh; pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) { bh = sb_getblk(sb, block); lock_buffer(bh); memset(bh->b_data, 0 , sb->s_blocksize); set_buffer_uptodate(bh); unlock_buffer(bh); return bh; } return NULL; } static inline struct buffer_head * affs_getemptyblk(struct super_block *sb, int block) { struct buffer_head *bh; pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) { bh = sb_getblk(sb, block); wait_on_buffer(bh); set_buffer_uptodate(bh); return bh; } return NULL; } static inline void affs_brelse(struct buffer_head *bh) { if (bh) pr_debug("%s: %lld\n", __func__, (long long) bh->b_blocknr); brelse(bh); } static inline void affs_adjust_checksum(struct buffer_head *bh, u32 val) { u32 tmp = be32_to_cpu(((__be32 *)bh->b_data)[5]); ((__be32 *)bh->b_data)[5] = cpu_to_be32(tmp - val); } static inline void affs_adjust_bitmapchecksum(struct buffer_head *bh, u32 val) { u32 tmp = be32_to_cpu(((__be32 *)bh->b_data)[0]); ((__be32 *)bh->b_data)[0] = cpu_to_be32(tmp - val); } static inline void affs_lock_link(struct inode *inode) { mutex_lock(&AFFS_I(inode)->i_link_lock); } static inline void affs_unlock_link(struct inode *inode) { mutex_unlock(&AFFS_I(inode)->i_link_lock); } static inline void affs_lock_dir(struct inode *inode) { mutex_lock_nested(&AFFS_I(inode)->i_hash_lock, SINGLE_DEPTH_NESTING); } static inline void affs_unlock_dir(struct inode *inode) { mutex_unlock(&AFFS_I(inode)->i_hash_lock); } static inline void affs_lock_ext(struct inode *inode) { mutex_lock(&AFFS_I(inode)->i_ext_lock); } static inline void affs_unlock_ext(struct inode *inode) { mutex_unlock(&AFFS_I(inode)->i_ext_lock); } |
| 1 1 1 1 3 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware VMCI Driver * * Copyright (C) 2012 VMware, Inc. All rights reserved. */ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> #include <linux/miscdevice.h> #include <linux/interrupt.h> #include <linux/highmem.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/pci.h> #include <linux/smp.h> #include <linux/fs.h> #include <linux/io.h> #include "vmci_handle_array.h" #include "vmci_queue_pair.h" #include "vmci_datagram.h" #include "vmci_doorbell.h" #include "vmci_resource.h" #include "vmci_context.h" #include "vmci_driver.h" #include "vmci_event.h" #define VMCI_UTIL_NUM_RESOURCES 1 enum { VMCI_NOTIFY_RESOURCE_QUEUE_PAIR = 0, VMCI_NOTIFY_RESOURCE_DOOR_BELL = 1, }; enum { VMCI_NOTIFY_RESOURCE_ACTION_NOTIFY = 0, VMCI_NOTIFY_RESOURCE_ACTION_CREATE = 1, VMCI_NOTIFY_RESOURCE_ACTION_DESTROY = 2, }; /* * VMCI driver initialization. This block can also be used to * pass initial group membership etc. */ struct vmci_init_blk { u32 cid; u32 flags; }; /* VMCIqueue_pairAllocInfo_VMToVM */ struct vmci_qp_alloc_info_vmvm { struct vmci_handle handle; u32 peer; u32 flags; u64 produce_size; u64 consume_size; u64 produce_page_file; /* User VA. */ u64 consume_page_file; /* User VA. */ u64 produce_page_file_size; /* Size of the file name array. */ u64 consume_page_file_size; /* Size of the file name array. */ s32 result; u32 _pad; }; /* VMCISetNotifyInfo: Used to pass notify flag's address to the host driver. */ struct vmci_set_notify_info { u64 notify_uva; s32 result; u32 _pad; }; /* * Per-instance host state */ struct vmci_host_dev { struct vmci_ctx *context; int user_version; enum vmci_obj_type ct_type; struct mutex lock; /* Mutex lock for vmci context access */ }; static struct vmci_ctx *host_context; static bool vmci_host_device_initialized; static atomic_t vmci_host_active_users = ATOMIC_INIT(0); /* * Determines whether the VMCI host personality is * available. Since the core functionality of the host driver is * always present, all guests could possibly use the host * personality. However, to minimize the deviation from the * pre-unified driver state of affairs, we only consider the host * device active if there is no active guest device or if there * are VMX'en with active VMCI contexts using the host device. */ bool vmci_host_code_active(void) { return vmci_host_device_initialized && (!vmci_guest_code_active() || atomic_read(&vmci_host_active_users) > 0); } int vmci_host_users(void) { return atomic_read(&vmci_host_active_users); } /* * Called on open of /dev/vmci. */ static int vmci_host_open(struct inode *inode, struct file *filp) { struct vmci_host_dev *vmci_host_dev; vmci_host_dev = kzalloc(sizeof(struct vmci_host_dev), GFP_KERNEL); if (vmci_host_dev == NULL) return -ENOMEM; vmci_host_dev->ct_type = VMCIOBJ_NOT_SET; mutex_init(&vmci_host_dev->lock); filp->private_data = vmci_host_dev; return 0; } /* * Called on close of /dev/vmci, most often when the process * exits. */ static int vmci_host_close(struct inode *inode, struct file *filp) { struct vmci_host_dev *vmci_host_dev = filp->private_data; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { vmci_ctx_destroy(vmci_host_dev->context); vmci_host_dev->context = NULL; /* * The number of active contexts is used to track whether any * VMX'en are using the host personality. It is incremented when * a context is created through the IOCTL_VMCI_INIT_CONTEXT * ioctl. */ atomic_dec(&vmci_host_active_users); } vmci_host_dev->ct_type = VMCIOBJ_NOT_SET; kfree(vmci_host_dev); filp->private_data = NULL; return 0; } /* * This is used to wake up the VMX when a VMCI call arrives, or * to wake up select() or poll() at the next clock tick. */ static __poll_t vmci_host_poll(struct file *filp, poll_table *wait) { struct vmci_host_dev *vmci_host_dev = filp->private_data; struct vmci_ctx *context; __poll_t mask = 0; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { /* * Read context only if ct_type == VMCIOBJ_CONTEXT to make * sure that context is initialized */ context = vmci_host_dev->context; /* Check for VMCI calls to this VM context. */ if (wait) poll_wait(filp, &context->host_context.wait_queue, wait); spin_lock(&context->lock); if (context->pending_datagrams > 0 || vmci_handle_arr_get_size( context->pending_doorbell_array) > 0) { mask = EPOLLIN; } spin_unlock(&context->lock); } return mask; } /* * Copies the handles of a handle array into a user buffer, and * returns the new length in userBufferSize. If the copy to the * user buffer fails, the functions still returns VMCI_SUCCESS, * but retval != 0. */ static int drv_cp_harray_to_user(void __user *user_buf_uva, u64 *user_buf_size, struct vmci_handle_arr *handle_array, int *retval) { u32 array_size = 0; struct vmci_handle *handles; if (handle_array) array_size = vmci_handle_arr_get_size(handle_array); if (array_size * sizeof(*handles) > *user_buf_size) return VMCI_ERROR_MORE_DATA; *user_buf_size = array_size * sizeof(*handles); if (*user_buf_size) *retval = copy_to_user(user_buf_uva, vmci_handle_arr_get_handles (handle_array), *user_buf_size); return VMCI_SUCCESS; } /* * Sets up a given context for notify to work. Maps the notify * boolean in user VA into kernel space. */ static int vmci_host_setup_notify(struct vmci_ctx *context, unsigned long uva) { int retval; if (context->notify_page) { pr_devel("%s: Notify mechanism is already set up\n", __func__); return VMCI_ERROR_DUPLICATE_ENTRY; } /* * We are using 'bool' internally, but let's make sure we explicit * about the size. */ BUILD_BUG_ON(sizeof(bool) != sizeof(u8)); /* * Lock physical page backing a given user VA. */ retval = get_user_pages_fast(uva, 1, FOLL_WRITE, &context->notify_page); if (retval != 1) { context->notify_page = NULL; return VMCI_ERROR_GENERIC; } if (context->notify_page == NULL) return VMCI_ERROR_UNAVAILABLE; /* * Map the locked page and set up notify pointer. */ context->notify = kmap(context->notify_page) + (uva & (PAGE_SIZE - 1)); vmci_ctx_check_signal_notify(context); return VMCI_SUCCESS; } static int vmci_host_get_version(struct vmci_host_dev *vmci_host_dev, unsigned int cmd, void __user *uptr) { if (cmd == IOCTL_VMCI_VERSION2) { int __user *vptr = uptr; if (get_user(vmci_host_dev->user_version, vptr)) return -EFAULT; } /* * The basic logic here is: * * If the user sends in a version of 0 tell it our version. * If the user didn't send in a version, tell it our version. * If the user sent in an old version, tell it -its- version. * If the user sent in an newer version, tell it our version. * * The rationale behind telling the caller its version is that * Workstation 6.5 required that VMX and VMCI kernel module were * version sync'd. All new VMX users will be programmed to * handle the VMCI kernel module version. */ if (vmci_host_dev->user_version > 0 && vmci_host_dev->user_version < VMCI_VERSION_HOSTQP) { return vmci_host_dev->user_version; } return VMCI_VERSION; } #define vmci_ioctl_err(fmt, ...) \ pr_devel("%s: " fmt, ioctl_name, ##__VA_ARGS__) static int vmci_host_do_init_context(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_init_blk init_block; const struct cred *cred; int retval; if (copy_from_user(&init_block, uptr, sizeof(init_block))) { vmci_ioctl_err("error reading init block\n"); return -EFAULT; } mutex_lock(&vmci_host_dev->lock); if (vmci_host_dev->ct_type != VMCIOBJ_NOT_SET) { vmci_ioctl_err("received VMCI init on initialized handle\n"); retval = -EINVAL; goto out; } if (init_block.flags & ~VMCI_PRIVILEGE_FLAG_RESTRICTED) { vmci_ioctl_err("unsupported VMCI restriction flag\n"); retval = -EINVAL; goto out; } cred = get_current_cred(); vmci_host_dev->context = vmci_ctx_create(init_block.cid, init_block.flags, 0, vmci_host_dev->user_version, cred); put_cred(cred); if (IS_ERR(vmci_host_dev->context)) { retval = PTR_ERR(vmci_host_dev->context); vmci_ioctl_err("error initializing context\n"); goto out; } /* * Copy cid to userlevel, we do this to allow the VMX * to enforce its policy on cid generation. */ init_block.cid = vmci_ctx_get_id(vmci_host_dev->context); if (copy_to_user(uptr, &init_block, sizeof(init_block))) { vmci_ctx_destroy(vmci_host_dev->context); vmci_host_dev->context = NULL; vmci_ioctl_err("error writing init block\n"); retval = -EFAULT; goto out; } vmci_host_dev->ct_type = VMCIOBJ_CONTEXT; atomic_inc(&vmci_host_active_users); vmci_call_vsock_callback(true); retval = 0; out: mutex_unlock(&vmci_host_dev->lock); return retval; } static int vmci_host_do_send_datagram(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_datagram_snd_rcv_info send_info; struct vmci_datagram *dg = NULL; u32 cid; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&send_info, uptr, sizeof(send_info))) return -EFAULT; if (send_info.len > VMCI_MAX_DG_SIZE) { vmci_ioctl_err("datagram is too big (size=%d)\n", send_info.len); return -EINVAL; } if (send_info.len < sizeof(*dg)) { vmci_ioctl_err("datagram is too small (size=%d)\n", send_info.len); return -EINVAL; } dg = memdup_user((void __user *)(uintptr_t)send_info.addr, send_info.len); if (IS_ERR(dg)) { vmci_ioctl_err( "cannot allocate memory to dispatch datagram\n"); return PTR_ERR(dg); } if (VMCI_DG_SIZE(dg) != send_info.len) { vmci_ioctl_err("datagram size mismatch\n"); kfree(dg); return -EINVAL; } pr_devel("Datagram dst (handle=0x%x:0x%x) src (handle=0x%x:0x%x), payload (size=%llu bytes)\n", dg->dst.context, dg->dst.resource, dg->src.context, dg->src.resource, (unsigned long long)dg->payload_size); /* Get source context id. */ cid = vmci_ctx_get_id(vmci_host_dev->context); send_info.result = vmci_datagram_dispatch(cid, dg, true); kfree(dg); return copy_to_user(uptr, &send_info, sizeof(send_info)) ? -EFAULT : 0; } static int vmci_host_do_receive_datagram(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_datagram_snd_rcv_info recv_info; struct vmci_datagram *dg = NULL; int retval; size_t size; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&recv_info, uptr, sizeof(recv_info))) return -EFAULT; size = recv_info.len; recv_info.result = vmci_ctx_dequeue_datagram(vmci_host_dev->context, &size, &dg); if (recv_info.result >= VMCI_SUCCESS) { void __user *ubuf = (void __user *)(uintptr_t)recv_info.addr; retval = copy_to_user(ubuf, dg, VMCI_DG_SIZE(dg)); kfree(dg); if (retval != 0) return -EFAULT; } return copy_to_user(uptr, &recv_info, sizeof(recv_info)) ? -EFAULT : 0; } static int vmci_host_do_alloc_queuepair(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_handle handle; int vmci_status; int __user *retptr; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (vmci_host_dev->user_version < VMCI_VERSION_NOVMVM) { struct vmci_qp_alloc_info_vmvm alloc_info; struct vmci_qp_alloc_info_vmvm __user *info = uptr; if (copy_from_user(&alloc_info, uptr, sizeof(alloc_info))) return -EFAULT; handle = alloc_info.handle; retptr = &info->result; vmci_status = vmci_qp_broker_alloc(alloc_info.handle, alloc_info.peer, alloc_info.flags, VMCI_NO_PRIVILEGE_FLAGS, alloc_info.produce_size, alloc_info.consume_size, NULL, vmci_host_dev->context); if (vmci_status == VMCI_SUCCESS) vmci_status = VMCI_SUCCESS_QUEUEPAIR_CREATE; } else { struct vmci_qp_alloc_info alloc_info; struct vmci_qp_alloc_info __user *info = uptr; struct vmci_qp_page_store page_store; if (copy_from_user(&alloc_info, uptr, sizeof(alloc_info))) return -EFAULT; handle = alloc_info.handle; retptr = &info->result; page_store.pages = alloc_info.ppn_va; page_store.len = alloc_info.num_ppns; vmci_status = vmci_qp_broker_alloc(alloc_info.handle, alloc_info.peer, alloc_info.flags, VMCI_NO_PRIVILEGE_FLAGS, alloc_info.produce_size, alloc_info.consume_size, &page_store, vmci_host_dev->context); } if (put_user(vmci_status, retptr)) { if (vmci_status >= VMCI_SUCCESS) { vmci_status = vmci_qp_broker_detach(handle, vmci_host_dev->context); } return -EFAULT; } return 0; } static int vmci_host_do_queuepair_setva(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_qp_set_va_info set_va_info; struct vmci_qp_set_va_info __user *info = uptr; s32 result; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (vmci_host_dev->user_version < VMCI_VERSION_NOVMVM) { vmci_ioctl_err("is not allowed\n"); return -EINVAL; } if (copy_from_user(&set_va_info, uptr, sizeof(set_va_info))) return -EFAULT; if (set_va_info.va) { /* * VMX is passing down a new VA for the queue * pair mapping. */ result = vmci_qp_broker_map(set_va_info.handle, vmci_host_dev->context, set_va_info.va); } else { /* * The queue pair is about to be unmapped by * the VMX. */ result = vmci_qp_broker_unmap(set_va_info.handle, vmci_host_dev->context, 0); } return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_queuepair_setpf(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_qp_page_file_info page_file_info; struct vmci_qp_page_file_info __user *info = uptr; s32 result; if (vmci_host_dev->user_version < VMCI_VERSION_HOSTQP || vmci_host_dev->user_version >= VMCI_VERSION_NOVMVM) { vmci_ioctl_err("not supported on this VMX (version=%d)\n", vmci_host_dev->user_version); return -EINVAL; } if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&page_file_info, uptr, sizeof(*info))) return -EFAULT; /* * Communicate success pre-emptively to the caller. Note that the * basic premise is that it is incumbent upon the caller not to look at * the info.result field until after the ioctl() returns. And then, * only if the ioctl() result indicates no error. We send up the * SUCCESS status before calling SetPageStore() store because failing * to copy up the result code means unwinding the SetPageStore(). * * It turns out the logic to unwind a SetPageStore() opens a can of * worms. For example, if a host had created the queue_pair and a * guest attaches and SetPageStore() is successful but writing success * fails, then ... the host has to be stopped from writing (anymore) * data into the queue_pair. That means an additional test in the * VMCI_Enqueue() code path. Ugh. */ if (put_user(VMCI_SUCCESS, &info->result)) { /* * In this case, we can't write a result field of the * caller's info block. So, we don't even try to * SetPageStore(). */ return -EFAULT; } result = vmci_qp_broker_set_page_store(page_file_info.handle, page_file_info.produce_va, page_file_info.consume_va, vmci_host_dev->context); if (result < VMCI_SUCCESS) { if (put_user(result, &info->result)) { /* * Note that in this case the SetPageStore() * call failed but we were unable to * communicate that to the caller (because the * copy_to_user() call failed). So, if we * simply return an error (in this case * -EFAULT) then the caller will know that the * SetPageStore failed even though we couldn't * put the result code in the result field and * indicate exactly why it failed. * * That says nothing about the issue where we * were once able to write to the caller's info * memory and now can't. Something more * serious is probably going on than the fact * that SetPageStore() didn't work. */ return -EFAULT; } } return 0; } static int vmci_host_do_qp_detach(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_qp_dtch_info detach_info; struct vmci_qp_dtch_info __user *info = uptr; s32 result; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&detach_info, uptr, sizeof(detach_info))) return -EFAULT; result = vmci_qp_broker_detach(detach_info.handle, vmci_host_dev->context); if (result == VMCI_SUCCESS && vmci_host_dev->user_version < VMCI_VERSION_NOVMVM) { result = VMCI_SUCCESS_LAST_DETACH; } return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_ctx_add_notify(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_info ar_info; struct vmci_ctx_info __user *info = uptr; s32 result; u32 cid; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&ar_info, uptr, sizeof(ar_info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); result = vmci_ctx_add_notification(cid, ar_info.remote_cid); return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_ctx_remove_notify(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_info ar_info; struct vmci_ctx_info __user *info = uptr; u32 cid; int result; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&ar_info, uptr, sizeof(ar_info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); result = vmci_ctx_remove_notification(cid, ar_info.remote_cid); return put_user(result, &info->result) ? -EFAULT : 0; } static int vmci_host_do_ctx_get_cpt_state(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_chkpt_buf_info get_info; u32 cid; void *cpt_buf; int retval; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&get_info, uptr, sizeof(get_info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); get_info.result = vmci_ctx_get_chkpt_state(cid, get_info.cpt_type, &get_info.buf_size, &cpt_buf); if (get_info.result == VMCI_SUCCESS && get_info.buf_size) { void __user *ubuf = (void __user *)(uintptr_t)get_info.cpt_buf; retval = copy_to_user(ubuf, cpt_buf, get_info.buf_size); kfree(cpt_buf); if (retval) return -EFAULT; } return copy_to_user(uptr, &get_info, sizeof(get_info)) ? -EFAULT : 0; } static int vmci_host_do_ctx_set_cpt_state(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_chkpt_buf_info set_info; u32 cid; void *cpt_buf; int retval; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&set_info, uptr, sizeof(set_info))) return -EFAULT; cpt_buf = memdup_user((void __user *)(uintptr_t)set_info.cpt_buf, set_info.buf_size); if (IS_ERR(cpt_buf)) return PTR_ERR(cpt_buf); cid = vmci_ctx_get_id(vmci_host_dev->context); set_info.result = vmci_ctx_set_chkpt_state(cid, set_info.cpt_type, set_info.buf_size, cpt_buf); retval = copy_to_user(uptr, &set_info, sizeof(set_info)) ? -EFAULT : 0; kfree(cpt_buf); return retval; } static int vmci_host_do_get_context_id(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { u32 __user *u32ptr = uptr; return put_user(VMCI_HOST_CONTEXT_ID, u32ptr) ? -EFAULT : 0; } static int vmci_host_do_set_notify(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_set_notify_info notify_info; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(¬ify_info, uptr, sizeof(notify_info))) return -EFAULT; if (notify_info.notify_uva) { notify_info.result = vmci_host_setup_notify(vmci_host_dev->context, notify_info.notify_uva); } else { vmci_ctx_unset_notify(vmci_host_dev->context); notify_info.result = VMCI_SUCCESS; } return copy_to_user(uptr, ¬ify_info, sizeof(notify_info)) ? -EFAULT : 0; } static int vmci_host_do_notify_resource(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_dbell_notify_resource_info info; u32 cid; if (vmci_host_dev->user_version < VMCI_VERSION_NOTIFY) { vmci_ioctl_err("invalid for current VMX versions\n"); return -EINVAL; } if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (copy_from_user(&info, uptr, sizeof(info))) return -EFAULT; cid = vmci_ctx_get_id(vmci_host_dev->context); switch (info.action) { case VMCI_NOTIFY_RESOURCE_ACTION_NOTIFY: if (info.resource == VMCI_NOTIFY_RESOURCE_DOOR_BELL) { u32 flags = VMCI_NO_PRIVILEGE_FLAGS; info.result = vmci_ctx_notify_dbell(cid, info.handle, flags); } else { info.result = VMCI_ERROR_UNAVAILABLE; } break; case VMCI_NOTIFY_RESOURCE_ACTION_CREATE: info.result = vmci_ctx_dbell_create(cid, info.handle); break; case VMCI_NOTIFY_RESOURCE_ACTION_DESTROY: info.result = vmci_ctx_dbell_destroy(cid, info.handle); break; default: vmci_ioctl_err("got unknown action (action=%d)\n", info.action); info.result = VMCI_ERROR_INVALID_ARGS; } return copy_to_user(uptr, &info, sizeof(info)) ? -EFAULT : 0; } static int vmci_host_do_recv_notifications(struct vmci_host_dev *vmci_host_dev, const char *ioctl_name, void __user *uptr) { struct vmci_ctx_notify_recv_info info; struct vmci_handle_arr *db_handle_array; struct vmci_handle_arr *qp_handle_array; void __user *ubuf; u32 cid; int retval = 0; if (vmci_host_dev->ct_type != VMCIOBJ_CONTEXT) { vmci_ioctl_err("only valid for contexts\n"); return -EINVAL; } if (vmci_host_dev->user_version < VMCI_VERSION_NOTIFY) { vmci_ioctl_err("not supported for the current vmx version\n"); return -EINVAL; } if (copy_from_user(&info, uptr, sizeof(info))) return -EFAULT; if ((info.db_handle_buf_size && !info.db_handle_buf_uva) || (info.qp_handle_buf_size && !info.qp_handle_buf_uva)) { return -EINVAL; } cid = vmci_ctx_get_id(vmci_host_dev->context); info.result = vmci_ctx_rcv_notifications_get(cid, &db_handle_array, &qp_handle_array); if (info.result != VMCI_SUCCESS) return copy_to_user(uptr, &info, sizeof(info)) ? -EFAULT : 0; ubuf = (void __user *)(uintptr_t)info.db_handle_buf_uva; info.result = drv_cp_harray_to_user(ubuf, &info.db_handle_buf_size, db_handle_array, &retval); if (info.result == VMCI_SUCCESS && !retval) { ubuf = (void __user *)(uintptr_t)info.qp_handle_buf_uva; info.result = drv_cp_harray_to_user(ubuf, &info.qp_handle_buf_size, qp_handle_array, &retval); } if (!retval && copy_to_user(uptr, &info, sizeof(info))) retval = -EFAULT; vmci_ctx_rcv_notifications_release(cid, db_handle_array, qp_handle_array, info.result == VMCI_SUCCESS && !retval); return retval; } static long vmci_host_unlocked_ioctl(struct file *filp, unsigned int iocmd, unsigned long ioarg) { #define VMCI_DO_IOCTL(ioctl_name, ioctl_fn) do { \ char *name = "IOCTL_VMCI_" # ioctl_name; \ return vmci_host_do_ ## ioctl_fn( \ vmci_host_dev, name, uptr); \ } while (0) struct vmci_host_dev *vmci_host_dev = filp->private_data; void __user *uptr = (void __user *)ioarg; switch (iocmd) { case IOCTL_VMCI_INIT_CONTEXT: VMCI_DO_IOCTL(INIT_CONTEXT, init_context); case IOCTL_VMCI_DATAGRAM_SEND: VMCI_DO_IOCTL(DATAGRAM_SEND, send_datagram); case IOCTL_VMCI_DATAGRAM_RECEIVE: VMCI_DO_IOCTL(DATAGRAM_RECEIVE, receive_datagram); case IOCTL_VMCI_QUEUEPAIR_ALLOC: VMCI_DO_IOCTL(QUEUEPAIR_ALLOC, alloc_queuepair); case IOCTL_VMCI_QUEUEPAIR_SETVA: VMCI_DO_IOCTL(QUEUEPAIR_SETVA, queuepair_setva); case IOCTL_VMCI_QUEUEPAIR_SETPAGEFILE: VMCI_DO_IOCTL(QUEUEPAIR_SETPAGEFILE, queuepair_setpf); case IOCTL_VMCI_QUEUEPAIR_DETACH: VMCI_DO_IOCTL(QUEUEPAIR_DETACH, qp_detach); case IOCTL_VMCI_CTX_ADD_NOTIFICATION: VMCI_DO_IOCTL(CTX_ADD_NOTIFICATION, ctx_add_notify); case IOCTL_VMCI_CTX_REMOVE_NOTIFICATION: VMCI_DO_IOCTL(CTX_REMOVE_NOTIFICATION, ctx_remove_notify); case IOCTL_VMCI_CTX_GET_CPT_STATE: VMCI_DO_IOCTL(CTX_GET_CPT_STATE, ctx_get_cpt_state); case IOCTL_VMCI_CTX_SET_CPT_STATE: VMCI_DO_IOCTL(CTX_SET_CPT_STATE, ctx_set_cpt_state); case IOCTL_VMCI_GET_CONTEXT_ID: VMCI_DO_IOCTL(GET_CONTEXT_ID, get_context_id); case IOCTL_VMCI_SET_NOTIFY: VMCI_DO_IOCTL(SET_NOTIFY, set_notify); case IOCTL_VMCI_NOTIFY_RESOURCE: VMCI_DO_IOCTL(NOTIFY_RESOURCE, notify_resource); case IOCTL_VMCI_NOTIFICATIONS_RECEIVE: VMCI_DO_IOCTL(NOTIFICATIONS_RECEIVE, recv_notifications); case IOCTL_VMCI_VERSION: case IOCTL_VMCI_VERSION2: return vmci_host_get_version(vmci_host_dev, iocmd, uptr); default: pr_devel("%s: Unknown ioctl (iocmd=%d)\n", __func__, iocmd); return -EINVAL; } #undef VMCI_DO_IOCTL } static const struct file_operations vmuser_fops = { .owner = THIS_MODULE, .open = vmci_host_open, .release = vmci_host_close, .poll = vmci_host_poll, .unlocked_ioctl = vmci_host_unlocked_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static struct miscdevice vmci_host_miscdev = { .name = "vmci", .minor = MISC_DYNAMIC_MINOR, .fops = &vmuser_fops, }; int __init vmci_host_init(void) { int error; host_context = vmci_ctx_create(VMCI_HOST_CONTEXT_ID, VMCI_DEFAULT_PROC_PRIVILEGE_FLAGS, -1, VMCI_VERSION, NULL); if (IS_ERR(host_context)) { error = PTR_ERR(host_context); pr_warn("Failed to initialize VMCIContext (error%d)\n", error); return error; } error = misc_register(&vmci_host_miscdev); if (error) { pr_warn("Module registration error (name=%s, major=%d, minor=%d, err=%d)\n", vmci_host_miscdev.name, MISC_MAJOR, vmci_host_miscdev.minor, error); pr_warn("Unable to initialize host personality\n"); vmci_ctx_destroy(host_context); return error; } pr_info("VMCI host device registered (name=%s, major=%d, minor=%d)\n", vmci_host_miscdev.name, MISC_MAJOR, vmci_host_miscdev.minor); vmci_host_device_initialized = true; return 0; } void __exit vmci_host_exit(void) { vmci_host_device_initialized = false; misc_deregister(&vmci_host_miscdev); vmci_ctx_destroy(host_context); vmci_qp_broker_exit(); pr_debug("VMCI host driver module unloaded\n"); } |
| 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * IB infrastructure: * Establish SMC-R as an Infiniband Client to be notified about added and * removed IB devices of type RDMA. * Determine device and port characteristics for these IB devices. * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/etherdevice.h> #include <linux/if_vlan.h> #include <linux/random.h> #include <linux/workqueue.h> #include <linux/scatterlist.h> #include <linux/wait.h> #include <linux/mutex.h> #include <linux/inetdevice.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> #include "smc_pnet.h" #include "smc_ib.h" #include "smc_core.h" #include "smc_wr.h" #include "smc.h" #include "smc_netlink.h" #define SMC_MAX_CQE 32766 /* max. # of completion queue elements */ #define SMC_QP_MIN_RNR_TIMER 5 #define SMC_QP_TIMEOUT 15 /* 4096 * 2 ** timeout usec */ #define SMC_QP_RETRY_CNT 7 /* 7: infinite */ #define SMC_QP_RNR_RETRY 7 /* 7: infinite */ struct smc_ib_devices smc_ib_devices = { /* smc-registered ib devices */ .mutex = __MUTEX_INITIALIZER(smc_ib_devices.mutex), .list = LIST_HEAD_INIT(smc_ib_devices.list), }; u8 local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */ static int smc_ib_modify_qp_init(struct smc_link *lnk) { struct ib_qp_attr qp_attr; memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.qp_state = IB_QPS_INIT; qp_attr.pkey_index = 0; qp_attr.port_num = lnk->ibport; qp_attr.qp_access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE; return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_ACCESS_FLAGS | IB_QP_PORT); } static int smc_ib_modify_qp_rtr(struct smc_link *lnk) { enum ib_qp_attr_mask qp_attr_mask = IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN | IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER; struct ib_qp_attr qp_attr; u8 hop_lim = 1; memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.qp_state = IB_QPS_RTR; qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu); qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport); if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway) hop_lim = IPV6_DEFAULT_HOPLIMIT; rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, hop_lim, 0); rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid); if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway) memcpy(&qp_attr.ah_attr.roce.dmac, lnk->lgr->nexthop_mac, sizeof(lnk->lgr->nexthop_mac)); else memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac, sizeof(lnk->peer_mac)); qp_attr.dest_qp_num = lnk->peer_qpn; qp_attr.rq_psn = lnk->peer_psn; /* starting receive packet seq # */ qp_attr.max_dest_rd_atomic = 1; /* max # of resources for incoming * requests */ qp_attr.min_rnr_timer = SMC_QP_MIN_RNR_TIMER; return ib_modify_qp(lnk->roce_qp, &qp_attr, qp_attr_mask); } int smc_ib_modify_qp_rts(struct smc_link *lnk) { struct ib_qp_attr qp_attr; memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.qp_state = IB_QPS_RTS; qp_attr.timeout = SMC_QP_TIMEOUT; /* local ack timeout */ qp_attr.retry_cnt = SMC_QP_RETRY_CNT; /* retry count */ qp_attr.rnr_retry = SMC_QP_RNR_RETRY; /* RNR retries, 7=infinite */ qp_attr.sq_psn = lnk->psn_initial; /* starting send packet seq # */ qp_attr.max_rd_atomic = 1; /* # of outstanding RDMA reads and * atomic ops allowed */ return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE | IB_QP_TIMEOUT | IB_QP_RETRY_CNT | IB_QP_SQ_PSN | IB_QP_RNR_RETRY | IB_QP_MAX_QP_RD_ATOMIC); } int smc_ib_modify_qp_error(struct smc_link *lnk) { struct ib_qp_attr qp_attr; memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.qp_state = IB_QPS_ERR; return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE); } int smc_ib_ready_link(struct smc_link *lnk) { struct smc_link_group *lgr = smc_get_lgr(lnk); int rc = 0; rc = smc_ib_modify_qp_init(lnk); if (rc) goto out; rc = smc_ib_modify_qp_rtr(lnk); if (rc) goto out; smc_wr_remember_qp_attr(lnk); rc = ib_req_notify_cq(lnk->smcibdev->roce_cq_recv, IB_CQ_SOLICITED_MASK); if (rc) goto out; rc = smc_wr_rx_post_init(lnk); if (rc) goto out; smc_wr_remember_qp_attr(lnk); if (lgr->role == SMC_SERV) { rc = smc_ib_modify_qp_rts(lnk); if (rc) goto out; smc_wr_remember_qp_attr(lnk); } out: return rc; } static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport) { const struct ib_gid_attr *attr; int rc; attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0); if (IS_ERR(attr)) return -ENODEV; rc = rdma_read_gid_l2_fields(attr, NULL, smcibdev->mac[ibport - 1]); rdma_put_gid_attr(attr); return rc; } /* Create an identifier unique for this instance of SMC-R. * The MAC-address of the first active registered IB device * plus a random 2-byte number is used to create this identifier. * This name is delivered to the peer during connection initialization. */ static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev, u8 ibport) { memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1], sizeof(smcibdev->mac[ibport - 1])); } bool smc_ib_is_valid_local_systemid(void) { return !is_zero_ether_addr(&local_systemid[2]); } static void smc_ib_init_local_systemid(void) { get_random_bytes(&local_systemid[0], 2); } bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) { return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; } int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway) { struct neighbour *neigh = NULL; struct rtable *rt = NULL; struct flowi4 fl4 = { .saddr = saddr, .daddr = daddr }; if (daddr == cpu_to_be32(INADDR_NONE)) goto out; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out; if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) goto out_rt; neigh = dst_neigh_lookup(&rt->dst, &fl4.daddr); if (!neigh) goto out_rt; memcpy(nexthop_mac, neigh->ha, ETH_ALEN); *uses_gateway = rt->rt_uses_gateway; neigh_release(neigh); ip_rt_put(rt); return 0; out_rt: ip_rt_put(rt); out: return -ENOENT; } static int smc_ib_determine_gid_rcu(const struct net_device *ndev, const struct ib_gid_attr *attr, u8 gid[], u8 *sgid_index, struct smc_init_info_smcrv2 *smcrv2) { if (!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) { if (gid) memcpy(gid, &attr->gid, SMC_GID_SIZE); if (sgid_index) *sgid_index = attr->index; return 0; } if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) { struct in_device *in_dev = __in_dev_get_rcu(ndev); struct net *net = dev_net(ndev); const struct in_ifaddr *ifa; bool subnet_match = false; if (!in_dev) goto out; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (!inet_ifa_match(smcrv2->saddr, ifa)) continue; subnet_match = true; break; } if (!subnet_match) goto out; if (smcrv2->daddr && smc_ib_find_route(net, smcrv2->saddr, smcrv2->daddr, smcrv2->nexthop_mac, &smcrv2->uses_gateway)) goto out; if (gid) memcpy(gid, &attr->gid, SMC_GID_SIZE); if (sgid_index) *sgid_index = attr->index; return 0; } out: return -ENODEV; } /* determine the gid for an ib-device port and vlan id */ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index, struct smc_init_info_smcrv2 *smcrv2) { const struct ib_gid_attr *attr; const struct net_device *ndev; int i; for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) { attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i); if (IS_ERR(attr)) continue; rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (!IS_ERR(ndev) && ((!vlan_id && !is_vlan_dev(ndev)) || (vlan_id && is_vlan_dev(ndev) && vlan_dev_vlan_id(ndev) == vlan_id))) { if (!smc_ib_determine_gid_rcu(ndev, attr, gid, sgid_index, smcrv2)) { rcu_read_unlock(); rdma_put_gid_attr(attr); return 0; } } rcu_read_unlock(); rdma_put_gid_attr(attr); } return -ENODEV; } /* check if gid is still defined on smcibdev */ static bool smc_ib_check_link_gid(u8 gid[SMC_GID_SIZE], bool smcrv2, struct smc_ib_device *smcibdev, u8 ibport) { const struct ib_gid_attr *attr; bool rc = false; int i; for (i = 0; !rc && i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) { attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i); if (IS_ERR(attr)) continue; rcu_read_lock(); if ((!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) || (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && !(ipv6_addr_type((const struct in6_addr *)&attr->gid) & IPV6_ADDR_LINKLOCAL))) if (!memcmp(gid, &attr->gid, SMC_GID_SIZE)) rc = true; rcu_read_unlock(); rdma_put_gid_attr(attr); } return rc; } /* check all links if the gid is still defined on smcibdev */ static void smc_ib_gid_check(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr; int i; spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry(lgr, &smc_lgr_list.list, list) { if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN)) continue; /* lgr is not affected */ if (list_empty(&lgr->list)) continue; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state == SMC_LNK_UNUSED || lgr->lnk[i].smcibdev != smcibdev) continue; if (!smc_ib_check_link_gid(lgr->lnk[i].gid, lgr->smc_version == SMC_V2, smcibdev, ibport)) smcr_port_err(smcibdev, ibport); } } spin_unlock_bh(&smc_lgr_list.lock); } static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) { int rc; memset(&smcibdev->pattr[ibport - 1], 0, sizeof(smcibdev->pattr[ibport - 1])); rc = ib_query_port(smcibdev->ibdev, ibport, &smcibdev->pattr[ibport - 1]); if (rc) goto out; /* the SMC protocol requires specification of the RoCE MAC address */ rc = smc_ib_fill_mac(smcibdev, ibport); if (rc) goto out; if (!smc_ib_is_valid_local_systemid() && smc_ib_port_active(smcibdev, ibport)) /* create unique system identifier */ smc_ib_define_local_systemid(smcibdev, ibport); out: return rc; } /* process context wrapper for might_sleep smc_ib_remember_port_attr */ static void smc_ib_port_event_work(struct work_struct *work) { struct smc_ib_device *smcibdev = container_of( work, struct smc_ib_device, port_event_work); u8 port_idx; for_each_set_bit(port_idx, &smcibdev->port_event_mask, SMC_MAX_PORTS) { smc_ib_remember_port_attr(smcibdev, port_idx + 1); clear_bit(port_idx, &smcibdev->port_event_mask); if (!smc_ib_port_active(smcibdev, port_idx + 1)) { set_bit(port_idx, smcibdev->ports_going_away); smcr_port_err(smcibdev, port_idx + 1); } else { clear_bit(port_idx, smcibdev->ports_going_away); smcr_port_add(smcibdev, port_idx + 1); smc_ib_gid_check(smcibdev, port_idx + 1); } } } /* can be called in IRQ context */ static void smc_ib_global_event_handler(struct ib_event_handler *handler, struct ib_event *ibevent) { struct smc_ib_device *smcibdev; bool schedule = false; u8 port_idx; smcibdev = container_of(handler, struct smc_ib_device, event_handler); switch (ibevent->event) { case IB_EVENT_DEVICE_FATAL: /* terminate all ports on device */ for (port_idx = 0; port_idx < SMC_MAX_PORTS; port_idx++) { set_bit(port_idx, &smcibdev->port_event_mask); if (!test_and_set_bit(port_idx, smcibdev->ports_going_away)) schedule = true; } if (schedule) schedule_work(&smcibdev->port_event_work); break; case IB_EVENT_PORT_ACTIVE: port_idx = ibevent->element.port_num - 1; if (port_idx >= SMC_MAX_PORTS) break; set_bit(port_idx, &smcibdev->port_event_mask); if (test_and_clear_bit(port_idx, smcibdev->ports_going_away)) schedule_work(&smcibdev->port_event_work); break; case IB_EVENT_PORT_ERR: port_idx = ibevent->element.port_num - 1; if (port_idx >= SMC_MAX_PORTS) break; set_bit(port_idx, &smcibdev->port_event_mask); if (!test_and_set_bit(port_idx, smcibdev->ports_going_away)) schedule_work(&smcibdev->port_event_work); break; case IB_EVENT_GID_CHANGE: port_idx = ibevent->element.port_num - 1; if (port_idx >= SMC_MAX_PORTS) break; set_bit(port_idx, &smcibdev->port_event_mask); schedule_work(&smcibdev->port_event_work); break; default: break; } } void smc_ib_dealloc_protection_domain(struct smc_link *lnk) { if (lnk->roce_pd) ib_dealloc_pd(lnk->roce_pd); lnk->roce_pd = NULL; } int smc_ib_create_protection_domain(struct smc_link *lnk) { int rc; lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0); rc = PTR_ERR_OR_ZERO(lnk->roce_pd); if (IS_ERR(lnk->roce_pd)) lnk->roce_pd = NULL; return rc; } static bool smcr_diag_is_dev_critical(struct smc_lgr_list *smc_lgr, struct smc_ib_device *smcibdev) { struct smc_link_group *lgr; bool rc = false; int i; spin_lock_bh(&smc_lgr->lock); list_for_each_entry(lgr, &smc_lgr->list, list) { if (lgr->is_smcd) continue; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state == SMC_LNK_UNUSED || lgr->lnk[i].smcibdev != smcibdev) continue; if (lgr->type == SMC_LGR_SINGLE || lgr->type == SMC_LGR_ASYMMETRIC_LOCAL) { rc = true; goto out; } } } out: spin_unlock_bh(&smc_lgr->lock); return rc; } static int smc_nl_handle_dev_port(struct sk_buff *skb, struct ib_device *ibdev, struct smc_ib_device *smcibdev, int port) { char smc_pnet[SMC_MAX_PNETID_LEN + 1]; struct nlattr *port_attrs; unsigned char port_state; int lnk_count = 0; port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT + port); if (!port_attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcibdev->pnetid_by_user[port])) goto errattr; memcpy(smc_pnet, &smcibdev->pnetid[port], SMC_MAX_PNETID_LEN); smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet)) goto errattr; if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV, smcibdev->ndev_ifidx[port])) goto errattr; if (nla_put_u8(skb, SMC_NLA_DEV_PORT_VALID, 1)) goto errattr; port_state = smc_ib_port_active(smcibdev, port + 1); if (nla_put_u8(skb, SMC_NLA_DEV_PORT_STATE, port_state)) goto errattr; lnk_count = atomic_read(&smcibdev->lnk_cnt_by_port[port]); if (nla_put_u32(skb, SMC_NLA_DEV_PORT_LNK_CNT, lnk_count)) goto errattr; nla_nest_end(skb, port_attrs); return 0; errattr: nla_nest_cancel(skb, port_attrs); errout: return -EMSGSIZE; } static bool smc_nl_handle_pci_values(const struct smc_pci_dev *smc_pci_dev, struct sk_buff *skb) { if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev->pci_fid)) return false; if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev->pci_pchid)) return false; if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev->pci_vendor)) return false; if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev->pci_device)) return false; if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev->pci_id)) return false; return true; } static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev, struct sk_buff *skb, struct netlink_callback *cb) { char smc_ibname[IB_DEVICE_NAME_MAX]; struct smc_pci_dev smc_pci_dev; struct pci_dev *pci_dev; unsigned char is_crit; struct nlattr *attrs; void *nlh; int i; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_DEV_SMCR); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCR); if (!attrs) goto errout; is_crit = smcr_diag_is_dev_critical(&smc_lgr_list, smcibdev); if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, is_crit)) goto errattr; if (smcibdev->ibdev->dev.parent) { memset(&smc_pci_dev, 0, sizeof(smc_pci_dev)); pci_dev = to_pci_dev(smcibdev->ibdev->dev.parent); smc_set_pci_values(pci_dev, &smc_pci_dev); if (!smc_nl_handle_pci_values(&smc_pci_dev, skb)) goto errattr; } snprintf(smc_ibname, sizeof(smc_ibname), "%s", smcibdev->ibdev->name); if (nla_put_string(skb, SMC_NLA_DEV_IB_NAME, smc_ibname)) goto errattr; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(smcibdev->ibdev, i)) continue; if (smc_nl_handle_dev_port(skb, smcibdev->ibdev, smcibdev, i - 1)) goto errattr; } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static void smc_nl_prep_smcr_dev(struct smc_ib_devices *dev_list, struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_ib_device *smcibdev; int snum = cb_ctx->pos[0]; int num = 0; mutex_lock(&dev_list->mutex); list_for_each_entry(smcibdev, &dev_list->list, list) { if (num < snum) goto next; if (smc_nl_handle_smcr_dev(smcibdev, skb, cb)) goto errout; next: num++; } errout: mutex_unlock(&dev_list->mutex); cb_ctx->pos[0] = num; } int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb) { smc_nl_prep_smcr_dev(&smc_ib_devices, skb, cb); return skb->len; } static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { struct smc_link *lnk = (struct smc_link *)priv; struct smc_ib_device *smcibdev = lnk->smcibdev; u8 port_idx; switch (ibevent->event) { case IB_EVENT_QP_FATAL: case IB_EVENT_QP_ACCESS_ERR: port_idx = ibevent->element.qp->port - 1; if (port_idx >= SMC_MAX_PORTS) break; set_bit(port_idx, &smcibdev->port_event_mask); if (!test_and_set_bit(port_idx, smcibdev->ports_going_away)) schedule_work(&smcibdev->port_event_work); break; default: break; } } void smc_ib_destroy_queue_pair(struct smc_link *lnk) { if (lnk->roce_qp) ib_destroy_qp(lnk->roce_qp); lnk->roce_qp = NULL; } /* create a queue pair within the protection domain for a link */ int smc_ib_create_queue_pair(struct smc_link *lnk) { struct ib_qp_init_attr qp_attr = { .event_handler = smc_ib_qp_event_handler, .qp_context = lnk, .send_cq = lnk->smcibdev->roce_cq_send, .recv_cq = lnk->smcibdev->roce_cq_recv, .srq = NULL, .cap = { /* include unsolicited rdma_writes as well, * there are max. 2 RDMA_WRITE per 1 WR_SEND */ .max_send_wr = SMC_WR_BUF_CNT * 3, .max_recv_wr = SMC_WR_BUF_CNT * 3, .max_send_sge = SMC_IB_MAX_SEND_SGE, .max_recv_sge = lnk->wr_rx_sge_cnt, .max_inline_data = 0, }, .sq_sig_type = IB_SIGNAL_REQ_WR, .qp_type = IB_QPT_RC, }; int rc; lnk->roce_qp = ib_create_qp(lnk->roce_pd, &qp_attr); rc = PTR_ERR_OR_ZERO(lnk->roce_qp); if (IS_ERR(lnk->roce_qp)) lnk->roce_qp = NULL; else smc_wr_remember_qp_attr(lnk); return rc; } void smc_ib_put_memory_region(struct ib_mr *mr) { ib_dereg_mr(mr); } static int smc_ib_map_mr_sg(struct smc_buf_desc *buf_slot, u8 link_idx) { unsigned int offset = 0; int sg_num; /* map the largest prefix of a dma mapped SG list */ sg_num = ib_map_mr_sg(buf_slot->mr[link_idx], buf_slot->sgt[link_idx].sgl, buf_slot->sgt[link_idx].orig_nents, &offset, PAGE_SIZE); return sg_num; } /* Allocate a memory region and map the dma mapped SG list of buf_slot */ int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags, struct smc_buf_desc *buf_slot, u8 link_idx) { if (buf_slot->mr[link_idx]) return 0; /* already done */ buf_slot->mr[link_idx] = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, 1 << buf_slot->order); if (IS_ERR(buf_slot->mr[link_idx])) { int rc; rc = PTR_ERR(buf_slot->mr[link_idx]); buf_slot->mr[link_idx] = NULL; return rc; } if (smc_ib_map_mr_sg(buf_slot, link_idx) != buf_slot->sgt[link_idx].orig_nents) return -EINVAL; return 0; } bool smc_ib_is_sg_need_sync(struct smc_link *lnk, struct smc_buf_desc *buf_slot) { struct scatterlist *sg; unsigned int i; bool ret = false; /* for now there is just one DMA address */ for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg, buf_slot->sgt[lnk->link_idx].nents, i) { if (!sg_dma_len(sg)) break; if (dma_need_sync(lnk->smcibdev->ibdev->dma_device, sg_dma_address(sg))) { ret = true; goto out; } } out: return ret; } /* synchronize buffer usage for cpu access */ void smc_ib_sync_sg_for_cpu(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction) { struct scatterlist *sg; unsigned int i; if (!(buf_slot->is_dma_need_sync & (1U << lnk->link_idx))) return; /* for now there is just one DMA address */ for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg, buf_slot->sgt[lnk->link_idx].nents, i) { if (!sg_dma_len(sg)) break; ib_dma_sync_single_for_cpu(lnk->smcibdev->ibdev, sg_dma_address(sg), sg_dma_len(sg), data_direction); } } /* synchronize buffer usage for device access */ void smc_ib_sync_sg_for_device(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction) { struct scatterlist *sg; unsigned int i; if (!(buf_slot->is_dma_need_sync & (1U << lnk->link_idx))) return; /* for now there is just one DMA address */ for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg, buf_slot->sgt[lnk->link_idx].nents, i) { if (!sg_dma_len(sg)) break; ib_dma_sync_single_for_device(lnk->smcibdev->ibdev, sg_dma_address(sg), sg_dma_len(sg), data_direction); } } /* Map a new TX or RX buffer SG-table to DMA */ int smc_ib_buf_map_sg(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction) { int mapped_nents; mapped_nents = ib_dma_map_sg(lnk->smcibdev->ibdev, buf_slot->sgt[lnk->link_idx].sgl, buf_slot->sgt[lnk->link_idx].orig_nents, data_direction); if (!mapped_nents) return -ENOMEM; return mapped_nents; } void smc_ib_buf_unmap_sg(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction) { if (!buf_slot->sgt[lnk->link_idx].sgl->dma_address) return; /* already unmapped */ ib_dma_unmap_sg(lnk->smcibdev->ibdev, buf_slot->sgt[lnk->link_idx].sgl, buf_slot->sgt[lnk->link_idx].orig_nents, data_direction); buf_slot->sgt[lnk->link_idx].sgl->dma_address = 0; } long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) { struct ib_cq_init_attr cqattr = { .cqe = SMC_MAX_CQE, .comp_vector = 0 }; int cqe_size_order, smc_order; long rc; mutex_lock(&smcibdev->mutex); rc = 0; if (smcibdev->initialized) goto out; /* the calculated number of cq entries fits to mlx5 cq allocation */ cqe_size_order = cache_line_size() == 128 ? 7 : 6; smc_order = MAX_PAGE_ORDER - cqe_size_order; if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE) cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2; smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev, smc_wr_tx_cq_handler, NULL, smcibdev, &cqattr); rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_send); if (IS_ERR(smcibdev->roce_cq_send)) { smcibdev->roce_cq_send = NULL; goto out; } smcibdev->roce_cq_recv = ib_create_cq(smcibdev->ibdev, smc_wr_rx_cq_handler, NULL, smcibdev, &cqattr); rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_recv); if (IS_ERR(smcibdev->roce_cq_recv)) { smcibdev->roce_cq_recv = NULL; goto err; } smc_wr_add_dev(smcibdev); smcibdev->initialized = 1; goto out; err: ib_destroy_cq(smcibdev->roce_cq_send); out: mutex_unlock(&smcibdev->mutex); return rc; } static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev) { mutex_lock(&smcibdev->mutex); if (!smcibdev->initialized) goto out; smcibdev->initialized = 0; ib_destroy_cq(smcibdev->roce_cq_recv); ib_destroy_cq(smcibdev->roce_cq_send); smc_wr_remove_dev(smcibdev); out: mutex_unlock(&smcibdev->mutex); } static struct ib_client smc_ib_client; static void smc_copy_netdev_ifindex(struct smc_ib_device *smcibdev, int port) { struct ib_device *ibdev = smcibdev->ibdev; struct net_device *ndev; ndev = ib_device_get_netdev(ibdev, port + 1); if (ndev) { smcibdev->ndev_ifidx[port] = ndev->ifindex; dev_put(ndev); } } void smc_ib_ndev_change(struct net_device *ndev, unsigned long event) { struct smc_ib_device *smcibdev; struct ib_device *libdev; struct net_device *lndev; u8 port_cnt; int i; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(smcibdev, &smc_ib_devices.list, list) { port_cnt = smcibdev->ibdev->phys_port_cnt; for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); i++) { libdev = smcibdev->ibdev; lndev = ib_device_get_netdev(libdev, i + 1); dev_put(lndev); if (lndev != ndev) continue; if (event == NETDEV_REGISTER) smcibdev->ndev_ifidx[i] = ndev->ifindex; if (event == NETDEV_UNREGISTER) smcibdev->ndev_ifidx[i] = 0; } } mutex_unlock(&smc_ib_devices.mutex); } /* callback function for ib_register_client() */ static int smc_ib_add_dev(struct ib_device *ibdev) { struct smc_ib_device *smcibdev; u8 port_cnt; int i; if (ibdev->node_type != RDMA_NODE_IB_CA) return -EOPNOTSUPP; smcibdev = kzalloc(sizeof(*smcibdev), GFP_KERNEL); if (!smcibdev) return -ENOMEM; smcibdev->ibdev = ibdev; INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work); atomic_set(&smcibdev->lnk_cnt, 0); init_waitqueue_head(&smcibdev->lnks_deleted); mutex_init(&smcibdev->mutex); mutex_lock(&smc_ib_devices.mutex); list_add_tail(&smcibdev->list, &smc_ib_devices.list); mutex_unlock(&smc_ib_devices.mutex); ib_set_client_data(ibdev, &smc_ib_client, smcibdev); INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev, smc_ib_global_event_handler); ib_register_event_handler(&smcibdev->event_handler); /* trigger reading of the port attributes */ port_cnt = smcibdev->ibdev->phys_port_cnt; pr_warn_ratelimited("smc: adding ib device %s with port count %d\n", smcibdev->ibdev->name, port_cnt); for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); i++) { set_bit(i, &smcibdev->port_event_mask); /* determine pnetids of the port */ if (smc_pnetid_by_dev_port(ibdev->dev.parent, i, smcibdev->pnetid[i])) smc_pnetid_by_table_ib(smcibdev, i + 1); smc_copy_netdev_ifindex(smcibdev, i); pr_warn_ratelimited("smc: ib device %s port %d has pnetid " "%.16s%s\n", smcibdev->ibdev->name, i + 1, smcibdev->pnetid[i], smcibdev->pnetid_by_user[i] ? " (user defined)" : ""); } schedule_work(&smcibdev->port_event_work); return 0; } /* callback function for ib_unregister_client() */ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) { struct smc_ib_device *smcibdev = client_data; mutex_lock(&smc_ib_devices.mutex); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ mutex_unlock(&smc_ib_devices.mutex); pr_warn_ratelimited("smc: removing ib device %s\n", smcibdev->ibdev->name); smc_smcr_terminate_all(smcibdev); smc_ib_cleanup_per_ibdev(smcibdev); ib_unregister_event_handler(&smcibdev->event_handler); cancel_work_sync(&smcibdev->port_event_work); kfree(smcibdev); } static struct ib_client smc_ib_client = { .name = "smc_ib", .add = smc_ib_add_dev, .remove = smc_ib_remove_dev, }; int __init smc_ib_register_client(void) { smc_ib_init_local_systemid(); return ib_register_client(&smc_ib_client); } void smc_ib_unregister_client(void) { ib_unregister_client(&smc_ib_client); } |
| 105 105 102 3 2 2 7 7 7 7 7 7 39 102 141 139 2 139 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * * Portions of this code from linux/fs/ext2/acl.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ #include <linux/f2fs_fs.h> #include "f2fs.h" #include "xattr.h" #include "acl.h" static inline size_t f2fs_acl_size(int count) { if (count <= 4) { return sizeof(struct f2fs_acl_header) + count * sizeof(struct f2fs_acl_entry_short); } else { return sizeof(struct f2fs_acl_header) + 4 * sizeof(struct f2fs_acl_entry_short) + (count - 4) * sizeof(struct f2fs_acl_entry); } } static inline int f2fs_acl_count(size_t size) { ssize_t s; size -= sizeof(struct f2fs_acl_header); s = size - 4 * sizeof(struct f2fs_acl_entry_short); if (s < 0) { if (size % sizeof(struct f2fs_acl_entry_short)) return -1; return size / sizeof(struct f2fs_acl_entry_short); } else { if (s % sizeof(struct f2fs_acl_entry)) return -1; return s / sizeof(struct f2fs_acl_entry) + 4; } } static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) { int i, count; struct posix_acl *acl; struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value; struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); const char *end = value + size; if (size < sizeof(struct f2fs_acl_header)) return ERR_PTR(-EINVAL); if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION)) return ERR_PTR(-EINVAL); count = f2fs_acl_count(size); if (count < 0) return ERR_PTR(-EINVAL); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); for (i = 0; i < count; i++) { if ((char *)entry > end) goto fail; acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag); acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm); switch (acl->a_entries[i].e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry_short)); break; case ACL_USER: acl->a_entries[i].e_uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; case ACL_GROUP: acl->a_entries[i].e_gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; default: goto fail; } } if ((char *)entry != end) goto fail; return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi, const struct posix_acl *acl, size_t *size) { struct f2fs_acl_header *f2fs_acl; struct f2fs_acl_entry *entry; int i; f2fs_acl = f2fs_kmalloc(sbi, sizeof(struct f2fs_acl_header) + acl->a_count * sizeof(struct f2fs_acl_entry), GFP_NOFS); if (!f2fs_acl) return ERR_PTR(-ENOMEM); f2fs_acl->a_version = cpu_to_le32(F2FS_ACL_VERSION); entry = (struct f2fs_acl_entry *)(f2fs_acl + 1); for (i = 0; i < acl->a_count; i++) { entry->e_tag = cpu_to_le16(acl->a_entries[i].e_tag); entry->e_perm = cpu_to_le16(acl->a_entries[i].e_perm); switch (acl->a_entries[i].e_tag) { case ACL_USER: entry->e_id = cpu_to_le32( from_kuid(&init_user_ns, acl->a_entries[i].e_uid)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; case ACL_GROUP: entry->e_id = cpu_to_le32( from_kgid(&init_user_ns, acl->a_entries[i].e_gid)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry_short)); break; default: goto fail; } } *size = f2fs_acl_size(acl->a_count); return (void *)f2fs_acl; fail: kfree(f2fs_acl); return ERR_PTR(-EINVAL); } static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, struct page *dpage) { int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT; void *value = NULL; struct posix_acl *acl; int retval; if (type == ACL_TYPE_ACCESS) name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage); if (retval > 0) { value = f2fs_kmalloc(F2FS_I_SB(inode), retval, GFP_F2FS_ZERO); if (!value) return ERR_PTR(-ENOMEM); retval = f2fs_getxattr(inode, name_index, "", value, retval, dpage); } if (retval > 0) acl = f2fs_acl_from_disk(value, retval); else if (retval == -ENODATA) acl = NULL; else acl = ERR_PTR(retval); kfree(value); return acl; } struct posix_acl *f2fs_get_acl(struct inode *inode, int type, bool rcu) { if (rcu) return ERR_PTR(-ECHILD); return __f2fs_get_acl(inode, type, NULL); } static int f2fs_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; if (is_inode_flag_set(inode, FI_ACL_MODE)) mode = F2FS_I(inode)->i_acl_mode; 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; } static int __f2fs_set_acl(struct mnt_idmap *idmap, struct inode *inode, int type, struct posix_acl *acl, struct page *ipage) { int name_index; void *value = NULL; size_t size = 0; int error; umode_t mode = inode->i_mode; switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl && !ipage) { error = f2fs_acl_update_mode(idmap, inode, &mode, &acl); if (error) return error; set_acl_inode(inode, mode); } break; case ACL_TYPE_DEFAULT: name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; default: return -EINVAL; } if (acl) { value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size); if (IS_ERR(value)) { clear_inode_flag(inode, FI_ACL_MODE); return PTR_ERR(value); } } error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0); kfree(value); if (!error) set_cached_acl(inode, type, acl); clear_inode_flag(inode, FI_ACL_MODE); return error; } int f2fs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct inode *inode = d_inode(dentry); if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; return __f2fs_set_acl(idmap, inode, type, acl, NULL); } /* * Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create * are copied from posix_acl.c */ static struct posix_acl *f2fs_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; } static int f2fs_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; } static int f2fs_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl, struct page *dpage) { 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 = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); clone = f2fs_acl_clone(p, GFP_NOFS); if (!clone) { ret = -ENOMEM; goto release_acl; } ret = f2fs_acl_create_masq(clone, mode); if (ret < 0) goto 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; release_clone: posix_acl_release(clone); release_acl: posix_acl_release(p); return ret; } int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, struct page *dpage) { struct posix_acl *default_acl = NULL, *acl = NULL; int error; error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage); if (error) return error; f2fs_mark_inode_dirty_sync(inode, true); if (default_acl) { error = __f2fs_set_acl(NULL, inode, ACL_TYPE_DEFAULT, default_acl, ipage); posix_acl_release(default_acl); } else { inode->i_default_acl = NULL; } if (acl) { if (!error) error = __f2fs_set_acl(NULL, inode, ACL_TYPE_ACCESS, acl, ipage); posix_acl_release(acl); } else { inode->i_acl = NULL; } return error; } |
| 7 7 7 6 3 3 3 3 4 4 5 7 7 7 7 1 1 15 5 15 6 15 6 11 15 6 8 3 4 7 15 15 7 1 1 1 1 15 14 6 6 11 11 14 13 15 8 7 15 5 1 4 5 1 1 1 1 1 3 4 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 | /* * PCM Plug-In shared (kernel/library) code * Copyright (c) 1999 by Jaroslav Kysela <perex@perex.cz> * Copyright (c) 2000 by Abramo Bagnara <abramo@alsa-project.org> * * * This library is free software; you can redistribute it and/or modify * it under the terms of the GNU Library General Public License as * published by the Free Software Foundation; either version 2 of * the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU Library General Public License for more details. * * You should have received a copy of the GNU Library General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ #if 0 #define PLUGIN_DEBUG #endif #include <linux/slab.h> #include <linux/time.h> #include <linux/vmalloc.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include "pcm_plugin.h" #define snd_pcm_plug_first(plug) ((plug)->runtime->oss.plugin_first) #define snd_pcm_plug_last(plug) ((plug)->runtime->oss.plugin_last) /* * because some cards might have rates "very close", we ignore * all "resampling" requests within +-5% */ static int rate_match(unsigned int src_rate, unsigned int dst_rate) { unsigned int low = (src_rate * 95) / 100; unsigned int high = (src_rate * 105) / 100; return dst_rate >= low && dst_rate <= high; } static int snd_pcm_plugin_alloc(struct snd_pcm_plugin *plugin, snd_pcm_uframes_t frames) { struct snd_pcm_plugin_format *format; ssize_t width; size_t size; unsigned int channel; struct snd_pcm_plugin_channel *c; if (plugin->stream == SNDRV_PCM_STREAM_PLAYBACK) { format = &plugin->src_format; } else { format = &plugin->dst_format; } width = snd_pcm_format_physical_width(format->format); if (width < 0) return width; size = array3_size(frames, format->channels, width); /* check for too large period size once again */ if (size > 1024 * 1024) return -ENOMEM; if (snd_BUG_ON(size % 8)) return -ENXIO; size /= 8; if (plugin->buf_frames < frames) { kvfree(plugin->buf); plugin->buf = kvzalloc(size, GFP_KERNEL); plugin->buf_frames = frames; } if (!plugin->buf) { plugin->buf_frames = 0; return -ENOMEM; } c = plugin->buf_channels; if (plugin->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED) { for (channel = 0; channel < format->channels; channel++, c++) { c->frames = frames; c->enabled = 1; c->wanted = 0; c->area.addr = plugin->buf; c->area.first = channel * width; c->area.step = format->channels * width; } } else if (plugin->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED) { if (snd_BUG_ON(size % format->channels)) return -EINVAL; size /= format->channels; for (channel = 0; channel < format->channels; channel++, c++) { c->frames = frames; c->enabled = 1; c->wanted = 0; c->area.addr = plugin->buf + (channel * size); c->area.first = 0; c->area.step = width; } } else return -EINVAL; return 0; } int snd_pcm_plug_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t frames) { int err; if (snd_BUG_ON(!snd_pcm_plug_first(plug))) return -ENXIO; if (snd_pcm_plug_stream(plug) == SNDRV_PCM_STREAM_PLAYBACK) { struct snd_pcm_plugin *plugin = snd_pcm_plug_first(plug); while (plugin->next) { if (plugin->dst_frames) frames = plugin->dst_frames(plugin, frames); if ((snd_pcm_sframes_t)frames <= 0) return -ENXIO; plugin = plugin->next; err = snd_pcm_plugin_alloc(plugin, frames); if (err < 0) return err; } } else { struct snd_pcm_plugin *plugin = snd_pcm_plug_last(plug); while (plugin->prev) { if (plugin->src_frames) frames = plugin->src_frames(plugin, frames); if ((snd_pcm_sframes_t)frames <= 0) return -ENXIO; plugin = plugin->prev; err = snd_pcm_plugin_alloc(plugin, frames); if (err < 0) return err; } } return 0; } snd_pcm_sframes_t snd_pcm_plugin_client_channels(struct snd_pcm_plugin *plugin, snd_pcm_uframes_t frames, struct snd_pcm_plugin_channel **channels) { *channels = plugin->buf_channels; return frames; } int snd_pcm_plugin_build(struct snd_pcm_substream *plug, const char *name, struct snd_pcm_plugin_format *src_format, struct snd_pcm_plugin_format *dst_format, size_t extra, struct snd_pcm_plugin **ret) { struct snd_pcm_plugin *plugin; unsigned int channels; if (snd_BUG_ON(!plug)) return -ENXIO; if (snd_BUG_ON(!src_format || !dst_format)) return -ENXIO; plugin = kzalloc(sizeof(*plugin) + extra, GFP_KERNEL); if (plugin == NULL) return -ENOMEM; plugin->name = name; plugin->plug = plug; plugin->stream = snd_pcm_plug_stream(plug); plugin->access = SNDRV_PCM_ACCESS_RW_INTERLEAVED; plugin->src_format = *src_format; plugin->src_width = snd_pcm_format_physical_width(src_format->format); snd_BUG_ON(plugin->src_width <= 0); plugin->dst_format = *dst_format; plugin->dst_width = snd_pcm_format_physical_width(dst_format->format); snd_BUG_ON(plugin->dst_width <= 0); if (plugin->stream == SNDRV_PCM_STREAM_PLAYBACK) channels = src_format->channels; else channels = dst_format->channels; plugin->buf_channels = kcalloc(channels, sizeof(*plugin->buf_channels), GFP_KERNEL); if (plugin->buf_channels == NULL) { snd_pcm_plugin_free(plugin); return -ENOMEM; } plugin->client_channels = snd_pcm_plugin_client_channels; *ret = plugin; return 0; } int snd_pcm_plugin_free(struct snd_pcm_plugin *plugin) { if (! plugin) return 0; if (plugin->private_free) plugin->private_free(plugin); kfree(plugin->buf_channels); kvfree(plugin->buf); kfree(plugin); return 0; } static snd_pcm_sframes_t calc_dst_frames(struct snd_pcm_substream *plug, snd_pcm_sframes_t frames, bool check_size) { struct snd_pcm_plugin *plugin, *plugin_next; plugin = snd_pcm_plug_first(plug); while (plugin && frames > 0) { plugin_next = plugin->next; if (check_size && plugin->buf_frames && frames > plugin->buf_frames) frames = plugin->buf_frames; if (plugin->dst_frames) { frames = plugin->dst_frames(plugin, frames); if (frames < 0) return frames; } plugin = plugin_next; } return frames; } static snd_pcm_sframes_t calc_src_frames(struct snd_pcm_substream *plug, snd_pcm_sframes_t frames, bool check_size) { struct snd_pcm_plugin *plugin, *plugin_prev; plugin = snd_pcm_plug_last(plug); while (plugin && frames > 0) { plugin_prev = plugin->prev; if (plugin->src_frames) { frames = plugin->src_frames(plugin, frames); if (frames < 0) return frames; } if (check_size && plugin->buf_frames && frames > plugin->buf_frames) frames = plugin->buf_frames; plugin = plugin_prev; } return frames; } snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug, snd_pcm_uframes_t drv_frames) { if (snd_BUG_ON(!plug)) return -ENXIO; switch (snd_pcm_plug_stream(plug)) { case SNDRV_PCM_STREAM_PLAYBACK: return calc_src_frames(plug, drv_frames, false); case SNDRV_PCM_STREAM_CAPTURE: return calc_dst_frames(plug, drv_frames, false); default: snd_BUG(); return -EINVAL; } } snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug, snd_pcm_uframes_t clt_frames) { if (snd_BUG_ON(!plug)) return -ENXIO; switch (snd_pcm_plug_stream(plug)) { case SNDRV_PCM_STREAM_PLAYBACK: return calc_dst_frames(plug, clt_frames, false); case SNDRV_PCM_STREAM_CAPTURE: return calc_src_frames(plug, clt_frames, false); default: snd_BUG(); return -EINVAL; } } static int snd_pcm_plug_formats(const struct snd_mask *mask, snd_pcm_format_t format) { struct snd_mask formats = *mask; u64 linfmts = (SNDRV_PCM_FMTBIT_U8 | SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_U16_LE | SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_U16_BE | SNDRV_PCM_FMTBIT_S16_BE | SNDRV_PCM_FMTBIT_U24_LE | SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_U24_BE | SNDRV_PCM_FMTBIT_S24_BE | SNDRV_PCM_FMTBIT_U24_3LE | SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_U24_3BE | SNDRV_PCM_FMTBIT_S24_3BE | SNDRV_PCM_FMTBIT_U32_LE | SNDRV_PCM_FMTBIT_S32_LE | SNDRV_PCM_FMTBIT_U32_BE | SNDRV_PCM_FMTBIT_S32_BE); snd_mask_set(&formats, (__force int)SNDRV_PCM_FORMAT_MU_LAW); if (formats.bits[0] & lower_32_bits(linfmts)) formats.bits[0] |= lower_32_bits(linfmts); if (formats.bits[1] & upper_32_bits(linfmts)) formats.bits[1] |= upper_32_bits(linfmts); return snd_mask_test(&formats, (__force int)format); } static const snd_pcm_format_t preferred_formats[] = { SNDRV_PCM_FORMAT_S16_LE, SNDRV_PCM_FORMAT_S16_BE, SNDRV_PCM_FORMAT_U16_LE, SNDRV_PCM_FORMAT_U16_BE, SNDRV_PCM_FORMAT_S24_3LE, SNDRV_PCM_FORMAT_S24_3BE, SNDRV_PCM_FORMAT_U24_3LE, SNDRV_PCM_FORMAT_U24_3BE, SNDRV_PCM_FORMAT_S24_LE, SNDRV_PCM_FORMAT_S24_BE, SNDRV_PCM_FORMAT_U24_LE, SNDRV_PCM_FORMAT_U24_BE, SNDRV_PCM_FORMAT_S32_LE, SNDRV_PCM_FORMAT_S32_BE, SNDRV_PCM_FORMAT_U32_LE, SNDRV_PCM_FORMAT_U32_BE, SNDRV_PCM_FORMAT_S8, SNDRV_PCM_FORMAT_U8 }; snd_pcm_format_t snd_pcm_plug_slave_format(snd_pcm_format_t format, const struct snd_mask *format_mask) { int i; if (snd_mask_test(format_mask, (__force int)format)) return format; if (!snd_pcm_plug_formats(format_mask, format)) return (__force snd_pcm_format_t)-EINVAL; if (snd_pcm_format_linear(format)) { unsigned int width = snd_pcm_format_width(format); int unsignd = snd_pcm_format_unsigned(format) > 0; int big = snd_pcm_format_big_endian(format) > 0; unsigned int badness, best = -1; snd_pcm_format_t best_format = (__force snd_pcm_format_t)-1; for (i = 0; i < ARRAY_SIZE(preferred_formats); i++) { snd_pcm_format_t f = preferred_formats[i]; unsigned int w; if (!snd_mask_test(format_mask, (__force int)f)) continue; w = snd_pcm_format_width(f); if (w >= width) badness = w - width; else badness = width - w + 32; badness += snd_pcm_format_unsigned(f) != unsignd; badness += snd_pcm_format_big_endian(f) != big; if (badness < best) { best_format = f; best = badness; } } if ((__force int)best_format >= 0) return best_format; else return (__force snd_pcm_format_t)-EINVAL; } else { switch (format) { case SNDRV_PCM_FORMAT_MU_LAW: for (i = 0; i < ARRAY_SIZE(preferred_formats); ++i) { snd_pcm_format_t format1 = preferred_formats[i]; if (snd_mask_test(format_mask, (__force int)format1)) return format1; } fallthrough; default: return (__force snd_pcm_format_t)-EINVAL; } } } int snd_pcm_plug_format_plugins(struct snd_pcm_substream *plug, struct snd_pcm_hw_params *params, struct snd_pcm_hw_params *slave_params) { struct snd_pcm_plugin_format tmpformat; struct snd_pcm_plugin_format dstformat; struct snd_pcm_plugin_format srcformat; snd_pcm_access_t src_access, dst_access; struct snd_pcm_plugin *plugin = NULL; int err; int stream = snd_pcm_plug_stream(plug); int slave_interleaved = (params_channels(slave_params) == 1 || params_access(slave_params) == SNDRV_PCM_ACCESS_RW_INTERLEAVED); switch (stream) { case SNDRV_PCM_STREAM_PLAYBACK: dstformat.format = params_format(slave_params); dstformat.rate = params_rate(slave_params); dstformat.channels = params_channels(slave_params); srcformat.format = params_format(params); srcformat.rate = params_rate(params); srcformat.channels = params_channels(params); src_access = SNDRV_PCM_ACCESS_RW_INTERLEAVED; dst_access = (slave_interleaved ? SNDRV_PCM_ACCESS_RW_INTERLEAVED : SNDRV_PCM_ACCESS_RW_NONINTERLEAVED); break; case SNDRV_PCM_STREAM_CAPTURE: dstformat.format = params_format(params); dstformat.rate = params_rate(params); dstformat.channels = params_channels(params); srcformat.format = params_format(slave_params); srcformat.rate = params_rate(slave_params); srcformat.channels = params_channels(slave_params); src_access = (slave_interleaved ? SNDRV_PCM_ACCESS_RW_INTERLEAVED : SNDRV_PCM_ACCESS_RW_NONINTERLEAVED); dst_access = SNDRV_PCM_ACCESS_RW_INTERLEAVED; break; default: snd_BUG(); return -EINVAL; } tmpformat = srcformat; pdprintf("srcformat: format=%i, rate=%i, channels=%i\n", srcformat.format, srcformat.rate, srcformat.channels); pdprintf("dstformat: format=%i, rate=%i, channels=%i\n", dstformat.format, dstformat.rate, dstformat.channels); /* Format change (linearization) */ if (! rate_match(srcformat.rate, dstformat.rate) && ! snd_pcm_format_linear(srcformat.format)) { if (srcformat.format != SNDRV_PCM_FORMAT_MU_LAW) return -EINVAL; tmpformat.format = SNDRV_PCM_FORMAT_S16; err = snd_pcm_plugin_build_mulaw(plug, &srcformat, &tmpformat, &plugin); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* channels reduction */ if (srcformat.channels > dstformat.channels) { tmpformat.channels = dstformat.channels; err = snd_pcm_plugin_build_route(plug, &srcformat, &tmpformat, &plugin); pdprintf("channels reduction: src=%i, dst=%i returns %i\n", srcformat.channels, tmpformat.channels, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* rate resampling */ if (!rate_match(srcformat.rate, dstformat.rate)) { if (srcformat.format != SNDRV_PCM_FORMAT_S16) { /* convert to S16 for resampling */ tmpformat.format = SNDRV_PCM_FORMAT_S16; err = snd_pcm_plugin_build_linear(plug, &srcformat, &tmpformat, &plugin); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } tmpformat.rate = dstformat.rate; err = snd_pcm_plugin_build_rate(plug, &srcformat, &tmpformat, &plugin); pdprintf("rate down resampling: src=%i, dst=%i returns %i\n", srcformat.rate, tmpformat.rate, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* format change */ if (srcformat.format != dstformat.format) { tmpformat.format = dstformat.format; if (srcformat.format == SNDRV_PCM_FORMAT_MU_LAW || tmpformat.format == SNDRV_PCM_FORMAT_MU_LAW) { err = snd_pcm_plugin_build_mulaw(plug, &srcformat, &tmpformat, &plugin); } else if (snd_pcm_format_linear(srcformat.format) && snd_pcm_format_linear(tmpformat.format)) { err = snd_pcm_plugin_build_linear(plug, &srcformat, &tmpformat, &plugin); } else return -EINVAL; pdprintf("format change: src=%i, dst=%i returns %i\n", srcformat.format, tmpformat.format, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* channels extension */ if (srcformat.channels < dstformat.channels) { tmpformat.channels = dstformat.channels; err = snd_pcm_plugin_build_route(plug, &srcformat, &tmpformat, &plugin); pdprintf("channels extension: src=%i, dst=%i returns %i\n", srcformat.channels, tmpformat.channels, err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } srcformat = tmpformat; src_access = dst_access; } /* de-interleave */ if (src_access != dst_access) { err = snd_pcm_plugin_build_copy(plug, &srcformat, &tmpformat, &plugin); pdprintf("interleave change (copy: returns %i)\n", err); if (err < 0) return err; err = snd_pcm_plugin_append(plugin); if (err < 0) { snd_pcm_plugin_free(plugin); return err; } } return 0; } snd_pcm_sframes_t snd_pcm_plug_client_channels_buf(struct snd_pcm_substream *plug, char *buf, snd_pcm_uframes_t count, struct snd_pcm_plugin_channel **channels) { struct snd_pcm_plugin *plugin; struct snd_pcm_plugin_channel *v; struct snd_pcm_plugin_format *format; int width, nchannels, channel; int stream = snd_pcm_plug_stream(plug); if (snd_BUG_ON(!buf)) return -ENXIO; if (stream == SNDRV_PCM_STREAM_PLAYBACK) { plugin = snd_pcm_plug_first(plug); format = &plugin->src_format; } else { plugin = snd_pcm_plug_last(plug); format = &plugin->dst_format; } v = plugin->buf_channels; *channels = v; width = snd_pcm_format_physical_width(format->format); if (width < 0) return width; nchannels = format->channels; if (snd_BUG_ON(plugin->access != SNDRV_PCM_ACCESS_RW_INTERLEAVED && format->channels > 1)) return -ENXIO; for (channel = 0; channel < nchannels; channel++, v++) { v->frames = count; v->enabled = 1; v->wanted = (stream == SNDRV_PCM_STREAM_CAPTURE); v->area.addr = buf; v->area.first = channel * width; v->area.step = nchannels * width; } return count; } snd_pcm_sframes_t snd_pcm_plug_write_transfer(struct snd_pcm_substream *plug, struct snd_pcm_plugin_channel *src_channels, snd_pcm_uframes_t size) { struct snd_pcm_plugin *plugin, *next; struct snd_pcm_plugin_channel *dst_channels; int err; snd_pcm_sframes_t frames = size; plugin = snd_pcm_plug_first(plug); while (plugin) { if (frames <= 0) return frames; next = plugin->next; if (next) { snd_pcm_sframes_t frames1 = frames; if (plugin->dst_frames) { frames1 = plugin->dst_frames(plugin, frames); if (frames1 <= 0) return frames1; } err = next->client_channels(next, frames1, &dst_channels); if (err < 0) return err; if (err != frames1) { frames = err; if (plugin->src_frames) { frames = plugin->src_frames(plugin, frames1); if (frames <= 0) return frames; } } } else dst_channels = NULL; pdprintf("write plugin: %s, %li\n", plugin->name, frames); frames = plugin->transfer(plugin, src_channels, dst_channels, frames); if (frames < 0) return frames; src_channels = dst_channels; plugin = next; } return calc_src_frames(plug, frames, true); } snd_pcm_sframes_t snd_pcm_plug_read_transfer(struct snd_pcm_substream *plug, struct snd_pcm_plugin_channel *dst_channels_final, snd_pcm_uframes_t size) { struct snd_pcm_plugin *plugin, *next; struct snd_pcm_plugin_channel *src_channels, *dst_channels; snd_pcm_sframes_t frames = size; int err; frames = calc_src_frames(plug, frames, true); if (frames < 0) return frames; src_channels = NULL; plugin = snd_pcm_plug_first(plug); while (plugin && frames > 0) { next = plugin->next; if (next) { err = plugin->client_channels(plugin, frames, &dst_channels); if (err < 0) return err; frames = err; } else { dst_channels = dst_channels_final; } pdprintf("read plugin: %s, %li\n", plugin->name, frames); frames = plugin->transfer(plugin, src_channels, dst_channels, frames); if (frames < 0) return frames; plugin = next; src_channels = dst_channels; } return frames; } int snd_pcm_area_silence(const struct snd_pcm_channel_area *dst_area, size_t dst_offset, size_t samples, snd_pcm_format_t format) { /* FIXME: sub byte resolution and odd dst_offset */ unsigned char *dst; unsigned int dst_step; int width; const unsigned char *silence; if (!dst_area->addr) return 0; dst = dst_area->addr + (dst_area->first + dst_area->step * dst_offset) / 8; width = snd_pcm_format_physical_width(format); if (width <= 0) return -EINVAL; if (dst_area->step == (unsigned int) width && width >= 8) return snd_pcm_format_set_silence(format, dst, samples); silence = snd_pcm_format_silence_64(format); if (! silence) return -EINVAL; dst_step = dst_area->step / 8; if (width == 4) { /* Ima ADPCM */ int dstbit = dst_area->first % 8; int dstbit_step = dst_area->step % 8; while (samples-- > 0) { if (dstbit) *dst &= 0xf0; else *dst &= 0x0f; dst += dst_step; dstbit += dstbit_step; if (dstbit == 8) { dst++; dstbit = 0; } } } else { width /= 8; while (samples-- > 0) { memcpy(dst, silence, width); dst += dst_step; } } return 0; } int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_area, size_t src_offset, const struct snd_pcm_channel_area *dst_area, size_t dst_offset, size_t samples, snd_pcm_format_t format) { /* FIXME: sub byte resolution and odd dst_offset */ char *src, *dst; int width; int src_step, dst_step; src = src_area->addr + (src_area->first + src_area->step * src_offset) / 8; if (!src_area->addr) return snd_pcm_area_silence(dst_area, dst_offset, samples, format); dst = dst_area->addr + (dst_area->first + dst_area->step * dst_offset) / 8; if (!dst_area->addr) return 0; width = snd_pcm_format_physical_width(format); if (width <= 0) return -EINVAL; if (src_area->step == (unsigned int) width && dst_area->step == (unsigned int) width && width >= 8) { size_t bytes = samples * width / 8; memcpy(dst, src, bytes); return 0; } src_step = src_area->step / 8; dst_step = dst_area->step / 8; if (width == 4) { /* Ima ADPCM */ int srcbit = src_area->first % 8; int srcbit_step = src_area->step % 8; int dstbit = dst_area->first % 8; int dstbit_step = dst_area->step % 8; while (samples-- > 0) { unsigned char srcval; if (srcbit) srcval = *src & 0x0f; else srcval = (*src & 0xf0) >> 4; if (dstbit) *dst = (*dst & 0xf0) | srcval; else *dst = (*dst & 0x0f) | (srcval << 4); src += src_step; srcbit += srcbit_step; if (srcbit == 8) { src++; srcbit = 0; } dst += dst_step; dstbit += dstbit_step; if (dstbit == 8) { dst++; dstbit = 0; } } } else { width /= 8; while (samples-- > 0) { memcpy(dst, src, width); src += src_step; dst += dst_step; } } return 0; } |
| 11756 11756 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Latched RB-trees * * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org> * * Since RB-trees have non-atomic modifications they're not immediately suited * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for * lockless lookups; we cannot guarantee they return a correct result. * * The simplest solution is a seqlock + RB-tree, this will allow lockless * lookups; but has the constraint (inherent to the seqlock) that read sides * cannot nest in write sides. * * If we need to allow unconditional lookups (say as required for NMI context * usage) we need a more complex setup; this data structure provides this by * employing the latch technique -- see @write_seqcount_latch_begin -- to * implement a latched RB-tree which does allow for unconditional lookups by * virtue of always having (at least) one stable copy of the tree. * * However, while we have the guarantee that there is at all times one stable * copy, this does not guarantee an iteration will not observe modifications. * What might have been a stable copy at the start of the iteration, need not * remain so for the duration of the iteration. * * Therefore, this does require a lockless RB-tree iteration to be non-fatal; * see the comment in lib/rbtree.c. Note however that we only require the first * condition -- not seeing partial stores -- because the latch thing isolates * us from loops. If we were to interrupt a modification the lookup would be * pointed at the stable tree and complete while the modification was halted. */ #ifndef RB_TREE_LATCH_H #define RB_TREE_LATCH_H #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/rcupdate.h> struct latch_tree_node { struct rb_node node[2]; }; struct latch_tree_root { seqcount_latch_t seq; struct rb_root tree[2]; }; /** * latch_tree_ops - operators to define the tree order * @less: used for insertion; provides the (partial) order between two elements. * @comp: used for lookups; provides the order between the search key and an element. * * The operators are related like: * * comp(a->key,b) < 0 := less(a,b) * comp(a->key,b) > 0 := less(b,a) * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) * * If these operators define a partial order on the elements we make no * guarantee on which of the elements matching the key is found. See * latch_tree_find(). */ struct latch_tree_ops { bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b); int (*comp)(void *key, struct latch_tree_node *b); }; static __always_inline struct latch_tree_node * __lt_from_rb(struct rb_node *node, int idx) { return container_of(node, struct latch_tree_node, node[idx]); } static __always_inline void __lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx, bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b)) { struct rb_root *root = <r->tree[idx]; struct rb_node **link = &root->rb_node; struct rb_node *node = <n->node[idx]; struct rb_node *parent = NULL; struct latch_tree_node *ltp; while (*link) { parent = *link; ltp = __lt_from_rb(parent, idx); if (less(ltn, ltp)) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node_rcu(node, parent, link); rb_insert_color(node, root); } static __always_inline void __lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx) { rb_erase(<n->node[idx], <r->tree[idx]); } static __always_inline struct latch_tree_node * __lt_find(void *key, struct latch_tree_root *ltr, int idx, int (*comp)(void *key, struct latch_tree_node *node)) { struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node); struct latch_tree_node *ltn; int c; while (node) { ltn = __lt_from_rb(node, idx); c = comp(key, ltn); if (c < 0) node = rcu_dereference_raw(node->rb_left); else if (c > 0) node = rcu_dereference_raw(node->rb_right); else return ltn; } return NULL; } /** * latch_tree_insert() - insert @node into the trees @root * @node: nodes to insert * @root: trees to insert @node into * @ops: operators defining the node order * * It inserts @node into @root in an ordered fashion such that we can always * observe one complete tree. See the comment for write_seqcount_latch_begin(). * * The inserts use rcu_assign_pointer() to publish the element such that the * tree structure is stored before we can observe the new @node. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_insert(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { write_seqcount_latch_begin(&root->seq); __lt_insert(node, root, 0, ops->less); write_seqcount_latch(&root->seq); __lt_insert(node, root, 1, ops->less); write_seqcount_latch_end(&root->seq); } /** * latch_tree_erase() - removes @node from the trees @root * @node: nodes to remote * @root: trees to remove @node from * @ops: operators defining the node order * * Removes @node from the trees @root in an ordered fashion such that we can * always observe one complete tree. See the comment for * write_seqcount_latch_begin(). * * It is assumed that @node will observe one RCU quiescent state before being * reused of freed. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_erase(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { write_seqcount_latch_begin(&root->seq); __lt_erase(node, root, 0); write_seqcount_latch(&root->seq); __lt_erase(node, root, 1); write_seqcount_latch_end(&root->seq); } /** * latch_tree_find() - find the node matching @key in the trees @root * @key: search key * @root: trees to search for @key * @ops: operators defining the node order * * Does a lockless lookup in the trees @root for the node matching @key. * * It is assumed that this is called while holding the appropriate RCU read * side lock. * * If the operators define a partial order on the elements (there are multiple * elements which have the same key value) it is undefined which of these * elements will be found. Nor is it possible to iterate the tree to find * further elements with the same key value. * * Returns: a pointer to the node matching @key or NULL. */ static __always_inline struct latch_tree_node * latch_tree_find(void *key, struct latch_tree_root *root, const struct latch_tree_ops *ops) { struct latch_tree_node *node; unsigned int seq; do { seq = read_seqcount_latch(&root->seq); node = __lt_find(key, root, seq & 1, ops->comp); } while (read_seqcount_latch_retry(&root->seq, seq)); return node; } #endif /* RB_TREE_LATCH_H */ |
| 141 140 133 14 141 99 99 85 69 83 90 90 42 90 99 99 99 99 94 90 99 99 81 99 99 89 89 89 89 89 89 86 80 87 20 14 10 20 14 7 14 14 13 7 87 12 87 3 3 3 3 3 89 87 89 89 89 89 79 89 89 88 87 14 98 95 32 32 77 90 55 92 69 69 69 69 97 79 83 77 77 126 133 127 118 92 91 127 141 141 141 141 141 75 140 141 141 141 141 141 59 141 141 98 99 90 94 3 95 63 32 95 98 97 17 77 98 98 97 98 3 95 98 98 98 3 95 81 1 63 32 32 95 95 95 90 36 98 89 82 81 7 99 94 89 90 88 26 26 99 98 98 3 96 78 78 5 7 77 13 14 14 14 142 142 141 28 137 34 14 66 33 98 99 80 1 66 33 98 3 96 99 78 98 27 95 108 143 13 77 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_foreground.h" #include "btree_gc.h" #include "btree_io.h" #include "btree_iter.h" #include "btree_journal_iter.h" #include "btree_key_cache.h" #include "btree_update_interior.h" #include "btree_write_buffer.h" #include "buckets.h" #include "disk_accounting.h" #include "errcode.h" #include "error.h" #include "journal.h" #include "journal_io.h" #include "journal_reclaim.h" #include "replicas.h" #include "snapshot.h" #include <linux/prefetch.h> static const char * const trans_commit_flags_strs[] = { #define x(n, ...) #n, BCH_TRANS_COMMIT_FLAGS() #undef x NULL }; void bch2_trans_commit_flags_to_text(struct printbuf *out, enum bch_trans_commit_flags flags) { enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; prt_printf(out, "watermark=%s", bch2_watermarks[watermark]); flags >>= BCH_WATERMARK_BITS; if (flags) { prt_char(out, ' '); bch2_prt_bitflags(out, trans_commit_flags_strs, flags); } } static void verify_update_old_key(struct btree_trans *trans, struct btree_insert_entry *i) { #ifdef CONFIG_BCACHEFS_DEBUG struct bch_fs *c = trans->c; struct bkey u; struct bkey_s_c k = bch2_btree_path_peek_slot_exact(trans->paths + i->path, &u); if (unlikely(trans->journal_replay_not_finished)) { struct bkey_i *j_k = bch2_journal_keys_peek_slot(c, i->btree_id, i->level, i->k->k.p); if (j_k) k = bkey_i_to_s_c(j_k); } u = *k.k; u.needs_whiteout = i->old_k.needs_whiteout; BUG_ON(memcmp(&i->old_k, &u, sizeof(struct bkey))); BUG_ON(i->old_v != k.v); #endif } static inline struct btree_path_level *insert_l(struct btree_trans *trans, struct btree_insert_entry *i) { return (trans->paths + i->path)->l + i->level; } static inline bool same_leaf_as_prev(struct btree_trans *trans, struct btree_insert_entry *i) { return i != trans->updates && insert_l(trans, &i[0])->b == insert_l(trans, &i[-1])->b; } static inline bool same_leaf_as_next(struct btree_trans *trans, struct btree_insert_entry *i) { return i + 1 < trans->updates + trans->nr_updates && insert_l(trans, &i[0])->b == insert_l(trans, &i[1])->b; } inline void bch2_btree_node_prep_for_write(struct btree_trans *trans, struct btree_path *path, struct btree *b) { struct bch_fs *c = trans->c; if (unlikely(btree_node_just_written(b)) && bch2_btree_post_write_cleanup(c, b)) bch2_trans_node_reinit_iter(trans, b); /* * If the last bset has been written, or if it's gotten too big - start * a new bset to insert into: */ if (want_new_bset(c, b)) bch2_btree_init_next(trans, b); } static noinline int trans_lock_write_fail(struct btree_trans *trans, struct btree_insert_entry *i) { while (--i >= trans->updates) { if (same_leaf_as_prev(trans, i)) continue; bch2_btree_node_unlock_write(trans, trans->paths + i->path, insert_l(trans, i)->b); } trace_and_count(trans->c, trans_restart_would_deadlock_write, trans); return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock_write); } static inline int bch2_trans_lock_write(struct btree_trans *trans) { EBUG_ON(trans->write_locked); trans_for_each_update(trans, i) { if (same_leaf_as_prev(trans, i)) continue; if (bch2_btree_node_lock_write(trans, trans->paths + i->path, &insert_l(trans, i)->b->c)) return trans_lock_write_fail(trans, i); if (!i->cached) bch2_btree_node_prep_for_write(trans, trans->paths + i->path, insert_l(trans, i)->b); } trans->write_locked = true; return 0; } static inline void bch2_trans_unlock_updates_write(struct btree_trans *trans) { if (likely(trans->write_locked)) { trans_for_each_update(trans, i) if (btree_node_locked_type(trans->paths + i->path, i->level) == BTREE_NODE_WRITE_LOCKED) bch2_btree_node_unlock_write_inlined(trans, trans->paths + i->path, insert_l(trans, i)->b); trans->write_locked = false; } } /* Inserting into a given leaf node (last stage of insert): */ /* Handle overwrites and do insert, for non extents: */ bool bch2_btree_bset_insert_key(struct btree_trans *trans, struct btree_path *path, struct btree *b, struct btree_node_iter *node_iter, struct bkey_i *insert) { struct bkey_packed *k; unsigned clobber_u64s = 0, new_u64s = 0; EBUG_ON(btree_node_just_written(b)); EBUG_ON(bset_written(b, btree_bset_last(b))); EBUG_ON(bkey_deleted(&insert->k) && bkey_val_u64s(&insert->k)); EBUG_ON(bpos_lt(insert->k.p, b->data->min_key)); EBUG_ON(bpos_gt(insert->k.p, b->data->max_key)); EBUG_ON(insert->k.u64s > bch2_btree_keys_u64s_remaining(b)); EBUG_ON(!b->c.level && !bpos_eq(insert->k.p, path->pos)); k = bch2_btree_node_iter_peek_all(node_iter, b); if (k && bkey_cmp_left_packed(b, k, &insert->k.p)) k = NULL; /* @k is the key being overwritten/deleted, if any: */ EBUG_ON(k && bkey_deleted(k)); /* Deleting, but not found? nothing to do: */ if (bkey_deleted(&insert->k) && !k) return false; if (bkey_deleted(&insert->k)) { /* Deleting: */ btree_account_key_drop(b, k); k->type = KEY_TYPE_deleted; if (k->needs_whiteout) push_whiteout(b, insert->k.p); k->needs_whiteout = false; if (k >= btree_bset_last(b)->start) { clobber_u64s = k->u64s; bch2_bset_delete(b, k, clobber_u64s); goto fix_iter; } else { bch2_btree_path_fix_key_modified(trans, b, k); } return true; } if (k) { /* Overwriting: */ btree_account_key_drop(b, k); k->type = KEY_TYPE_deleted; insert->k.needs_whiteout = k->needs_whiteout; k->needs_whiteout = false; if (k >= btree_bset_last(b)->start) { clobber_u64s = k->u64s; goto overwrite; } else { bch2_btree_path_fix_key_modified(trans, b, k); } } k = bch2_btree_node_iter_bset_pos(node_iter, b, bset_tree_last(b)); overwrite: bch2_bset_insert(b, k, insert, clobber_u64s); new_u64s = k->u64s; fix_iter: if (clobber_u64s != new_u64s) bch2_btree_node_iter_fix(trans, path, b, node_iter, k, clobber_u64s, new_u64s); return true; } static int __btree_node_flush(struct journal *j, struct journal_entry_pin *pin, unsigned i, u64 seq) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct btree_write *w = container_of(pin, struct btree_write, journal); struct btree *b = container_of(w, struct btree, writes[i]); struct btree_trans *trans = bch2_trans_get(c); unsigned long old, new; unsigned idx = w - b->writes; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); old = READ_ONCE(b->flags); do { new = old; if (!(old & (1 << BTREE_NODE_dirty)) || !!(old & (1 << BTREE_NODE_write_idx)) != idx || w->journal.seq != seq) break; new &= ~BTREE_WRITE_TYPE_MASK; new |= BTREE_WRITE_journal_reclaim; new |= 1 << BTREE_NODE_need_write; } while (!try_cmpxchg(&b->flags, &old, new)); btree_node_write_if_need(trans, b, SIX_LOCK_read); six_unlock_read(&b->c.lock); bch2_trans_put(trans); return 0; } int bch2_btree_node_flush0(struct journal *j, struct journal_entry_pin *pin, u64 seq) { return __btree_node_flush(j, pin, 0, seq); } int bch2_btree_node_flush1(struct journal *j, struct journal_entry_pin *pin, u64 seq) { return __btree_node_flush(j, pin, 1, seq); } inline void bch2_btree_add_journal_pin(struct bch_fs *c, struct btree *b, u64 seq) { struct btree_write *w = btree_current_write(b); bch2_journal_pin_add(&c->journal, seq, &w->journal, btree_node_write_idx(b) == 0 ? bch2_btree_node_flush0 : bch2_btree_node_flush1); } /** * bch2_btree_insert_key_leaf() - insert a key one key into a leaf node * @trans: btree transaction object * @path: path pointing to @insert's pos * @insert: key to insert * @journal_seq: sequence number of journal reservation */ inline void bch2_btree_insert_key_leaf(struct btree_trans *trans, struct btree_path *path, struct bkey_i *insert, u64 journal_seq) { struct bch_fs *c = trans->c; struct btree *b = path_l(path)->b; struct bset_tree *t = bset_tree_last(b); struct bset *i = bset(b, t); int old_u64s = bset_u64s(t); int old_live_u64s = b->nr.live_u64s; int live_u64s_added, u64s_added; if (unlikely(!bch2_btree_bset_insert_key(trans, path, b, &path_l(path)->iter, insert))) return; i->journal_seq = cpu_to_le64(max(journal_seq, le64_to_cpu(i->journal_seq))); bch2_btree_add_journal_pin(c, b, journal_seq); if (unlikely(!btree_node_dirty(b))) { EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags)); set_btree_node_dirty_acct(c, b); } live_u64s_added = (int) b->nr.live_u64s - old_live_u64s; u64s_added = (int) bset_u64s(t) - old_u64s; if (b->sib_u64s[0] != U16_MAX && live_u64s_added < 0) b->sib_u64s[0] = max(0, (int) b->sib_u64s[0] + live_u64s_added); if (b->sib_u64s[1] != U16_MAX && live_u64s_added < 0) b->sib_u64s[1] = max(0, (int) b->sib_u64s[1] + live_u64s_added); if (u64s_added > live_u64s_added && bch2_maybe_compact_whiteouts(c, b)) bch2_trans_node_reinit_iter(trans, b); } /* Cached btree updates: */ /* Normal update interface: */ static inline void btree_insert_entry_checks(struct btree_trans *trans, struct btree_insert_entry *i) { struct btree_path *path = trans->paths + i->path; BUG_ON(!bpos_eq(i->k->k.p, path->pos)); BUG_ON(i->cached != path->cached); BUG_ON(i->level != path->level); BUG_ON(i->btree_id != path->btree_id); EBUG_ON(!i->level && btree_type_has_snapshots(i->btree_id) && !(i->flags & BTREE_UPDATE_internal_snapshot_node) && test_bit(JOURNAL_replay_done, &trans->c->journal.flags) && i->k->k.p.snapshot && bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot) > 0); } static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans, unsigned flags) { return bch2_journal_res_get(&trans->c->journal, &trans->journal_res, trans->journal_u64s, flags); } #define JSET_ENTRY_LOG_U64s 4 static noinline void journal_transaction_name(struct btree_trans *trans) { struct bch_fs *c = trans->c; struct journal *j = &c->journal; struct jset_entry *entry = bch2_journal_add_entry(j, &trans->journal_res, BCH_JSET_ENTRY_log, 0, 0, JSET_ENTRY_LOG_U64s); struct jset_entry_log *l = container_of(entry, struct jset_entry_log, entry); strncpy(l->d, trans->fn, JSET_ENTRY_LOG_U64s * sizeof(u64)); } static inline int btree_key_can_insert(struct btree_trans *trans, struct btree *b, unsigned u64s) { if (!bch2_btree_node_insert_fits(b, u64s)) return -BCH_ERR_btree_insert_btree_node_full; return 0; } noinline static int btree_key_can_insert_cached_slowpath(struct btree_trans *trans, unsigned flags, struct btree_path *path, unsigned new_u64s) { struct bkey_cached *ck = (void *) path->l[0].b; struct bkey_i *new_k; int ret; bch2_trans_unlock_updates_write(trans); bch2_trans_unlock(trans); new_k = kmalloc(new_u64s * sizeof(u64), GFP_KERNEL); if (!new_k) { bch_err(trans->c, "error allocating memory for key cache key, btree %s u64s %u", bch2_btree_id_str(path->btree_id), new_u64s); return -BCH_ERR_ENOMEM_btree_key_cache_insert; } ret = bch2_trans_relock(trans) ?: bch2_trans_lock_write(trans); if (unlikely(ret)) { kfree(new_k); return ret; } memcpy(new_k, ck->k, ck->u64s * sizeof(u64)); trans_for_each_update(trans, i) if (i->old_v == &ck->k->v) i->old_v = &new_k->v; kfree(ck->k); ck->u64s = new_u64s; ck->k = new_k; return 0; } static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags, struct btree_path *path, unsigned u64s) { struct bch_fs *c = trans->c; struct bkey_cached *ck = (void *) path->l[0].b; unsigned new_u64s; struct bkey_i *new_k; unsigned watermark = flags & BCH_WATERMARK_MASK; EBUG_ON(path->level); if (watermark < BCH_WATERMARK_reclaim && !test_bit(BKEY_CACHED_DIRTY, &ck->flags) && bch2_btree_key_cache_must_wait(c)) return -BCH_ERR_btree_insert_need_journal_reclaim; /* * bch2_varint_decode can read past the end of the buffer by at most 7 * bytes (it won't be used): */ u64s += 1; if (u64s <= ck->u64s) return 0; new_u64s = roundup_pow_of_two(u64s); new_k = krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT|__GFP_NOWARN); if (unlikely(!new_k)) return btree_key_can_insert_cached_slowpath(trans, flags, path, new_u64s); trans_for_each_update(trans, i) if (i->old_v == &ck->k->v) i->old_v = &new_k->v; ck->u64s = new_u64s; ck->k = new_k; return 0; } /* Triggers: */ static int run_one_mem_trigger(struct btree_trans *trans, struct btree_insert_entry *i, unsigned flags) { verify_update_old_key(trans, i); if (unlikely(flags & BTREE_TRIGGER_norun)) return 0; struct bkey_s_c old = { &i->old_k, i->old_v }; struct bkey_i *new = i->k; const struct bkey_ops *old_ops = bch2_bkey_type_ops(old.k->type); const struct bkey_ops *new_ops = bch2_bkey_type_ops(i->k->k.type); if (old_ops->trigger == new_ops->trigger) return bch2_key_trigger(trans, i->btree_id, i->level, old, bkey_i_to_s(new), BTREE_TRIGGER_insert|BTREE_TRIGGER_overwrite|flags); else return bch2_key_trigger_new(trans, i->btree_id, i->level, bkey_i_to_s(new), flags) ?: bch2_key_trigger_old(trans, i->btree_id, i->level, old, flags); } static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_entry *i) { verify_update_old_key(trans, i); if ((i->flags & BTREE_TRIGGER_norun) || !btree_node_type_has_trans_triggers(i->bkey_type)) return 0; /* * Transactional triggers create new btree_insert_entries, so we can't * pass them a pointer to a btree_insert_entry, that memory is going to * move: */ struct bkey old_k = i->old_k; struct bkey_s_c old = { &old_k, i->old_v }; const struct bkey_ops *old_ops = bch2_bkey_type_ops(old.k->type); const struct bkey_ops *new_ops = bch2_bkey_type_ops(i->k->k.type); unsigned flags = i->flags|BTREE_TRIGGER_transactional; if (!i->insert_trigger_run && !i->overwrite_trigger_run && old_ops->trigger == new_ops->trigger) { i->overwrite_trigger_run = true; i->insert_trigger_run = true; return bch2_key_trigger(trans, i->btree_id, i->level, old, bkey_i_to_s(i->k), BTREE_TRIGGER_insert| BTREE_TRIGGER_overwrite|flags) ?: 1; } else if (!i->overwrite_trigger_run) { i->overwrite_trigger_run = true; return bch2_key_trigger_old(trans, i->btree_id, i->level, old, flags) ?: 1; } else if (!i->insert_trigger_run) { i->insert_trigger_run = true; return bch2_key_trigger_new(trans, i->btree_id, i->level, bkey_i_to_s(i->k), flags) ?: 1; } else { return 0; } } static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, unsigned *btree_id_updates_start) { bool trans_trigger_run; /* * Running triggers will append more updates to the list of updates as * we're walking it: */ do { trans_trigger_run = false; for (unsigned i = *btree_id_updates_start; i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; i++) { if (trans->updates[i].btree_id < btree_id) { *btree_id_updates_start = i; continue; } int ret = run_one_trans_trigger(trans, trans->updates + i); if (ret < 0) return ret; if (ret) trans_trigger_run = true; } } while (trans_trigger_run); trans_for_each_update(trans, i) BUG_ON(!(i->flags & BTREE_TRIGGER_norun) && i->btree_id == btree_id && btree_node_type_has_trans_triggers(i->bkey_type) && (!i->insert_trigger_run || !i->overwrite_trigger_run)); return 0; } static int bch2_trans_commit_run_triggers(struct btree_trans *trans) { unsigned btree_id = 0, btree_id_updates_start = 0; int ret = 0; /* * * For a given btree, this algorithm runs insert triggers before * overwrite triggers: this is so that when extents are being moved * (e.g. by FALLOCATE_FL_INSERT_RANGE), we don't drop references before * they are re-added. */ for (btree_id = 0; btree_id < BTREE_ID_NR; btree_id++) { if (btree_id == BTREE_ID_alloc) continue; ret = run_btree_triggers(trans, btree_id, &btree_id_updates_start); if (ret) return ret; } btree_id_updates_start = 0; ret = run_btree_triggers(trans, BTREE_ID_alloc, &btree_id_updates_start); if (ret) return ret; #ifdef CONFIG_BCACHEFS_DEBUG trans_for_each_update(trans, i) BUG_ON(!(i->flags & BTREE_TRIGGER_norun) && btree_node_type_has_trans_triggers(i->bkey_type) && (!i->insert_trigger_run || !i->overwrite_trigger_run)); #endif return 0; } static noinline int bch2_trans_commit_run_gc_triggers(struct btree_trans *trans) { trans_for_each_update(trans, i) if (btree_node_type_has_triggers(i->bkey_type) && gc_visited(trans->c, gc_pos_btree(i->btree_id, i->level, i->k->k.p))) { int ret = run_one_mem_trigger(trans, i, i->flags|BTREE_TRIGGER_gc); if (ret) return ret; } return 0; } static inline int bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, struct btree_insert_entry **stopped_at, unsigned long trace_ip) { struct bch_fs *c = trans->c; struct btree_trans_commit_hook *h; unsigned u64s = 0; int ret = 0; bch2_trans_verify_not_unlocked_or_in_restart(trans); if (race_fault()) { trace_and_count(c, trans_restart_fault_inject, trans, trace_ip); return btree_trans_restart(trans, BCH_ERR_transaction_restart_fault_inject); } /* * Check if the insert will fit in the leaf node with the write lock * held, otherwise another thread could write the node changing the * amount of space available: */ prefetch(&trans->c->journal.flags); trans_for_each_update(trans, i) { /* Multiple inserts might go to same leaf: */ if (!same_leaf_as_prev(trans, i)) u64s = 0; u64s += i->k->k.u64s; ret = !i->cached ? btree_key_can_insert(trans, insert_l(trans, i)->b, u64s) : btree_key_can_insert_cached(trans, flags, trans->paths + i->path, u64s); if (ret) { *stopped_at = i; return ret; } i->k->k.needs_whiteout = false; } /* * Don't get journal reservation until after we know insert will * succeed: */ if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) { ret = bch2_trans_journal_res_get(trans, (flags & BCH_WATERMARK_MASK)| JOURNAL_RES_GET_NONBLOCK); if (ret) return ret; if (unlikely(trans->journal_transaction_names)) journal_transaction_name(trans); } /* * Not allowed to fail after we've gotten our journal reservation - we * have to use it: */ if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) && !(flags & BCH_TRANS_COMMIT_no_journal_res)) { if (bch2_journal_seq_verify) trans_for_each_update(trans, i) i->k->k.bversion.lo = trans->journal_res.seq; else if (bch2_inject_invalid_keys) trans_for_each_update(trans, i) i->k->k.bversion = MAX_VERSION; } h = trans->hooks; while (h) { ret = h->fn(trans, h); if (ret) return ret; h = h->next; } struct jset_entry *entry = trans->journal_entries; percpu_down_read(&c->mark_lock); for (entry = trans->journal_entries; entry != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); entry = vstruct_next(entry)) if (entry->type == BCH_JSET_ENTRY_write_buffer_keys && entry->start->k.type == KEY_TYPE_accounting) { ret = bch2_accounting_trans_commit_hook(trans, bkey_i_to_accounting(entry->start), flags); if (ret) goto revert_fs_usage; } percpu_up_read(&c->mark_lock); /* XXX: we only want to run this if deltas are nonzero */ bch2_trans_account_disk_usage_change(trans); trans_for_each_update(trans, i) if (btree_node_type_has_atomic_triggers(i->bkey_type)) { ret = run_one_mem_trigger(trans, i, BTREE_TRIGGER_atomic|i->flags); if (ret) goto fatal_err; } if (unlikely(c->gc_pos.phase)) { ret = bch2_trans_commit_run_gc_triggers(trans); if (ret) goto fatal_err; } struct bkey_validate_context validate_context = { .from = BKEY_VALIDATE_commit }; if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) validate_context.flags = BCH_VALIDATE_write|BCH_VALIDATE_commit; for (struct jset_entry *i = trans->journal_entries; i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); i = vstruct_next(i)) { ret = bch2_journal_entry_validate(c, NULL, i, bcachefs_metadata_version_current, CPU_BIG_ENDIAN, validate_context); if (unlikely(ret)) { bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", trans->fn); goto fatal_err; } } trans_for_each_update(trans, i) { validate_context.level = i->level; validate_context.btree = i->btree_id; ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), validate_context); if (unlikely(ret)){ bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", trans->fn, (void *) i->ip_allocated); goto fatal_err; } btree_insert_entry_checks(trans, i); } if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) { struct journal *j = &c->journal; struct jset_entry *entry; trans_for_each_update(trans, i) { if (i->key_cache_already_flushed) continue; if (i->flags & BTREE_UPDATE_nojournal) continue; verify_update_old_key(trans, i); if (trans->journal_transaction_names) { entry = bch2_journal_add_entry(j, &trans->journal_res, BCH_JSET_ENTRY_overwrite, i->btree_id, i->level, i->old_k.u64s); bkey_reassemble((struct bkey_i *) entry->start, (struct bkey_s_c) { &i->old_k, i->old_v }); } entry = bch2_journal_add_entry(j, &trans->journal_res, BCH_JSET_ENTRY_btree_keys, i->btree_id, i->level, i->k->k.u64s); bkey_copy((struct bkey_i *) entry->start, i->k); } memcpy_u64s_small(journal_res_entry(&c->journal, &trans->journal_res), trans->journal_entries, trans->journal_entries_u64s); trans->journal_res.offset += trans->journal_entries_u64s; trans->journal_res.u64s -= trans->journal_entries_u64s; if (trans->journal_seq) *trans->journal_seq = trans->journal_res.seq; } trans_for_each_update(trans, i) { struct btree_path *path = trans->paths + i->path; if (!i->cached) bch2_btree_insert_key_leaf(trans, path, i->k, trans->journal_res.seq); else if (!i->key_cache_already_flushed) bch2_btree_insert_key_cached(trans, flags, i); else bch2_btree_key_cache_drop(trans, path); } return 0; fatal_err: bch2_fs_fatal_error(c, "fatal error in transaction commit: %s", bch2_err_str(ret)); percpu_down_read(&c->mark_lock); revert_fs_usage: for (struct jset_entry *entry2 = trans->journal_entries; entry2 != entry; entry2 = vstruct_next(entry2)) if (entry2->type == BCH_JSET_ENTRY_write_buffer_keys && entry2->start->k.type == KEY_TYPE_accounting) bch2_accounting_trans_commit_revert(trans, bkey_i_to_accounting(entry2->start), flags); percpu_up_read(&c->mark_lock); return ret; } static noinline void bch2_drop_overwrites_from_journal(struct btree_trans *trans) { /* * Accounting keys aren't deduped in the journal: we have to compare * each individual update against what's in the btree to see if it has * been applied yet, and accounting updates also don't overwrite, * they're deltas that accumulate. */ trans_for_each_update(trans, i) if (i->k->k.type != KEY_TYPE_accounting) bch2_journal_key_overwritten(trans->c, i->btree_id, i->level, i->k->k.p); } static int bch2_trans_commit_journal_pin_flush(struct journal *j, struct journal_entry_pin *_pin, u64 seq) { return 0; } /* * Get journal reservation, take write locks, and attempt to do btree update(s): */ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags, struct btree_insert_entry **stopped_at, unsigned long trace_ip) { struct bch_fs *c = trans->c; int ret = 0, u64s_delta = 0; for (unsigned idx = 0; idx < trans->nr_updates; idx++) { struct btree_insert_entry *i = trans->updates + idx; if (i->cached) continue; u64s_delta += !bkey_deleted(&i->k->k) ? i->k->k.u64s : 0; u64s_delta -= i->old_btree_u64s; if (!same_leaf_as_next(trans, i)) { if (u64s_delta <= 0) { ret = bch2_foreground_maybe_merge(trans, i->path, i->level, flags); if (unlikely(ret)) return ret; } u64s_delta = 0; } } ret = bch2_trans_lock_write(trans); if (unlikely(ret)) return ret; ret = bch2_trans_commit_write_locked(trans, flags, stopped_at, trace_ip); if (!ret && unlikely(trans->journal_replay_not_finished)) bch2_drop_overwrites_from_journal(trans); bch2_trans_unlock_updates_write(trans); if (!ret && trans->journal_pin) bch2_journal_pin_add(&c->journal, trans->journal_res.seq, trans->journal_pin, bch2_trans_commit_journal_pin_flush); /* * Drop journal reservation after dropping write locks, since dropping * the journal reservation may kick off a journal write: */ if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) bch2_journal_res_put(&c->journal, &trans->journal_res); return ret; } static int journal_reclaim_wait_done(struct bch_fs *c) { int ret = bch2_journal_error(&c->journal) ?: bch2_btree_key_cache_wait_done(c); if (!ret) journal_reclaim_kick(&c->journal); return ret; } static noinline int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, struct btree_insert_entry *i, int ret, unsigned long trace_ip) { struct bch_fs *c = trans->c; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; switch (ret) { case -BCH_ERR_btree_insert_btree_node_full: ret = bch2_btree_split_leaf(trans, i->path, flags); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) trace_and_count(c, trans_restart_btree_node_split, trans, trace_ip, trans->paths + i->path); break; case -BCH_ERR_btree_insert_need_mark_replicas: ret = drop_locks_do(trans, bch2_accounting_update_sb(trans)); break; case -BCH_ERR_journal_res_get_blocked: /* * XXX: this should probably be a separate BTREE_INSERT_NONBLOCK * flag */ if ((flags & BCH_TRANS_COMMIT_journal_reclaim) && watermark < BCH_WATERMARK_reclaim) { ret = -BCH_ERR_journal_reclaim_would_deadlock; break; } ret = drop_locks_do(trans, bch2_trans_journal_res_get(trans, (flags & BCH_WATERMARK_MASK)| JOURNAL_RES_GET_CHECK)); break; case -BCH_ERR_btree_insert_need_journal_reclaim: bch2_trans_unlock(trans); trace_and_count(c, trans_blocked_journal_reclaim, trans, trace_ip); track_event_change(&c->times[BCH_TIME_blocked_key_cache_flush], true); wait_event_freezable(c->journal.reclaim_wait, (ret = journal_reclaim_wait_done(c))); track_event_change(&c->times[BCH_TIME_blocked_key_cache_flush], false); if (ret < 0) break; ret = bch2_trans_relock(trans); break; default: BUG_ON(ret >= 0); break; } BUG_ON(bch2_err_matches(ret, BCH_ERR_transaction_restart) != !!trans->restarted); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOSPC) && (flags & BCH_TRANS_COMMIT_no_enospc), c, "%s: incorrectly got %s\n", __func__, bch2_err_str(ret)); return ret; } /* * This is for updates done in the early part of fsck - btree_gc - before we've * gone RW. we only add the new key to the list of keys for journal replay to * do. */ static noinline int do_bch2_trans_commit_to_journal_replay(struct btree_trans *trans) { struct bch_fs *c = trans->c; BUG_ON(current != c->recovery_task); trans_for_each_update(trans, i) { int ret = bch2_journal_key_insert(c, i->btree_id, i->level, i->k); if (ret) return ret; } for (struct jset_entry *i = trans->journal_entries; i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); i = vstruct_next(i)) if (i->type == BCH_JSET_ENTRY_btree_keys || i->type == BCH_JSET_ENTRY_write_buffer_keys) { int ret = bch2_journal_key_insert(c, i->btree_id, i->level, i->start); if (ret) return ret; } return 0; } int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) { struct btree_insert_entry *errored_at = NULL; struct bch_fs *c = trans->c; int ret = 0; bch2_trans_verify_not_unlocked_or_in_restart(trans); if (!trans->nr_updates && !trans->journal_entries_u64s) goto out_reset; ret = bch2_trans_commit_run_triggers(trans); if (ret) goto out_reset; if (!(flags & BCH_TRANS_COMMIT_no_check_rw) && unlikely(!bch2_write_ref_tryget(c, BCH_WRITE_REF_trans))) { if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) ret = do_bch2_trans_commit_to_journal_replay(trans); else ret = -BCH_ERR_erofs_trans_commit; goto out_reset; } EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags)); trans->journal_u64s = trans->journal_entries_u64s; trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names); if (trans->journal_transaction_names) trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s); trans_for_each_update(trans, i) { struct btree_path *path = trans->paths + i->path; EBUG_ON(!path->should_be_locked); ret = bch2_btree_path_upgrade(trans, path, i->level + 1); if (unlikely(ret)) goto out; EBUG_ON(!btree_node_intent_locked(path, i->level)); if (i->key_cache_already_flushed) continue; if (i->flags & BTREE_UPDATE_nojournal) continue; /* we're going to journal the key being updated: */ trans->journal_u64s += jset_u64s(i->k->k.u64s); /* and we're also going to log the overwrite: */ if (trans->journal_transaction_names) trans->journal_u64s += jset_u64s(i->old_k.u64s); } if (trans->extra_disk_res) { ret = bch2_disk_reservation_add(c, trans->disk_res, trans->extra_disk_res, (flags & BCH_TRANS_COMMIT_no_enospc) ? BCH_DISK_RESERVATION_NOFAIL : 0); if (ret) goto err; } retry: errored_at = NULL; bch2_trans_verify_not_unlocked_or_in_restart(trans); if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) memset(&trans->journal_res, 0, sizeof(trans->journal_res)); memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta)); ret = do_bch2_trans_commit(trans, flags, &errored_at, _RET_IP_); /* make sure we didn't drop or screw up locks: */ bch2_trans_verify_locks(trans); if (ret) goto err; trace_and_count(c, transaction_commit, trans, _RET_IP_); out: if (likely(!(flags & BCH_TRANS_COMMIT_no_check_rw))) bch2_write_ref_put(c, BCH_WRITE_REF_trans); out_reset: if (!ret) bch2_trans_downgrade(trans); bch2_trans_reset_updates(trans); return ret; err: ret = bch2_trans_commit_error(trans, flags, errored_at, ret, _RET_IP_); if (ret) goto out; /* * We might have done another transaction commit in the error path - * i.e. btree write buffer flush - which will have made use of * trans->journal_res, but with BCH_TRANS_COMMIT_no_journal_res that is * how the journal sequence number to pin is passed in - so we must * restart: */ if (flags & BCH_TRANS_COMMIT_no_journal_res) { ret = -BCH_ERR_transaction_restart_nested; goto out; } goto retry; } |
| 28 2845 2850 2845 62 62 62 5356 5352 5359 5519 5514 5510 5510 5513 5512 987 986 986 46 47 46 1 1 2848 2850 26 25 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 | // SPDX-License-Identifier: GPL-2.0 #include "blk-rq-qos.h" /* * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, * false if 'v' + 1 would be bigger than 'below'. */ static bool atomic_inc_below(atomic_t *v, unsigned int below) { unsigned int cur = atomic_read(v); do { if (cur >= below) return false; } while (!atomic_try_cmpxchg(v, &cur, cur + 1)); return true; } bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit) { return atomic_inc_below(&rq_wait->inflight, limit); } void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio) { do { if (rqos->ops->cleanup) rqos->ops->cleanup(rqos, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_done(struct rq_qos *rqos, struct request *rq) { do { if (rqos->ops->done) rqos->ops->done(rqos, rq); rqos = rqos->next; } while (rqos); } void __rq_qos_issue(struct rq_qos *rqos, struct request *rq) { do { if (rqos->ops->issue) rqos->ops->issue(rqos, rq); rqos = rqos->next; } while (rqos); } void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq) { do { if (rqos->ops->requeue) rqos->ops->requeue(rqos, rq); rqos = rqos->next; } while (rqos); } void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio) { do { if (rqos->ops->throttle) rqos->ops->throttle(rqos, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio) { do { if (rqos->ops->track) rqos->ops->track(rqos, rq, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio) { do { if (rqos->ops->merge) rqos->ops->merge(rqos, rq, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio) { do { if (rqos->ops->done_bio) rqos->ops->done_bio(rqos, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_queue_depth_changed(struct rq_qos *rqos) { do { if (rqos->ops->queue_depth_changed) rqos->ops->queue_depth_changed(rqos); rqos = rqos->next; } while (rqos); } /* * Return true, if we can't increase the depth further by scaling */ bool rq_depth_calc_max_depth(struct rq_depth *rqd) { unsigned int depth; bool ret = false; /* * For QD=1 devices, this is a special case. It's important for those * to have one request ready when one completes, so force a depth of * 2 for those devices. On the backend, it'll be a depth of 1 anyway, * since the device can't have more than that in flight. If we're * scaling down, then keep a setting of 1/1/1. */ if (rqd->queue_depth == 1) { if (rqd->scale_step > 0) rqd->max_depth = 1; else { rqd->max_depth = 2; ret = true; } } else { /* * scale_step == 0 is our default state. If we have suffered * latency spikes, step will be > 0, and we shrink the * allowed write depths. If step is < 0, we're only doing * writes, and we allow a temporarily higher depth to * increase performance. */ depth = min_t(unsigned int, rqd->default_depth, rqd->queue_depth); if (rqd->scale_step > 0) depth = 1 + ((depth - 1) >> min(31, rqd->scale_step)); else if (rqd->scale_step < 0) { unsigned int maxd = 3 * rqd->queue_depth / 4; depth = 1 + ((depth - 1) << -rqd->scale_step); if (depth > maxd) { depth = maxd; ret = true; } } rqd->max_depth = depth; } return ret; } /* Returns true on success and false if scaling up wasn't possible */ bool rq_depth_scale_up(struct rq_depth *rqd) { /* * Hit max in previous round, stop here */ if (rqd->scaled_max) return false; rqd->scale_step--; rqd->scaled_max = rq_depth_calc_max_depth(rqd); return true; } /* * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we * had a latency violation. Returns true on success and returns false if * scaling down wasn't possible. */ bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) { /* * Stop scaling down when we've hit the limit. This also prevents * ->scale_step from going to crazy values, if the device can't * keep up. */ if (rqd->max_depth == 1) return false; if (rqd->scale_step < 0 && hard_throttle) rqd->scale_step = 0; else rqd->scale_step++; rqd->scaled_max = false; rq_depth_calc_max_depth(rqd); return true; } struct rq_qos_wait_data { struct wait_queue_entry wq; struct task_struct *task; struct rq_wait *rqw; acquire_inflight_cb_t *cb; void *private_data; bool got_token; }; static int rq_qos_wake_function(struct wait_queue_entry *curr, unsigned int mode, int wake_flags, void *key) { struct rq_qos_wait_data *data = container_of(curr, struct rq_qos_wait_data, wq); /* * If we fail to get a budget, return -1 to interrupt the wake up loop * in __wake_up_common. */ if (!data->cb(data->rqw, data->private_data)) return -1; data->got_token = true; wake_up_process(data->task); list_del_init_careful(&curr->entry); return 1; } /** * rq_qos_wait - throttle on a rqw if we need to * @rqw: rqw to throttle on * @private_data: caller provided specific data * @acquire_inflight_cb: inc the rqw->inflight counter if we can * @cleanup_cb: the callback to cleanup in case we race with a waker * * This provides a uniform place for the rq_qos users to do their throttling. * Since you can end up with a lot of things sleeping at once, this manages the * waking up based on the resources available. The acquire_inflight_cb should * inc the rqw->inflight if we have the ability to do so, or return false if not * and then we will sleep until the room becomes available. * * cleanup_cb is in case that we race with a waker and need to cleanup the * inflight count accordingly. */ void rq_qos_wait(struct rq_wait *rqw, void *private_data, acquire_inflight_cb_t *acquire_inflight_cb, cleanup_cb_t *cleanup_cb) { struct rq_qos_wait_data data = { .wq = { .func = rq_qos_wake_function, .entry = LIST_HEAD_INIT(data.wq.entry), }, .task = current, .rqw = rqw, .cb = acquire_inflight_cb, .private_data = private_data, }; bool has_sleeper; has_sleeper = wq_has_sleeper(&rqw->wait); if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) return; has_sleeper = !prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); do { /* The memory barrier in set_current_state saves us here. */ if (data.got_token) break; if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) { finish_wait(&rqw->wait, &data.wq); /* * We raced with rq_qos_wake_function() getting a token, * which means we now have two. Put our local token * and wake anyone else potentially waiting for one. */ if (data.got_token) cleanup_cb(rqw, private_data); return; } io_schedule(); has_sleeper = true; set_current_state(TASK_UNINTERRUPTIBLE); } while (1); finish_wait(&rqw->wait, &data.wq); } void rq_qos_exit(struct request_queue *q) { mutex_lock(&q->rq_qos_mutex); while (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit(rqos); } mutex_unlock(&q->rq_qos_mutex); } int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, const struct rq_qos_ops *ops) { struct request_queue *q = disk->queue; lockdep_assert_held(&q->rq_qos_mutex); rqos->disk = disk; rqos->id = id; rqos->ops = ops; /* * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. */ blk_mq_freeze_queue(q); if (rq_qos_id(q, rqos->id)) goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; blk_mq_unfreeze_queue(q); if (rqos->ops->debugfs_attrs) { mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_register_rqos(rqos); mutex_unlock(&q->debugfs_mutex); } return 0; ebusy: blk_mq_unfreeze_queue(q); return -EBUSY; } void rq_qos_del(struct rq_qos *rqos) { struct request_queue *q = rqos->disk->queue; struct rq_qos **cur; lockdep_assert_held(&q->rq_qos_mutex); blk_mq_freeze_queue(q); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } blk_mq_unfreeze_queue(q); mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_rqos(rqos); mutex_unlock(&q->debugfs_mutex); } |
| 64 53 50 11 1 4 11 138 6 81 220 1 219 216 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 */ #include <linux/fs.h> #include <linux/slab.h> #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_unicode.h" #include "jfs_debug.h" /* * NAME: jfs_strfromUCS() * * FUNCTION: Convert little-endian unicode string to character string * */ int jfs_strfromUCS_le(char *to, const __le16 * from, int len, struct nls_table *codepage) { int i; int outlen = 0; static int warn_again = 5; /* Only warn up to 5 times total */ int warn = !!warn_again; /* once per string */ if (codepage) { for (i = 0; (i < len) && from[i]; i++) { int charlen; charlen = codepage->uni2char(le16_to_cpu(from[i]), &to[outlen], NLS_MAX_CHARSET_SIZE); if (charlen > 0) outlen += charlen; else to[outlen++] = '?'; } } else { for (i = 0; (i < len) && from[i]; i++) { if (unlikely(le16_to_cpu(from[i]) & 0xff00)) { to[i] = '?'; if (unlikely(warn)) { warn--; warn_again--; printk(KERN_ERR "non-latin1 character 0x%x found in JFS file name\n", le16_to_cpu(from[i])); printk(KERN_ERR "mount with iocharset=utf8 to access\n"); } } else to[i] = (char) (le16_to_cpu(from[i])); } outlen = i; } to[outlen] = 0; return outlen; } /* * NAME: jfs_strtoUCS() * * FUNCTION: Convert character string to unicode string * */ static int jfs_strtoUCS(wchar_t * to, const unsigned char *from, int len, struct nls_table *codepage) { int charlen; int i; if (codepage) { for (i = 0; len && *from; i++, from += charlen, len -= charlen) { charlen = codepage->char2uni(from, len, &to[i]); if (charlen < 1) { jfs_err("jfs_strtoUCS: char2uni returned %d.", charlen); jfs_err("charset = %s, char = 0x%x", codepage->charset, *from); return charlen; } } } else { for (i = 0; (i < len) && from[i]; i++) to[i] = (wchar_t) from[i]; } to[i] = 0; return i; } /* * NAME: get_UCSname() * * FUNCTION: Allocate and translate to unicode string * */ int get_UCSname(struct component_name * uniName, struct dentry *dentry) { struct nls_table *nls_tab = JFS_SBI(dentry->d_sb)->nls_tab; int length = dentry->d_name.len; if (length > JFS_NAME_MAX) return -ENAMETOOLONG; uniName->name = kmalloc_array(length + 1, sizeof(wchar_t), GFP_NOFS); if (uniName->name == NULL) return -ENOMEM; uniName->namlen = jfs_strtoUCS(uniName->name, dentry->d_name.name, length, nls_tab); if (uniName->namlen < 0) { kfree(uniName->name); return uniName->namlen; } return 0; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_RCUPDATE_WAIT_H #define _LINUX_SCHED_RCUPDATE_WAIT_H /* * RCU synchronization types and methods: */ #include <linux/rcupdate.h> #include <linux/completion.h> #include <linux/sched.h> /* * Structure allowing asynchronous waiting on RCU. */ struct rcu_synchronize { struct rcu_head head; struct completion completion; }; void wakeme_after_rcu(struct rcu_head *head); void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array); #define _wait_rcu_gp(checktiny, state, ...) \ do { \ call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ __wait_rcu_gp(checktiny, state, ARRAY_SIZE(__crcu_array), __crcu_array, __rs_array); \ } while (0) #define wait_rcu_gp(...) _wait_rcu_gp(false, TASK_UNINTERRUPTIBLE, __VA_ARGS__) #define wait_rcu_gp_state(state, ...) _wait_rcu_gp(false, state, __VA_ARGS__) /** * synchronize_rcu_mult - Wait concurrently for multiple grace periods * @...: List of call_rcu() functions for different grace periods to wait on * * This macro waits concurrently for multiple types of RCU grace periods. * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait * on concurrent RCU and RCU-tasks grace periods. Waiting on a given SRCU * domain requires you to write a wrapper function for that SRCU domain's * call_srcu() function, with this wrapper supplying the pointer to the * corresponding srcu_struct. * * Note that call_rcu_hurry() should be used instead of call_rcu() * because in kernels built with CONFIG_RCU_LAZY=y the delay between the * invocation of call_rcu() and that of the corresponding RCU callback * can be multiple seconds. * * The first argument tells Tiny RCU's _wait_rcu_gp() not to * bother waiting for RCU. The reason for this is because anywhere * synchronize_rcu_mult() can be called is automatically already a full * grace period. */ #define synchronize_rcu_mult(...) \ _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), TASK_UNINTERRUPTIBLE, __VA_ARGS__) static inline void cond_resched_rcu(void) { #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) rcu_read_unlock(); cond_resched(); rcu_read_lock(); #endif } // Has the current task blocked within its current RCU read-side // critical section? static inline bool has_rcu_reader_blocked(void) { #ifdef CONFIG_PREEMPT_RCU return !list_empty(¤t->rcu_node_entry); #else return false; #endif } #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ |
| 17 12 16 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* * linux/fs/nls/nls_cp737.c * * Charset cp737 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397, 0x0398, 0x0399, 0x039a, 0x039b, 0x039c, 0x039d, 0x039e, 0x039f, 0x03a0, /* 0x90*/ 0x03a1, 0x03a3, 0x03a4, 0x03a5, 0x03a6, 0x03a7, 0x03a8, 0x03a9, 0x03b1, 0x03b2, 0x03b3, 0x03b4, 0x03b5, 0x03b6, 0x03b7, 0x03b8, /* 0xa0*/ 0x03b9, 0x03ba, 0x03bb, 0x03bc, 0x03bd, 0x03be, 0x03bf, 0x03c0, 0x03c1, 0x03c3, 0x03c2, 0x03c4, 0x03c5, 0x03c6, 0x03c7, 0x03c8, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, /* 0xd0*/ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x03c9, 0x03ac, 0x03ad, 0x03ae, 0x03ca, 0x03af, 0x03cc, 0x03cd, 0x03cb, 0x03ce, 0x0386, 0x0388, 0x0389, 0x038a, 0x038c, 0x038e, /* 0xf0*/ 0x038f, 0x00b1, 0x2265, 0x2264, 0x03aa, 0x03ab, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0x00, 0x00, 0x00, 0x00, 0xfa, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, /* 0xf0-0xf7 */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xea, 0x00, /* 0x80-0x87 */ 0xeb, 0xec, 0xed, 0x00, 0xee, 0x00, 0xef, 0xf0, /* 0x88-0x8f */ 0x00, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, /* 0x90-0x97 */ 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, /* 0x98-0x9f */ 0x8f, 0x90, 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, /* 0xa0-0xa7 */ 0x96, 0x97, 0xf4, 0xf5, 0xe1, 0xe2, 0xe3, 0xe5, /* 0xa8-0xaf */ 0x00, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, /* 0xb0-0xb7 */ 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, /* 0xb8-0xbf */ 0xa7, 0xa8, 0xaa, 0xa9, 0xab, 0xac, 0xad, 0xae, /* 0xc0-0xc7 */ 0xaf, 0xe0, 0xe4, 0xe8, 0xe6, 0xe7, 0xe9, 0x00, /* 0xc8-0xcf */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, /* 0x78-0x7f */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0xfb, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xf7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0xf3, 0xf2, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0xd5, 0xd6, 0xc9, 0xb8, 0xb7, 0xbb, /* 0x50-0x57 */ 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, 0xc7, /* 0x58-0x5f */ 0xcc, 0xb5, 0xb6, 0xb9, 0xd1, 0xd2, 0xcb, 0xcf, /* 0x60-0x67 */ 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, NULL, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x80-0x87 */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0x88-0x8f */ 0xa8, 0xa9, 0xab, 0xac, 0xad, 0xae, 0xaf, 0xe0, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xe1, 0xe2, 0xe3, 0xe5, 0xe6, 0xe7, /* 0xe8-0xef */ 0xe9, 0xf1, 0xf2, 0xf3, 0xe4, 0xe8, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x98-0x9f */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0xa0-0xa7 */ 0x90, 0x91, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0x97, 0xea, 0xeb, 0xec, 0xf4, 0xed, 0xee, 0xef, /* 0xe0-0xe7 */ 0xf5, 0xf0, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp737", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp737(void) { return register_nls(&table); } static void __exit exit_nls_cp737(void) { unregister_nls(&table); } module_init(init_nls_cp737) module_exit(exit_nls_cp737) MODULE_DESCRIPTION("NLS Codepage 737 (Greek)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 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 | // SPDX-License-Identifier: GPL-2.0-only /* * 9P Client * * Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/idr.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/uio.h> #include <linux/netfs.h> #include <net/9p/9p.h> #include <linux/parser.h> #include <linux/seq_file.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include "protocol.h" #define CREATE_TRACE_POINTS #include <trace/events/9p.h> /* DEFAULT MSIZE = 32 pages worth of payload + P9_HDRSZ + * room for write (16 extra) or read (11 extra) operands. */ #define DEFAULT_MSIZE ((128 * 1024) + P9_IOHDRSZ) /* Client Option Parsing (code inspired by NFS code) * - a little lazy - parse all client options */ enum { Opt_msize, Opt_trans, Opt_legacy, Opt_version, Opt_err, }; static const match_table_t tokens = { {Opt_msize, "msize=%u"}, {Opt_legacy, "noextend"}, {Opt_trans, "trans=%s"}, {Opt_version, "version=%s"}, {Opt_err, NULL}, }; inline int p9_is_proto_dotl(struct p9_client *clnt) { return clnt->proto_version == p9_proto_2000L; } EXPORT_SYMBOL(p9_is_proto_dotl); inline int p9_is_proto_dotu(struct p9_client *clnt) { return clnt->proto_version == p9_proto_2000u; } EXPORT_SYMBOL(p9_is_proto_dotu); int p9_show_client_options(struct seq_file *m, struct p9_client *clnt) { if (clnt->msize != DEFAULT_MSIZE) seq_printf(m, ",msize=%u", clnt->msize); seq_printf(m, ",trans=%s", clnt->trans_mod->name); switch (clnt->proto_version) { case p9_proto_legacy: seq_puts(m, ",noextend"); break; case p9_proto_2000u: seq_puts(m, ",version=9p2000.u"); break; case p9_proto_2000L: /* Default */ break; } if (clnt->trans_mod->show_options) return clnt->trans_mod->show_options(m, clnt); return 0; } EXPORT_SYMBOL(p9_show_client_options); /* Some error codes are taken directly from the server replies, * make sure they are valid. */ static int safe_errno(int err) { if (err > 0 || err < -MAX_ERRNO) { p9_debug(P9_DEBUG_ERROR, "Invalid error code %d\n", err); return -EPROTO; } return err; } /* Interpret mount option for protocol version */ static int get_protocol_version(char *s) { int version = -EINVAL; if (!strcmp(s, "9p2000")) { version = p9_proto_legacy; p9_debug(P9_DEBUG_9P, "Protocol version: Legacy\n"); } else if (!strcmp(s, "9p2000.u")) { version = p9_proto_2000u; p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.u\n"); } else if (!strcmp(s, "9p2000.L")) { version = p9_proto_2000L; p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.L\n"); } else { pr_info("Unknown protocol version %s\n", s); } return version; } /** * parse_opts - parse mount options into client structure * @opts: options string passed from mount * @clnt: existing v9fs client information * * Return 0 upon success, -ERRNO upon failure */ static int parse_opts(char *opts, struct p9_client *clnt) { char *options, *tmp_options; char *p; substring_t args[MAX_OPT_ARGS]; int option; char *s; int ret = 0; clnt->proto_version = p9_proto_2000L; clnt->msize = DEFAULT_MSIZE; if (!opts) return 0; tmp_options = kstrdup(opts, GFP_KERNEL); if (!tmp_options) return -ENOMEM; options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token, r; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case Opt_msize: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } if (option < 4096) { p9_debug(P9_DEBUG_ERROR, "msize should be at least 4k\n"); ret = -EINVAL; continue; } clnt->msize = option; break; case Opt_trans: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of trans arg\n"); goto free_and_return; } v9fs_put_trans(clnt->trans_mod); clnt->trans_mod = v9fs_get_trans_by_name(s); if (!clnt->trans_mod) { pr_info("Could not find request transport: %s\n", s); ret = -EINVAL; } kfree(s); break; case Opt_legacy: clnt->proto_version = p9_proto_legacy; break; case Opt_version: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of version arg\n"); goto free_and_return; } r = get_protocol_version(s); if (r < 0) ret = r; else clnt->proto_version = r; kfree(s); break; default: continue; } } free_and_return: if (ret) v9fs_put_trans(clnt->trans_mod); kfree(tmp_options); return ret; } static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc, int alloc_msize) { if (likely(c->fcall_cache) && alloc_msize == c->msize) { fc->sdata = kmem_cache_alloc(c->fcall_cache, GFP_NOFS); fc->cache = c->fcall_cache; } else { fc->sdata = kmalloc(alloc_msize, GFP_NOFS); fc->cache = NULL; } if (!fc->sdata) return -ENOMEM; fc->capacity = alloc_msize; fc->id = 0; fc->tag = P9_NOTAG; return 0; } void p9_fcall_fini(struct p9_fcall *fc) { /* sdata can be NULL for interrupted requests in trans_rdma, * and kmem_cache_free does not do NULL-check for us */ if (unlikely(!fc->sdata)) return; if (fc->cache) kmem_cache_free(fc->cache, fc->sdata); else kfree(fc->sdata); } EXPORT_SYMBOL(p9_fcall_fini); static struct kmem_cache *p9_req_cache; /** * p9_tag_alloc - Allocate a new request. * @c: Client session. * @type: Transaction type. * @t_size: Buffer size for holding this request * (automatic calculation by format template if 0). * @r_size: Buffer size for holding server's reply on this request * (automatic calculation by format template if 0). * @fmt: Format template for assembling 9p request message * (see p9pdu_vwritef). * @ap: Variable arguments to be fed to passed format template * (see p9pdu_vwritef). * * Context: Process context. * Return: Pointer to new request. */ static struct p9_req_t * p9_tag_alloc(struct p9_client *c, int8_t type, uint t_size, uint r_size, const char *fmt, va_list ap) { struct p9_req_t *req = kmem_cache_alloc(p9_req_cache, GFP_NOFS); int alloc_tsize; int alloc_rsize; int tag; va_list apc; va_copy(apc, ap); alloc_tsize = min_t(size_t, c->msize, t_size ?: p9_msg_buf_size(c, type, fmt, apc)); va_end(apc); alloc_rsize = min_t(size_t, c->msize, r_size ?: p9_msg_buf_size(c, type + 1, fmt, ap)); if (!req) return ERR_PTR(-ENOMEM); if (p9_fcall_init(c, &req->tc, alloc_tsize)) goto free_req; if (p9_fcall_init(c, &req->rc, alloc_rsize)) goto free; p9pdu_reset(&req->tc); p9pdu_reset(&req->rc); req->t_err = 0; req->status = REQ_STATUS_ALLOC; /* refcount needs to be set to 0 before inserting into the idr * so p9_tag_lookup does not accept a request that is not fully * initialized. refcount_set to 2 below will mark request ready. */ refcount_set(&req->refcount, 0); init_waitqueue_head(&req->wq); INIT_LIST_HEAD(&req->req_list); idr_preload(GFP_NOFS); spin_lock_irq(&c->lock); if (type == P9_TVERSION) tag = idr_alloc(&c->reqs, req, P9_NOTAG, P9_NOTAG + 1, GFP_NOWAIT); else tag = idr_alloc(&c->reqs, req, 0, P9_NOTAG, GFP_NOWAIT); req->tc.tag = tag; spin_unlock_irq(&c->lock); idr_preload_end(); if (tag < 0) goto free; /* Init ref to two because in the general case there is one ref * that is put asynchronously by a writer thread, one ref * temporarily given by p9_tag_lookup and put by p9_client_cb * in the recv thread, and one ref put by p9_req_put in the * main thread. The only exception is virtio that does not use * p9_tag_lookup but does not have a writer thread either * (the write happens synchronously in the request/zc_request * callback), so p9_client_cb eats the second ref there * as the pointer is duplicated directly by virtqueue_add_sgs() */ refcount_set(&req->refcount, 2); return req; free: p9_fcall_fini(&req->tc); p9_fcall_fini(&req->rc); free_req: kmem_cache_free(p9_req_cache, req); return ERR_PTR(-ENOMEM); } /** * p9_tag_lookup - Look up a request by tag. * @c: Client session. * @tag: Transaction ID. * * Context: Any context. * Return: A request, or %NULL if there is no request with that tag. */ struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag) { struct p9_req_t *req; rcu_read_lock(); again: req = idr_find(&c->reqs, tag); if (req) { /* We have to be careful with the req found under rcu_read_lock * Thanks to SLAB_TYPESAFE_BY_RCU we can safely try to get the * ref again without corrupting other data, then check again * that the tag matches once we have the ref */ if (!p9_req_try_get(req)) goto again; if (req->tc.tag != tag) { p9_req_put(c, req); goto again; } } rcu_read_unlock(); return req; } EXPORT_SYMBOL(p9_tag_lookup); /** * p9_tag_remove - Remove a tag. * @c: Client session. * @r: Request of reference. * * Context: Any context. */ static void p9_tag_remove(struct p9_client *c, struct p9_req_t *r) { unsigned long flags; u16 tag = r->tc.tag; p9_debug(P9_DEBUG_MUX, "freeing clnt %p req %p tag: %d\n", c, r, tag); spin_lock_irqsave(&c->lock, flags); idr_remove(&c->reqs, tag); spin_unlock_irqrestore(&c->lock, flags); } int p9_req_put(struct p9_client *c, struct p9_req_t *r) { if (refcount_dec_and_test(&r->refcount)) { p9_tag_remove(c, r); p9_fcall_fini(&r->tc); p9_fcall_fini(&r->rc); kmem_cache_free(p9_req_cache, r); return 1; } return 0; } EXPORT_SYMBOL(p9_req_put); /** * p9_tag_cleanup - cleans up tags structure and reclaims resources * @c: v9fs client struct * * This frees resources associated with the tags structure * */ static void p9_tag_cleanup(struct p9_client *c) { struct p9_req_t *req; int id; rcu_read_lock(); idr_for_each_entry(&c->reqs, req, id) { pr_info("Tag %d still in use\n", id); if (p9_req_put(c, req) == 0) pr_warn("Packet with tag %d has still references", req->tc.tag); } rcu_read_unlock(); } /** * p9_client_cb - call back from transport to client * @c: client state * @req: request received * @status: request status, one of REQ_STATUS_* * */ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status) { p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc.tag); /* This barrier is needed to make sure any change made to req before * the status change is visible to another thread */ smp_wmb(); WRITE_ONCE(req->status, status); wake_up(&req->wq); p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc.tag); p9_req_put(c, req); } EXPORT_SYMBOL(p9_client_cb); /** * p9_parse_header - parse header arguments out of a packet * @pdu: packet to parse * @size: size of packet * @type: type of request * @tag: tag of packet * @rewind: set if we need to rewind offset afterwards */ int p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag, int rewind) { s8 r_type; s16 r_tag; s32 r_size; int offset = pdu->offset; int err; pdu->offset = 0; err = p9pdu_readf(pdu, 0, "dbw", &r_size, &r_type, &r_tag); if (err) goto rewind_and_exit; if (type) *type = r_type; if (tag) *tag = r_tag; if (size) *size = r_size; if (pdu->size != r_size || r_size < 7) { err = -EINVAL; goto rewind_and_exit; } pdu->id = r_type; pdu->tag = r_tag; p9_debug(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n", pdu->size, pdu->id, pdu->tag); rewind_and_exit: if (rewind) pdu->offset = offset; return err; } EXPORT_SYMBOL(p9_parse_header); /** * p9_check_errors - check 9p packet for error return and process it * @c: current client instance * @req: request to parse and check for error conditions * * returns error code if one is discovered, otherwise returns 0 * * this will have to be more complicated if we have multiple * error packet types */ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) { s8 type; int err; int ecode; err = p9_parse_header(&req->rc, NULL, &type, NULL, 0); if (req->rc.size > req->rc.capacity && !req->rc.zc) { pr_err("requested packet size too big: %d does not fit %zu (type=%d)\n", req->rc.size, req->rc.capacity, req->rc.id); return -EIO; } /* dump the response from server * This should be after check errors which poplulate pdu_fcall. */ trace_9p_protocol_dump(c, &req->rc); if (err) { p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); return err; } if (type != P9_RERROR && type != P9_RLERROR) return 0; if (!p9_is_proto_dotl(c)) { char *ename = NULL; err = p9pdu_readf(&req->rc, c->proto_version, "s?d", &ename, &ecode); if (err) { kfree(ename); goto out_err; } if (p9_is_proto_dotu(c) && ecode < 512) err = -ecode; if (!err) { err = p9_errstr2errno(ename, strlen(ename)); p9_debug(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, ename); } kfree(ename); } else { err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode); if (err) goto out_err; err = -ecode; p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode); } return err; out_err: p9_debug(P9_DEBUG_ERROR, "couldn't parse error%d\n", err); return err; } static struct p9_req_t * p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...); /** * p9_client_flush - flush (cancel) a request * @c: client state * @oldreq: request to cancel * * This sents a flush for a particular request and links * the flush request to the original request. The current * code only supports a single flush request although the protocol * allows for multiple flush requests to be sent for a single request. * */ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) { struct p9_req_t *req; s16 oldtag; int err; err = p9_parse_header(&oldreq->tc, NULL, NULL, &oldtag, 1); if (err) return err; p9_debug(P9_DEBUG_9P, ">>> TFLUSH tag %d\n", oldtag); req = p9_client_rpc(c, P9_TFLUSH, "w", oldtag); if (IS_ERR(req)) return PTR_ERR(req); /* if we haven't received a response for oldreq, * remove it from the list */ if (READ_ONCE(oldreq->status) == REQ_STATUS_SENT) { if (c->trans_mod->cancelled) c->trans_mod->cancelled(c, oldreq); } p9_req_put(c, req); return 0; } static struct p9_req_t *p9_client_prepare_req(struct p9_client *c, int8_t type, uint t_size, uint r_size, const char *fmt, va_list ap) { int err; struct p9_req_t *req; va_list apc; p9_debug(P9_DEBUG_MUX, "client %p op %d\n", c, type); /* we allow for any status other than disconnected */ if (c->status == Disconnected) return ERR_PTR(-EIO); /* if status is begin_disconnected we allow only clunk request */ if (c->status == BeginDisconnect && type != P9_TCLUNK) return ERR_PTR(-EIO); va_copy(apc, ap); req = p9_tag_alloc(c, type, t_size, r_size, fmt, apc); va_end(apc); if (IS_ERR(req)) return req; /* marshall the data */ p9pdu_prepare(&req->tc, req->tc.tag, type); err = p9pdu_vwritef(&req->tc, c->proto_version, fmt, ap); if (err) goto reterr; p9pdu_finalize(c, &req->tc); trace_9p_client_req(c, type, req->tc.tag); return req; reterr: p9_req_put(c, req); /* We have to put also the 2nd reference as it won't be used */ p9_req_put(c, req); return ERR_PTR(err); } /** * p9_client_rpc - issue a request and wait for a response * @c: client session * @type: type of request * @fmt: protocol format string (see protocol.c) * * Returns request structure (which client must free using p9_req_put) */ static struct p9_req_t * p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) { va_list ap; int sigpending, err; unsigned long flags; struct p9_req_t *req; /* Passing zero for tsize/rsize to p9_client_prepare_req() tells it to * auto determine an appropriate (small) request/response size * according to actual message data being sent. Currently RDMA * transport is excluded from this response message size optimization, * as it would not cope with it, due to its pooled response buffers * (using an optimized request size for RDMA as well though). */ const uint tsize = 0; const uint rsize = c->trans_mod->pooled_rbuffers ? c->msize : 0; va_start(ap, fmt); req = p9_client_prepare_req(c, type, tsize, rsize, fmt, ap); va_end(ap); if (IS_ERR(req)) return req; req->tc.zc = false; req->rc.zc = false; if (signal_pending(current)) { sigpending = 1; clear_thread_flag(TIF_SIGPENDING); } else { sigpending = 0; } err = c->trans_mod->request(c, req); if (err < 0) { /* write won't happen */ p9_req_put(c, req); if (err != -ERESTARTSYS && err != -EFAULT) c->status = Disconnected; goto recalc_sigpending; } again: /* Wait for the response */ err = wait_event_killable(req->wq, READ_ONCE(req->status) >= REQ_STATUS_RCVD); /* Make sure our req is coherent with regard to updates in other * threads - echoes to wmb() in the callback */ smp_rmb(); if (err == -ERESTARTSYS && c->status == Connected && type == P9_TFLUSH) { sigpending = 1; clear_thread_flag(TIF_SIGPENDING); goto again; } if (READ_ONCE(req->status) == REQ_STATUS_ERROR) { p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); err = req->t_err; } if (err == -ERESTARTSYS && c->status == Connected) { p9_debug(P9_DEBUG_MUX, "flushing\n"); sigpending = 1; clear_thread_flag(TIF_SIGPENDING); if (c->trans_mod->cancel(c, req)) p9_client_flush(c, req); /* if we received the response anyway, don't signal error */ if (READ_ONCE(req->status) == REQ_STATUS_RCVD) err = 0; } recalc_sigpending: if (sigpending) { spin_lock_irqsave(¤t->sighand->siglock, flags); recalc_sigpending(); spin_unlock_irqrestore(¤t->sighand->siglock, flags); } if (err < 0) goto reterr; err = p9_check_errors(c, req); trace_9p_client_res(c, type, req->rc.tag, err); if (!err) return req; reterr: p9_req_put(c, req); return ERR_PTR(safe_errno(err)); } /** * p9_client_zc_rpc - issue a request and wait for a response * @c: client session * @type: type of request * @uidata: destination for zero copy read * @uodata: source for zero copy write * @inlen: read buffer size * @olen: write buffer size * @in_hdrlen: reader header size, This is the size of response protocol data * @fmt: protocol format string (see protocol.c) * * Returns request structure (which client must free using p9_req_put) */ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, struct iov_iter *uidata, struct iov_iter *uodata, int inlen, int olen, int in_hdrlen, const char *fmt, ...) { va_list ap; int sigpending, err; unsigned long flags; struct p9_req_t *req; va_start(ap, fmt); /* We allocate a inline protocol data of only 4k bytes. * The actual content is passed in zero-copy fashion. */ req = p9_client_prepare_req(c, type, P9_ZC_HDR_SZ, P9_ZC_HDR_SZ, fmt, ap); va_end(ap); if (IS_ERR(req)) return req; req->tc.zc = true; req->rc.zc = true; if (signal_pending(current)) { sigpending = 1; clear_thread_flag(TIF_SIGPENDING); } else { sigpending = 0; } err = c->trans_mod->zc_request(c, req, uidata, uodata, inlen, olen, in_hdrlen); if (err < 0) { if (err == -EIO) c->status = Disconnected; if (err != -ERESTARTSYS) goto recalc_sigpending; } if (READ_ONCE(req->status) == REQ_STATUS_ERROR) { p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); err = req->t_err; } if (err == -ERESTARTSYS && c->status == Connected) { p9_debug(P9_DEBUG_MUX, "flushing\n"); sigpending = 1; clear_thread_flag(TIF_SIGPENDING); if (c->trans_mod->cancel(c, req)) p9_client_flush(c, req); /* if we received the response anyway, don't signal error */ if (READ_ONCE(req->status) == REQ_STATUS_RCVD) err = 0; } recalc_sigpending: if (sigpending) { spin_lock_irqsave(¤t->sighand->siglock, flags); recalc_sigpending(); spin_unlock_irqrestore(¤t->sighand->siglock, flags); } if (err < 0) goto reterr; err = p9_check_errors(c, req); trace_9p_client_res(c, type, req->rc.tag, err); if (!err) return req; reterr: p9_req_put(c, req); return ERR_PTR(safe_errno(err)); } static struct p9_fid *p9_fid_create(struct p9_client *clnt) { int ret; struct p9_fid *fid; p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt); fid = kzalloc(sizeof(*fid), GFP_KERNEL); if (!fid) return NULL; fid->mode = -1; fid->uid = current_fsuid(); fid->clnt = clnt; refcount_set(&fid->count, 1); idr_preload(GFP_KERNEL); spin_lock_irq(&clnt->lock); ret = idr_alloc_u32(&clnt->fids, fid, &fid->fid, P9_NOFID - 1, GFP_NOWAIT); spin_unlock_irq(&clnt->lock); idr_preload_end(); if (!ret) { trace_9p_fid_ref(fid, P9_FID_REF_CREATE); return fid; } kfree(fid); return NULL; } static void p9_fid_destroy(struct p9_fid *fid) { struct p9_client *clnt; unsigned long flags; p9_debug(P9_DEBUG_FID, "fid %d\n", fid->fid); trace_9p_fid_ref(fid, P9_FID_REF_DESTROY); clnt = fid->clnt; spin_lock_irqsave(&clnt->lock, flags); idr_remove(&clnt->fids, fid->fid); spin_unlock_irqrestore(&clnt->lock, flags); kfree(fid->rdir); kfree(fid); } /* We also need to export tracepoint symbols for tracepoint_enabled() */ EXPORT_TRACEPOINT_SYMBOL(9p_fid_ref); void do_trace_9p_fid_get(struct p9_fid *fid) { trace_9p_fid_ref(fid, P9_FID_REF_GET); } EXPORT_SYMBOL(do_trace_9p_fid_get); void do_trace_9p_fid_put(struct p9_fid *fid) { trace_9p_fid_ref(fid, P9_FID_REF_PUT); } EXPORT_SYMBOL(do_trace_9p_fid_put); static int p9_client_version(struct p9_client *c) { int err; struct p9_req_t *req; char *version = NULL; int msize; p9_debug(P9_DEBUG_9P, ">>> TVERSION msize %d protocol %d\n", c->msize, c->proto_version); switch (c->proto_version) { case p9_proto_2000L: req = p9_client_rpc(c, P9_TVERSION, "ds", c->msize, "9P2000.L"); break; case p9_proto_2000u: req = p9_client_rpc(c, P9_TVERSION, "ds", c->msize, "9P2000.u"); break; case p9_proto_legacy: req = p9_client_rpc(c, P9_TVERSION, "ds", c->msize, "9P2000"); break; default: return -EINVAL; } if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, c->proto_version, "ds", &msize, &version); if (err) { p9_debug(P9_DEBUG_9P, "version error %d\n", err); trace_9p_protocol_dump(c, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RVERSION msize %d %s\n", msize, version); if (!strncmp(version, "9P2000.L", 8)) { c->proto_version = p9_proto_2000L; } else if (!strncmp(version, "9P2000.u", 8)) { c->proto_version = p9_proto_2000u; } else if (!strncmp(version, "9P2000", 6)) { c->proto_version = p9_proto_legacy; } else { p9_debug(P9_DEBUG_ERROR, "server returned an unknown version: %s\n", version); err = -EREMOTEIO; goto error; } if (msize < 4096) { p9_debug(P9_DEBUG_ERROR, "server returned a msize < 4096: %d\n", msize); err = -EREMOTEIO; goto error; } if (msize < c->msize) c->msize = msize; error: kfree(version); p9_req_put(c, req); return err; } struct p9_client *p9_client_create(const char *dev_name, char *options) { int err; static atomic_t seqno = ATOMIC_INIT(0); struct p9_client *clnt; char *client_id; char *cache_name; clnt = kmalloc(sizeof(*clnt), GFP_KERNEL); if (!clnt) return ERR_PTR(-ENOMEM); clnt->trans_mod = NULL; clnt->trans = NULL; clnt->fcall_cache = NULL; client_id = utsname()->nodename; memcpy(clnt->name, client_id, strlen(client_id) + 1); spin_lock_init(&clnt->lock); idr_init(&clnt->fids); idr_init(&clnt->reqs); err = parse_opts(options, clnt); if (err < 0) goto free_client; if (!clnt->trans_mod) clnt->trans_mod = v9fs_get_default_trans(); if (!clnt->trans_mod) { err = -EPROTONOSUPPORT; p9_debug(P9_DEBUG_ERROR, "No transport defined or default transport\n"); goto free_client; } p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n", clnt, clnt->trans_mod, clnt->msize, clnt->proto_version); err = clnt->trans_mod->create(clnt, dev_name, options); if (err) goto put_trans; if (clnt->msize > clnt->trans_mod->maxsize) { clnt->msize = clnt->trans_mod->maxsize; pr_info("Limiting 'msize' to %d as this is the maximum " "supported by transport %s\n", clnt->msize, clnt->trans_mod->name ); } if (clnt->msize < 4096) { p9_debug(P9_DEBUG_ERROR, "Please specify a msize of at least 4k\n"); err = -EINVAL; goto close_trans; } err = p9_client_version(clnt); if (err) goto close_trans; cache_name = kasprintf(GFP_KERNEL, "9p-fcall-cache-%u", atomic_inc_return(&seqno)); if (!cache_name) { err = -ENOMEM; goto close_trans; } /* P9_HDRSZ + 4 is the smallest packet header we can have that is * followed by data accessed from userspace by read */ clnt->fcall_cache = kmem_cache_create_usercopy(cache_name, clnt->msize, 0, 0, P9_HDRSZ + 4, clnt->msize - (P9_HDRSZ + 4), NULL); kfree(cache_name); return clnt; close_trans: clnt->trans_mod->close(clnt); put_trans: v9fs_put_trans(clnt->trans_mod); free_client: kfree(clnt); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_create); void p9_client_destroy(struct p9_client *clnt) { struct p9_fid *fid; int id; p9_debug(P9_DEBUG_MUX, "clnt %p\n", clnt); if (clnt->trans_mod) clnt->trans_mod->close(clnt); v9fs_put_trans(clnt->trans_mod); idr_for_each_entry(&clnt->fids, fid, id) { pr_info("Found fid %d not clunked\n", fid->fid); p9_fid_destroy(fid); } p9_tag_cleanup(clnt); kmem_cache_destroy(clnt->fcall_cache); kfree(clnt); } EXPORT_SYMBOL(p9_client_destroy); void p9_client_disconnect(struct p9_client *clnt) { p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt); clnt->status = Disconnected; } EXPORT_SYMBOL(p9_client_disconnect); void p9_client_begin_disconnect(struct p9_client *clnt) { p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt); clnt->status = BeginDisconnect; } EXPORT_SYMBOL(p9_client_begin_disconnect); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, const char *uname, kuid_t n_uname, const char *aname) { int err; struct p9_req_t *req; struct p9_fid *fid; struct p9_qid qid; p9_debug(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n", afid ? afid->fid : -1, uname, aname); fid = p9_fid_create(clnt); if (!fid) { err = -ENOMEM; goto error; } fid->uid = n_uname; req = p9_client_rpc(clnt, P9_TATTACH, "ddss?u", fid->fid, afid ? afid->fid : P9_NOFID, uname, aname, n_uname); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", &qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n", qid.type, qid.path, qid.version); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); p9_req_put(clnt, req); return fid; error: if (fid) p9_fid_destroy(fid); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_attach); struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, const unsigned char * const *wnames, int clone) { int err; struct p9_client *clnt; struct p9_fid *fid; struct p9_qid *wqids; struct p9_req_t *req; u16 nwqids, count; wqids = NULL; clnt = oldfid->clnt; if (clone) { fid = p9_fid_create(clnt); if (!fid) { err = -ENOMEM; goto error; } fid->uid = oldfid->uid; } else { fid = oldfid; } p9_debug(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n", oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL); req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid, nwname, wnames); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "R", &nwqids, &wqids); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto clunk_fid; } p9_req_put(clnt, req); p9_debug(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids); if (nwqids != nwname) { err = -ENOENT; goto clunk_fid; } for (count = 0; count < nwqids; count++) p9_debug(P9_DEBUG_9P, "<<< [%d] %x.%llx.%x\n", count, wqids[count].type, wqids[count].path, wqids[count].version); if (nwname) memmove(&fid->qid, &wqids[nwqids - 1], sizeof(struct p9_qid)); else memmove(&fid->qid, &oldfid->qid, sizeof(struct p9_qid)); kfree(wqids); return fid; clunk_fid: kfree(wqids); p9_fid_put(fid); fid = NULL; error: if (fid && fid != oldfid) p9_fid_destroy(fid); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_walk); int p9_client_open(struct p9_fid *fid, int mode) { int err; struct p9_client *clnt; struct p9_req_t *req; struct p9_qid qid; int iounit; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> %s fid %d mode %d\n", p9_is_proto_dotl(clnt) ? "TLOPEN" : "TOPEN", fid->fid, mode); if (fid->mode != -1) return -EINVAL; if (p9_is_proto_dotl(clnt)) req = p9_client_rpc(clnt, P9_TLOPEN, "dd", fid->fid, mode & P9L_MODE_MASK); else req = p9_client_rpc(clnt, P9_TOPEN, "db", fid->fid, mode & P9L_MODE_MASK); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< %s qid %x.%llx.%x iounit %x\n", p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN", qid.type, qid.path, qid.version, iounit); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); fid->mode = mode; fid->iounit = iounit; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_open); int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; int iounit; p9_debug(P9_DEBUG_9P, ">>> TLCREATE fid %d name %s flags %d mode %d gid %d\n", ofid->fid, name, flags, mode, from_kgid(&init_user_ns, gid)); clnt = ofid->clnt; if (ofid->mode != -1) return -EINVAL; req = p9_client_rpc(clnt, P9_TLCREATE, "dsddg", ofid->fid, name, flags, mode & P9L_MODE_MASK, gid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", qid, &iounit); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< RLCREATE qid %x.%llx.%x iounit %x\n", qid->type, qid->path, qid->version, iounit); memmove(&ofid->qid, qid, sizeof(struct p9_qid)); ofid->mode = flags; ofid->iounit = iounit; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_create_dotl); int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode, char *extension) { int err; struct p9_client *clnt; struct p9_req_t *req; struct p9_qid qid; int iounit; p9_debug(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n", fid->fid, name, perm, mode); clnt = fid->clnt; if (fid->mode != -1) return -EINVAL; req = p9_client_rpc(clnt, P9_TCREATE, "dsdb?s", fid->fid, name, perm, mode & P9L_MODE_MASK, extension); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n", qid.type, qid.path, qid.version, iounit); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); fid->mode = mode; fid->iounit = iounit; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_fcreate); int p9_client_symlink(struct p9_fid *dfid, const char *name, const char *symtgt, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TSYMLINK dfid %d name %s symtgt %s\n", dfid->fid, name, symtgt); clnt = dfid->clnt; req = p9_client_rpc(clnt, P9_TSYMLINK, "dssg", dfid->fid, name, symtgt, gid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< RSYMLINK qid %x.%llx.%x\n", qid->type, qid->path, qid->version); free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_symlink); int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, const char *newname) { struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TLINK dfid %d oldfid %d newname %s\n", dfid->fid, oldfid->fid, newname); clnt = dfid->clnt; req = p9_client_rpc(clnt, P9_TLINK, "dds", dfid->fid, oldfid->fid, newname); if (IS_ERR(req)) return PTR_ERR(req); p9_debug(P9_DEBUG_9P, "<<< RLINK\n"); p9_req_put(clnt, req); return 0; } EXPORT_SYMBOL(p9_client_link); int p9_client_fsync(struct p9_fid *fid, int datasync) { int err = 0; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TFSYNC fid %d datasync:%d\n", fid->fid, datasync); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TFSYNC, "dd", fid->fid, datasync); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_fsync); int p9_client_clunk(struct p9_fid *fid) { int err = 0; struct p9_client *clnt; struct p9_req_t *req; int retries = 0; again: p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid, retries); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TCLUNK, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid); p9_req_put(clnt, req); error: /* Fid is not valid even after a failed clunk * If interrupted, retry once then give up and * leak fid until umount. */ if (err == -ERESTARTSYS) { if (retries++ == 0) goto again; } else { p9_fid_destroy(fid); } return err; } EXPORT_SYMBOL(p9_client_clunk); int p9_client_remove(struct p9_fid *fid) { int err = 0; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TREMOVE fid %d\n", fid->fid); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TREMOVE, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid); p9_req_put(clnt, req); error: if (err == -ERESTARTSYS) p9_fid_put(fid); else p9_fid_destroy(fid); return err; } EXPORT_SYMBOL(p9_client_remove); int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; p9_debug(P9_DEBUG_9P, ">>> TUNLINKAT fid %d %s %d\n", dfid->fid, name, flags); clnt = dfid->clnt; req = p9_client_rpc(clnt, P9_TUNLINKAT, "dsd", dfid->fid, name, flags); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_unlinkat); int p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err) { int total = 0; *err = 0; while (iov_iter_count(to)) { int count; count = p9_client_read_once(fid, offset, to, err); if (!count || *err) break; offset += count; total += count; } return total; } EXPORT_SYMBOL(p9_client_read); int p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err) { struct p9_client *clnt = fid->clnt; struct p9_req_t *req; int count = iov_iter_count(to); int rsize, received, non_zc = 0; char *dataptr; *err = 0; p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %zu\n", fid->fid, offset, iov_iter_count(to)); rsize = fid->iounit; if (!rsize || rsize > clnt->msize - P9_IOHDRSZ) rsize = clnt->msize - P9_IOHDRSZ; if (count < rsize) rsize = count; /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { /* response header len is 11 * PDU Header(7) + IO Size (4) */ req = p9_client_zc_rpc(clnt, P9_TREAD, to, NULL, rsize, 0, 11, "dqd", fid->fid, offset, rsize); } else { non_zc = 1; req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, rsize); } if (IS_ERR(req)) { *err = PTR_ERR(req); if (!non_zc) iov_iter_revert(to, count - iov_iter_count(to)); return 0; } *err = p9pdu_readf(&req->rc, clnt->proto_version, "D", &received, &dataptr); if (*err) { if (!non_zc) iov_iter_revert(to, count - iov_iter_count(to)); trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); return 0; } if (rsize < received) { pr_err("bogus RREAD count (%d > %d)\n", received, rsize); received = rsize; } p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received); if (non_zc) { int n = copy_to_iter(dataptr, received, to); if (n != received) { *err = -EFAULT; p9_req_put(clnt, req); return n; } } else { iov_iter_revert(to, count - received - iov_iter_count(to)); } p9_req_put(clnt, req); return received; } EXPORT_SYMBOL(p9_client_read_once); int p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) { struct p9_client *clnt = fid->clnt; struct p9_req_t *req; int total = 0; *err = 0; while (iov_iter_count(from)) { int count = iov_iter_count(from); int rsize = fid->iounit; int written; if (!rsize || rsize > clnt->msize - P9_IOHDRSZ) rsize = clnt->msize - P9_IOHDRSZ; if (count < rsize) rsize = count; p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n", fid->fid, offset, rsize, count); /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0, rsize, P9_ZC_HDR_SZ, "dqd", fid->fid, offset, rsize); } else { req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid, offset, rsize, from); } if (IS_ERR(req)) { iov_iter_revert(from, count - iov_iter_count(from)); *err = PTR_ERR(req); break; } *err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &written); if (*err) { iov_iter_revert(from, count - iov_iter_count(from)); trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); break; } if (rsize < written) { pr_err("bogus RWRITE count (%d > %d)\n", written, rsize); written = rsize; } p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written); p9_req_put(clnt, req); iov_iter_revert(from, count - written - iov_iter_count(from)); total += written; offset += written; } return total; } EXPORT_SYMBOL(p9_client_write); void p9_client_write_subreq(struct netfs_io_subrequest *subreq) { struct netfs_io_request *wreq = subreq->rreq; struct p9_fid *fid = wreq->netfs_priv; struct p9_client *clnt = fid->clnt; struct p9_req_t *req; unsigned long long start = subreq->start + subreq->transferred; int written, len = subreq->len - subreq->transferred; int err; p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu len %d\n", fid->fid, start, len); /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && len > 1024) { req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, &subreq->io_iter, 0, wreq->len, P9_ZC_HDR_SZ, "dqd", fid->fid, start, len); } else { req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid, start, len, &subreq->io_iter); } if (IS_ERR(req)) { netfs_write_subrequest_terminated(subreq, PTR_ERR(req), false); return; } err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &written); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); netfs_write_subrequest_terminated(subreq, err, false); return; } if (written > len) { pr_err("bogus RWRITE count (%d > %u)\n", written, len); written = len; } p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", len); p9_req_put(clnt, req); netfs_write_subrequest_terminated(subreq, written, false); } EXPORT_SYMBOL(p9_client_write_subreq); struct p9_wstat *p9_client_stat(struct p9_fid *fid) { int err; struct p9_client *clnt; struct p9_wstat *ret; struct p9_req_t *req; u16 ignored; p9_debug(P9_DEBUG_9P, ">>> TSTAT fid %d\n", fid->fid); ret = kmalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TSTAT, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "wS", &ignored, ret); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RSTAT sz=%x type=%x dev=%x qid=%x.%llx.%x\n" "<<< mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n" "<<< name=%s uid=%s gid=%s muid=%s extension=(%s)\n" "<<< uid=%d gid=%d n_muid=%d\n", ret->size, ret->type, ret->dev, ret->qid.type, ret->qid.path, ret->qid.version, ret->mode, ret->atime, ret->mtime, ret->length, ret->name, ret->uid, ret->gid, ret->muid, ret->extension, from_kuid(&init_user_ns, ret->n_uid), from_kgid(&init_user_ns, ret->n_gid), from_kuid(&init_user_ns, ret->n_muid)); p9_req_put(clnt, req); return ret; error: kfree(ret); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_stat); struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, u64 request_mask) { int err; struct p9_client *clnt; struct p9_stat_dotl *ret; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TGETATTR fid %d, request_mask %lld\n", fid->fid, request_mask); ret = kmalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TGETATTR, "dq", fid->fid, request_mask); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "A", ret); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RGETATTR st_result_mask=%lld\n" "<<< qid=%x.%llx.%x\n" "<<< st_mode=%8.8x st_nlink=%llu\n" "<<< st_uid=%d st_gid=%d\n" "<<< st_rdev=%llx st_size=%llx st_blksize=%llu st_blocks=%llu\n" "<<< st_atime_sec=%lld st_atime_nsec=%lld\n" "<<< st_mtime_sec=%lld st_mtime_nsec=%lld\n" "<<< st_ctime_sec=%lld st_ctime_nsec=%lld\n" "<<< st_btime_sec=%lld st_btime_nsec=%lld\n" "<<< st_gen=%lld st_data_version=%lld\n", ret->st_result_mask, ret->qid.type, ret->qid.path, ret->qid.version, ret->st_mode, ret->st_nlink, from_kuid(&init_user_ns, ret->st_uid), from_kgid(&init_user_ns, ret->st_gid), ret->st_rdev, ret->st_size, ret->st_blksize, ret->st_blocks, ret->st_atime_sec, ret->st_atime_nsec, ret->st_mtime_sec, ret->st_mtime_nsec, ret->st_ctime_sec, ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec, ret->st_gen, ret->st_data_version); p9_req_put(clnt, req); return ret; error: kfree(ret); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_getattr_dotl); static int p9_client_statsize(struct p9_wstat *wst, int proto_version) { int ret; /* NOTE: size shouldn't include its own length */ /* size[2] type[2] dev[4] qid[13] */ /* mode[4] atime[4] mtime[4] length[8]*/ /* name[s] uid[s] gid[s] muid[s] */ ret = 2 + 4 + 13 + 4 + 4 + 4 + 8 + 2 + 2 + 2 + 2; if (wst->name) ret += strlen(wst->name); if (wst->uid) ret += strlen(wst->uid); if (wst->gid) ret += strlen(wst->gid); if (wst->muid) ret += strlen(wst->muid); if (proto_version == p9_proto_2000u || proto_version == p9_proto_2000L) { /* extension[s] n_uid[4] n_gid[4] n_muid[4] */ ret += 2 + 4 + 4 + 4; if (wst->extension) ret += strlen(wst->extension); } return ret; } int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; wst->size = p9_client_statsize(wst, clnt->proto_version); p9_debug(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid); p9_debug(P9_DEBUG_9P, " sz=%x type=%x dev=%x qid=%x.%llx.%x\n" " mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n" " name=%s uid=%s gid=%s muid=%s extension=(%s)\n" " uid=%d gid=%d n_muid=%d\n", wst->size, wst->type, wst->dev, wst->qid.type, wst->qid.path, wst->qid.version, wst->mode, wst->atime, wst->mtime, wst->length, wst->name, wst->uid, wst->gid, wst->muid, wst->extension, from_kuid(&init_user_ns, wst->n_uid), from_kgid(&init_user_ns, wst->n_gid), from_kuid(&init_user_ns, wst->n_muid)); req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size + 2, wst); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_wstat); int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TSETATTR fid %d\n", fid->fid); p9_debug(P9_DEBUG_9P, " valid=%x mode=%x uid=%d gid=%d size=%lld\n", p9attr->valid, p9attr->mode, from_kuid(&init_user_ns, p9attr->uid), from_kgid(&init_user_ns, p9attr->gid), p9attr->size); p9_debug(P9_DEBUG_9P, " atime_sec=%lld atime_nsec=%lld\n", p9attr->atime_sec, p9attr->atime_nsec); p9_debug(P9_DEBUG_9P, " mtime_sec=%lld mtime_nsec=%lld\n", p9attr->mtime_sec, p9attr->mtime_nsec); req = p9_client_rpc(clnt, P9_TSETATTR, "dI", fid->fid, p9attr); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_setattr); int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb) { int err; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TSTATFS fid %d\n", fid->fid); req = p9_client_rpc(clnt, P9_TSTATFS, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type, &sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail, &sb->files, &sb->ffree, &sb->fsid, &sb->namelen); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RSTATFS fid %d type 0x%x bsize %u blocks %llu bfree %llu bavail %llu files %llu ffree %llu fsid %llu namelen %u\n", fid->fid, sb->type, sb->bsize, sb->blocks, sb->bfree, sb->bavail, sb->files, sb->ffree, sb->fsid, sb->namelen); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_statfs); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TRENAME fid %d newdirfid %d name %s\n", fid->fid, newdirfid->fid, name); req = p9_client_rpc(clnt, P9_TRENAME, "dds", fid->fid, newdirfid->fid, name); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_rename); int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name, struct p9_fid *newdirfid, const char *new_name) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = olddirfid->clnt; p9_debug(P9_DEBUG_9P, ">>> TRENAMEAT olddirfid %d old name %s newdirfid %d new name %s\n", olddirfid->fid, old_name, newdirfid->fid, new_name); req = p9_client_rpc(clnt, P9_TRENAMEAT, "dsds", olddirfid->fid, old_name, newdirfid->fid, new_name); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n", newdirfid->fid, new_name); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_renameat); /* An xattrwalk without @attr_name gives the fid for the lisxattr namespace */ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, const char *attr_name, u64 *attr_size) { int err; struct p9_req_t *req; struct p9_client *clnt; struct p9_fid *attr_fid; clnt = file_fid->clnt; attr_fid = p9_fid_create(clnt); if (!attr_fid) { err = -ENOMEM; goto error; } p9_debug(P9_DEBUG_9P, ">>> TXATTRWALK file_fid %d, attr_fid %d name '%s'\n", file_fid->fid, attr_fid->fid, attr_name); req = p9_client_rpc(clnt, P9_TXATTRWALK, "dds", file_fid->fid, attr_fid->fid, attr_name); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "q", attr_size); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto clunk_fid; } p9_req_put(clnt, req); p9_debug(P9_DEBUG_9P, "<<< RXATTRWALK fid %d size %llu\n", attr_fid->fid, *attr_size); return attr_fid; clunk_fid: p9_fid_put(attr_fid); attr_fid = NULL; error: if (attr_fid && attr_fid != file_fid) p9_fid_destroy(attr_fid); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(p9_client_xattrwalk); int p9_client_xattrcreate(struct p9_fid *fid, const char *name, u64 attr_size, int flags) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; p9_debug(P9_DEBUG_9P, ">>> TXATTRCREATE fid %d name %s size %llu flag %d\n", fid->fid, name, attr_size, flags); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TXATTRCREATE, "dsqd", fid->fid, name, attr_size, flags); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL_GPL(p9_client_xattrcreate); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) { int err, rsize, non_zc = 0; struct p9_client *clnt; struct p9_req_t *req; char *dataptr; struct kvec kv = {.iov_base = data, .iov_len = count}; struct iov_iter to; iov_iter_kvec(&to, ITER_DEST, &kv, 1, count); p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, offset, count); clnt = fid->clnt; rsize = fid->iounit; if (!rsize || rsize > clnt->msize - P9_READDIRHDRSZ) rsize = clnt->msize - P9_READDIRHDRSZ; if (count < rsize) rsize = count; /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { /* response header len is 11 * PDU Header(7) + IO Size (4) */ req = p9_client_zc_rpc(clnt, P9_TREADDIR, &to, NULL, rsize, 0, 11, "dqd", fid->fid, offset, rsize); } else { non_zc = 1; req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid, offset, rsize); } if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "D", &count, &dataptr); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } if (rsize < count) { pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize); count = rsize; } p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); if (non_zc) memmove(data, dataptr, count); p9_req_put(clnt, req); return count; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_readdir); int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode, dev_t rdev, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d minor %d\n", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev)); req = p9_client_rpc(clnt, P9_TMKNOD, "dsdddg", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev), gid); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type, qid->path, qid->version); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_mknod_dotl); int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n", fid->fid, name, mode, from_kgid(&init_user_ns, gid)); req = p9_client_rpc(clnt, P9_TMKDIR, "dsdg", fid->fid, name, mode, gid); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type, qid->path, qid->version); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_mkdir_dotl); int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TLOCK fid %d type %i flags %d start %lld length %lld proc_id %d client_id %s\n", fid->fid, flock->type, flock->flags, flock->start, flock->length, flock->proc_id, flock->client_id); req = p9_client_rpc(clnt, P9_TLOCK, "dbdqqds", fid->fid, flock->type, flock->flags, flock->start, flock->length, flock->proc_id, flock->client_id); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "b", status); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_lock_dotl); int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TGETLOCK fid %d, type %i start %lld length %lld proc_id %d client_id %s\n", fid->fid, glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); req = p9_client_rpc(clnt, P9_TGETLOCK, "dbqqds", fid->fid, glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "bqqds", &glock->type, &glock->start, &glock->length, &glock->proc_id, &glock->client_id); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld proc_id %d client_id %s\n", glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_getlock_dotl); int p9_client_readlink(struct p9_fid *fid, char **target) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TREADLINK fid %d\n", fid->fid); req = p9_client_rpc(clnt, P9_TREADLINK, "d", fid->fid); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "s", target); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_readlink); int __init p9_client_init(void) { p9_req_cache = KMEM_CACHE(p9_req_t, SLAB_TYPESAFE_BY_RCU); return p9_req_cache ? 0 : -ENOMEM; } void __exit p9_client_exit(void) { kmem_cache_destroy(p9_req_cache); } |
| 28 323 307 19 147 126 23 369 351 18 347 322 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/bitmap.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) */ #include <linux/buffer_head.h> #include "ext4.h" unsigned int ext4_count_free(char *bitmap, unsigned int numchars) { return numchars * BITS_PER_BYTE - memweight(bitmap, numchars); } int ext4_inode_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { __u32 hi; __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); int sz; if (!ext4_has_metadata_csum(sb)) return 1; sz = EXT4_INODES_PER_GROUP(sb) >> 3; provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) { hi = le16_to_cpu(gdp->bg_inode_bitmap_csum_hi); provided |= (hi << 16); } else calculated &= 0xFFFF; return provided == calculated; } void ext4_inode_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); int sz; if (!ext4_has_metadata_csum(sb)) return; sz = EXT4_INODES_PER_GROUP(sb) >> 3; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16); } int ext4_block_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { __u32 hi; __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) { hi = le16_to_cpu(gdp->bg_block_bitmap_csum_hi); provided |= (hi << 16); } else calculated &= 0xFFFF; return provided == calculated; } void ext4_block_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); gdp->bg_block_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) gdp->bg_block_bitmap_csum_hi = cpu_to_le16(csum >> 16); } |
| 6363 2 6150 6150 221 219 221 313 314 315 314 315 6000 6000 6001 5989 9 5999 18 18 18 18 18 18 263 262 263 263 263 79 76 79 76 80 359 359 8098 1 702 704 703 700 6159 6154 6156 2 6101 3246 6 6 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_CLOCK_WAS_SET (1 << 1) #define TK_UPDATE_ALL (TK_CLEAR_NTP | TK_CLOCK_WAS_SET) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; /* * The most important data for readout fits into a single 64 byte * cache line. */ struct tk_data { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; struct timekeeper shadow_timekeeper; raw_spinlock_t lock; } ____cacheline_aligned; static struct tk_data tk_core; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; unsigned long timekeeper_lock_irqsave(void) { unsigned long flags; raw_spin_lock_irqsave(&tk_core.lock, flags); return flags; } void timekeeper_unlock_irqrestore(unsigned long flags) { raw_spin_unlock_irqrestore(&tk_core.lock, flags); } /* * Multigrain timestamps require tracking the latest fine-grained timestamp * that has been issued, and never returning a coarse-grained timestamp that is * earlier than that value. * * mg_floor represents the latest fine-grained time that has been handed out as * a file timestamp on the system. This is tracked as a monotonic ktime_t, and * converted to a realtime clock value on an as-needed basis. * * Maintaining mg_floor ensures the multigrain interfaces never issue a * timestamp earlier than one that has been previously issued. * * The exception to this rule is when there is a backward realtime clock jump. If * such an event occurs, a timestamp can appear to be earlier than a previous one. */ static __cacheline_aligned_in_smp atomic64_t mg_floor; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_real, timespec64_to_ktime(tmp)); WRITE_ONCE(tk->offs_tai, ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0))); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_boot, ktime_add(tk->offs_boot, delta)); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the tk_core.lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ write_seqcount_latch_begin(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); write_seqcount_latch_end(&tkf->seq); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_get_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update_staged(tkd, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { struct tk_fast *tkf = &tk_fast_mono; struct tk_read_base *tkr; u64 baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return baser + delta; } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; int ret; guard(raw_spinlock_irqsave)(&tk_core.lock); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { guard(raw_spinlock_irqsave)(&tk_core.lock); return raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Leap state update for both shadow and the real timekeeper * Separate to spare a full memcpy() of the timekeeper. */ static void tk_update_leap_state_all(struct tk_data *tkd) { write_seqcount_begin(&tkd->seq); tk_update_leap_state(&tkd->shadow_timekeeper); tkd->timekeeper.next_leap_ktime = tkd->shadow_timekeeper.next_leap_ktime; write_seqcount_end(&tkd->seq); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* * Restore the shadow timekeeper from the real timekeeper. */ static void timekeeping_restore_shadow(struct tk_data *tkd) { lockdep_assert_held(&tkd->lock); memcpy(&tkd->shadow_timekeeper, &tkd->timekeeper, sizeof(tkd->timekeeper)); } static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int action) { struct timekeeper *tk = &tk_core.shadow_timekeeper; lockdep_assert_held(&tkd->lock); /* * Block out readers before running the updates below because that * updates VDSO and other time related infrastructure. Not blocking * the readers might let a reader see time going backwards when * reading from the VDSO after the VDSO update and then reading in * the kernel from the timekeeper before that got updated. */ write_seqcount_begin(&tkd->seq); if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * Update the real timekeeper. * * We could avoid this memcpy() by switching pointers, but that has * the downside that the reader side does not longer benefit from * the cacheline optimized data layout of the timekeeper and requires * another indirection. */ memcpy(&tkd->timekeeper, tk, sizeof(*tk)); write_seqcount_end(&tkd->seq); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; if (IS_ENABLED(CONFIG_64BIT)) { /* * Paired with WRITE_ONCE()s in tk_set_wall_to_mono() and * tk_update_sleep_time(). */ return ktime_add(tmono, READ_ONCE(*offset)); } do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; ktime_t base_boot; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_boot = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_boot); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } static bool convert_clock(u64 *val, u32 numerator, u32 denominator) { u64 rem, res; if (!numerator || !denominator) return false; res = div64_u64_rem(*val, denominator, &rem) * numerator; *val = res + div_u64(rem * numerator, denominator); return true; } static bool convert_base_to_cs(struct system_counterval_t *scv) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; u32 num, den; /* The timestamp was taken from the time keeper clock source */ if (cs->id == scv->cs_id) return true; /* * Check whether cs_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != scv->cs_id) return false; num = scv->use_nsecs ? cs->freq_khz : base->numerator; den = scv->use_nsecs ? USEC_PER_SEC : base->denominator; if (!convert_clock(&scv->cycles, num, den)) return false; scv->cycles += base->offset; return true; } static bool convert_cs_to_base(u64 *cycles, enum clocksource_ids base_id) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; /* * Check whether base_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != base_id) return false; *cycles -= base->offset; if (!convert_clock(cycles, base->denominator, base->numerator)) return false; return true; } static bool convert_ns_to_cs(u64 *delta) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; if (BITS_TO_BYTES(fls64(*delta) + tkr->shift) >= sizeof(*delta)) return false; *delta = div_u64((*delta << tkr->shift) - tkr->xtime_nsec, tkr->mult); return true; } /** * ktime_real_to_base_clock() - Convert CLOCK_REALTIME timestamp to a base clock timestamp * @treal: CLOCK_REALTIME timestamp to convert * @base_id: base clocksource id * @cycles: pointer to store the converted base clock timestamp * * Converts a supplied, future realtime clock value to the corresponding base clock value. * * Return: true if the conversion is successful, false otherwise. */ bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 delta; do { seq = read_seqcount_begin(&tk_core.seq); if ((u64)treal < tk->tkr_mono.base_real) return false; delta = (u64)treal - tk->tkr_mono.base_real; if (!convert_ns_to_cs(&delta)) return false; *cycles = tk->tkr_mono.cycle_last + delta; if (!convert_cs_to_base(cycles, base_id)) return false; } while (read_seqcount_retry(&tk_core.seq, seq)); return true; } EXPORT_SYMBOL_GPL(ktime_real_to_base_clock); /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource */ if (system_counterval.cs_id == CSID_GENERIC || !convert_base_to_cs(&system_counterval)) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * timekeeping_clocksource_has_base - Check whether the current clocksource * is based on given a base clock * @id: base clocksource ID * * Note: The return value is a snapshot which can become invalid right * after the function returns. * * Return: true if the timekeeper clocksource has a base clock with @id, * false otherwise */ bool timekeeping_clocksource_has_base(enum clocksource_ids id) { /* * This is a snapshot, so no point in using the sequence * count. Just prevent the compiler from re-evaluating @base as the * clocksource might change concurrently. */ struct clocksource_base *base = READ_ONCE(tk_core.timekeeper.tkr_mono.clock->base); return base ? base->id == id : false; } EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timespec64 ts_delta, xt; if (!timespec64_valid_settod(ts)) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); xt = tk_xtime(tks); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tks->wall_to_monotonic, &ts_delta) > 0) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, ts_delta)); tk_set_xtime(tks, ts); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); return 0; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 tmp; timekeeping_forward_now(tks); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tks), *ts); if (timespec64_compare(&tks->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_xtime_add(tks, ts); tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, *ts)); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); return 0; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct clocksource *new = data, *old = NULL; /* * If the clocksource is in a module, get a module reference. * Succeeds for built-in code (owner == NULL) as well. Abort if the * reference can't be acquired. */ if (!try_module_get(new->owner)) return 0; /* Abort if the device can't be enabled */ if (new->enable && new->enable(new) != 0) { module_put(new->owner); return 0; } scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); old = tks->tkr_mono.clock; tk_setup_internals(tks, new); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } static __init void tkd_basic_setup(struct tk_data *tkd) { raw_spin_lock_init(&tkd->lock); seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock; tkd_basic_setup(&tk_core); read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); guard(raw_spinlock_irqsave)(&tk_core.lock); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tks, clock); tk_set_xtime(tks, &wall_time); tks->raw_sec = 0; tk_set_wall_to_mono(tks, wall_to_mono); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { scoped_guard(raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; suspend_timing_needed = false; timekeeping_forward_now(tks); __timekeeping_inject_sleeptime(tks, delta); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock = tks->tkr_mono.clock; struct timespec64 ts_new, ts_delta; bool inject_sleeptime = false; u64 cycle_now, nsec; unsigned long flags; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&tk_core.lock, flags); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tks->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tks, &ts_delta); } /* Re-base the last cycle value */ tks->tkr_mono.cycle_last = cycle_now; tks->tkr_raw.cycle_last = cycle_now; tks->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); raw_spin_unlock_irqrestore(&tk_core.lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } int timekeeping_suspend(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; unsigned long flags; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&tk_core.lock, flags); timekeeping_forward_now(tks); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tks->tkr_mono.clock; cycle_now = tks->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tks), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update_from_shadow(&tk_core, 0); halt_fast_timekeeper(tks); raw_spin_unlock_irqrestore(&tk_core.lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u64 ntp_tl = ntp_tick_length(); u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tl)) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tl; mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *tk = &tk_core.shadow_timekeeper; struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; int shift = 0, maxshift; u64 offset; guard(raw_spinlock_irqsave)(&tk_core.lock); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); timekeeping_update_from_shadow(&tk_core, clock_set); return !!clock_set; } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); /** * ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor * @ts: timespec64 to be filled * * Fetch the global mg_floor value, convert it to realtime and compare it * to the current coarse-grained time. Fill @ts with whichever is * latest. Note that this is a filesystem-specific interface and should be * avoided outside of that context. */ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 floor = atomic64_read(&mg_floor); ktime_t f_real, offset, coarse; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); coarse = timespec64_to_ktime(*ts); f_real = ktime_add(floor, offset); if (ktime_after(f_real, coarse)) *ts = ktime_to_timespec64(f_real); } /** * ktime_get_real_ts64_mg - attempt to update floor value and return result * @ts: pointer to the timespec to be set * * Get a monotonic fine-grained time value and attempt to swap it into * mg_floor. If that succeeds then accept the new floor value. If it fails * then another task raced in during the interim time and updated the * floor. Since any update to the floor must be later than the previous * floor, either outcome is acceptable. * * Typically this will be called after calling ktime_get_coarse_real_ts64_mg(), * and determining that the resulting coarse-grained timestamp did not effect * a change in ctime. Any more recent floor value would effect a change to * ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure. * * @ts will be filled with the latest floor value, regardless of the outcome of * the cmpxchg. Note that this is a filesystem specific interface and should be * avoided outside of that context. */ void ktime_get_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t old = atomic64_read(&mg_floor); ktime_t offset, mono; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; mono = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); mono = ktime_add_ns(mono, nsecs); /* * Attempt to update the floor with the new time value. As any * update must be later then the existing floor, and would effect * a change to ctime from the perspective of the current task, * accept the resulting floor value regardless of the outcome of * the swap. */ if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); timekeeping_inc_mg_floor_swaps(); } else { /* * Another task changed mg_floor since "old" was fetched. * "old" has been updated with the latest value of "mg_floor". * That value is newer than the previous floor value, which * is enough to effect a change to ctime. Accept it. */ *ts = ktime_to_timespec64(ktime_add(old, offset)); } } void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function * @txc: Pointer to kernel_timex structure containing NTP parameters */ int do_adjtimex(struct __kernel_timex *txc) { struct audit_ntp_data ad; bool offset_set = false; bool clock_set = false; struct timespec64 ts; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; offset_set = delta.tv_sec != 0; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; s32 orig_tai, tai; orig_tai = tai = tks->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tks, tai); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); clock_set = true; } else { tk_update_leap_state_all(&tk_core); } } audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) clock_set |= timekeeping_advance(TK_ADV_FREQ); if (clock_set) clock_was_set(CLOCK_SET_WALL); ntp_notify_cmos_timer(offset_set); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function * @phase_ts: Pointer to timespec64 structure representing phase timestamp * @raw_ts: Pointer to timespec64 structure representing raw timestamp */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { guard(raw_spinlock_irqsave)(&tk_core.lock); __hardpps(phase_ts, raw_ts); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ |
| 1050 1045 1050 1050 1048 1050 1051 4 1050 1048 4 1051 1488 1490 570 680 1049 384 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions to sequence PREFLUSH and FUA writes. * * Copyright (C) 2011 Max Planck Institute for Gravitational Physics * Copyright (C) 2011 Tejun Heo <tj@kernel.org> * * REQ_{PREFLUSH|FUA} requests are decomposed to sequences consisted of three * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request * properties and hardware capability. * * If a request doesn't have data, only REQ_PREFLUSH makes sense, which * indicates a simple flush request. If there is data, REQ_PREFLUSH indicates * that the device cache should be flushed before the data is executed, and * REQ_FUA means that the data must be on non-volatile media on request * completion. * * If the device doesn't have writeback cache, PREFLUSH and FUA don't make any * difference. The requests are either completed immediately if there's no data * or executed as normal requests otherwise. * * If the device has writeback cache and supports FUA, REQ_PREFLUSH is * translated to PREFLUSH but REQ_FUA is passed down directly with DATA. * * If the device has writeback cache and doesn't support FUA, REQ_PREFLUSH * is translated to PREFLUSH and REQ_FUA to POSTFLUSH. * * The actual execution of flush is double buffered. Whenever a request * needs to execute PRE or POSTFLUSH, it queues at * fq->flush_queue[fq->flush_pending_idx]. Once certain criteria are met, a * REQ_OP_FLUSH is issued and the pending_idx is toggled. When the flush * completes, all the requests which were pending are proceeded to the next * step. This allows arbitrary merging of different types of PREFLUSH/FUA * requests. * * Currently, the following conditions are used to determine when to issue * flush. * * C1. At any given time, only one flush shall be in progress. This makes * double buffering sufficient. * * C2. Flush is deferred if any request is executing DATA of its sequence. * This avoids issuing separate POSTFLUSHes for requests which shared * PREFLUSH. * * C3. The second condition is ignored if there is a request which has * waited longer than FLUSH_PENDING_TIMEOUT. This is to avoid * starvation in the unlikely case where there are continuous stream of * FUA (without PREFLUSH) requests. * * For devices which support FUA, it isn't clear whether C2 (and thus C3) * is beneficial. * * Note that a sequenced PREFLUSH/FUA request with DATA is completed twice. * Once while executing DATA and again after the whole sequence is * complete. The first completion updates the contained bio but doesn't * finish it so that the bio submitter is notified only after the whole * sequence is complete. This is implemented by testing RQF_FLUSH_SEQ in * req_bio_endio(). * * The above peculiarity requires that each PREFLUSH/FUA request has only one * bio attached to it, which is guaranteed as they aren't allowed to be * merged in the usual way. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/gfp.h> #include <linux/part_stat.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" /* PREFLUSH/FUA sequences */ enum { REQ_FSEQ_PREFLUSH = (1 << 0), /* pre-flushing in progress */ REQ_FSEQ_DATA = (1 << 1), /* data write in progress */ REQ_FSEQ_POSTFLUSH = (1 << 2), /* post-flushing in progress */ REQ_FSEQ_DONE = (1 << 3), REQ_FSEQ_ACTIONS = REQ_FSEQ_PREFLUSH | REQ_FSEQ_DATA | REQ_FSEQ_POSTFLUSH, /* * If flush has been pending longer than the following timeout, * it's issued even if flush_data requests are still in flight. */ FLUSH_PENDING_TIMEOUT = 5 * HZ, }; static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, blk_opf_t flags); static inline struct blk_flush_queue * blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx) { return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq; } static unsigned int blk_flush_cur_seq(struct request *rq) { return 1 << ffz(rq->flush.seq); } static void blk_flush_restore_request(struct request *rq) { /* * After flush data completion, @rq->bio is %NULL but we need to * complete the bio again. @rq->biotail is guaranteed to equal the * original @rq->bio. Restore it. */ rq->bio = rq->biotail; if (rq->bio) rq->__sector = rq->bio->bi_iter.bi_sector; /* make @rq a normal request */ rq->rq_flags &= ~RQF_FLUSH_SEQ; rq->end_io = rq->flush.saved_end_io; } static void blk_account_io_flush(struct request *rq) { struct block_device *part = rq->q->disk->part0; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); part_stat_add(part, nsecs[STAT_FLUSH], blk_time_get_ns() - rq->start_time_ns); part_stat_unlock(); } /** * blk_flush_complete_seq - complete flush sequence * @rq: PREFLUSH/FUA request being sequenced * @fq: flush queue * @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero) * @error: whether an error occurred * * @rq just completed @seq part of its flush sequence, record the * completion and trigger the next step. * * CONTEXT: * spin_lock_irq(fq->mq_flush_lock) */ static void blk_flush_complete_seq(struct request *rq, struct blk_flush_queue *fq, unsigned int seq, blk_status_t error) { struct request_queue *q = rq->q; struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx]; blk_opf_t cmd_flags; BUG_ON(rq->flush.seq & seq); rq->flush.seq |= seq; cmd_flags = rq->cmd_flags; if (likely(!error)) seq = blk_flush_cur_seq(rq); else seq = REQ_FSEQ_DONE; switch (seq) { case REQ_FSEQ_PREFLUSH: case REQ_FSEQ_POSTFLUSH: /* queue for flush */ if (list_empty(pending)) fq->flush_pending_since = jiffies; list_add_tail(&rq->queuelist, pending); break; case REQ_FSEQ_DATA: fq->flush_data_in_flight++; spin_lock(&q->requeue_lock); list_move(&rq->queuelist, &q->requeue_list); spin_unlock(&q->requeue_lock); blk_mq_kick_requeue_list(q); break; case REQ_FSEQ_DONE: /* * @rq was previously adjusted by blk_insert_flush() for * flush sequencing and may already have gone through the * flush data request completion path. Restore @rq for * normal completion and end it. */ list_del_init(&rq->queuelist); blk_flush_restore_request(rq); blk_mq_end_request(rq, error); break; default: BUG(); } blk_kick_flush(q, fq, cmd_flags); } static enum rq_end_io_ret flush_end_io(struct request *flush_rq, blk_status_t error) { struct request_queue *q = flush_rq->q; struct list_head *running; struct request *rq, *n; unsigned long flags = 0; struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); if (!req_ref_put_and_test(flush_rq)) { fq->rq_status = error; spin_unlock_irqrestore(&fq->mq_flush_lock, flags); return RQ_END_IO_NONE; } blk_account_io_flush(flush_rq); /* * Flush request has to be marked as IDLE when it is really ended * because its .end_io() is called from timeout code path too for * avoiding use-after-free. */ WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE); if (fq->rq_status != BLK_STS_OK) { error = fq->rq_status; fq->rq_status = BLK_STS_OK; } if (!q->elevator) { flush_rq->tag = BLK_MQ_NO_TAG; } else { blk_mq_put_driver_tag(flush_rq); flush_rq->internal_tag = BLK_MQ_NO_TAG; } running = &fq->flush_queue[fq->flush_running_idx]; BUG_ON(fq->flush_pending_idx == fq->flush_running_idx); /* account completion of the flush request */ fq->flush_running_idx ^= 1; /* and push the waiting requests to the next stage */ list_for_each_entry_safe(rq, n, running, queuelist) { unsigned int seq = blk_flush_cur_seq(rq); BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH); list_del_init(&rq->queuelist); blk_flush_complete_seq(rq, fq, seq, error); } spin_unlock_irqrestore(&fq->mq_flush_lock, flags); return RQ_END_IO_NONE; } bool is_flush_rq(struct request *rq) { return rq->end_io == flush_end_io; } /** * blk_kick_flush - consider issuing flush request * @q: request_queue being kicked * @fq: flush queue * @flags: cmd_flags of the original request * * Flush related states of @q have changed, consider issuing flush request. * Please read the comment at the top of this file for more info. * * CONTEXT: * spin_lock_irq(fq->mq_flush_lock) * */ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, blk_opf_t flags) { struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx]; struct request *first_rq = list_first_entry(pending, struct request, queuelist); struct request *flush_rq = fq->flush_rq; /* C1 described at the top of this file */ if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending)) return; /* C2 and C3 */ if (fq->flush_data_in_flight && time_before(jiffies, fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) return; /* * Issue flush and toggle pending_idx. This makes pending_idx * different from running_idx, which means flush is in flight. */ fq->flush_pending_idx ^= 1; blk_rq_init(q, flush_rq); /* * In case of none scheduler, borrow tag from the first request * since they can't be in flight at the same time. And acquire * the tag's ownership for flush req. * * In case of IO scheduler, flush rq need to borrow scheduler tag * just for cheating put/get driver tag. */ flush_rq->mq_ctx = first_rq->mq_ctx; flush_rq->mq_hctx = first_rq->mq_hctx; if (!q->elevator) flush_rq->tag = first_rq->tag; else flush_rq->internal_tag = first_rq->internal_tag; flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH; flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK); flush_rq->rq_flags |= RQF_FLUSH_SEQ; flush_rq->end_io = flush_end_io; /* * Order WRITE ->end_io and WRITE rq->ref, and its pair is the one * implied in refcount_inc_not_zero() called from * blk_mq_find_and_get_req(), which orders WRITE/READ flush_rq->ref * and READ flush_rq->end_io */ smp_wmb(); req_ref_set(flush_rq, 1); spin_lock(&q->requeue_lock); list_add_tail(&flush_rq->queuelist, &q->flush_list); spin_unlock(&q->requeue_lock); blk_mq_kick_requeue_list(q); } static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq, blk_status_t error) { struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct blk_mq_ctx *ctx = rq->mq_ctx; unsigned long flags; struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx); if (q->elevator) { WARN_ON(rq->tag < 0); blk_mq_put_driver_tag(rq); } /* * After populating an empty queue, kick it to avoid stall. Read * the comment in flush_end_io(). */ spin_lock_irqsave(&fq->mq_flush_lock, flags); fq->flush_data_in_flight--; /* * May have been corrupted by rq->rq_next reuse, we need to * re-initialize rq->queuelist before reusing it here. */ INIT_LIST_HEAD(&rq->queuelist); blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); spin_unlock_irqrestore(&fq->mq_flush_lock, flags); blk_mq_sched_restart(hctx); return RQ_END_IO_NONE; } static void blk_rq_init_flush(struct request *rq) { rq->flush.seq = 0; rq->rq_flags |= RQF_FLUSH_SEQ; rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ rq->end_io = mq_flush_data_end_io; } /* * Insert a PREFLUSH/FUA request into the flush state machine. * Returns true if the request has been consumed by the flush state machine, * or false if the caller should continue to process it. */ bool blk_insert_flush(struct request *rq) { struct request_queue *q = rq->q; struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); bool supports_fua = q->limits.features & BLK_FEAT_FUA; unsigned int policy = 0; /* FLUSH/FUA request must never be merged */ WARN_ON_ONCE(rq->bio != rq->biotail); if (blk_rq_sectors(rq)) policy |= REQ_FSEQ_DATA; /* * Check which flushes we need to sequence for this operation. */ if (blk_queue_write_cache(q)) { if (rq->cmd_flags & REQ_PREFLUSH) policy |= REQ_FSEQ_PREFLUSH; if ((rq->cmd_flags & REQ_FUA) && !supports_fua) policy |= REQ_FSEQ_POSTFLUSH; } /* * @policy now records what operations need to be done. Adjust * REQ_PREFLUSH and FUA for the driver. */ rq->cmd_flags &= ~REQ_PREFLUSH; if (!supports_fua) rq->cmd_flags &= ~REQ_FUA; /* * REQ_PREFLUSH|REQ_FUA implies REQ_SYNC, so if we clear any * of those flags, we have to set REQ_SYNC to avoid skewing * the request accounting. */ rq->cmd_flags |= REQ_SYNC; switch (policy) { case 0: /* * An empty flush handed down from a stacking driver may * translate into nothing if the underlying device does not * advertise a write-back cache. In this case, simply * complete the request. */ blk_mq_end_request(rq, 0); return true; case REQ_FSEQ_DATA: /* * If there's data, but no flush is necessary, the request can * be processed directly without going through flush machinery. * Queue for normal execution. */ return false; case REQ_FSEQ_DATA | REQ_FSEQ_POSTFLUSH: /* * Initialize the flush fields and completion handler to trigger * the post flush, and then just pass the command on. */ blk_rq_init_flush(rq); rq->flush.seq |= REQ_FSEQ_PREFLUSH; spin_lock_irq(&fq->mq_flush_lock); fq->flush_data_in_flight++; spin_unlock_irq(&fq->mq_flush_lock); return false; default: /* * Mark the request as part of a flush sequence and submit it * for further processing to the flush state machine. */ blk_rq_init_flush(rq); spin_lock_irq(&fq->mq_flush_lock); blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0); spin_unlock_irq(&fq->mq_flush_lock); return true; } } /** * blkdev_issue_flush - queue a flush * @bdev: blockdev to issue flush for * * Description: * Issue a flush for the block device in question. */ int blkdev_issue_flush(struct block_device *bdev) { struct bio bio; bio_init(&bio, bdev, NULL, 0, REQ_OP_WRITE | REQ_PREFLUSH); return submit_bio_wait(&bio); } EXPORT_SYMBOL(blkdev_issue_flush); struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, gfp_t flags) { struct blk_flush_queue *fq; int rq_sz = sizeof(struct request); fq = kzalloc_node(sizeof(*fq), flags, node); if (!fq) goto fail; spin_lock_init(&fq->mq_flush_lock); rq_sz = round_up(rq_sz + cmd_size, cache_line_size()); fq->flush_rq = kzalloc_node(rq_sz, flags, node); if (!fq->flush_rq) goto fail_rq; INIT_LIST_HEAD(&fq->flush_queue[0]); INIT_LIST_HEAD(&fq->flush_queue[1]); return fq; fail_rq: kfree(fq); fail: return NULL; } void blk_free_flush_queue(struct blk_flush_queue *fq) { /* bio based request queue hasn't flush queue */ if (!fq) return; kfree(fq->flush_rq); kfree(fq); } /* * Allow driver to set its own lock class to fq->mq_flush_lock for * avoiding lockdep complaint. * * flush_end_io() may be called recursively from some driver, such as * nvme-loop, so lockdep may complain 'possible recursive locking' because * all 'struct blk_flush_queue' instance share same mq_flush_lock lock class * key. We need to assign different lock class for these driver's * fq->mq_flush_lock for avoiding the lockdep warning. * * Use dynamically allocated lock class key for each 'blk_flush_queue' * instance is over-kill, and more worse it introduces horrible boot delay * issue because synchronize_rcu() is implied in lockdep_unregister_key which * is called for each hctx release. SCSI probing may synchronously create and * destroy lots of MQ request_queues for non-existent devices, and some robot * test kernel always enable lockdep option. It is observed that more than half * an hour is taken during SCSI MQ probe with per-fq lock class. */ void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key) { lockdep_set_class(&hctx->fq->mq_flush_lock, key); } EXPORT_SYMBOL_GPL(blk_mq_hctx_set_fq_lock_class); |
| 52 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PATH_H #define _LINUX_PATH_H struct dentry; struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; } __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); static inline int path_equal(const struct path *path1, const struct path *path2) { return path1->mnt == path2->mnt && path1->dentry == path2->dentry; } /* * Cleanup macro for use with __free(path_put). Avoids dereference and * copying @path unlike DEFINE_FREE(). path_put() will handle the empty * path correctly just ensure @path is initialized: * * struct path path __free(path_put) = {}; */ #define __free_path_put path_put #endif /* _LINUX_PATH_H */ |
| 6237 6235 6248 6259 6263 1373 107 104 12 110 110 69 69 118 118 116 118 118 118 273 297 296 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/mnt_idmapping.h> #include <uapi/linux/lsm.h> #define CREATE_TRACE_POINTS #include <trace/events/capability.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable_helper - Determine whether a task has a particular effective * capability. * @cred: The credentials to use * @target_ns: The user namespace of the resource being accessed * @cred_ns: The user namespace of the credentials * @cap: The capability to check for * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * See cap_capable for more details. */ static inline int cap_capable_helper(const struct cred *cred, struct user_namespace *target_ns, const struct user_namespace *cred_ns, int cap) { struct user_namespace *ns = target_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (likely(ns == cred_ns)) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @target_ns: The user namespace of the resource being accessed * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h (unused) * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *target_ns, int cap, unsigned int opts) { const struct user_namespace *cred_ns = cred->user_ns; int ret = cap_capable_helper(cred, target_ns, cred_ns, cap); trace_cap_capable(cred, target_ns, cred_ns, cap, ret); return ret; } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Return: 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * 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. * * Return: 0 if successful, -ve on error. */ int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { int error; error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(vfsuid_t rootvfsuid) { struct user_namespace *ns; kuid_t kroot; if (!vfsuid_valid(rootvfsuid)) return false; kroot = vfsuid_into_kuid(rootvfsuid); for (ns = current_user_ns();; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { int size; kuid_t kroot; vfsuid_t vfsroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf, sizeof(struct vfs_ns_cap_data), GFP_NOFS); dput(dentry); /* gcc11 complains if we don't check for !tmpbuf */ if (size < 0 || !tmpbuf) goto out_free; fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header(size, cap)) { root = 0; } else if (is_v3header(size, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ vfsroot = make_vfsuid(idmap, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), vfsuid_into_kuid(vfsroot)); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(vfsroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } /** * rootid_from_xattr - translate root uid of vfs caps * * @value: vfs caps value which may be modified by this function * @size: size of @ivalue * @task_ns: user namespace of the caller */ static vfsuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns) { const struct vfs_ns_cap_data *nscap = value; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); return VFSUIDT_INIT(make_kuid(task_ns, rootid)); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /** * cap_convert_nscap - check vfs caps * * @idmap: idmap of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * 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. * * Return: On success, return the new size; on error, return < 0. */ int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; vfsuid_t vfsrootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; vfsrootid = rootid_from_xattr(*ivalue, size, task_ns); if (!vfsuid_valid(vfsrootid)) return -EINVAL; rootid = from_vfsuid(idmap, fs_ns, vfsrootid); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.val = (new->cap_bset.val & caps->permitted.val) | (new->cap_inheritable.val & caps->inheritable.val); if (caps->permitted.val & ~new->cap_permitted.val) /* insufficient to execute correctly */ ret = -EPERM; /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * * @idmap: idmap of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * * 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. */ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; vfsuid_t rootvfsuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid); if (!vfsuid_valid(rootvfsuid)) return -ENODATA; /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ if (!rootid_owns_currentns(rootvfsuid)) return -ENODATA; cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted); cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable); /* * Rev1 had just a single 32-bit word, later expanded * to a second one for the high bits */ if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) { cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32; cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32; } cpu_caps->permitted.val &= CAP_VALID_MASK; cpu_caps->inheritable.val &= CAP_VALID_MASK; cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid); return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, const struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file_mnt_idmap(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. * * Return: 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * 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. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied. * * Return: 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilities to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Determine if scheduler policy change is permitted * @p: The task to affect * * Determine if the requested scheduler policy change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_setioprio - Determine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Determine if the requested I/O priority change is permitted for the specified * task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_setnice - Determine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Determine if the requested task priority change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2: The argument data for this function * @arg3: The argument data for this function * @arg4: The argument data for this function * @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Return: 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits */ ) /* cannot change a locked bit */ return -EPERM; /* * Doing anything requires privilege (go read about the * "sendmail capabilities bug"), except for unprivileged bits. * Indeed, the SECURE_ALL_UNPRIVILEGED bits are not * restrictions enforced by the kernel but by user space on * itself. */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) { const unsigned long unpriv_and_locks = SECURE_ALL_UNPRIVILEGED | SECURE_ALL_UNPRIVILEGED << 1; const unsigned long changed = old->securebits ^ arg2; /* For legacy reason, denies non-change. */ if (!changed) return -EPERM; /* Denies privileged changes. */ if (changed & ~unpriv_and_locks) return -EPERM; } new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * * Return: 0 if permission granted, negative error code if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { return cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); } /** * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. * * Return: 0 if this mapping should be allowed or -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } #ifdef CONFIG_SECURITY static const struct lsm_id capability_lsmid = { .name = "capability", .id = LSM_ID_CAPABILITY, }; static struct security_hook_list capability_hooks[] __ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), &capability_lsmid); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 4 30 54 124 26 1 10 4 26 26 12 18 13 12 2 26 26 11 5 3 3 5 2 3 3 1 1 3 2 1 1 11 6 4 4 4 8 124 124 48 48 71 5 17 16 17 42 33 30 30 39 39 2 39 1 39 42 33 42 22 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/partitions/msdos.c * * Code extracted from drivers/block/genhd.c * Copyright (C) 1991-1998 Linus Torvalds * * Thanks to Branko Lankester, lankeste@fwi.uva.nl, who found a bug * in the early extended-partition checks and added DM partitions * * Support for DiskManager v6.0x added by Mark Lord, * with information provided by OnTrack. This now works for linux fdisk * and LILO, as well as loadlin and bootln. Note that disks other than * /dev/hda *must* have a "DOS" type 0x51 partition in the first slot (hda1). * * More flexible handling of extended partitions - aeb, 950831 * * Check partition table on IDE disks for common CHS translations * * Re-organised Feb 1998 Russell King * * BSD disklabel support by Yossi Gottlieb <yogo@math.tau.ac.il> * updated by Marc Espie <Marc.Espie@openbsd.org> * * Unixware slices support by Andrzej Krzysztofowicz <ankry@mif.pg.gda.pl> * and Krzysztof G. Baranowski <kgb@knm.org.pl> */ #include <linux/msdos_fs.h> #include <linux/msdos_partition.h> #include "check.h" #include "efi.h" /* * Many architectures don't like unaligned accesses, while * the nr_sects and start_sect partition table entries are * at a 2 (mod 4) address. */ #include <linux/unaligned.h> static inline sector_t nr_sects(struct msdos_partition *p) { return (sector_t)get_unaligned_le32(&p->nr_sects); } static inline sector_t start_sect(struct msdos_partition *p) { return (sector_t)get_unaligned_le32(&p->start_sect); } static inline int is_extended_partition(struct msdos_partition *p) { return (p->sys_ind == DOS_EXTENDED_PARTITION || p->sys_ind == WIN98_EXTENDED_PARTITION || p->sys_ind == LINUX_EXTENDED_PARTITION); } #define MSDOS_LABEL_MAGIC1 0x55 #define MSDOS_LABEL_MAGIC2 0xAA static inline int msdos_magic_present(unsigned char *p) { return (p[0] == MSDOS_LABEL_MAGIC1 && p[1] == MSDOS_LABEL_MAGIC2); } /* Value is EBCDIC 'IBMA' */ #define AIX_LABEL_MAGIC1 0xC9 #define AIX_LABEL_MAGIC2 0xC2 #define AIX_LABEL_MAGIC3 0xD4 #define AIX_LABEL_MAGIC4 0xC1 static int aix_magic_present(struct parsed_partitions *state, unsigned char *p) { struct msdos_partition *pt = (struct msdos_partition *) (p + 0x1be); Sector sect; unsigned char *d; int slot, ret = 0; if (!(p[0] == AIX_LABEL_MAGIC1 && p[1] == AIX_LABEL_MAGIC2 && p[2] == AIX_LABEL_MAGIC3 && p[3] == AIX_LABEL_MAGIC4)) return 0; /* * Assume the partition table is valid if Linux partitions exists. * Note that old Solaris/x86 partitions use the same indicator as * Linux swap partitions, so we consider that a Linux partition as * well. */ for (slot = 1; slot <= 4; slot++, pt++) { if (pt->sys_ind == SOLARIS_X86_PARTITION || pt->sys_ind == LINUX_RAID_PARTITION || pt->sys_ind == LINUX_DATA_PARTITION || pt->sys_ind == LINUX_LVM_PARTITION || is_extended_partition(pt)) return 0; } d = read_part_sector(state, 7, §); if (d) { if (d[0] == '_' && d[1] == 'L' && d[2] == 'V' && d[3] == 'M') ret = 1; put_dev_sector(sect); } return ret; } static void set_info(struct parsed_partitions *state, int slot, u32 disksig) { struct partition_meta_info *info = &state->parts[slot].info; snprintf(info->uuid, sizeof(info->uuid), "%08x-%02x", disksig, slot); info->volname[0] = 0; state->parts[slot].has_info = true; } /* * Create devices for each logical partition in an extended partition. * The logical partitions form a linked list, with each entry being * a partition table with two entries. The first entry * is the real data partition (with a start relative to the partition * table start). The second is a pointer to the next logical partition * (with a start relative to the entire extended partition). * We do not create a Linux partition for the partition tables, but * only for the actual data partitions. */ static void parse_extended(struct parsed_partitions *state, sector_t first_sector, sector_t first_size, u32 disksig) { struct msdos_partition *p; Sector sect; unsigned char *data; sector_t this_sector, this_size; sector_t sector_size; int loopct = 0; /* number of links followed without finding a data partition */ int i; sector_size = queue_logical_block_size(state->disk->queue) / 512; this_sector = first_sector; this_size = first_size; while (1) { if (++loopct > 100) return; if (state->next == state->limit) return; data = read_part_sector(state, this_sector, §); if (!data) return; if (!msdos_magic_present(data + 510)) goto done; p = (struct msdos_partition *) (data + 0x1be); /* * Usually, the first entry is the real data partition, * the 2nd entry is the next extended partition, or empty, * and the 3rd and 4th entries are unused. * However, DRDOS sometimes has the extended partition as * the first entry (when the data partition is empty), * and OS/2 seems to use all four entries. */ /* * First process the data partition(s) */ for (i = 0; i < 4; i++, p++) { sector_t offs, size, next; if (!nr_sects(p) || is_extended_partition(p)) continue; /* Check the 3rd and 4th entries - these sometimes contain random garbage */ offs = start_sect(p)*sector_size; size = nr_sects(p)*sector_size; next = this_sector + offs; if (i >= 2) { if (offs + size > this_size) continue; if (next < first_sector) continue; if (next + size > first_sector + first_size) continue; } put_partition(state, state->next, next, size); set_info(state, state->next, disksig); if (p->sys_ind == LINUX_RAID_PARTITION) state->parts[state->next].flags = ADDPART_FLAG_RAID; loopct = 0; if (++state->next == state->limit) goto done; } /* * Next, process the (first) extended partition, if present. * (So far, there seems to be no reason to make * parse_extended() recursive and allow a tree * of extended partitions.) * It should be a link to the next logical partition. */ p -= 4; for (i = 0; i < 4; i++, p++) if (nr_sects(p) && is_extended_partition(p)) break; if (i == 4) goto done; /* nothing left to do */ this_sector = first_sector + start_sect(p) * sector_size; this_size = nr_sects(p) * sector_size; put_dev_sector(sect); } done: put_dev_sector(sect); } #define SOLARIS_X86_NUMSLICE 16 #define SOLARIS_X86_VTOC_SANE (0x600DDEEEUL) struct solaris_x86_slice { __le16 s_tag; /* ID tag of partition */ __le16 s_flag; /* permission flags */ __le32 s_start; /* start sector no of partition */ __le32 s_size; /* # of blocks in partition */ }; struct solaris_x86_vtoc { unsigned int v_bootinfo[3]; /* info needed by mboot */ __le32 v_sanity; /* to verify vtoc sanity */ __le32 v_version; /* layout version */ char v_volume[8]; /* volume name */ __le16 v_sectorsz; /* sector size in bytes */ __le16 v_nparts; /* number of partitions */ unsigned int v_reserved[10]; /* free space */ struct solaris_x86_slice v_slice[SOLARIS_X86_NUMSLICE]; /* slice headers */ unsigned int timestamp[SOLARIS_X86_NUMSLICE]; /* timestamp */ char v_asciilabel[128]; /* for compatibility */ }; /* james@bpgc.com: Solaris has a nasty indicator: 0x82 which also indicates linux swap. Be careful before believing this is Solaris. */ static void parse_solaris_x86(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_SOLARIS_X86_PARTITION Sector sect; struct solaris_x86_vtoc *v; int i; short max_nparts; v = read_part_sector(state, offset + 1, §); if (!v) return; if (le32_to_cpu(v->v_sanity) != SOLARIS_X86_VTOC_SANE) { put_dev_sector(sect); return; } { char tmp[1 + BDEVNAME_SIZE + 10 + 11 + 1]; snprintf(tmp, sizeof(tmp), " %s%d: <solaris:", state->name, origin); strlcat(state->pp_buf, tmp, PAGE_SIZE); } if (le32_to_cpu(v->v_version) != 1) { char tmp[64]; snprintf(tmp, sizeof(tmp), " cannot handle version %d vtoc>\n", le32_to_cpu(v->v_version)); strlcat(state->pp_buf, tmp, PAGE_SIZE); put_dev_sector(sect); return; } /* Ensure we can handle previous case of VTOC with 8 entries gracefully */ max_nparts = le16_to_cpu(v->v_nparts) > 8 ? SOLARIS_X86_NUMSLICE : 8; for (i = 0; i < max_nparts && state->next < state->limit; i++) { struct solaris_x86_slice *s = &v->v_slice[i]; char tmp[3 + 10 + 1 + 1]; if (s->s_size == 0) continue; snprintf(tmp, sizeof(tmp), " [s%d]", i); strlcat(state->pp_buf, tmp, PAGE_SIZE); /* solaris partitions are relative to current MS-DOS * one; must add the offset of the current partition */ put_partition(state, state->next++, le32_to_cpu(s->s_start)+offset, le32_to_cpu(s->s_size)); } put_dev_sector(sect); strlcat(state->pp_buf, " >\n", PAGE_SIZE); #endif } /* check against BSD src/sys/sys/disklabel.h for consistency */ #define BSD_DISKMAGIC (0x82564557UL) /* The disk magic number */ #define BSD_MAXPARTITIONS 16 #define OPENBSD_MAXPARTITIONS 16 #define BSD_FS_UNUSED 0 /* disklabel unused partition entry ID */ struct bsd_disklabel { __le32 d_magic; /* the magic number */ __s16 d_type; /* drive type */ __s16 d_subtype; /* controller/d_type specific */ char d_typename[16]; /* type name, e.g. "eagle" */ char d_packname[16]; /* pack identifier */ __u32 d_secsize; /* # of bytes per sector */ __u32 d_nsectors; /* # of data sectors per track */ __u32 d_ntracks; /* # of tracks per cylinder */ __u32 d_ncylinders; /* # of data cylinders per unit */ __u32 d_secpercyl; /* # of data sectors per cylinder */ __u32 d_secperunit; /* # of data sectors per unit */ __u16 d_sparespertrack; /* # of spare sectors per track */ __u16 d_sparespercyl; /* # of spare sectors per cylinder */ __u32 d_acylinders; /* # of alt. cylinders per unit */ __u16 d_rpm; /* rotational speed */ __u16 d_interleave; /* hardware sector interleave */ __u16 d_trackskew; /* sector 0 skew, per track */ __u16 d_cylskew; /* sector 0 skew, per cylinder */ __u32 d_headswitch; /* head switch time, usec */ __u32 d_trkseek; /* track-to-track seek, usec */ __u32 d_flags; /* generic flags */ #define NDDATA 5 __u32 d_drivedata[NDDATA]; /* drive-type specific information */ #define NSPARE 5 __u32 d_spare[NSPARE]; /* reserved for future use */ __le32 d_magic2; /* the magic number (again) */ __le16 d_checksum; /* xor of data incl. partitions */ /* filesystem and partition information: */ __le16 d_npartitions; /* number of partitions in following */ __le32 d_bbsize; /* size of boot area at sn0, bytes */ __le32 d_sbsize; /* max size of fs superblock, bytes */ struct bsd_partition { /* the partition table */ __le32 p_size; /* number of sectors in partition */ __le32 p_offset; /* starting sector */ __le32 p_fsize; /* filesystem basic fragment size */ __u8 p_fstype; /* filesystem type, see below */ __u8 p_frag; /* filesystem fragments per block */ __le16 p_cpg; /* filesystem cylinders per group */ } d_partitions[BSD_MAXPARTITIONS]; /* actually may be more */ }; #if defined(CONFIG_BSD_DISKLABEL) /* * Create devices for BSD partitions listed in a disklabel, under a * dos-like partition. See parse_extended() for more information. */ static void parse_bsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin, char *flavour, int max_partitions) { Sector sect; struct bsd_disklabel *l; struct bsd_partition *p; char tmp[64]; l = read_part_sector(state, offset + 1, §); if (!l) return; if (le32_to_cpu(l->d_magic) != BSD_DISKMAGIC) { put_dev_sector(sect); return; } snprintf(tmp, sizeof(tmp), " %s%d: <%s:", state->name, origin, flavour); strlcat(state->pp_buf, tmp, PAGE_SIZE); if (le16_to_cpu(l->d_npartitions) < max_partitions) max_partitions = le16_to_cpu(l->d_npartitions); for (p = l->d_partitions; p - l->d_partitions < max_partitions; p++) { sector_t bsd_start, bsd_size; if (state->next == state->limit) break; if (p->p_fstype == BSD_FS_UNUSED) continue; bsd_start = le32_to_cpu(p->p_offset); bsd_size = le32_to_cpu(p->p_size); /* FreeBSD has relative offset if C partition offset is zero */ if (memcmp(flavour, "bsd\0", 4) == 0 && le32_to_cpu(l->d_partitions[2].p_offset) == 0) bsd_start += offset; if (offset == bsd_start && size == bsd_size) /* full parent partition, we have it already */ continue; if (offset > bsd_start || offset+size < bsd_start+bsd_size) { strlcat(state->pp_buf, "bad subpartition - ignored\n", PAGE_SIZE); continue; } put_partition(state, state->next++, bsd_start, bsd_size); } put_dev_sector(sect); if (le16_to_cpu(l->d_npartitions) > max_partitions) { snprintf(tmp, sizeof(tmp), " (ignored %d more)", le16_to_cpu(l->d_npartitions) - max_partitions); strlcat(state->pp_buf, tmp, PAGE_SIZE); } strlcat(state->pp_buf, " >\n", PAGE_SIZE); } #endif static void parse_freebsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_BSD_DISKLABEL parse_bsd(state, offset, size, origin, "bsd", BSD_MAXPARTITIONS); #endif } static void parse_netbsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_BSD_DISKLABEL parse_bsd(state, offset, size, origin, "netbsd", BSD_MAXPARTITIONS); #endif } static void parse_openbsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_BSD_DISKLABEL parse_bsd(state, offset, size, origin, "openbsd", OPENBSD_MAXPARTITIONS); #endif } #define UNIXWARE_DISKMAGIC (0xCA5E600DUL) /* The disk magic number */ #define UNIXWARE_DISKMAGIC2 (0x600DDEEEUL) /* The slice table magic nr */ #define UNIXWARE_NUMSLICE 16 #define UNIXWARE_FS_UNUSED 0 /* Unused slice entry ID */ struct unixware_slice { __le16 s_label; /* label */ __le16 s_flags; /* permission flags */ __le32 start_sect; /* starting sector */ __le32 nr_sects; /* number of sectors in slice */ }; struct unixware_disklabel { __le32 d_type; /* drive type */ __le32 d_magic; /* the magic number */ __le32 d_version; /* version number */ char d_serial[12]; /* serial number of the device */ __le32 d_ncylinders; /* # of data cylinders per device */ __le32 d_ntracks; /* # of tracks per cylinder */ __le32 d_nsectors; /* # of data sectors per track */ __le32 d_secsize; /* # of bytes per sector */ __le32 d_part_start; /* # of first sector of this partition*/ __le32 d_unknown1[12]; /* ? */ __le32 d_alt_tbl; /* byte offset of alternate table */ __le32 d_alt_len; /* byte length of alternate table */ __le32 d_phys_cyl; /* # of physical cylinders per device */ __le32 d_phys_trk; /* # of physical tracks per cylinder */ __le32 d_phys_sec; /* # of physical sectors per track */ __le32 d_phys_bytes; /* # of physical bytes per sector */ __le32 d_unknown2; /* ? */ __le32 d_unknown3; /* ? */ __le32 d_pad[8]; /* pad */ struct unixware_vtoc { __le32 v_magic; /* the magic number */ __le32 v_version; /* version number */ char v_name[8]; /* volume name */ __le16 v_nslices; /* # of slices */ __le16 v_unknown1; /* ? */ __le32 v_reserved[10]; /* reserved */ struct unixware_slice v_slice[UNIXWARE_NUMSLICE]; /* slice headers */ } vtoc; }; /* 408 */ /* * Create devices for Unixware partitions listed in a disklabel, under a * dos-like partition. See parse_extended() for more information. */ static void parse_unixware(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_UNIXWARE_DISKLABEL Sector sect; struct unixware_disklabel *l; struct unixware_slice *p; l = read_part_sector(state, offset + 29, §); if (!l) return; if (le32_to_cpu(l->d_magic) != UNIXWARE_DISKMAGIC || le32_to_cpu(l->vtoc.v_magic) != UNIXWARE_DISKMAGIC2) { put_dev_sector(sect); return; } { char tmp[1 + BDEVNAME_SIZE + 10 + 12 + 1]; snprintf(tmp, sizeof(tmp), " %s%d: <unixware:", state->name, origin); strlcat(state->pp_buf, tmp, PAGE_SIZE); } p = &l->vtoc.v_slice[1]; /* I omit the 0th slice as it is the same as whole disk. */ while (p - &l->vtoc.v_slice[0] < UNIXWARE_NUMSLICE) { if (state->next == state->limit) break; if (p->s_label != UNIXWARE_FS_UNUSED) put_partition(state, state->next++, le32_to_cpu(p->start_sect), le32_to_cpu(p->nr_sects)); p++; } put_dev_sector(sect); strlcat(state->pp_buf, " >\n", PAGE_SIZE); #endif } #define MINIX_NR_SUBPARTITIONS 4 /* * Minix 2.0.0/2.0.2 subpartition support. * Anand Krishnamurthy <anandk@wiproge.med.ge.com> * Rajeev V. Pillai <rajeevvp@yahoo.com> */ static void parse_minix(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_MINIX_SUBPARTITION Sector sect; unsigned char *data; struct msdos_partition *p; int i; data = read_part_sector(state, offset, §); if (!data) return; p = (struct msdos_partition *)(data + 0x1be); /* The first sector of a Minix partition can have either * a secondary MBR describing its subpartitions, or * the normal boot sector. */ if (msdos_magic_present(data + 510) && p->sys_ind == MINIX_PARTITION) { /* subpartition table present */ char tmp[1 + BDEVNAME_SIZE + 10 + 9 + 1]; snprintf(tmp, sizeof(tmp), " %s%d: <minix:", state->name, origin); strlcat(state->pp_buf, tmp, PAGE_SIZE); for (i = 0; i < MINIX_NR_SUBPARTITIONS; i++, p++) { if (state->next == state->limit) break; /* add each partition in use */ if (p->sys_ind == MINIX_PARTITION) put_partition(state, state->next++, start_sect(p), nr_sects(p)); } strlcat(state->pp_buf, " >\n", PAGE_SIZE); } put_dev_sector(sect); #endif /* CONFIG_MINIX_SUBPARTITION */ } static struct { unsigned char id; void (*parse)(struct parsed_partitions *, sector_t, sector_t, int); } subtypes[] = { {FREEBSD_PARTITION, parse_freebsd}, {NETBSD_PARTITION, parse_netbsd}, {OPENBSD_PARTITION, parse_openbsd}, {MINIX_PARTITION, parse_minix}, {UNIXWARE_PARTITION, parse_unixware}, {SOLARIS_X86_PARTITION, parse_solaris_x86}, {NEW_SOLARIS_X86_PARTITION, parse_solaris_x86}, {0, NULL}, }; int msdos_partition(struct parsed_partitions *state) { sector_t sector_size; Sector sect; unsigned char *data; struct msdos_partition *p; struct fat_boot_sector *fb; int slot; u32 disksig; sector_size = queue_logical_block_size(state->disk->queue) / 512; data = read_part_sector(state, 0, §); if (!data) return -1; /* * Note order! (some AIX disks, e.g. unbootable kind, * have no MSDOS 55aa) */ if (aix_magic_present(state, data)) { put_dev_sector(sect); #ifdef CONFIG_AIX_PARTITION return aix_partition(state); #else strlcat(state->pp_buf, " [AIX]", PAGE_SIZE); return 0; #endif } if (!msdos_magic_present(data + 510)) { put_dev_sector(sect); return 0; } /* * Now that the 55aa signature is present, this is probably * either the boot sector of a FAT filesystem or a DOS-type * partition table. Reject this in case the boot indicator * is not 0 or 0x80. */ p = (struct msdos_partition *) (data + 0x1be); for (slot = 1; slot <= 4; slot++, p++) { if (p->boot_ind != 0 && p->boot_ind != 0x80) { /* * Even without a valid boot indicator value * its still possible this is valid FAT filesystem * without a partition table. */ fb = (struct fat_boot_sector *) data; if (slot == 1 && fb->reserved && fb->fats && fat_valid_media(fb->media)) { strlcat(state->pp_buf, "\n", PAGE_SIZE); put_dev_sector(sect); return 1; } else { put_dev_sector(sect); return 0; } } } #ifdef CONFIG_EFI_PARTITION p = (struct msdos_partition *) (data + 0x1be); for (slot = 1 ; slot <= 4 ; slot++, p++) { /* If this is an EFI GPT disk, msdos should ignore it. */ if (p->sys_ind == EFI_PMBR_OSTYPE_EFI_GPT) { put_dev_sector(sect); return 0; } } #endif p = (struct msdos_partition *) (data + 0x1be); disksig = le32_to_cpup((__le32 *)(data + 0x1b8)); /* * Look for partitions in two passes: * First find the primary and DOS-type extended partitions. * On the second pass look inside *BSD, Unixware and Solaris partitions. */ state->next = 5; for (slot = 1 ; slot <= 4 ; slot++, p++) { sector_t start = start_sect(p)*sector_size; sector_t size = nr_sects(p)*sector_size; if (!size) continue; if (is_extended_partition(p)) { /* * prevent someone doing mkfs or mkswap on an * extended partition, but leave room for LILO * FIXME: this uses one logical sector for > 512b * sector, although it may not be enough/proper. */ sector_t n = 2; n = min(size, max(sector_size, n)); put_partition(state, slot, start, n); strlcat(state->pp_buf, " <", PAGE_SIZE); parse_extended(state, start, size, disksig); strlcat(state->pp_buf, " >", PAGE_SIZE); continue; } put_partition(state, slot, start, size); set_info(state, slot, disksig); if (p->sys_ind == LINUX_RAID_PARTITION) state->parts[slot].flags = ADDPART_FLAG_RAID; if (p->sys_ind == DM6_PARTITION) strlcat(state->pp_buf, "[DM]", PAGE_SIZE); if (p->sys_ind == EZD_PARTITION) strlcat(state->pp_buf, "[EZD]", PAGE_SIZE); } strlcat(state->pp_buf, "\n", PAGE_SIZE); /* second pass - output for each on a separate line */ p = (struct msdos_partition *) (0x1be + data); for (slot = 1 ; slot <= 4 ; slot++, p++) { unsigned char id = p->sys_ind; int n; if (!nr_sects(p)) continue; for (n = 0; subtypes[n].parse && id != subtypes[n].id; n++) ; if (!subtypes[n].parse) continue; subtypes[n].parse(state, start_sect(p) * sector_size, nr_sects(p) * sector_size, slot); } put_dev_sector(sect); return 1; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * OSS compatible i/o control * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_readq.h" #include "seq_oss_writeq.h" #include "seq_oss_timer.h" #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "seq_oss_event.h" static int snd_seq_oss_synth_info_user(struct seq_oss_devinfo *dp, void __user *arg) { struct synth_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; if (snd_seq_oss_synth_make_info(dp, info.device, &info) < 0) return -EINVAL; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_seq_oss_midi_info_user(struct seq_oss_devinfo *dp, void __user *arg) { struct midi_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; if (snd_seq_oss_midi_make_info(dp, info.device, &info) < 0) return -EINVAL; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_seq_oss_oob_user(struct seq_oss_devinfo *dp, void __user *arg) { unsigned char ev[8]; struct snd_seq_event tmpev; if (copy_from_user(ev, arg, 8)) return -EFAULT; memset(&tmpev, 0, sizeof(tmpev)); snd_seq_oss_fill_addr(dp, &tmpev, dp->addr.client, dp->addr.port); tmpev.time.tick = 0; if (! snd_seq_oss_process_event(dp, (union evrec *)ev, &tmpev)) { snd_seq_oss_dispatch(dp, &tmpev, 0, 0); } return 0; } int snd_seq_oss_ioctl(struct seq_oss_devinfo *dp, unsigned int cmd, unsigned long carg) { int dev, val; void __user *arg = (void __user *)carg; int __user *p = arg; switch (cmd) { case SNDCTL_TMR_TIMEBASE: case SNDCTL_TMR_TEMPO: case SNDCTL_TMR_START: case SNDCTL_TMR_STOP: case SNDCTL_TMR_CONTINUE: case SNDCTL_TMR_METRONOME: case SNDCTL_TMR_SOURCE: case SNDCTL_TMR_SELECT: case SNDCTL_SEQ_CTRLRATE: return snd_seq_oss_timer_ioctl(dp->timer, cmd, arg); case SNDCTL_SEQ_PANIC: snd_seq_oss_reset(dp); return -EINVAL; case SNDCTL_SEQ_SYNC: if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return 0; while (snd_seq_oss_writeq_sync(dp->writeq)) ; if (signal_pending(current)) return -ERESTARTSYS; return 0; case SNDCTL_SEQ_RESET: snd_seq_oss_reset(dp); return 0; case SNDCTL_SEQ_TESTMIDI: if (get_user(dev, p)) return -EFAULT; return snd_seq_oss_midi_open(dp, dev, dp->file_mode); case SNDCTL_SEQ_GETINCOUNT: if (dp->readq == NULL || ! is_read_mode(dp->file_mode)) return 0; return put_user(dp->readq->qlen, p) ? -EFAULT : 0; case SNDCTL_SEQ_GETOUTCOUNT: if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return 0; return put_user(snd_seq_oss_writeq_get_free_size(dp->writeq), p) ? -EFAULT : 0; case SNDCTL_SEQ_GETTIME: return put_user(snd_seq_oss_timer_cur_tick(dp->timer), p) ? -EFAULT : 0; case SNDCTL_SEQ_RESETSAMPLES: if (get_user(dev, p)) return -EFAULT; return snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); case SNDCTL_SEQ_NRSYNTHS: return put_user(dp->max_synthdev, p) ? -EFAULT : 0; case SNDCTL_SEQ_NRMIDIS: return put_user(dp->max_mididev, p) ? -EFAULT : 0; case SNDCTL_SYNTH_MEMAVL: if (get_user(dev, p)) return -EFAULT; val = snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); return put_user(val, p) ? -EFAULT : 0; case SNDCTL_FM_4OP_ENABLE: if (get_user(dev, p)) return -EFAULT; snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); return 0; case SNDCTL_SYNTH_INFO: case SNDCTL_SYNTH_ID: return snd_seq_oss_synth_info_user(dp, arg); case SNDCTL_SEQ_OUTOFBAND: return snd_seq_oss_oob_user(dp, arg); case SNDCTL_MIDI_INFO: return snd_seq_oss_midi_info_user(dp, arg); case SNDCTL_SEQ_THRESHOLD: if (! is_write_mode(dp->file_mode)) return 0; if (get_user(val, p)) return -EFAULT; if (val < 1) val = 1; if (val >= dp->writeq->maxlen) val = dp->writeq->maxlen - 1; snd_seq_oss_writeq_set_output(dp->writeq, val); return 0; case SNDCTL_MIDI_PRETIME: if (dp->readq == NULL || !is_read_mode(dp->file_mode)) return 0; if (get_user(val, p)) return -EFAULT; if (val <= 0) val = -1; else val = (HZ * val) / 10; dp->readq->pre_event_timeout = val; return put_user(val, p) ? -EFAULT : 0; default: if (! is_write_mode(dp->file_mode)) return -EIO; return snd_seq_oss_synth_ioctl(dp, 0, cmd, carg); } return 0; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Network filesystem support services. * * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See: * * Documentation/filesystems/netfs_library.rst * * for a description of the network filesystem interface declared here. */ #ifndef _LINUX_NETFS_H #define _LINUX_NETFS_H #include <linux/workqueue.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/uio.h> #include <linux/rolling_buffer.h> enum netfs_sreq_ref_trace; typedef struct mempool_s mempool_t; struct folio_queue; /** * folio_start_private_2 - Start an fscache write on a folio. [DEPRECATED] * @folio: The folio. * * Call this function before writing a folio to a local cache. Starting a * second write before the first one finishes is not allowed. * * Note that this should no longer be used. */ static inline void folio_start_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio); folio_get(folio); folio_set_private_2(folio); } enum netfs_io_source { NETFS_SOURCE_UNKNOWN, NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, NETFS_INVALID_READ, NETFS_UPLOAD_TO_SERVER, NETFS_WRITE_TO_CACHE, NETFS_INVALID_WRITE, } __mode(byte); typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); /* * Per-inode context. This wraps the VFS inode. */ struct netfs_inode { struct inode inode; /* The VFS inode */ const struct netfs_request_ops *ops; #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; #endif struct mutex wb_lock; /* Writeback serialisation */ loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ #define NETFS_ICTX_MODIFIED_ATTR 3 /* Indicate change in mtime/ctime */ #define NETFS_ICTX_SINGLE_NO_UPLOAD 4 /* Monolithic payload, cache but no upload */ }; /* * A netfs group - for instance a ceph snap. This is marked on dirty pages and * pages marked with a group must be flushed before they can be written under * the domain of another group. */ struct netfs_group { refcount_t ref; void (*free)(struct netfs_group *netfs_group); }; /* * Information about a dirty page (attached only if necessary). * folio->private */ struct netfs_folio { struct netfs_group *netfs_group; /* Filesystem's grouping marker (or NULL). */ unsigned int dirty_offset; /* Write-streaming dirty data offset */ unsigned int dirty_len; /* Write-streaming dirty data length */ }; #define NETFS_FOLIO_INFO 0x1UL /* OR'd with folio->private. */ #define NETFS_FOLIO_COPY_TO_CACHE ((struct netfs_group *)0x356UL) /* Write to the cache only */ static inline bool netfs_is_folio_info(const void *priv) { return (unsigned long)priv & NETFS_FOLIO_INFO; } static inline struct netfs_folio *__netfs_folio_info(const void *priv) { if (netfs_is_folio_info(priv)) return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO); return NULL; } static inline struct netfs_folio *netfs_folio_info(struct folio *folio) { return __netfs_folio_info(folio_get_private(folio)); } static inline struct netfs_group *netfs_folio_group(struct folio *folio) { struct netfs_folio *finfo; void *priv = folio_get_private(folio); finfo = netfs_folio_info(folio); if (finfo) return finfo->netfs_group; return priv; } /* * Stream of I/O subrequests going to a particular destination, such as the * server or the local cache. This is mainly intended for writing where we may * have to write to multiple destinations concurrently. */ struct netfs_io_stream { /* Submission tracking */ struct netfs_io_subrequest *construct; /* Op being constructed */ size_t sreq_max_len; /* Maximum size of a subrequest */ unsigned int sreq_max_segs; /* 0 or max number of segments in an iterator */ unsigned int submit_off; /* Folio offset we're submitting from */ unsigned int submit_len; /* Amount of data left to submit */ unsigned int submit_extendable_to; /* Amount I/O can be rounded up to */ void (*prepare_write)(struct netfs_io_subrequest *subreq); void (*issue_write)(struct netfs_io_subrequest *subreq); /* Collection tracking */ struct list_head subrequests; /* Contributory I/O operations */ struct netfs_io_subrequest *front; /* Op being collected */ unsigned long long collected_to; /* Position we've collected results to */ size_t transferred; /* The amount transferred from this stream */ enum netfs_io_source source; /* Where to read from/write to */ unsigned short error; /* Aggregate error for the stream */ unsigned char stream_nr; /* Index of stream in parent table */ bool avail; /* T if stream is available */ bool active; /* T if stream is active */ bool need_retry; /* T if this stream needs retrying */ bool failed; /* T if this stream failed */ }; /* * Resources required to do operations on a cache. */ struct netfs_cache_resources { const struct netfs_cache_ops *ops; void *cache_priv; void *cache_priv2; unsigned int debug_id; /* Cookie debug ID */ unsigned int inval_counter; /* object->inval_counter at begin_op */ }; /* * Descriptor for a single component subrequest. Each operation represents an * individual read/write from/to a server, a cache, a journal, etc.. * * The buffer iterator is persistent for the life of the subrequest struct and * the pages it points to can be relied on to exist for the duration. */ struct netfs_io_subrequest { struct netfs_io_request *rreq; /* Supervising I/O request */ struct work_struct work; struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ unsigned long long start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ unsigned int nr_segs; /* Number of segs in io_iter */ u8 retry_count; /* The number of retries (0 on initial pass) */ enum netfs_io_source source; /* Where to read from/write to */ unsigned char stream_nr; /* I/O stream this belongs to */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_MADE_PROGRESS 4 /* Set if we transferred at least some data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ #define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ #define NETFS_SREQ_HIT_EOF 7 /* Set if short due to EOF */ #define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ #define NETFS_SREQ_FAILED 10 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_GAPS, /* This read is a synchronous read to fill gaps */ NETFS_READ_SINGLE, /* This read should be treated as a single object */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_WRITEBACK, /* This write was triggered by writepages */ NETFS_WRITEBACK_SINGLE, /* This monolithic write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_WRITE, /* This is a direct I/O write */ NETFS_PGPRIV2_COPY_TO_CACHE, /* [DEPRECATED] This is writing read data to the cache */ nr__netfs_io_origin } __mode(byte); /* * Descriptor for an I/O helper request. This is used to make multiple I/O * operations to a variety of data stores and then stitch the result together. */ struct netfs_io_request { union { struct work_struct work; struct rcu_head rcu; }; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ struct kiocb *iocb; /* AIO completion vector */ struct netfs_cache_resources cache_resources; struct netfs_io_request *copy_to_cache; /* Request to write just-read data to the cache */ struct readahead_control *ractl; /* Readahead descriptor */ struct list_head proc_link; /* Link in netfs_iorequests */ struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ #define NR_IO_STREAMS 2 //wreq->nr_io_streams struct netfs_group *group; /* Writeback group being written back */ struct rolling_buffer buffer; /* Unencrypted buffer */ #define NETFS_ROLLBUF_PUT_MARK ROLLBUF_MARK_1 #define NETFS_ROLLBUF_PAGECACHE_MARK ROLLBUF_MARK_2 wait_queue_head_t waitq; /* Processor waiter */ void *netfs_priv; /* Private data for the netfs */ void *netfs_priv2; /* Private data for the netfs */ struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ unsigned int wsize; /* Maximum write size (0 for none) */ atomic_t subreq_counter; /* Next subreq->debug_index */ unsigned int nr_group_rel; /* Number of refs to release on ->group */ spinlock_t lock; /* Lock for queuing subreqs */ unsigned long long submitted; /* Amount submitted for I/O so far */ unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ long error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ unsigned long long i_size; /* Size of the file */ unsigned long long start; /* Start position */ atomic64_t issued_to; /* Write issuer folio cursor */ unsigned long long collected_to; /* Point we've collected to */ unsigned long long cleaned_to; /* Position we've cleaned folios to */ unsigned long long abandon_to; /* Position to abandon folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ unsigned char front_folio_order; /* Order (size) of front folio */ refcount_t ref; unsigned long flags; #define NETFS_RREQ_OFFLOAD_COLLECTION 0 /* Offload collection to workqueue */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ #define NETFS_RREQ_FOLIO_COPY_TO_CACHE 6 /* Copy current folio to cache from read */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ #define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ #define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ #define NETFS_RREQ_NEED_RETRY 14 /* Need to try retrying */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; void (*cleanup)(struct netfs_io_request *req); }; /* * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { mempool_t *request_pool; mempool_t *subrequest_pool; int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); void (*free_subrequest)(struct netfs_io_subrequest *rreq); /* Read request handling */ void (*expand_readahead)(struct netfs_io_request *rreq); int (*prepare_read)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio **foliop, void **_fsdata); void (*done)(struct netfs_io_request *rreq); /* Modification handling */ void (*update_i_size)(struct inode *inode, loff_t i_size); void (*post_modify)(struct inode *inode); /* Write request handling */ void (*begin_writeback)(struct netfs_io_request *wreq); void (*prepare_write)(struct netfs_io_subrequest *subreq); void (*issue_write)(struct netfs_io_subrequest *subreq); void (*retry_request)(struct netfs_io_request *wreq, struct netfs_io_stream *stream); void (*invalidate_cache)(struct netfs_io_request *wreq); }; /* * How to handle reading from a hole. */ enum netfs_read_from_hole { NETFS_READ_HOLE_IGNORE, NETFS_READ_HOLE_CLEAR, NETFS_READ_HOLE_FAIL, }; /* * Table of operations for access to a cache. */ struct netfs_cache_ops { /* End an operation */ void (*end_operation)(struct netfs_cache_resources *cres); /* Read data from the cache */ int (*read)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv); /* Write data to the cache */ int (*write)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, netfs_io_terminated_t term_func, void *term_func_priv); /* Write data to the cache from a netfs subrequest. */ void (*issue_write)(struct netfs_io_subrequest *subreq); /* Expand readahead request */ void (*expand_readahead)(struct netfs_cache_resources *cres, unsigned long long *_start, unsigned long long *_len, unsigned long long i_size); /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, unsigned long long i_size); /* Prepare a write subrequest, working out if we're allowed to do it * and finding out the maximum amount of data to gather before * attempting to submit. If we're not permitted to do it, the * subrequest should be marked failed. */ void (*prepare_write_subreq)(struct netfs_io_subrequest *subreq); /* Prepare a write operation, working out what part of the write we can * actually do. */ int (*prepare_write)(struct netfs_cache_resources *cres, loff_t *_start, size_t *_len, size_t upper_len, loff_t i_size, bool no_space_allocated_yet); /* Prepare an on-demand read operation, shortening it to a cached/uncached * boundary as appropriate. */ enum netfs_io_source (*prepare_ondemand_read)(struct netfs_cache_resources *cres, loff_t start, size_t *_len, loff_t i_size, unsigned long *_flags, ino_t ino); /* Query the occupancy of the cache in a region, returning where the * next chunk of data starts and how long it is. */ int (*query_occupancy)(struct netfs_cache_resources *cres, loff_t start, size_t len, size_t granularity, loff_t *_data_start, size_t *_data_len); }; /* High-level read API. */ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); /* High-level write API */ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct netfs_group *netfs_group); ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, struct netfs_group *netfs_group); ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, struct netfs_group *netfs_group); ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); /* Single, monolithic object read/write API. */ void netfs_single_mark_inode_dirty(struct inode *inode); ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_iter *iter); int netfs_writeback_single(struct address_space *mapping, struct writeback_control *wbc, struct iov_iter *iter); /* Address operations API */ struct readahead_control; void netfs_readahead(struct readahead_control *); int netfs_read_folio(struct file *, struct folio *); int netfs_write_begin(struct netfs_inode *, struct file *, struct address_space *, loff_t pos, unsigned int len, struct folio **, void **fsdata); int netfs_writepages(struct address_space *mapping, struct writeback_control *wbc); bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio); int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool netfs_release_folio(struct folio *folio, gfp_t gfp); /* VMA operations API. */ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); /* (Sub)request management API. */ void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq); void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what); void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what); ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, struct iov_iter *new, iov_iter_extraction_t extraction_flags); size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs); void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq); void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, bool was_async); void netfs_queue_write_request(struct netfs_io_subrequest *subreq); int netfs_start_io_read(struct inode *inode); void netfs_end_io_read(struct inode *inode); int netfs_start_io_write(struct inode *inode); void netfs_end_io_write(struct inode *inode); int netfs_start_io_direct(struct inode *inode); void netfs_end_io_direct(struct inode *inode); /* Miscellaneous APIs. */ struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp, unsigned int trace /*enum netfs_folioq_trace*/); void netfs_folioq_free(struct folio_queue *folioq, unsigned int trace /*enum netfs_trace_folioq*/); /* Buffer wrangling helpers API. */ int netfs_alloc_folioq_buffer(struct address_space *mapping, struct folio_queue **_buffer, size_t *_cur_size, ssize_t size, gfp_t gfp); void netfs_free_folioq_buffer(struct folio_queue *fq); /** * netfs_inode - Get the netfs inode context from the inode * @inode: The inode to query * * Get the netfs lib inode context from the network filesystem's inode. The * context struct is expected to directly follow on from the VFS inode struct. */ static inline struct netfs_inode *netfs_inode(struct inode *inode) { return container_of(inode, struct netfs_inode, inode); } /** * netfs_inode_init - Initialise a netfslib inode context * @ctx: The netfs inode to initialise * @ops: The netfs's operations list * @use_zero_point: True to use the zero_point read optimisation * * Initialise the netfs library context struct. This is expected to follow on * directly from the VFS inode struct. */ static inline void netfs_inode_init(struct netfs_inode *ctx, const struct netfs_request_ops *ops, bool use_zero_point) { ctx->ops = ops; ctx->remote_i_size = i_size_read(&ctx->inode); ctx->zero_point = LLONG_MAX; ctx->flags = 0; atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif mutex_init(&ctx->wb_lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { ctx->zero_point = ctx->remote_i_size; mapping_set_release_always(ctx->inode.i_mapping); } } /** * netfs_resize_file - Note that a file got resized * @ctx: The netfs inode being resized * @new_i_size: The new file size * @changed_on_server: The change was applied to the server * * Inform the netfs lib that a file got resized so that it can adjust its state. */ static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size, bool changed_on_server) { if (changed_on_server) ctx->remote_i_size = new_i_size; if (new_i_size < ctx->zero_point) ctx->zero_point = new_i_size; } /** * netfs_i_cookie - Get the cache cookie from the inode * @ctx: The netfs inode to query * * Get the caching cookie (if enabled) from the network filesystem's inode. */ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) { #if IS_ENABLED(CONFIG_FSCACHE) return ctx->cache; #else return NULL; #endif } /** * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete * @inode: The netfs inode to wait on * * Wait for outstanding I/O requests of any type to complete. This is intended * to be called from inode eviction routines. This makes sure that any * resources held by those requests are cleaned up before we let the inode get * cleaned up. */ static inline void netfs_wait_for_outstanding_io(struct inode *inode) { struct netfs_inode *ictx = netfs_inode(inode); wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0); } #endif /* _LINUX_NETFS_H */ |
| 15 15 15 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | /* * linux/fs/nls/mac-gaelic.c * * Charset macgaelic translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ /* * COPYRIGHT AND PERMISSION NOTICE * * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under * the Terms of Use in http://www.unicode.org/copyright.html. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of the Unicode data files and any associated documentation (the "Data * Files") or Unicode software and any associated documentation (the * "Software") to deal in the Data Files or Software without restriction, * including without limitation the rights to use, copy, modify, merge, * publish, distribute, and/or sell copies of the Data Files or Software, and * to permit persons to whom the Data Files or Software are furnished to do * so, provided that (a) the above copyright notice(s) and this permission * notice appear with all copies of the Data Files or Software, (b) both the * above copyright notice(s) and this permission notice appear in associated * documentation, and (c) there is clear notice in each modified Data File or * in the Software as well as in the documentation associated with the Data * File(s) or Software that the data or software has been modified. * * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR * PERFORMANCE OF THE DATA FILES OR SOFTWARE. * * Except as contained in this notice, the name of a copyright holder shall * not be used in advertising or otherwise to promote the sale, use or other * dealings in these Data Files or Software without prior written * authorization of the copyright holder. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00 */ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10 */ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20 */ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30 */ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40 */ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50 */ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60 */ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70 */ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80 */ 0x00c4, 0x00c5, 0x00c7, 0x00c9, 0x00d1, 0x00d6, 0x00dc, 0x00e1, 0x00e0, 0x00e2, 0x00e4, 0x00e3, 0x00e5, 0x00e7, 0x00e9, 0x00e8, /* 0x90 */ 0x00ea, 0x00eb, 0x00ed, 0x00ec, 0x00ee, 0x00ef, 0x00f1, 0x00f3, 0x00f2, 0x00f4, 0x00f6, 0x00f5, 0x00fa, 0x00f9, 0x00fb, 0x00fc, /* 0xa0 */ 0x2020, 0x00b0, 0x00a2, 0x00a3, 0x00a7, 0x2022, 0x00b6, 0x00df, 0x00ae, 0x00a9, 0x2122, 0x00b4, 0x00a8, 0x2260, 0x00c6, 0x00d8, /* 0xb0 */ 0x1e02, 0x00b1, 0x2264, 0x2265, 0x1e03, 0x010a, 0x010b, 0x1e0a, 0x1e0b, 0x1e1e, 0x1e1f, 0x0120, 0x0121, 0x1e40, 0x00e6, 0x00f8, /* 0xc0 */ 0x1e41, 0x1e56, 0x1e57, 0x027c, 0x0192, 0x017f, 0x1e60, 0x00ab, 0x00bb, 0x2026, 0x00a0, 0x00c0, 0x00c3, 0x00d5, 0x0152, 0x0153, /* 0xd0 */ 0x2013, 0x2014, 0x201c, 0x201d, 0x2018, 0x2019, 0x1e61, 0x1e9b, 0x00ff, 0x0178, 0x1e6a, 0x20ac, 0x2039, 0x203a, 0x0176, 0x0177, /* 0xe0 */ 0x1e6b, 0x00b7, 0x1ef2, 0x1ef3, 0x204a, 0x00c2, 0x00ca, 0x00c1, 0x00cb, 0x00c8, 0x00cd, 0x00ce, 0x00cf, 0x00cc, 0x00d3, 0x00d4, /* 0xf0 */ 0x2663, 0x00d2, 0x00da, 0x00db, 0x00d9, 0x0131, 0x00dd, 0x00fd, 0x0174, 0x0175, 0x1e84, 0x1e85, 0x1e80, 0x1e81, 0x1e82, 0x1e83, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xca, 0x00, 0xa2, 0xa3, 0x00, 0x00, 0x00, 0xa4, /* 0xa0-0xa7 */ 0xac, 0xa9, 0x00, 0xc7, 0x00, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ 0xa1, 0xb1, 0x00, 0x00, 0xab, 0x00, 0xa6, 0xe1, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xc8, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, /* 0xc0-0xc7 */ 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0xf6, 0x00, 0xa7, /* 0xd8-0xdf */ 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, /* 0xe0-0xe7 */ 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0x00, /* 0xf0-0xf7 */ 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0xf7, 0x00, 0xd8, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0xb5, 0xb6, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0xbb, 0xbc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0xf8, 0xf9, 0xde, 0xdf, /* 0x70-0x77 */ 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page02[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page1e[256] = { 0x00, 0x00, 0xb0, 0xb4, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0xb7, 0xb8, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb9, 0xba, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0xbd, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc1, 0xc2, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0xc6, 0xd6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0xda, 0xe0, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xfc, 0xfd, 0xfe, 0xff, 0xfa, 0xfb, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0xe2, 0xe3, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0x00, 0x00, /* 0x18-0x1f */ 0xa0, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page26[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0xf0, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, page02, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page1e, NULL, page20, page21, page22, NULL, NULL, NULL, page26, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x00-0x07 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x08-0x0f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x10-0x17 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x18-0x1f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x20-0x27 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x28-0x2f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x30-0x37 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x38-0x3f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x40-0x47 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x48-0x4f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x50-0x57 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x58-0x5f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x60-0x67 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x68-0x6f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x70-0x77 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x78-0x7f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x80-0x87 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x88-0x8f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x90-0x97 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x98-0x9f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa0-0xa7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa8-0xaf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb0-0xb7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb8-0xbf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc0-0xc7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc8-0xcf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd0-0xd7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd8-0xdf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe0-0xe7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe8-0xef */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf0-0xf7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "macgaelic", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_macgaelic(void) { return register_nls(&table); } static void __exit exit_nls_macgaelic(void) { unregister_nls(&table); } module_init(init_nls_macgaelic) module_exit(exit_nls_macgaelic) MODULE_DESCRIPTION("NLS Codepage macgaelic"); MODULE_LICENSE("Dual BSD/GPL"); |
| 12 4223 3213 1383 117 2615 1604 3264 3184 800 11 8 3 3037 3283 2889 9 2889 2147 2146 2148 2586 6 2589 1444 1445 223 60 164 3355 60 3531 9 10 9 7 2 6 6 6 60 61 13 12 1 1 59 61 61 1281 60 61 12 12 12 17 17 3205 18 1 3194 2 3198 3207 3192 3190 3190 3172 3177 3177 92 92 1195 1196 1195 1197 1197 1201 1392 1388 1387 1391 1383 1146 1391 30 1771 3316 32 3288 1790 3284 2824 2938 5 3078 3074 1 1 3350 3331 14 5 1538 3332 3324 2586 1679 1152 966 1745 3337 3182 3071 3335 5 3309 3320 1629 3171 2 3315 1681 2587 1536 2 2761 1 1 421 3190 13 3178 3173 15 629 48 47 541 1191 1193 1151 1201 1809 15 1149 1389 1804 1736 1198 1 1808 1155 1154 3321 9 63 18 2 3280 1204 1204 1208 1204 8 7 7 7 8 50 48 1 1 2 3068 2586 2585 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright (C) 2016 - 2020 Christoph Hellwig */ #include <linux/init.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/major.h> #include <linux/device_cgroup.h> #include <linux/blkdev.h> #include <linux/blk-integrity.h> #include <linux/backing-dev.h> #include <linux/module.h> #include <linux/blkpg.h> #include <linux/magic.h> #include <linux/buffer_head.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/uio.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/part_stat.h> #include <linux/uaccess.h> #include <linux/stat.h> #include "../fs/internal.h" #include "blk.h" /* Should we allow writing to mounted block devices? */ static bool bdev_allow_write_mounted = IS_ENABLED(CONFIG_BLK_DEV_WRITE_MOUNTED); struct bdev_inode { struct block_device bdev; struct inode vfs_inode; }; static inline struct bdev_inode *BDEV_I(struct inode *inode) { return container_of(inode, struct bdev_inode, vfs_inode); } static inline struct inode *BD_INODE(struct block_device *bdev) { return &container_of(bdev, struct bdev_inode, bdev)->vfs_inode; } struct block_device *I_BDEV(struct inode *inode) { return &BDEV_I(inode)->bdev; } EXPORT_SYMBOL(I_BDEV); struct block_device *file_bdev(struct file *bdev_file) { return I_BDEV(bdev_file->f_mapping->host); } EXPORT_SYMBOL(file_bdev); static void bdev_write_inode(struct block_device *bdev) { struct inode *inode = BD_INODE(bdev); int ret; spin_lock(&inode->i_lock); while (inode->i_state & I_DIRTY) { spin_unlock(&inode->i_lock); ret = write_inode_now(inode, true); if (ret) pr_warn_ratelimited( "VFS: Dirty inode writeback failed for block device %pg (err=%d).\n", bdev, ret); spin_lock(&inode->i_lock); } spin_unlock(&inode->i_lock); } /* Kill _all_ buffers and pagecache , dirty or not.. */ static void kill_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_mapping; if (mapping_empty(mapping)) return; invalidate_bh_lrus(); truncate_inode_pages(mapping, 0); } /* Invalidate clean unused buffers and pagecache. */ void invalidate_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_mapping; if (mapping->nrpages) { invalidate_bh_lrus(); lru_add_drain_all(); /* make sure all lru add caches are flushed */ invalidate_mapping_pages(mapping, 0, -1); } } EXPORT_SYMBOL(invalidate_bdev); /* * Drop all buffers & page cache for given bdev range. This function bails * with error if bdev has other exclusive owner (such as filesystem). */ int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, loff_t lstart, loff_t lend) { /* * If we don't hold exclusive handle for the device, upgrade to it * while we discard the buffer cache to avoid discarding buffers * under live filesystem. */ if (!(mode & BLK_OPEN_EXCL)) { int err = bd_prepare_to_claim(bdev, truncate_bdev_range, NULL); if (err) goto invalidate; } truncate_inode_pages_range(bdev->bd_mapping, lstart, lend); if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, truncate_bdev_range); return 0; invalidate: /* * Someone else has handle exclusively open. Try invalidating instead. * The 'end' argument is inclusive so the rounding is safe. */ return invalidate_inode_pages2_range(bdev->bd_mapping, lstart >> PAGE_SHIFT, lend >> PAGE_SHIFT); } static void set_init_blocksize(struct block_device *bdev) { unsigned int bsize = bdev_logical_block_size(bdev); loff_t size = i_size_read(BD_INODE(bdev)); while (bsize < PAGE_SIZE) { if (size & bsize) break; bsize <<= 1; } BD_INODE(bdev)->i_blkbits = blksize_bits(bsize); } int set_blocksize(struct file *file, int size) { struct inode *inode = file->f_mapping->host; struct block_device *bdev = I_BDEV(inode); if (blk_validate_block_size(size)) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ if (size < bdev_logical_block_size(bdev)) return -EINVAL; if (!file->private_data) return -EINVAL; /* Don't change the size if it is same as current */ if (inode->i_blkbits != blksize_bits(size)) { sync_blockdev(bdev); inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); } return 0; } EXPORT_SYMBOL(set_blocksize); int sb_set_blocksize(struct super_block *sb, int size) { if (set_blocksize(sb->s_bdev_file, size)) return 0; /* If we get here, we know size is power of two * and it's value is between 512 and PAGE_SIZE */ sb->s_blocksize = size; sb->s_blocksize_bits = blksize_bits(size); return sb->s_blocksize; } EXPORT_SYMBOL(sb_set_blocksize); int sb_min_blocksize(struct super_block *sb, int size) { int minsize = bdev_logical_block_size(sb->s_bdev); if (size < minsize) size = minsize; return sb_set_blocksize(sb, size); } EXPORT_SYMBOL(sb_min_blocksize); int sync_blockdev_nowait(struct block_device *bdev) { if (!bdev) return 0; return filemap_flush(bdev->bd_mapping); } EXPORT_SYMBOL_GPL(sync_blockdev_nowait); /* * Write out and wait upon all the dirty data associated with a block * device via its mapping. Does not take the superblock lock. */ int sync_blockdev(struct block_device *bdev) { if (!bdev) return 0; return filemap_write_and_wait(bdev->bd_mapping); } EXPORT_SYMBOL(sync_blockdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend) { return filemap_write_and_wait_range(bdev->bd_mapping, lstart, lend); } EXPORT_SYMBOL(sync_blockdev_range); /** * bdev_freeze - lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. * The reference counter (bd_fsfreeze_count) guarantees that only the last * unfreeze process can unfreeze the frozen filesystem actually when multiple * freeze requests arrive simultaneously. It counts up in bdev_freeze() and * count down in bdev_thaw(). When it becomes 0, thaw_bdev() will unfreeze * actually. * * Return: On success zero is returned, negative error code on failure. */ int bdev_freeze(struct block_device *bdev) { int error = 0; mutex_lock(&bdev->bd_fsfreeze_mutex); if (atomic_inc_return(&bdev->bd_fsfreeze_count) > 1) { mutex_unlock(&bdev->bd_fsfreeze_mutex); return 0; } mutex_lock(&bdev->bd_holder_lock); if (bdev->bd_holder_ops && bdev->bd_holder_ops->freeze) { error = bdev->bd_holder_ops->freeze(bdev); lockdep_assert_not_held(&bdev->bd_holder_lock); } else { mutex_unlock(&bdev->bd_holder_lock); error = sync_blockdev(bdev); } if (error) atomic_dec(&bdev->bd_fsfreeze_count); mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; } EXPORT_SYMBOL(bdev_freeze); /** * bdev_thaw - unlock filesystem * @bdev: blockdevice to unlock * * Unlocks the filesystem and marks it writeable again after bdev_freeze(). * * Return: On success zero is returned, negative error code on failure. */ int bdev_thaw(struct block_device *bdev) { int error = -EINVAL, nr_freeze; mutex_lock(&bdev->bd_fsfreeze_mutex); /* * If this returns < 0 it means that @bd_fsfreeze_count was * already 0 and no decrement was performed. */ nr_freeze = atomic_dec_if_positive(&bdev->bd_fsfreeze_count); if (nr_freeze < 0) goto out; error = 0; if (nr_freeze > 0) goto out; mutex_lock(&bdev->bd_holder_lock); if (bdev->bd_holder_ops && bdev->bd_holder_ops->thaw) { error = bdev->bd_holder_ops->thaw(bdev); lockdep_assert_not_held(&bdev->bd_holder_lock); } else { mutex_unlock(&bdev->bd_holder_lock); } if (error) atomic_inc(&bdev->bd_fsfreeze_count); out: mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; } EXPORT_SYMBOL(bdev_thaw); /* * pseudo-fs */ static __cacheline_aligned_in_smp DEFINE_MUTEX(bdev_lock); static struct kmem_cache *bdev_cachep __ro_after_init; static struct inode *bdev_alloc_inode(struct super_block *sb) { struct bdev_inode *ei = alloc_inode_sb(sb, bdev_cachep, GFP_KERNEL); if (!ei) return NULL; memset(&ei->bdev, 0, sizeof(ei->bdev)); if (security_bdev_alloc(&ei->bdev)) { kmem_cache_free(bdev_cachep, ei); return NULL; } return &ei->vfs_inode; } static void bdev_free_inode(struct inode *inode) { struct block_device *bdev = I_BDEV(inode); free_percpu(bdev->bd_stats); kfree(bdev->bd_meta_info); security_bdev_free(bdev); if (!bdev_is_partition(bdev)) { if (bdev->bd_disk && bdev->bd_disk->bdi) bdi_put(bdev->bd_disk->bdi); kfree(bdev->bd_disk); } if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR) blk_free_ext_minor(MINOR(bdev->bd_dev)); kmem_cache_free(bdev_cachep, BDEV_I(inode)); } static void init_once(void *data) { struct bdev_inode *ei = data; inode_init_once(&ei->vfs_inode); } static void bdev_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); } static const struct super_operations bdev_sops = { .statfs = simple_statfs, .alloc_inode = bdev_alloc_inode, .free_inode = bdev_free_inode, .drop_inode = generic_delete_inode, .evict_inode = bdev_evict_inode, }; static int bd_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, BDEVFS_MAGIC); if (!ctx) return -ENOMEM; fc->s_iflags |= SB_I_CGROUPWB; ctx->ops = &bdev_sops; return 0; } static struct file_system_type bd_type = { .name = "bdev", .init_fs_context = bd_init_fs_context, .kill_sb = kill_anon_super, }; struct super_block *blockdev_superblock __ro_after_init; static struct vfsmount *blockdev_mnt __ro_after_init; EXPORT_SYMBOL_GPL(blockdev_superblock); void __init bdev_cache_init(void) { int err; bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT|SLAB_PANIC), init_once); err = register_filesystem(&bd_type); if (err) panic("Cannot register bdev pseudo-fs"); blockdev_mnt = kern_mount(&bd_type); if (IS_ERR(blockdev_mnt)) panic("Cannot create bdev pseudo-fs"); blockdev_superblock = blockdev_mnt->mnt_sb; /* For writeback */ } struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) { struct block_device *bdev; struct inode *inode; inode = new_inode(blockdev_superblock); if (!inode) return NULL; inode->i_mode = S_IFBLK; inode->i_rdev = 0; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); bdev = I_BDEV(inode); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); mutex_init(&bdev->bd_holder_lock); atomic_set(&bdev->__bd_flags, partno); bdev->bd_mapping = &inode->i_data; bdev->bd_queue = disk->queue; if (partno && bdev_test_flag(disk->part0, BD_HAS_SUBMIT_BIO)) bdev_set_flag(bdev, BD_HAS_SUBMIT_BIO); bdev->bd_stats = alloc_percpu(struct disk_stats); if (!bdev->bd_stats) { iput(inode); return NULL; } bdev->bd_disk = disk; return bdev; } void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) { spin_lock(&bdev->bd_size_lock); i_size_write(BD_INODE(bdev), (loff_t)sectors << SECTOR_SHIFT); bdev->bd_nr_sectors = sectors; spin_unlock(&bdev->bd_size_lock); } void bdev_add(struct block_device *bdev, dev_t dev) { struct inode *inode = BD_INODE(bdev); if (bdev_stable_writes(bdev)) mapping_set_stable_writes(bdev->bd_mapping); bdev->bd_dev = dev; inode->i_rdev = dev; inode->i_ino = dev; insert_inode_hash(inode); } void bdev_unhash(struct block_device *bdev) { remove_inode_hash(BD_INODE(bdev)); } void bdev_drop(struct block_device *bdev) { iput(BD_INODE(bdev)); } long nr_blockdev_pages(void) { struct inode *inode; long ret = 0; spin_lock(&blockdev_superblock->s_inode_list_lock); list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) ret += inode->i_mapping->nrpages; spin_unlock(&blockdev_superblock->s_inode_list_lock); return ret; } /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest * @holder: holder trying to claim @bdev * @hops: holder ops * * Test whether @bdev can be claimed by @holder. * * RETURNS: * %true if @bdev can be claimed, %false otherwise. */ static bool bd_may_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops) { struct block_device *whole = bdev_whole(bdev); lockdep_assert_held(&bdev_lock); if (bdev->bd_holder) { /* * The same holder can always re-claim. */ if (bdev->bd_holder == holder) { if (WARN_ON_ONCE(bdev->bd_holder_ops != hops)) return false; return true; } return false; } /* * If the whole devices holder is set to bd_may_claim, a partition on * the device is claimed, but not the whole device. */ if (whole != bdev && whole->bd_holder && whole->bd_holder != bd_may_claim) return false; return true; } /** * bd_prepare_to_claim - claim a block device * @bdev: block device of interest * @holder: holder trying to claim @bdev * @hops: holder ops. * * Claim @bdev. This function fails if @bdev is already claimed by another * holder and waits if another claiming is in progress. return, the caller * has ownership of bd_claiming and bd_holder[s]. * * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. */ int bd_prepare_to_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops) { struct block_device *whole = bdev_whole(bdev); if (WARN_ON_ONCE(!holder)) return -EINVAL; retry: mutex_lock(&bdev_lock); /* if someone else claimed, fail */ if (!bd_may_claim(bdev, holder, hops)) { mutex_unlock(&bdev_lock); return -EBUSY; } /* if claiming is already in progress, wait for it to finish */ if (whole->bd_claiming) { wait_queue_head_t *wq = __var_waitqueue(&whole->bd_claiming); DEFINE_WAIT(wait); prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); mutex_unlock(&bdev_lock); schedule(); finish_wait(wq, &wait); goto retry; } /* yay, all mine */ whole->bd_claiming = holder; mutex_unlock(&bdev_lock); return 0; } EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ static void bd_clear_claiming(struct block_device *whole, void *holder) { lockdep_assert_held(&bdev_lock); /* tell others that we're done */ BUG_ON(whole->bd_claiming != holder); whole->bd_claiming = NULL; wake_up_var(&whole->bd_claiming); } /** * bd_finish_claiming - finish claiming of a block device * @bdev: block device of interest * @holder: holder that has claimed @bdev * @hops: block device holder operations * * Finish exclusive open of a block device. Mark the device as exlusively * open by the holder and wake up all waiters for exclusive open to finish. */ static void bd_finish_claiming(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops) { struct block_device *whole = bdev_whole(bdev); mutex_lock(&bdev_lock); BUG_ON(!bd_may_claim(bdev, holder, hops)); /* * Note that for a whole device bd_holders will be incremented twice, * and bd_holder will be set to bd_may_claim before being set to holder */ whole->bd_holders++; whole->bd_holder = bd_may_claim; bdev->bd_holders++; mutex_lock(&bdev->bd_holder_lock); bdev->bd_holder = holder; bdev->bd_holder_ops = hops; mutex_unlock(&bdev->bd_holder_lock); bd_clear_claiming(whole, holder); mutex_unlock(&bdev_lock); } /** * bd_abort_claiming - abort claiming of a block device * @bdev: block device of interest * @holder: holder that has claimed @bdev * * Abort claiming of a block device when the exclusive open failed. This can be * also used when exclusive open is not actually desired and we just needed * to block other exclusive openers for a while. */ void bd_abort_claiming(struct block_device *bdev, void *holder) { mutex_lock(&bdev_lock); bd_clear_claiming(bdev_whole(bdev), holder); mutex_unlock(&bdev_lock); } EXPORT_SYMBOL(bd_abort_claiming); static void bd_end_claim(struct block_device *bdev, void *holder) { struct block_device *whole = bdev_whole(bdev); bool unblock = false; /* * Release a claim on the device. The holder fields are protected with * bdev_lock. open_mutex is used to synchronize disk_holder unlinking. */ mutex_lock(&bdev_lock); WARN_ON_ONCE(bdev->bd_holder != holder); WARN_ON_ONCE(--bdev->bd_holders < 0); WARN_ON_ONCE(--whole->bd_holders < 0); if (!bdev->bd_holders) { mutex_lock(&bdev->bd_holder_lock); bdev->bd_holder = NULL; bdev->bd_holder_ops = NULL; mutex_unlock(&bdev->bd_holder_lock); if (bdev_test_flag(bdev, BD_WRITE_HOLDER)) unblock = true; } if (!whole->bd_holders) whole->bd_holder = NULL; mutex_unlock(&bdev_lock); /* * If this was the last claim, remove holder link and unblock evpoll if * it was a write holder. */ if (unblock) { disk_unblock_events(bdev->bd_disk); bdev_clear_flag(bdev, BD_WRITE_HOLDER); } } static void blkdev_flush_mapping(struct block_device *bdev) { WARN_ON_ONCE(bdev->bd_holders); sync_blockdev(bdev); kill_bdev(bdev); bdev_write_inode(bdev); } static void blkdev_put_whole(struct block_device *bdev) { if (atomic_dec_and_test(&bdev->bd_openers)) blkdev_flush_mapping(bdev); if (bdev->bd_disk->fops->release) bdev->bd_disk->fops->release(bdev->bd_disk); } static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) { struct gendisk *disk = bdev->bd_disk; int ret; if (disk->fops->open) { ret = disk->fops->open(disk, mode); if (ret) { /* avoid ghost partitions on a removed medium */ if (ret == -ENOMEDIUM && test_bit(GD_NEED_PART_SCAN, &disk->state)) bdev_disk_changed(disk, true); return ret; } } if (!atomic_read(&bdev->bd_openers)) set_init_blocksize(bdev); atomic_inc(&bdev->bd_openers); if (test_bit(GD_NEED_PART_SCAN, &disk->state)) { /* * Only return scanning errors if we are called from contexts * that explicitly want them, e.g. the BLKRRPART ioctl. */ ret = bdev_disk_changed(disk, false); if (ret && (mode & BLK_OPEN_STRICT_SCAN)) { blkdev_put_whole(bdev); return ret; } } return 0; } static int blkdev_get_part(struct block_device *part, blk_mode_t mode) { struct gendisk *disk = part->bd_disk; int ret; ret = blkdev_get_whole(bdev_whole(part), mode); if (ret) return ret; ret = -ENXIO; if (!bdev_nr_sectors(part)) goto out_blkdev_put; if (!atomic_read(&part->bd_openers)) { disk->open_partitions++; set_init_blocksize(part); } atomic_inc(&part->bd_openers); return 0; out_blkdev_put: blkdev_put_whole(bdev_whole(part)); return ret; } int bdev_permission(dev_t dev, blk_mode_t mode, void *holder) { int ret; ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, MAJOR(dev), MINOR(dev), ((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) | ((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0)); if (ret) return ret; /* Blocking writes requires exclusive opener */ if (mode & BLK_OPEN_RESTRICT_WRITES && !holder) return -EINVAL; /* * We're using error pointers to indicate to ->release() when we * failed to open that block device. Also this doesn't make sense. */ if (WARN_ON_ONCE(IS_ERR(holder))) return -EINVAL; return 0; } static void blkdev_put_part(struct block_device *part) { struct block_device *whole = bdev_whole(part); if (atomic_dec_and_test(&part->bd_openers)) { blkdev_flush_mapping(part); whole->bd_disk->open_partitions--; } blkdev_put_whole(whole); } struct block_device *blkdev_get_no_open(dev_t dev) { struct block_device *bdev; struct inode *inode; inode = ilookup(blockdev_superblock, dev); if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) { blk_request_module(dev); inode = ilookup(blockdev_superblock, dev); if (inode) pr_warn_ratelimited( "block device autoloading is deprecated and will be removed.\n"); } if (!inode) return NULL; /* switch from the inode reference to a device mode one: */ bdev = &BDEV_I(inode)->bdev; if (!kobject_get_unless_zero(&bdev->bd_device.kobj)) bdev = NULL; iput(inode); return bdev; } void blkdev_put_no_open(struct block_device *bdev) { put_device(&bdev->bd_device); } static bool bdev_writes_blocked(struct block_device *bdev) { return bdev->bd_writers < 0; } static void bdev_block_writes(struct block_device *bdev) { bdev->bd_writers--; } static void bdev_unblock_writes(struct block_device *bdev) { bdev->bd_writers++; } static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode) { if (bdev_allow_write_mounted) return true; /* Writes blocked? */ if (mode & BLK_OPEN_WRITE && bdev_writes_blocked(bdev)) return false; if (mode & BLK_OPEN_RESTRICT_WRITES && bdev->bd_writers > 0) return false; return true; } static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode) { if (bdev_allow_write_mounted) return; /* Claim exclusive or shared write access. */ if (mode & BLK_OPEN_RESTRICT_WRITES) bdev_block_writes(bdev); else if (mode & BLK_OPEN_WRITE) bdev->bd_writers++; } static inline bool bdev_unclaimed(const struct file *bdev_file) { return bdev_file->private_data == BDEV_I(bdev_file->f_mapping->host); } static void bdev_yield_write_access(struct file *bdev_file) { struct block_device *bdev; if (bdev_allow_write_mounted) return; if (bdev_unclaimed(bdev_file)) return; bdev = file_bdev(bdev_file); if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED) bdev_unblock_writes(bdev); else if (bdev_file->f_mode & FMODE_WRITE) bdev->bd_writers--; } /** * bdev_open - open a block device * @bdev: block device to open * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier * @hops: holder operations * @bdev_file: file for the block device * * Open the block device. If @holder is not %NULL, the block device is opened * with exclusive access. Exclusive opens may nest for the same @holder. * * CONTEXT: * Might sleep. * * RETURNS: * zero on success, -errno on failure. */ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops, struct file *bdev_file) { bool unblock_events = true; struct gendisk *disk = bdev->bd_disk; int ret; if (holder) { mode |= BLK_OPEN_EXCL; ret = bd_prepare_to_claim(bdev, holder, hops); if (ret) return ret; } else { if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) return -EIO; } disk_block_events(disk); mutex_lock(&disk->open_mutex); ret = -ENXIO; if (!disk_live(disk)) goto abort_claiming; if (!try_module_get(disk->fops->owner)) goto abort_claiming; ret = -EBUSY; if (!bdev_may_open(bdev, mode)) goto put_module; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); else ret = blkdev_get_whole(bdev, mode); if (ret) goto put_module; bdev_claim_write_access(bdev, mode); if (holder) { bd_finish_claiming(bdev, holder, hops); /* * Block event polling for write claims if requested. Any write * holder makes the write_holder state stick until all are * released. This is good enough and tracking individual * writeable reference is too fragile given the way @mode is * used in blkdev_get/put(). */ if ((mode & BLK_OPEN_WRITE) && !bdev_test_flag(bdev, BD_WRITE_HOLDER) && (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) { bdev_set_flag(bdev, BD_WRITE_HOLDER); unblock_events = false; } } mutex_unlock(&disk->open_mutex); if (unblock_events) disk_unblock_events(disk); bdev_file->f_flags |= O_LARGEFILE; bdev_file->f_mode |= FMODE_CAN_ODIRECT; if (bdev_nowait(bdev)) bdev_file->f_mode |= FMODE_NOWAIT; if (mode & BLK_OPEN_RESTRICT_WRITES) bdev_file->f_mode |= FMODE_WRITE_RESTRICTED; bdev_file->f_mapping = bdev->bd_mapping; bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping); bdev_file->private_data = holder; return 0; put_module: module_put(disk->fops->owner); abort_claiming: if (holder) bd_abort_claiming(bdev, holder); mutex_unlock(&disk->open_mutex); disk_unblock_events(disk); return ret; } /* * If BLK_OPEN_WRITE_IOCTL is set then this is a historical quirk * associated with the floppy driver where it has allowed ioctls if the * file was opened for writing, but does not allow reads or writes. * Make sure that this quirk is reflected in @f_flags. * * It can also happen if a block device is opened as O_RDWR | O_WRONLY. */ static unsigned blk_to_file_flags(blk_mode_t mode) { unsigned int flags = 0; if ((mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) == (BLK_OPEN_READ | BLK_OPEN_WRITE)) flags |= O_RDWR; else if (mode & BLK_OPEN_WRITE_IOCTL) flags |= O_RDWR | O_WRONLY; else if (mode & BLK_OPEN_WRITE) flags |= O_WRONLY; else if (mode & BLK_OPEN_READ) flags |= O_RDONLY; /* homeopathic, because O_RDONLY is 0 */ else WARN_ON_ONCE(true); if (mode & BLK_OPEN_NDELAY) flags |= O_NDELAY; return flags; } struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops) { struct file *bdev_file; struct block_device *bdev; unsigned int flags; int ret; ret = bdev_permission(dev, mode, holder); if (ret) return ERR_PTR(ret); bdev = blkdev_get_no_open(dev); if (!bdev) return ERR_PTR(-ENXIO); flags = blk_to_file_flags(mode); bdev_file = alloc_file_pseudo_noaccount(BD_INODE(bdev), blockdev_mnt, "", flags | O_LARGEFILE, &def_blk_fops); if (IS_ERR(bdev_file)) { blkdev_put_no_open(bdev); return bdev_file; } ihold(BD_INODE(bdev)); ret = bdev_open(bdev, mode, holder, hops, bdev_file); if (ret) { /* We failed to open the block device. Let ->release() know. */ bdev_file->private_data = ERR_PTR(ret); fput(bdev_file); return ERR_PTR(ret); } return bdev_file; } EXPORT_SYMBOL(bdev_file_open_by_dev); struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops) { struct file *file; dev_t dev; int error; error = lookup_bdev(path, &dev); if (error) return ERR_PTR(error); file = bdev_file_open_by_dev(dev, mode, holder, hops); if (!IS_ERR(file) && (mode & BLK_OPEN_WRITE)) { if (bdev_read_only(file_bdev(file))) { fput(file); file = ERR_PTR(-EACCES); } } return file; } EXPORT_SYMBOL(bdev_file_open_by_path); static inline void bd_yield_claim(struct file *bdev_file) { struct block_device *bdev = file_bdev(bdev_file); void *holder = bdev_file->private_data; lockdep_assert_held(&bdev->bd_disk->open_mutex); if (WARN_ON_ONCE(IS_ERR_OR_NULL(holder))) return; if (!bdev_unclaimed(bdev_file)) bd_end_claim(bdev, holder); } void bdev_release(struct file *bdev_file) { struct block_device *bdev = file_bdev(bdev_file); void *holder = bdev_file->private_data; struct gendisk *disk = bdev->bd_disk; /* We failed to open that block device. */ if (IS_ERR(holder)) goto put_no_open; /* * Sync early if it looks like we're the last one. If someone else * opens the block device between now and the decrement of bd_openers * then we did a sync that we didn't need to, but that's not the end * of the world and we want to avoid long (could be several minute) * syncs while holding the mutex. */ if (atomic_read(&bdev->bd_openers) == 1) sync_blockdev(bdev); mutex_lock(&disk->open_mutex); bdev_yield_write_access(bdev_file); if (holder) bd_yield_claim(bdev_file); /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE * event. This is to ensure detection of media removal commanded * from userland - e.g. eject(1). */ disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE); if (bdev_is_partition(bdev)) blkdev_put_part(bdev); else blkdev_put_whole(bdev); mutex_unlock(&disk->open_mutex); module_put(disk->fops->owner); put_no_open: blkdev_put_no_open(bdev); } /** * bdev_fput - yield claim to the block device and put the file * @bdev_file: open block device * * Yield claim on the block device and put the file. Ensure that the * block device can be reclaimed before the file is closed which is a * deferred operation. */ void bdev_fput(struct file *bdev_file) { if (WARN_ON_ONCE(bdev_file->f_op != &def_blk_fops)) return; if (bdev_file->private_data) { struct block_device *bdev = file_bdev(bdev_file); struct gendisk *disk = bdev->bd_disk; mutex_lock(&disk->open_mutex); bdev_yield_write_access(bdev_file); bd_yield_claim(bdev_file); /* * Tell release we already gave up our hold on the * device and if write restrictions are available that * we already gave up write access to the device. */ bdev_file->private_data = BDEV_I(bdev_file->f_mapping->host); mutex_unlock(&disk->open_mutex); } fput(bdev_file); } EXPORT_SYMBOL(bdev_fput); /** * lookup_bdev() - Look up a struct block_device by name. * @pathname: Name of the block device in the filesystem. * @dev: Pointer to the block device's dev_t, if found. * * Lookup the block device's dev_t at @pathname in the current * namespace if possible and return it in @dev. * * Context: May sleep. * Return: 0 if succeeded, negative errno otherwise. */ int lookup_bdev(const char *pathname, dev_t *dev) { struct inode *inode; struct path path; int error; if (!pathname || !*pathname) return -EINVAL; error = kern_path(pathname, LOOKUP_FOLLOW, &path); if (error) return error; inode = d_backing_inode(path.dentry); error = -ENOTBLK; if (!S_ISBLK(inode->i_mode)) goto out_path_put; error = -EACCES; if (!may_open_dev(&path)) goto out_path_put; *dev = inode->i_rdev; error = 0; out_path_put: path_put(&path); return error; } EXPORT_SYMBOL(lookup_bdev); /** * bdev_mark_dead - mark a block device as dead * @bdev: block device to operate on * @surprise: indicate a surprise removal * * Tell the file system that this devices or media is dead. If @surprise is set * to %true the device or media is already gone, if not we are preparing for an * orderly removal. * * This calls into the file system, which then typicall syncs out all dirty data * and writes back inodes and then invalidates any cached data in the inodes on * the file system. In addition we also invalidate the block device mapping. */ void bdev_mark_dead(struct block_device *bdev, bool surprise) { mutex_lock(&bdev->bd_holder_lock); if (bdev->bd_holder_ops && bdev->bd_holder_ops->mark_dead) bdev->bd_holder_ops->mark_dead(bdev, surprise); else { mutex_unlock(&bdev->bd_holder_lock); sync_blockdev(bdev); } invalidate_bdev(bdev); } /* * New drivers should not use this directly. There are some drivers however * that needs this for historical reasons. For example, the DASD driver has * historically had a shutdown to offline mode that doesn't actually remove the * gendisk that otherwise looks a lot like a safe device removal. */ EXPORT_SYMBOL_GPL(bdev_mark_dead); void sync_bdevs(bool wait) { struct inode *inode, *old_inode = NULL; spin_lock(&blockdev_superblock->s_inode_list_lock); list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { struct address_space *mapping = inode->i_mapping; struct block_device *bdev; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || mapping->nrpages == 0) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&blockdev_superblock->s_inode_list_lock); /* * 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. */ iput(old_inode); old_inode = inode; bdev = I_BDEV(inode); mutex_lock(&bdev->bd_disk->open_mutex); if (!atomic_read(&bdev->bd_openers)) { ; /* skip */ } else if (wait) { /* * We keep the error status of individual mapping so * that applications can catch the writeback error using * fsync(2). See filemap_fdatawait_keep_errors() for * details. */ filemap_fdatawait_keep_errors(inode->i_mapping); } else { filemap_fdatawrite(inode->i_mapping); } mutex_unlock(&bdev->bd_disk->open_mutex); spin_lock(&blockdev_superblock->s_inode_list_lock); } spin_unlock(&blockdev_superblock->s_inode_list_lock); iput(old_inode); } /* * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices. */ void bdev_statx(struct path *path, struct kstat *stat, u32 request_mask) { struct inode *backing_inode; struct block_device *bdev; if (!(request_mask & (STATX_DIOALIGN | STATX_WRITE_ATOMIC))) return; backing_inode = d_backing_inode(path->dentry); /* * Note that backing_inode is the inode of a block device node file, * not the block device's internal inode. Therefore it is *not* valid * to use I_BDEV() here; the block device has to be looked up by i_rdev * instead. */ bdev = blkdev_get_no_open(backing_inode->i_rdev); if (!bdev) return; if (request_mask & STATX_DIOALIGN) { stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; stat->dio_offset_align = bdev_logical_block_size(bdev); stat->result_mask |= STATX_DIOALIGN; } if (request_mask & STATX_WRITE_ATOMIC && bdev_can_atomic_write(bdev)) { struct request_queue *bd_queue = bdev->bd_queue; generic_fill_statx_atomic_writes(stat, queue_atomic_write_unit_min_bytes(bd_queue), queue_atomic_write_unit_max_bytes(bd_queue)); } blkdev_put_no_open(bdev); } bool disk_live(struct gendisk *disk) { return !inode_unhashed(BD_INODE(disk->part0)); } EXPORT_SYMBOL_GPL(disk_live); unsigned int block_size(struct block_device *bdev) { return 1 << BD_INODE(bdev)->i_blkbits; } EXPORT_SYMBOL_GPL(block_size); static int __init setup_bdev_allow_write_mounted(char *str) { if (kstrtobool(str, &bdev_allow_write_mounted)) pr_warn("Invalid option string for bdev_allow_write_mounted:" " '%s'\n", str); return 1; } __setup("bdev_allow_write_mounted=", setup_bdev_allow_write_mounted); |
| 1 234 236 233 199 17 124 123 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * * Copyright (C) 2011 Novell Inc. * Copyright (C) 2016 Red Hat, Inc. */ struct ovl_config { char *upperdir; char *workdir; char **lowerdirs; bool default_permissions; int redirect_mode; int verity_mode; bool index; int uuid; bool nfs_export; int xino; bool metacopy; bool userxattr; bool ovl_volatile; }; struct ovl_sb { struct super_block *sb; dev_t pseudo_dev; /* Unusable (conflicting) uuid */ bool bad_uuid; /* Used as a lower layer (but maybe also as upper) */ bool is_lower; }; struct ovl_layer { /* ovl_free_fs() relies on @mnt being the first member! */ struct vfsmount *mnt; /* Trap in ovl inode cache */ struct inode *trap; struct ovl_sb *fs; /* Index of this layer in fs root (upper idx == 0) */ int idx; /* One fsid per unique underlying sb (upper fsid == 0) */ int fsid; /* xwhiteouts were found on this layer */ bool has_xwhiteouts; }; struct ovl_path { const struct ovl_layer *layer; struct dentry *dentry; }; struct ovl_entry { unsigned int __numlower; struct ovl_path __lowerstack[]; }; /* private information held for overlayfs's superblock */ struct ovl_fs { unsigned int numlayer; /* Number of unique fs among layers including upper fs */ unsigned int numfs; /* Number of data-only lower layers */ unsigned int numdatalayer; struct ovl_layer *layers; struct ovl_sb *fs; /* workbasedir is the path at workdir= mount option */ struct dentry *workbasedir; /* workdir is the 'work' or 'index' directory under workbasedir */ struct dentry *workdir; long namelen; /* pathnames of lower and upper dirs, for show_options */ struct ovl_config config; /* creds of process who forced instantiation of super block */ const struct cred *creator_cred; bool tmpfile; bool noxattr; bool nofh; /* Did we take the inuse lock? */ bool upperdir_locked; bool workdir_locked; /* Traps in ovl inode cache */ struct inode *workbasedir_trap; struct inode *workdir_trap; /* -1: disabled, 0: same fs, 1..32: number of unused ino bits */ int xino_mode; /* For allocation of non-persistent inode numbers */ atomic_long_t last_ino; /* Shared whiteout cache */ struct dentry *whiteout; bool no_shared_whiteout; /* r/o snapshot of upperdir sb's only taken on volatile mounts */ errseq_t errseq; }; /* Number of lower layers, not including data-only layers */ static inline unsigned int ovl_numlowerlayer(struct ovl_fs *ofs) { return ofs->numlayer - ofs->numdatalayer - 1; } static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs) { return ofs->layers[0].mnt; } static inline struct mnt_idmap *ovl_upper_mnt_idmap(struct ovl_fs *ofs) { return mnt_idmap(ovl_upper_mnt(ofs)); } extern struct file_system_type ovl_fs_type; static inline struct ovl_fs *OVL_FS(struct super_block *sb) { if (IS_ENABLED(CONFIG_OVERLAY_FS_DEBUG)) WARN_ON_ONCE(sb->s_type != &ovl_fs_type); return (struct ovl_fs *)sb->s_fs_info; } static inline bool ovl_should_sync(struct ovl_fs *ofs) { return !ofs->config.ovl_volatile; } static inline unsigned int ovl_numlower(struct ovl_entry *oe) { return oe ? oe->__numlower : 0; } static inline struct ovl_path *ovl_lowerstack(struct ovl_entry *oe) { return ovl_numlower(oe) ? oe->__lowerstack : NULL; } static inline struct ovl_path *ovl_lowerpath(struct ovl_entry *oe) { return ovl_lowerstack(oe); } static inline struct ovl_path *ovl_lowerdata(struct ovl_entry *oe) { struct ovl_path *lowerstack = ovl_lowerstack(oe); return lowerstack ? &lowerstack[oe->__numlower - 1] : NULL; } /* May return NULL if lazy lookup of lowerdata is needed */ static inline struct dentry *ovl_lowerdata_dentry(struct ovl_entry *oe) { struct ovl_path *lowerdata = ovl_lowerdata(oe); return lowerdata ? READ_ONCE(lowerdata->dentry) : NULL; } /* private information held for every overlayfs dentry */ static inline unsigned long *OVL_E_FLAGS(struct dentry *dentry) { return (unsigned long *) &dentry->d_fsdata; } struct ovl_inode { union { struct ovl_dir_cache *cache; /* directory */ const char *lowerdata_redirect; /* regular file */ }; const char *redirect; u64 version; unsigned long flags; struct inode vfs_inode; struct dentry *__upperdentry; struct ovl_entry *oe; /* synchronize copy up and more */ struct mutex lock; }; static inline struct ovl_inode *OVL_I(struct inode *inode) { return container_of(inode, struct ovl_inode, vfs_inode); } static inline struct ovl_entry *OVL_I_E(struct inode *inode) { return inode ? OVL_I(inode)->oe : NULL; } static inline struct ovl_entry *OVL_E(struct dentry *dentry) { return OVL_I_E(d_inode(dentry)); } static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi) { return READ_ONCE(oi->__upperdentry); } |
| 495 495 3 81 1 123 3 8 483 487 483 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 */ #ifndef BTRFS_EXTENT_IO_H #define BTRFS_EXTENT_IO_H #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/fiemap.h> #include <linux/btrfs_tree.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/rwsem.h> #include <linux/list.h> #include <linux/slab.h> #include "compression.h" #include "messages.h" #include "ulist.h" #include "misc.h" struct page; struct file; struct folio; struct inode; struct fiemap_extent_info; struct readahead_control; struct address_space; struct writeback_control; struct extent_io_tree; struct extent_map_tree; struct extent_state; struct btrfs_block_group; struct btrfs_fs_info; struct btrfs_inode; struct btrfs_root; struct btrfs_trans_handle; struct btrfs_tree_parent_check; enum { EXTENT_BUFFER_UPTODATE, EXTENT_BUFFER_DIRTY, EXTENT_BUFFER_CORRUPT, /* this got triggered by readahead */ EXTENT_BUFFER_READAHEAD, EXTENT_BUFFER_TREE_REF, EXTENT_BUFFER_STALE, EXTENT_BUFFER_WRITEBACK, /* read IO error */ EXTENT_BUFFER_READ_ERR, EXTENT_BUFFER_UNMAPPED, EXTENT_BUFFER_IN_TREE, /* write IO error */ EXTENT_BUFFER_WRITE_ERR, /* Indicate the extent buffer is written zeroed out (for zoned) */ EXTENT_BUFFER_ZONED_ZEROOUT, /* Indicate that extent buffer pages a being read */ EXTENT_BUFFER_READING, }; /* these are flags for __process_pages_contig */ enum { ENUM_BIT(PAGE_UNLOCK), /* Page starts writeback, clear dirty bit and set writeback bit */ ENUM_BIT(PAGE_START_WRITEBACK), ENUM_BIT(PAGE_END_WRITEBACK), ENUM_BIT(PAGE_SET_ORDERED), }; /* * Folio private values. Every page that is controlled by the extent map has * folio private set to this value. */ #define EXTENT_FOLIO_PRIVATE 1 /* * The extent buffer bitmap operations are done with byte granularity instead of * word granularity for two reasons: * 1. The bitmaps must be little-endian on disk. * 2. Bitmap items are not guaranteed to be aligned to a word and therefore a * single word in a bitmap may straddle two pages in the extent buffer. */ #define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE) #define BYTE_MASK ((1 << BITS_PER_BYTE) - 1) #define BITMAP_FIRST_BYTE_MASK(start) \ ((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK) #define BITMAP_LAST_BYTE_MASK(nbits) \ (BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1))) int __init extent_buffer_init_cachep(void); void __cold extent_buffer_free_cachep(void); #define INLINE_EXTENT_BUFFER_PAGES (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE) struct extent_buffer { u64 start; u32 len; u32 folio_size; unsigned long bflags; struct btrfs_fs_info *fs_info; /* * The address where the eb can be accessed without any cross-page handling. * This can be NULL if not possible. */ void *addr; spinlock_t refs_lock; atomic_t refs; int read_mirror; /* >= 0 if eb belongs to a log tree, -1 otherwise */ s8 log_index; u8 folio_shift; struct rcu_head rcu_head; struct rw_semaphore lock; /* * Pointers to all the folios of the extent buffer. * * For now the folio is always order 0 (aka, a single page). */ struct folio *folios[INLINE_EXTENT_BUFFER_PAGES]; #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; pid_t lock_owner; #endif }; struct btrfs_eb_write_context { struct writeback_control *wbc; struct extent_buffer *eb; /* Block group @eb resides in. Only used for zoned mode. */ struct btrfs_block_group *zoned_bg; }; static inline unsigned long offset_in_eb_folio(const struct extent_buffer *eb, u64 start) { ASSERT(eb->folio_size); return start & (eb->folio_size - 1); } /* * Get the correct offset inside the page of extent buffer. * * @eb: target extent buffer * @start: offset inside the extent buffer * * Will handle both sectorsize == PAGE_SIZE and sectorsize < PAGE_SIZE cases. */ static inline size_t get_eb_offset_in_folio(const struct extent_buffer *eb, unsigned long offset) { /* * 1) sectorsize == PAGE_SIZE and nodesize >= PAGE_SIZE case * 1.1) One large folio covering the whole eb * The eb->start is aligned to folio size, thus adding it * won't cause any difference. * 1.2) Several page sized folios * The eb->start is aligned to folio (page) size, thus * adding it won't cause any difference. * * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case * In this case there would only be one page sized folio, and there * may be several different extent buffers in the page/folio. * We need to add eb->start to properly access the offset inside * that eb. */ return offset_in_folio(eb->folios[0], offset + eb->start); } static inline unsigned long get_eb_folio_index(const struct extent_buffer *eb, unsigned long offset) { /* * 1) sectorsize == PAGE_SIZE and nodesize >= PAGE_SIZE case * 1.1) One large folio covering the whole eb. * the folio_shift would be large enough to always make us * return 0 as index. * 1.2) Several page sized folios * The folio_shift would be PAGE_SHIFT, giving us the correct * index. * * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case * The folio would only be page sized, and always give us 0 as index. */ return offset >> eb->folio_shift; } /* * Structure to record how many bytes and which ranges are set/cleared */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ u64 bytes_changed; /* Changed ranges */ struct ulist range_changed; }; static inline void extent_changeset_init(struct extent_changeset *changeset) { changeset->bytes_changed = 0; ulist_init(&changeset->range_changed); } static inline struct extent_changeset *extent_changeset_alloc(void) { struct extent_changeset *ret; ret = kmalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; extent_changeset_init(ret); return ret; } static inline void extent_changeset_prealloc(struct extent_changeset *changeset, gfp_t gfp_mask) { ulist_prealloc(&changeset->range_changed, gfp_mask); } static inline void extent_changeset_release(struct extent_changeset *changeset) { if (!changeset) return; changeset->bytes_changed = 0; ulist_release(&changeset->range_changed); } static inline void extent_changeset_free(struct extent_changeset *changeset) { if (!changeset) return; extent_changeset_release(changeset); kfree(changeset); } bool try_release_extent_mapping(struct folio *folio, gfp_t mask); int try_release_extent_buffer(struct folio *folio); int btrfs_read_folio(struct file *file, struct folio *folio); void extent_write_locked_range(struct inode *inode, const struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty); int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc); int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc); void btrfs_readahead(struct readahead_control *rac); int set_folio_extent_mapped(struct folio *folio); void clear_folio_extent_mapped(struct folio *folio); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level); struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, unsigned long len); struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, u64 start); struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src); struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, u64 start); void free_extent_buffer(struct extent_buffer *eb); void free_extent_buffer_stale(struct extent_buffer *eb); int read_extent_buffer_pages(struct extent_buffer *eb, int mirror_num, const struct btrfs_tree_parent_check *parent_check); int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, const struct btrfs_tree_parent_check *parent_check); static inline void wait_on_extent_buffer_writeback(struct extent_buffer *eb) { wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK, TASK_UNINTERRUPTIBLE); } void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u64 owner_root, u64 gen, int level); void btrfs_readahead_node_child(struct extent_buffer *node, int slot); static inline int num_extent_pages(const struct extent_buffer *eb) { /* * For sectorsize == PAGE_SIZE case, since nodesize is always aligned to * sectorsize, it's just eb->len >> PAGE_SHIFT. * * For sectorsize < PAGE_SIZE case, we could have nodesize < PAGE_SIZE, * thus have to ensure we get at least one page. */ return (eb->len >> PAGE_SHIFT) ?: 1; } /* * This can only be determined at runtime by checking eb::folios[0]. * * As we can have either one large folio covering the whole eb * (either nodesize <= PAGE_SIZE, or high order folio), or multiple * single-paged folios. */ static inline int num_extent_folios(const struct extent_buffer *eb) { if (folio_order(eb->folios[0])) return 1; return num_extent_pages(eb); } static inline int extent_buffer_uptodate(const struct extent_buffer *eb) { return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); } int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, unsigned long start, unsigned long len); void read_extent_buffer(const struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, void __user *dst, unsigned long start, unsigned long len); void write_extent_buffer(const struct extent_buffer *eb, const void *src, unsigned long start, unsigned long len); static inline void write_extent_buffer_chunk_tree_uuid( const struct extent_buffer *eb, const void *chunk_tree_uuid) { write_extent_buffer(eb, chunk_tree_uuid, offsetof(struct btrfs_header, chunk_tree_uuid), BTRFS_FSID_SIZE); } static inline void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *fsid) { write_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid), BTRFS_FSID_SIZE); } void copy_extent_buffer_full(const struct extent_buffer *dst, const struct extent_buffer *src); void copy_extent_buffer(const struct extent_buffer *dst, const struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, unsigned long len); void memcpy_extent_buffer(const struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_offset, unsigned long len); void memmove_extent_buffer(const struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_offset, unsigned long len); void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start, unsigned long len); int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start, unsigned long pos); void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start, unsigned long pos, unsigned long len); void extent_buffer_bitmap_clear(const struct extent_buffer *eb, unsigned long start, unsigned long pos, unsigned long len); void set_extent_buffer_dirty(struct extent_buffer *eb); void set_extent_buffer_uptodate(struct extent_buffer *eb); void clear_extent_buffer_uptodate(struct extent_buffer *eb); void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, const struct folio *locked_folio, struct extent_state **cached, u32 bits_to_clear, unsigned long page_ops); int extent_invalidate_folio(struct extent_io_tree *tree, struct folio *folio, size_t offset); void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans, struct extent_buffer *buf); int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, bool nofail); int btrfs_alloc_folio_array(unsigned int nr_folios, struct folio **folio_array); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS bool find_lock_delalloc_range(struct inode *inode, struct folio *locked_folio, u64 *start, u64 *end); #endif struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, u64 start); #ifdef CONFIG_BTRFS_DEBUG void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info); #else #define btrfs_extent_buffer_leak_debug_check(fs_info) do {} while (0) #endif #endif |
| 191 103 46 252 252 246 191 185 191 188 114 240 89 85 36 76 139 151 240 230 222 14 3 77 125 89 86 87 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_BSET_H #define _BCACHEFS_BSET_H #include <linux/kernel.h> #include <linux/types.h> #include "bcachefs.h" #include "bkey.h" #include "bkey_methods.h" #include "btree_types.h" #include "util.h" /* for time_stats */ #include "vstructs.h" /* * BKEYS: * * A bkey contains a key, a size field, a variable number of pointers, and some * ancillary flag bits. * * We use two different functions for validating bkeys, bkey_invalid and * bkey_deleted(). * * The one exception to the rule that ptr_invalid() filters out invalid keys is * that it also filters out keys of size 0 - these are keys that have been * completely overwritten. It'd be safe to delete these in memory while leaving * them on disk, just unnecessary work - so we filter them out when resorting * instead. * * We can't filter out stale keys when we're resorting, because garbage * collection needs to find them to ensure bucket gens don't wrap around - * unless we're rewriting the btree node those stale keys still exist on disk. * * We also implement functions here for removing some number of sectors from the * front or the back of a bkey - this is mainly used for fixing overlapping * extents, by removing the overlapping sectors from the older key. * * BSETS: * * A bset is an array of bkeys laid out contiguously in memory in sorted order, * along with a header. A btree node is made up of a number of these, written at * different times. * * There could be many of them on disk, but we never allow there to be more than * 4 in memory - we lazily resort as needed. * * We implement code here for creating and maintaining auxiliary search trees * (described below) for searching an individial bset, and on top of that we * implement a btree iterator. * * BTREE ITERATOR: * * Most of the code in bcache doesn't care about an individual bset - it needs * to search entire btree nodes and iterate over them in sorted order. * * The btree iterator code serves both functions; it iterates through the keys * in a btree node in sorted order, starting from either keys after a specific * point (if you pass it a search key) or the start of the btree node. * * AUXILIARY SEARCH TREES: * * Since keys are variable length, we can't use a binary search on a bset - we * wouldn't be able to find the start of the next key. But binary searches are * slow anyways, due to terrible cache behaviour; bcache originally used binary * searches and that code topped out at under 50k lookups/second. * * So we need to construct some sort of lookup table. Since we only insert keys * into the last (unwritten) set, most of the keys within a given btree node are * usually in sets that are mostly constant. We use two different types of * lookup tables to take advantage of this. * * Both lookup tables share in common that they don't index every key in the * set; they index one key every BSET_CACHELINE bytes, and then a linear search * is used for the rest. * * For sets that have been written to disk and are no longer being inserted * into, we construct a binary search tree in an array - traversing a binary * search tree in an array gives excellent locality of reference and is very * fast, since both children of any node are adjacent to each other in memory * (and their grandchildren, and great grandchildren...) - this means * prefetching can be used to great effect. * * It's quite useful performance wise to keep these nodes small - not just * because they're more likely to be in L2, but also because we can prefetch * more nodes on a single cacheline and thus prefetch more iterations in advance * when traversing this tree. * * Nodes in the auxiliary search tree must contain both a key to compare against * (we don't want to fetch the key from the set, that would defeat the purpose), * and a pointer to the key. We use a few tricks to compress both of these. * * To compress the pointer, we take advantage of the fact that one node in the * search tree corresponds to precisely BSET_CACHELINE bytes in the set. We have * a function (to_inorder()) that takes the index of a node in a binary tree and * returns what its index would be in an inorder traversal, so we only have to * store the low bits of the offset. * * The key is 84 bits (KEY_DEV + key->key, the offset on the device). To * compress that, we take advantage of the fact that when we're traversing the * search tree at every iteration we know that both our search key and the key * we're looking for lie within some range - bounded by our previous * comparisons. (We special case the start of a search so that this is true even * at the root of the tree). * * So we know the key we're looking for is between a and b, and a and b don't * differ higher than bit 50, we don't need to check anything higher than bit * 50. * * We don't usually need the rest of the bits, either; we only need enough bits * to partition the key range we're currently checking. Consider key n - the * key our auxiliary search tree node corresponds to, and key p, the key * immediately preceding n. The lowest bit we need to store in the auxiliary * search tree is the highest bit that differs between n and p. * * Note that this could be bit 0 - we might sometimes need all 80 bits to do the * comparison. But we'd really like our nodes in the auxiliary search tree to be * of fixed size. * * The solution is to make them fixed size, and when we're constructing a node * check if p and n differed in the bits we needed them to. If they don't we * flag that node, and when doing lookups we fallback to comparing against the * real key. As long as this doesn't happen to often (and it seems to reliably * happen a bit less than 1% of the time), we win - even on failures, that key * is then more likely to be in cache than if we were doing binary searches all * the way, since we're touching so much less memory. * * The keys in the auxiliary search tree are stored in (software) floating * point, with an exponent and a mantissa. The exponent needs to be big enough * to address all the bits in the original key, but the number of bits in the * mantissa is somewhat arbitrary; more bits just gets us fewer failures. * * We need 7 bits for the exponent and 3 bits for the key's offset (since keys * are 8 byte aligned); using 22 bits for the mantissa means a node is 4 bytes. * We need one node per 128 bytes in the btree node, which means the auxiliary * search trees take up 3% as much memory as the btree itself. * * Constructing these auxiliary search trees is moderately expensive, and we * don't want to be constantly rebuilding the search tree for the last set * whenever we insert another key into it. For the unwritten set, we use a much * simpler lookup table - it's just a flat array, so index i in the lookup table * corresponds to the i range of BSET_CACHELINE bytes in the set. Indexing * within each byte range works the same as with the auxiliary search trees. * * These are much easier to keep up to date when we insert a key - we do it * somewhat lazily; when we shift a key up we usually just increment the pointer * to it, only when it would overflow do we go to the trouble of finding the * first key in that range of bytes again. */ enum bset_aux_tree_type { BSET_NO_AUX_TREE, BSET_RO_AUX_TREE, BSET_RW_AUX_TREE, }; #define BSET_TREE_NR_TYPES 3 #define BSET_NO_AUX_TREE_VAL (U16_MAX) #define BSET_RW_AUX_TREE_VAL (U16_MAX - 1) static inline enum bset_aux_tree_type bset_aux_tree_type(const struct bset_tree *t) { switch (t->extra) { case BSET_NO_AUX_TREE_VAL: EBUG_ON(t->size); return BSET_NO_AUX_TREE; case BSET_RW_AUX_TREE_VAL: EBUG_ON(!t->size); return BSET_RW_AUX_TREE; default: EBUG_ON(!t->size); return BSET_RO_AUX_TREE; } } /* * BSET_CACHELINE was originally intended to match the hardware cacheline size - * it used to be 64, but I realized the lookup code would touch slightly less * memory if it was 128. * * It definites the number of bytes (in struct bset) per struct bkey_float in * the auxiliar search tree - when we're done searching the bset_float tree we * have this many bytes left that we do a linear search over. * * Since (after level 5) every level of the bset_tree is on a new cacheline, * we're touching one fewer cacheline in the bset tree in exchange for one more * cacheline in the linear search - but the linear search might stop before it * gets to the second cacheline. */ #define BSET_CACHELINE 256 static inline size_t btree_keys_cachelines(const struct btree *b) { return (1U << b->byte_order) / BSET_CACHELINE; } static inline size_t btree_aux_data_bytes(const struct btree *b) { return btree_keys_cachelines(b) * 8; } static inline size_t btree_aux_data_u64s(const struct btree *b) { return btree_aux_data_bytes(b) / sizeof(u64); } #define for_each_bset(_b, _t) \ for (struct bset_tree *_t = (_b)->set; _t < (_b)->set + (_b)->nsets; _t++) #define for_each_bset_c(_b, _t) \ for (const struct bset_tree *_t = (_b)->set; _t < (_b)->set + (_b)->nsets; _t++) #define bset_tree_for_each_key(_b, _t, _k) \ for (_k = btree_bkey_first(_b, _t); \ _k != btree_bkey_last(_b, _t); \ _k = bkey_p_next(_k)) static inline bool bset_has_ro_aux_tree(const struct bset_tree *t) { return bset_aux_tree_type(t) == BSET_RO_AUX_TREE; } static inline bool bset_has_rw_aux_tree(struct bset_tree *t) { return bset_aux_tree_type(t) == BSET_RW_AUX_TREE; } static inline void bch2_bset_set_no_aux_tree(struct btree *b, struct bset_tree *t) { BUG_ON(t < b->set); for (; t < b->set + ARRAY_SIZE(b->set); t++) { t->size = 0; t->extra = BSET_NO_AUX_TREE_VAL; t->aux_data_offset = U16_MAX; } } static inline void btree_node_set_format(struct btree *b, struct bkey_format f) { int len; b->format = f; b->nr_key_bits = bkey_format_key_bits(&f); len = bch2_compile_bkey_format(&b->format, b->aux_data); BUG_ON(len < 0 || len > U8_MAX); b->unpack_fn_len = len; bch2_bset_set_no_aux_tree(b, b->set); } static inline struct bset *bset_next_set(struct btree *b, unsigned block_bytes) { struct bset *i = btree_bset_last(b); EBUG_ON(!is_power_of_2(block_bytes)); return ((void *) i) + round_up(vstruct_bytes(i), block_bytes); } void bch2_btree_keys_init(struct btree *); void bch2_bset_init_first(struct btree *, struct bset *); void bch2_bset_init_next(struct btree *, struct btree_node_entry *); void bch2_bset_build_aux_tree(struct btree *, struct bset_tree *, bool); void bch2_bset_insert(struct btree *, struct bkey_packed *, struct bkey_i *, unsigned); void bch2_bset_delete(struct btree *, struct bkey_packed *, unsigned); /* Bkey utility code */ /* packed or unpacked */ static inline int bkey_cmp_p_or_unp(const struct btree *b, const struct bkey_packed *l, const struct bkey_packed *r_packed, const struct bpos *r) { EBUG_ON(r_packed && !bkey_packed(r_packed)); if (unlikely(!bkey_packed(l))) return bpos_cmp(packed_to_bkey_c(l)->p, *r); if (likely(r_packed)) return __bch2_bkey_cmp_packed_format_checked(l, r_packed, b); return __bch2_bkey_cmp_left_packed_format_checked(b, l, r); } static inline struct bset_tree * bch2_bkey_to_bset_inlined(struct btree *b, struct bkey_packed *k) { unsigned offset = __btree_node_key_to_offset(b, k); for_each_bset(b, t) if (offset <= t->end_offset) { EBUG_ON(offset < btree_bkey_first_offset(t)); return t; } BUG(); } struct bset_tree *bch2_bkey_to_bset(struct btree *, struct bkey_packed *); struct bkey_packed *bch2_bkey_prev_filter(struct btree *, struct bset_tree *, struct bkey_packed *, unsigned); static inline struct bkey_packed * bch2_bkey_prev_all(struct btree *b, struct bset_tree *t, struct bkey_packed *k) { return bch2_bkey_prev_filter(b, t, k, 0); } static inline struct bkey_packed * bch2_bkey_prev(struct btree *b, struct bset_tree *t, struct bkey_packed *k) { return bch2_bkey_prev_filter(b, t, k, 1); } /* Btree key iteration */ void bch2_btree_node_iter_push(struct btree_node_iter *, struct btree *, const struct bkey_packed *, const struct bkey_packed *); void bch2_btree_node_iter_init(struct btree_node_iter *, struct btree *, struct bpos *); void bch2_btree_node_iter_init_from_start(struct btree_node_iter *, struct btree *); struct bkey_packed *bch2_btree_node_iter_bset_pos(struct btree_node_iter *, struct btree *, struct bset_tree *); void bch2_btree_node_iter_sort(struct btree_node_iter *, struct btree *); void bch2_btree_node_iter_set_drop(struct btree_node_iter *, struct btree_node_iter_set *); void bch2_btree_node_iter_advance(struct btree_node_iter *, struct btree *); #define btree_node_iter_for_each(_iter, _set) \ for (_set = (_iter)->data; \ _set < (_iter)->data + ARRAY_SIZE((_iter)->data) && \ (_set)->k != (_set)->end; \ _set++) static inline bool __btree_node_iter_set_end(struct btree_node_iter *iter, unsigned i) { return iter->data[i].k == iter->data[i].end; } static inline bool bch2_btree_node_iter_end(struct btree_node_iter *iter) { return __btree_node_iter_set_end(iter, 0); } /* * When keys compare equal, deleted keys compare first: * * XXX: only need to compare pointers for keys that are both within a * btree_node_iterator - we need to break ties for prev() to work correctly */ static inline int bkey_iter_cmp(const struct btree *b, const struct bkey_packed *l, const struct bkey_packed *r) { return bch2_bkey_cmp_packed(b, l, r) ?: (int) bkey_deleted(r) - (int) bkey_deleted(l) ?: cmp_int(l, r); } static inline int btree_node_iter_cmp(const struct btree *b, struct btree_node_iter_set l, struct btree_node_iter_set r) { return bkey_iter_cmp(b, __btree_node_offset_to_key(b, l.k), __btree_node_offset_to_key(b, r.k)); } /* These assume r (the search key) is not a deleted key: */ static inline int bkey_iter_pos_cmp(const struct btree *b, const struct bkey_packed *l, const struct bpos *r) { return bkey_cmp_left_packed(b, l, r) ?: -((int) bkey_deleted(l)); } static inline int bkey_iter_cmp_p_or_unp(const struct btree *b, const struct bkey_packed *l, const struct bkey_packed *r_packed, const struct bpos *r) { return bkey_cmp_p_or_unp(b, l, r_packed, r) ?: -((int) bkey_deleted(l)); } static inline struct bkey_packed * __bch2_btree_node_iter_peek_all(struct btree_node_iter *iter, struct btree *b) { return __btree_node_offset_to_key(b, iter->data->k); } static inline struct bkey_packed * bch2_btree_node_iter_peek_all(struct btree_node_iter *iter, struct btree *b) { return !bch2_btree_node_iter_end(iter) ? __btree_node_offset_to_key(b, iter->data->k) : NULL; } static inline struct bkey_packed * bch2_btree_node_iter_peek(struct btree_node_iter *iter, struct btree *b) { struct bkey_packed *k; while ((k = bch2_btree_node_iter_peek_all(iter, b)) && bkey_deleted(k)) bch2_btree_node_iter_advance(iter, b); return k; } static inline struct bkey_packed * bch2_btree_node_iter_next_all(struct btree_node_iter *iter, struct btree *b) { struct bkey_packed *ret = bch2_btree_node_iter_peek_all(iter, b); if (ret) bch2_btree_node_iter_advance(iter, b); return ret; } struct bkey_packed *bch2_btree_node_iter_prev_all(struct btree_node_iter *, struct btree *); struct bkey_packed *bch2_btree_node_iter_prev(struct btree_node_iter *, struct btree *); struct bkey_s_c bch2_btree_node_iter_peek_unpack(struct btree_node_iter *, struct btree *, struct bkey *); #define for_each_btree_node_key(b, k, iter) \ for (bch2_btree_node_iter_init_from_start((iter), (b)); \ (k = bch2_btree_node_iter_peek((iter), (b))); \ bch2_btree_node_iter_advance(iter, b)) #define for_each_btree_node_key_unpack(b, k, iter, unpacked) \ for (bch2_btree_node_iter_init_from_start((iter), (b)); \ (k = bch2_btree_node_iter_peek_unpack((iter), (b), (unpacked))).k;\ bch2_btree_node_iter_advance(iter, b)) /* Accounting: */ struct btree_nr_keys bch2_btree_node_count_keys(struct btree *); static inline void btree_keys_account_key(struct btree_nr_keys *n, unsigned bset, struct bkey_packed *k, int sign) { n->live_u64s += k->u64s * sign; n->bset_u64s[bset] += k->u64s * sign; if (bkey_packed(k)) n->packed_keys += sign; else n->unpacked_keys += sign; } static inline void btree_keys_account_val_delta(struct btree *b, struct bkey_packed *k, int delta) { struct bset_tree *t = bch2_bkey_to_bset(b, k); b->nr.live_u64s += delta; b->nr.bset_u64s[t - b->set] += delta; } #define btree_keys_account_key_add(_nr, _bset_idx, _k) \ btree_keys_account_key(_nr, _bset_idx, _k, 1) #define btree_keys_account_key_drop(_nr, _bset_idx, _k) \ btree_keys_account_key(_nr, _bset_idx, _k, -1) #define btree_account_key_add(_b, _k) \ btree_keys_account_key(&(_b)->nr, \ bch2_bkey_to_bset(_b, _k) - (_b)->set, _k, 1) #define btree_account_key_drop(_b, _k) \ btree_keys_account_key(&(_b)->nr, \ bch2_bkey_to_bset(_b, _k) - (_b)->set, _k, -1) struct bset_stats { struct { size_t nr, bytes; } sets[BSET_TREE_NR_TYPES]; size_t floats; size_t failed; }; void bch2_btree_keys_stats(const struct btree *, struct bset_stats *); void bch2_bfloat_to_text(struct printbuf *, struct btree *, struct bkey_packed *); /* Debug stuff */ void bch2_dump_bset(struct bch_fs *, struct btree *, struct bset *, unsigned); void bch2_dump_btree_node(struct bch_fs *, struct btree *); void bch2_dump_btree_node_iter(struct btree *, struct btree_node_iter *); #ifdef CONFIG_BCACHEFS_DEBUG void __bch2_verify_btree_nr_keys(struct btree *); void bch2_btree_node_iter_verify(struct btree_node_iter *, struct btree *); void bch2_verify_insert_pos(struct btree *, struct bkey_packed *, struct bkey_packed *, unsigned); #else static inline void __bch2_verify_btree_nr_keys(struct btree *b) {} static inline void bch2_btree_node_iter_verify(struct btree_node_iter *iter, struct btree *b) {} static inline void bch2_verify_insert_pos(struct btree *b, struct bkey_packed *where, struct bkey_packed *insert, unsigned clobber_u64s) {} #endif static inline void bch2_verify_btree_nr_keys(struct btree *b) { if (bch2_debug_check_btree_accounting) __bch2_verify_btree_nr_keys(b); } #endif /* _BCACHEFS_BSET_H */ |
| 12 11 11 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 | /* * linux/fs/nls/mac-cyrillic.c * * Charset maccyrillic translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ /* * COPYRIGHT AND PERMISSION NOTICE * * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under * the Terms of Use in http://www.unicode.org/copyright.html. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of the Unicode data files and any associated documentation (the "Data * Files") or Unicode software and any associated documentation (the * "Software") to deal in the Data Files or Software without restriction, * including without limitation the rights to use, copy, modify, merge, * publish, distribute, and/or sell copies of the Data Files or Software, and * to permit persons to whom the Data Files or Software are furnished to do * so, provided that (a) the above copyright notice(s) and this permission * notice appear with all copies of the Data Files or Software, (b) both the * above copyright notice(s) and this permission notice appear in associated * documentation, and (c) there is clear notice in each modified Data File or * in the Software as well as in the documentation associated with the Data * File(s) or Software that the data or software has been modified. * * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR * PERFORMANCE OF THE DATA FILES OR SOFTWARE. * * Except as contained in this notice, the name of a copyright holder shall * not be used in advertising or otherwise to promote the sale, use or other * dealings in these Data Files or Software without prior written * authorization of the copyright holder. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00 */ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10 */ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20 */ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30 */ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40 */ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50 */ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60 */ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70 */ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80 */ 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f, /* 0x90 */ 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, 0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f, /* 0xa0 */ 0x2020, 0x00b0, 0x0490, 0x00a3, 0x00a7, 0x2022, 0x00b6, 0x0406, 0x00ae, 0x00a9, 0x2122, 0x0402, 0x0452, 0x2260, 0x0403, 0x0453, /* 0xb0 */ 0x221e, 0x00b1, 0x2264, 0x2265, 0x0456, 0x00b5, 0x0491, 0x0408, 0x0404, 0x0454, 0x0407, 0x0457, 0x0409, 0x0459, 0x040a, 0x045a, /* 0xc0 */ 0x0458, 0x0405, 0x00ac, 0x221a, 0x0192, 0x2248, 0x2206, 0x00ab, 0x00bb, 0x2026, 0x00a0, 0x040b, 0x045b, 0x040c, 0x045c, 0x0455, /* 0xd0 */ 0x2013, 0x2014, 0x201c, 0x201d, 0x2018, 0x2019, 0x00f7, 0x201e, 0x040e, 0x045e, 0x040f, 0x045f, 0x2116, 0x0401, 0x0451, 0x044f, /* 0xe0 */ 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, 0x043f, /* 0xf0 */ 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, 0x0448, 0x0449, 0x044a, 0x044b, 0x044c, 0x044d, 0x044e, 0x20ac, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xca, 0x00, 0x00, 0xa3, 0x00, 0x00, 0x00, 0xa4, /* 0xa0-0xa7 */ 0x00, 0xa9, 0x00, 0xc7, 0xc2, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ 0xa1, 0xb1, 0x00, 0x00, 0x00, 0xb5, 0xa6, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xc8, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd6, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page04[256] = { 0x00, 0xdd, 0xab, 0xae, 0xb8, 0xc1, 0xa7, 0xba, /* 0x00-0x07 */ 0xb7, 0xbc, 0xbe, 0xcb, 0xcd, 0x00, 0xd8, 0xda, /* 0x08-0x0f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x10-0x17 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x18-0x1f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x20-0x27 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x28-0x2f */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x30-0x37 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x38-0x3f */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0x40-0x47 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xdf, /* 0x48-0x4f */ 0x00, 0xde, 0xac, 0xaf, 0xb9, 0xcf, 0xb4, 0xbb, /* 0x50-0x57 */ 0xc0, 0xbd, 0xbf, 0xcc, 0xce, 0x00, 0xd9, 0xdb, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xa2, 0xb6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0xd7, 0x00, /* 0x18-0x1f */ 0xa0, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, NULL, page04, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, page21, page22, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "maccyrillic", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_maccyrillic(void) { return register_nls(&table); } static void __exit exit_nls_maccyrillic(void) { unregister_nls(&table); } module_init(init_nls_maccyrillic) module_exit(exit_nls_maccyrillic) MODULE_DESCRIPTION("NLS Codepage maccyrillic"); MODULE_LICENSE("Dual BSD/GPL"); |
| 6 6 137 109 93 92 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_BKEY_METHODS_H #define _BCACHEFS_BKEY_METHODS_H #include "bkey.h" struct bch_fs; struct btree; struct btree_trans; struct bkey; enum btree_node_type; extern const char * const bch2_bkey_types[]; extern const struct bkey_ops bch2_bkey_null_ops; /* * key_validate: checks validity of @k, returns 0 if good or -EINVAL if bad. If * invalid, entire key will be deleted. * * When invalid, error string is returned via @err. @rw indicates whether key is * being read or written; more aggressive checks can be enabled when rw == WRITE. */ struct bkey_ops { int (*key_validate)(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from); void (*val_to_text)(struct printbuf *, struct bch_fs *, struct bkey_s_c); void (*swab)(struct bkey_s); bool (*key_normalize)(struct bch_fs *, struct bkey_s); bool (*key_merge)(struct bch_fs *, struct bkey_s, struct bkey_s_c); int (*trigger)(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); void (*compat)(enum btree_id id, unsigned version, unsigned big_endian, int write, struct bkey_s); /* Size of value type when first created: */ unsigned min_val_size; }; extern const struct bkey_ops bch2_bkey_ops[]; static inline const struct bkey_ops *bch2_bkey_type_ops(enum bch_bkey_type type) { return likely(type < KEY_TYPE_MAX) ? &bch2_bkey_ops[type] : &bch2_bkey_null_ops; } int bch2_bkey_val_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); int __bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); int bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, struct bkey_validate_context); int bch2_bkey_in_btree_node(struct bch_fs *, struct btree *, struct bkey_s_c, struct bkey_validate_context from); void bch2_bpos_to_text(struct printbuf *, struct bpos); void bch2_bkey_to_text(struct printbuf *, const struct bkey *); void bch2_val_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_bkey_val_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_bkey_swab_val(struct bkey_s); bool bch2_bkey_normalize(struct bch_fs *, struct bkey_s); static inline bool bch2_bkey_maybe_mergable(const struct bkey *l, const struct bkey *r) { return l->type == r->type && !bversion_cmp(l->bversion, r->bversion) && bpos_eq(l->p, bkey_start_pos(r)); } bool bch2_bkey_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); static inline int bch2_key_trigger(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bkey_s_c old, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { const struct bkey_ops *ops = bch2_bkey_type_ops(old.k->type ?: new.k->type); return ops->trigger ? ops->trigger(trans, btree, level, old, new, flags) : 0; } static inline int bch2_key_trigger_old(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c old, enum btree_iter_update_trigger_flags flags) { struct bkey_i deleted; bkey_init(&deleted.k); deleted.k.p = old.k->p; return bch2_key_trigger(trans, btree_id, level, old, bkey_i_to_s(&deleted), BTREE_TRIGGER_overwrite|flags); } static inline int bch2_key_trigger_new(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { struct bkey_i deleted; bkey_init(&deleted.k); deleted.k.p = new.k->p; return bch2_key_trigger(trans, btree_id, level, bkey_i_to_s_c(&deleted), new, BTREE_TRIGGER_insert|flags); } void bch2_bkey_renumber(enum btree_node_type, struct bkey_packed *, int); void __bch2_bkey_compat(unsigned, enum btree_id, unsigned, unsigned, int, struct bkey_format *, struct bkey_packed *); static inline void bch2_bkey_compat(unsigned level, enum btree_id btree_id, unsigned version, unsigned big_endian, int write, struct bkey_format *f, struct bkey_packed *k) { if (version < bcachefs_metadata_version_current || big_endian != CPU_BIG_ENDIAN || IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) __bch2_bkey_compat(level, btree_id, version, big_endian, write, f, k); } #endif /* _BCACHEFS_BKEY_METHODS_H */ |
| 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 | // 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. * * Ethernet-type device handling. * * Version: @(#)eth.c 1.0.7 05/25/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Florian La Roche, <rzsfl@rz.uni-sb.de> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Mr Linux : Arp problems * Alan Cox : Generic queue tidyup (very tiny here) * Alan Cox : eth_header ntohs should be htons * Alan Cox : eth_rebuild_header missing an htons and * minor other things. * Tegge : Arp bug fixes. * Florian : Removed many unnecessary functions, code cleanup * and changes for new arp and skbuff. * Alan Cox : Redid header building to reflect new format. * Alan Cox : ARP only when compiled with CONFIG_INET * Greg Page : 802.2 and SNAP stuff. * Alan Cox : MAC layer pointers/new format. * Paul Gortmaker : eth_copy_and_sum shouldn't csum padding. * Alan Cox : Protect against forwarding explosions with * older network drivers and IFF_ALLMULTI. * Christer Weinigel : Better rebuild header message. * Andrew Morton : 26Feb01: kill ether_setup() - use netdev_boot_setup(). */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/nvmem-consumer.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/if_ether.h> #include <linux/of_net.h> #include <linux/pci.h> #include <linux/property.h> #include <net/dst.h> #include <net/arp.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/ip.h> #include <net/dsa.h> #include <net/flow_dissector.h> #include <net/gro.h> #include <linux/uaccess.h> #include <net/pkt_sched.h> /** * eth_header - create the Ethernet header * @skb: buffer to alter * @dev: source device * @type: Ethernet type field * @daddr: destination address (NULL leave destination address) * @saddr: source address (NULL use device source address) * @len: packet length (<= skb->len) * * * Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length * in here instead. */ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ethhdr *eth = skb_push(skb, ETH_HLEN); if (type != ETH_P_802_3 && type != ETH_P_802_2) eth->h_proto = htons(type); else eth->h_proto = htons(len); /* * Set the source hardware address. */ if (!saddr) saddr = dev->dev_addr; memcpy(eth->h_source, saddr, ETH_ALEN); if (daddr) { memcpy(eth->h_dest, daddr, ETH_ALEN); return ETH_HLEN; } /* * Anyway, the loopback-device should never use this function... */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { eth_zero_addr(eth->h_dest); return ETH_HLEN; } return -ETH_HLEN; } EXPORT_SYMBOL(eth_header); /** * eth_get_headlen - determine the length of header for an ethernet frame * @dev: pointer to network device * @data: pointer to start of frame * @len: total length of frame * * Make a best effort attempt to pull the length for all of the headers for * a given frame in a linear buffer. */ u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len) { const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG; const struct ethhdr *eth = (const struct ethhdr *)data; struct flow_keys_basic keys; /* this should never happen, but better safe than sorry */ if (unlikely(len < sizeof(*eth))) return len; /* parse any remaining L2/L3 headers, check for L4 */ if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data, eth->h_proto, sizeof(*eth), len, flags)) return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len); } EXPORT_SYMBOL(eth_get_headlen); /** * eth_type_trans - determine the packet's protocol ID. * @skb: received socket data * @dev: receiving network device * * The rule here is that we * assume 802.3 if the type field is short enough to be a length. * This is normal practice and works for any 'now in use' protocol. */ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) { unsigned short _service_access_point; const unsigned short *sap; const struct ethhdr *eth; skb->dev = dev; skb_reset_mac_header(skb); eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* * Some variants of DSA tagging don't have an ethertype field * at all, so we check here whether one of those tagging * variants has been configured on the receiving interface, * and if so, set skb->protocol without looking at the packet. */ if (unlikely(netdev_uses_dsa(dev))) return htons(ETH_P_XDSA); if (likely(eth_proto_is_802_3(eth->h_proto))) return eth->h_proto; /* * This is a magic hack to spot IPX packets. Older Novell breaks * the protocol design and runs IPX over 802.3 without an 802.2 LLC * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This * won't work for fault tolerant netware but does for the rest. */ sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point); if (sap && *sap == 0xFFFF) return htons(ETH_P_802_3); /* * Real 802.2 LLC */ return htons(ETH_P_802_2); } EXPORT_SYMBOL(eth_type_trans); /** * eth_header_parse - extract hardware address from packet * @skb: packet to extract header from * @haddr: destination buffer */ int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr) { const struct ethhdr *eth = eth_hdr(skb); memcpy(haddr, eth->h_source, ETH_ALEN); return ETH_ALEN; } EXPORT_SYMBOL(eth_header_parse); /** * eth_header_cache - fill cache entry from neighbour * @neigh: source neighbour * @hh: destination cache entry * @type: Ethernet type field * * Create an Ethernet header template from the neighbour. */ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type) { struct ethhdr *eth; const struct net_device *dev = neigh->dev; eth = (struct ethhdr *) (((u8 *) hh->hh_data) + (HH_DATA_OFF(sizeof(*eth)))); if (type == htons(ETH_P_802_3)) return -1; eth->h_proto = type; memcpy(eth->h_source, dev->dev_addr, ETH_ALEN); memcpy(eth->h_dest, neigh->ha, ETH_ALEN); /* Pairs with READ_ONCE() in neigh_resolve_output(), * neigh_hh_output() and neigh_update_hhs(). */ smp_store_release(&hh->hh_len, ETH_HLEN); return 0; } EXPORT_SYMBOL(eth_header_cache); /** * eth_header_cache_update - update cache entry * @hh: destination cache entry * @dev: network device * @haddr: new hardware address * * Called by Address Resolution module to notify changes in address. */ void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr) { memcpy(((u8 *) hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)), haddr, ETH_ALEN); } EXPORT_SYMBOL(eth_header_cache_update); /** * eth_header_parse_protocol - extract protocol from L2 header * @skb: packet to extract protocol from */ __be16 eth_header_parse_protocol(const struct sk_buff *skb) { const struct ethhdr *eth = eth_hdr(skb); return eth->h_proto; } EXPORT_SYMBOL(eth_header_parse_protocol); /** * eth_prepare_mac_addr_change - prepare for mac change * @dev: network device * @p: socket address */ int eth_prepare_mac_addr_change(struct net_device *dev, void *p) { struct sockaddr *addr = p; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; return 0; } EXPORT_SYMBOL(eth_prepare_mac_addr_change); /** * eth_commit_mac_addr_change - commit mac change * @dev: network device * @p: socket address */ void eth_commit_mac_addr_change(struct net_device *dev, void *p) { struct sockaddr *addr = p; eth_hw_addr_set(dev, addr->sa_data); } EXPORT_SYMBOL(eth_commit_mac_addr_change); /** * eth_mac_addr - set new Ethernet hardware address * @dev: network device * @p: socket address * * Change hardware address of device. * * This doesn't change hardware matching, so needs to be overridden * for most real devices. */ int eth_mac_addr(struct net_device *dev, void *p) { int ret; ret = eth_prepare_mac_addr_change(dev, p); if (ret < 0) return ret; eth_commit_mac_addr_change(dev, p); return 0; } EXPORT_SYMBOL(eth_mac_addr); int eth_validate_addr(struct net_device *dev) { if (!is_valid_ether_addr(dev->dev_addr)) return -EADDRNOTAVAIL; return 0; } EXPORT_SYMBOL(eth_validate_addr); const struct header_ops eth_header_ops ____cacheline_aligned = { .create = eth_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; /** * ether_setup - setup Ethernet network device * @dev: network device * * Fill in the fields of the device structure with Ethernet-generic values. */ void ether_setup(struct net_device *dev) { dev->header_ops = ð_header_ops; dev->type = ARPHRD_ETHER; dev->hard_header_len = ETH_HLEN; dev->min_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_DATA_LEN; dev->addr_len = ETH_ALEN; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->flags = IFF_BROADCAST|IFF_MULTICAST; dev->priv_flags |= IFF_TX_SKB_SHARING; eth_broadcast_addr(dev->broadcast); } EXPORT_SYMBOL(ether_setup); /** * alloc_etherdev_mqs - Allocates and sets up an Ethernet device * @sizeof_priv: Size of additional driver-private structure to be allocated * for this Ethernet device * @txqs: The number of TX queues this device has. * @rxqs: The number of RX queues this device has. * * Fill in the fields of the device structure with Ethernet-generic * values. Basically does everything except registering the device. * * Constructs a new net device, complete with a private data area of * size (sizeof_priv). A 32-byte (not bit) alignment is enforced for * this private data area. */ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs) { return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_ENUM, ether_setup, txqs, rxqs); } EXPORT_SYMBOL(alloc_etherdev_mqs); ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) { return sysfs_emit(buf, "%*phC\n", len, addr); } EXPORT_SYMBOL(sysfs_format_mac); struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; unsigned int hlen, off_eth; struct sk_buff *pp = NULL; struct ethhdr *eh, *eh2; struct sk_buff *p; __be16 type; int flush = 1; off_eth = skb_gro_offset(skb); hlen = off_eth + sizeof(*eh); eh = skb_gro_header(skb, hlen, off_eth); if (unlikely(!eh)) goto out; flush = 0; list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; eh2 = (struct ethhdr *)(p->data + off_eth); if (compare_ether_header(eh, eh2)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } type = eh->h_proto; ptype = gro_find_receive_by_type(type); if (ptype == NULL) { flush = 1; goto out; } skb_gro_pull(skb, sizeof(*eh)); skb_gro_postpull_rcsum(skb, eh, sizeof(*eh)); pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive, ipv6_gro_receive, inet_gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(eth_gro_receive); int eth_gro_complete(struct sk_buff *skb, int nhoff) { struct ethhdr *eh = (struct ethhdr *)(skb->data + nhoff); __be16 type = eh->h_proto; struct packet_offload *ptype; int err = -ENOSYS; if (skb->encapsulation) skb_set_inner_mac_header(skb, nhoff); ptype = gro_find_complete_by_type(type); if (ptype != NULL) err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, ipv6_gro_complete, inet_gro_complete, skb, nhoff + sizeof(*eh)); return err; } EXPORT_SYMBOL(eth_gro_complete); static struct packet_offload eth_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_TEB), .priority = 10, .callbacks = { .gro_receive = eth_gro_receive, .gro_complete = eth_gro_complete, }, }; static int __init eth_offload_init(void) { dev_add_offload(ð_packet_offload); return 0; } fs_initcall(eth_offload_init); unsigned char * __weak arch_get_platform_mac_address(void) { return NULL; } int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr) { unsigned char *addr; int ret; ret = of_get_mac_address(dev->of_node, mac_addr); if (!ret) return 0; addr = arch_get_platform_mac_address(); if (!addr) return -ENODEV; ether_addr_copy(mac_addr, addr); return 0; } EXPORT_SYMBOL(eth_platform_get_mac_address); /** * platform_get_ethdev_address - Set netdev's MAC address from a given device * @dev: Pointer to the device * @netdev: Pointer to netdev to write the address to * * Wrapper around eth_platform_get_mac_address() which writes the address * directly to netdev->dev_addr. */ int platform_get_ethdev_address(struct device *dev, struct net_device *netdev) { u8 addr[ETH_ALEN] __aligned(2); int ret; ret = eth_platform_get_mac_address(dev, addr); if (!ret) eth_hw_addr_set(netdev, addr); return ret; } EXPORT_SYMBOL(platform_get_ethdev_address); /** * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named * 'mac-address' associated with given device. * * @dev: Device with which the mac-address cell is associated. * @addrbuf: Buffer to which the MAC address will be copied on success. * * Returns 0 on success or a negative error number on failure. */ int nvmem_get_mac_address(struct device *dev, void *addrbuf) { struct nvmem_cell *cell; const void *mac; size_t len; cell = nvmem_cell_get(dev, "mac-address"); if (IS_ERR(cell)) return PTR_ERR(cell); mac = nvmem_cell_read(cell, &len); nvmem_cell_put(cell); if (IS_ERR(mac)) return PTR_ERR(mac); if (len != ETH_ALEN || !is_valid_ether_addr(mac)) { kfree(mac); return -EINVAL; } ether_addr_copy(addrbuf, mac); kfree(mac); return 0; } static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, const char *name, char *addr) { int ret; ret = fwnode_property_read_u8_array(fwnode, name, addr, ETH_ALEN); if (ret) return ret; if (!is_valid_ether_addr(addr)) return -EINVAL; return 0; } /** * fwnode_get_mac_address - Get the MAC from the firmware node * @fwnode: Pointer to the firmware node * @addr: Address of buffer to store the MAC in * * Search the firmware node for the best MAC address to use. 'mac-address' is * checked first, because that is supposed to contain to "most recent" MAC * address. If that isn't set, then 'local-mac-address' is checked next, * because that is the default address. If that isn't set, then the obsolete * 'address' is checked, just in case we're using an old device tree. * * Note that the 'address' property is supposed to contain a virtual address of * the register set, but some DTS files have redefined that property to be the * MAC address. * * All-zero MAC addresses are rejected, because those could be properties that * exist in the firmware tables, but were not updated by the firmware. For * example, the DTS could define 'mac-address' and 'local-mac-address', with * zero MAC addresses. Some older U-Boots only initialized 'local-mac-address'. * In this case, the real MAC is in 'local-mac-address', and 'mac-address' * exists but is all zeros. */ int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr) { if (!fwnode_get_mac_addr(fwnode, "mac-address", addr) || !fwnode_get_mac_addr(fwnode, "local-mac-address", addr) || !fwnode_get_mac_addr(fwnode, "address", addr)) return 0; return -ENOENT; } EXPORT_SYMBOL(fwnode_get_mac_address); /** * device_get_mac_address - Get the MAC for a given device * @dev: Pointer to the device * @addr: Address of buffer to store the MAC in */ int device_get_mac_address(struct device *dev, char *addr) { return fwnode_get_mac_address(dev_fwnode(dev), addr); } EXPORT_SYMBOL(device_get_mac_address); /** * device_get_ethdev_address - Set netdev's MAC address from a given device * @dev: Pointer to the device * @netdev: Pointer to netdev to write the address to * * Wrapper around device_get_mac_address() which writes the address * directly to netdev->dev_addr. */ int device_get_ethdev_address(struct device *dev, struct net_device *netdev) { u8 addr[ETH_ALEN]; int ret; ret = device_get_mac_address(dev, addr); if (!ret) eth_hw_addr_set(netdev, addr); return ret; } EXPORT_SYMBOL(device_get_ethdev_address); |
| 5668 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BIO_INTEGRITY_H #define _LINUX_BIO_INTEGRITY_H #include <linux/bio.h> enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ BIP_DISK_NOCHECK = 1 << 2, /* disable disk integrity checking */ BIP_IP_CHECKSUM = 1 << 3, /* IP checksum */ BIP_COPY_USER = 1 << 4, /* Kernel bounce buffer in use */ BIP_CHECK_GUARD = 1 << 5, /* guard check */ BIP_CHECK_REFTAG = 1 << 6, /* reftag check */ BIP_CHECK_APPTAG = 1 << 7, /* apptag check */ }; struct bio_integrity_payload { struct bio *bip_bio; /* parent bio */ struct bvec_iter bip_iter; unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ u16 app_tag; /* application tag value */ struct bvec_iter bio_iter; /* for rewinding parent bio */ struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; struct bio_vec bip_inline_vecs[];/* embedded bvec array */ }; #define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \ BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG) #ifdef CONFIG_BLK_DEV_INTEGRITY #define bip_for_each_vec(bvl, bip, iter) \ for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) #define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ for_each_bio(_bio) \ bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { struct bio_integrity_payload *bip = bio_integrity(bio); if (bip) return bip->bip_flags & flag; return false; } static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) { return bip->bip_iter.bi_sector; } static inline void bip_set_seed(struct bio_integrity_payload *bip, sector_t seed) { bip->bip_iter.bi_sector = seed; } struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr); int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter); int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta); void bio_integrity_unmap_user(struct bio *bio); bool bio_integrity_prep(struct bio *bio); void bio_integrity_advance(struct bio *bio, unsigned int bytes_done); void bio_integrity_trim(struct bio *bio); int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask); int bioset_integrity_create(struct bio_set *bs, int pool_size); void bioset_integrity_free(struct bio_set *bs); void bio_integrity_init(void); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { return NULL; } static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) { return 0; } static inline void bioset_integrity_free(struct bio_set *bs) { } static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) { return -EINVAL; } static inline int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta) { return -EINVAL; } static inline void bio_integrity_unmap_user(struct bio *bio) { } static inline bool bio_integrity_prep(struct bio *bio) { return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) { return 0; } static inline void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { } static inline void bio_integrity_trim(struct bio *bio) { } static inline void bio_integrity_init(void) { } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { return false; } static inline struct bio_integrity_payload * bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr) { return ERR_PTR(-EINVAL); } static inline int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { return 0; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #endif /* _LINUX_BIO_INTEGRITY_H */ |
| 22 228 229 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/truncate.h * * Common inline functions needed for truncate support */ /* * Truncate blocks that were not used by write. We have to truncate the * pagecache as well so that corresponding buffers get properly unmapped. */ static inline void ext4_truncate_failed_write(struct inode *inode) { struct address_space *mapping = inode->i_mapping; /* * We don't need to call ext4_break_layouts() because the blocks we * are truncating were never visible to userspace. */ filemap_invalidate_lock(mapping); truncate_inode_pages(mapping, inode->i_size); ext4_truncate(inode); filemap_invalidate_unlock(mapping); } /* * Work out how many blocks we need to proceed with the next chunk of a * truncate transaction. */ static inline unsigned long ext4_blocks_for_truncate(struct inode *inode) { ext4_lblk_t needed; needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9); /* Give ourselves just enough room to cope with inodes in which * i_blocks is corrupt: we've seen disk corruptions in the past * which resulted in random data in an inode which looked enough * like a regular file for ext4 to try to delete it. Things * will go a bit crazy if that happens, but at least we should * try not to panic the whole kernel. */ if (needed < 2) needed = 2; /* But we need to bound the transaction so we don't overflow the * journal. */ if (needed > EXT4_MAX_TRANS_DATA) needed = EXT4_MAX_TRANS_DATA; return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed; } |
| 4 1 1 1 1 1 2 2 2 2 2 2 2 5 3 2 3 1 2 1 1 5 5 1 2 1 2 1 2 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 | // SPDX-License-Identifier: GPL-2.0-only /* * CMOS/NV-RAM driver for Linux * * Copyright (C) 1997 Roman Hodek <Roman.Hodek@informatik.uni-erlangen.de> * idea by and with help from Richard Jelinek <rj@suse.de> * Portions copyright (c) 2001,2002 Sun Microsystems (thockin@sun.com) * * This driver allows you to access the contents of the non-volatile memory in * the mc146818rtc.h real-time clock. This chip is built into all PCs and into * many Atari machines. In the former it's called "CMOS-RAM", in the latter * "NVRAM" (NV stands for non-volatile). * * The data are supplied as a (seekable) character device, /dev/nvram. The * size of this file is dependent on the controller. The usual size is 114, * the number of freely available bytes in the memory (i.e., not used by the * RTC itself). * * Checksums over the NVRAM contents are managed by this driver. In case of a * bad checksum, reads and writes return -EIO. The checksum can be initialized * to a sane state either by ioctl(NVRAM_INIT) (clear whole NVRAM) or * ioctl(NVRAM_SETCKS) (doesn't change contents, just makes checksum valid * again; use with care!) * * 1.1 Cesar Barros: SMP locking fixes * added changelog * 1.2 Erik Gilling: Cobalt Networks support * Tim Hockin: general cleanup, Cobalt support * 1.3 Wim Van Sebroeck: convert PRINT_PROC to seq_file */ #define NVRAM_VERSION "1.3" #include <linux/module.h> #include <linux/nvram.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/miscdevice.h> #include <linux/ioport.h> #include <linux/fcntl.h> #include <linux/mc146818rtc.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/pagemap.h> #ifdef CONFIG_PPC #include <asm/nvram.h> #endif static DEFINE_MUTEX(nvram_mutex); static DEFINE_SPINLOCK(nvram_state_lock); static int nvram_open_cnt; /* #times opened */ static int nvram_open_mode; /* special open modes */ static ssize_t nvram_size; #define NVRAM_WRITE 1 /* opened for writing (exclusive) */ #define NVRAM_EXCL 2 /* opened with O_EXCL */ #ifdef CONFIG_X86 /* * These functions are provided to be called internally or by other parts of * the kernel. It's up to the caller to ensure correct checksum before reading * or after writing (needs to be done only once). * * It is worth noting that these functions all access bytes of general * purpose memory in the NVRAM - that is to say, they all add the * NVRAM_FIRST_BYTE offset. Pass them offsets into NVRAM as if you did not * know about the RTC cruft. */ #define NVRAM_BYTES (128 - NVRAM_FIRST_BYTE) /* Note that *all* calls to CMOS_READ and CMOS_WRITE must be done with * rtc_lock held. Due to the index-port/data-port design of the RTC, we * don't want two different things trying to get to it at once. (e.g. the * periodic 11 min sync from kernel/time/ntp.c vs. this driver.) */ static unsigned char __nvram_read_byte(int i) { return CMOS_READ(NVRAM_FIRST_BYTE + i); } static unsigned char pc_nvram_read_byte(int i) { unsigned long flags; unsigned char c; spin_lock_irqsave(&rtc_lock, flags); c = __nvram_read_byte(i); spin_unlock_irqrestore(&rtc_lock, flags); return c; } /* This races nicely with trying to read with checksum checking (nvram_read) */ static void __nvram_write_byte(unsigned char c, int i) { CMOS_WRITE(c, NVRAM_FIRST_BYTE + i); } static void pc_nvram_write_byte(unsigned char c, int i) { unsigned long flags; spin_lock_irqsave(&rtc_lock, flags); __nvram_write_byte(c, i); spin_unlock_irqrestore(&rtc_lock, flags); } /* On PCs, the checksum is built only over bytes 2..31 */ #define PC_CKS_RANGE_START 2 #define PC_CKS_RANGE_END 31 #define PC_CKS_LOC 32 static int __nvram_check_checksum(void) { int i; unsigned short sum = 0; unsigned short expect; for (i = PC_CKS_RANGE_START; i <= PC_CKS_RANGE_END; ++i) sum += __nvram_read_byte(i); expect = __nvram_read_byte(PC_CKS_LOC)<<8 | __nvram_read_byte(PC_CKS_LOC+1); return (sum & 0xffff) == expect; } static void __nvram_set_checksum(void) { int i; unsigned short sum = 0; for (i = PC_CKS_RANGE_START; i <= PC_CKS_RANGE_END; ++i) sum += __nvram_read_byte(i); __nvram_write_byte(sum >> 8, PC_CKS_LOC); __nvram_write_byte(sum & 0xff, PC_CKS_LOC + 1); } static long pc_nvram_set_checksum(void) { spin_lock_irq(&rtc_lock); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); return 0; } static long pc_nvram_initialize(void) { ssize_t i; spin_lock_irq(&rtc_lock); for (i = 0; i < NVRAM_BYTES; ++i) __nvram_write_byte(0, i); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); return 0; } static ssize_t pc_nvram_get_size(void) { return NVRAM_BYTES; } static ssize_t pc_nvram_read(char *buf, size_t count, loff_t *ppos) { char *p = buf; loff_t i; spin_lock_irq(&rtc_lock); if (!__nvram_check_checksum()) { spin_unlock_irq(&rtc_lock); return -EIO; } for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) *p = __nvram_read_byte(i); spin_unlock_irq(&rtc_lock); *ppos = i; return p - buf; } static ssize_t pc_nvram_write(char *buf, size_t count, loff_t *ppos) { char *p = buf; loff_t i; spin_lock_irq(&rtc_lock); if (!__nvram_check_checksum()) { spin_unlock_irq(&rtc_lock); return -EIO; } for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) __nvram_write_byte(*p, i); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); *ppos = i; return p - buf; } const struct nvram_ops arch_nvram_ops = { .read = pc_nvram_read, .write = pc_nvram_write, .read_byte = pc_nvram_read_byte, .write_byte = pc_nvram_write_byte, .get_size = pc_nvram_get_size, .set_checksum = pc_nvram_set_checksum, .initialize = pc_nvram_initialize, }; EXPORT_SYMBOL(arch_nvram_ops); #endif /* CONFIG_X86 */ /* * The are the file operation function for user access to /dev/nvram */ static loff_t nvram_misc_llseek(struct file *file, loff_t offset, int origin) { return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE, nvram_size); } static ssize_t nvram_misc_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *tmp; ssize_t ret; if (*ppos >= nvram_size) return 0; count = min_t(size_t, count, nvram_size - *ppos); count = min_t(size_t, count, PAGE_SIZE); tmp = kmalloc(count, GFP_KERNEL); if (!tmp) return -ENOMEM; ret = nvram_read(tmp, count, ppos); if (ret <= 0) goto out; if (copy_to_user(buf, tmp, ret)) { *ppos -= ret; ret = -EFAULT; } out: kfree(tmp); return ret; } static ssize_t nvram_misc_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *tmp; ssize_t ret; if (*ppos >= nvram_size) return 0; count = min_t(size_t, count, nvram_size - *ppos); count = min_t(size_t, count, PAGE_SIZE); tmp = memdup_user(buf, count); if (IS_ERR(tmp)) return PTR_ERR(tmp); ret = nvram_write(tmp, count, ppos); kfree(tmp); return ret; } static long nvram_misc_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { long ret = -ENOTTY; switch (cmd) { #ifdef CONFIG_PPC case OBSOLETE_PMAC_NVRAM_GET_OFFSET: pr_warn("nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); fallthrough; case IOC_NVRAM_GET_OFFSET: ret = -EINVAL; #ifdef CONFIG_PPC_PMAC if (machine_is(powermac)) { int part, offset; if (copy_from_user(&part, (void __user *)arg, sizeof(part)) != 0) return -EFAULT; if (part < pmac_nvram_OF || part > pmac_nvram_NR) return -EINVAL; offset = pmac_get_partition(part); if (offset < 0) return -EINVAL; if (copy_to_user((void __user *)arg, &offset, sizeof(offset)) != 0) return -EFAULT; ret = 0; } #endif break; #ifdef CONFIG_PPC32 case IOC_NVRAM_SYNC: if (ppc_md.nvram_sync != NULL) { mutex_lock(&nvram_mutex); ppc_md.nvram_sync(); mutex_unlock(&nvram_mutex); } ret = 0; break; #endif #elif defined(CONFIG_X86) || defined(CONFIG_M68K) case NVRAM_INIT: /* initialize NVRAM contents and checksum */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (arch_nvram_ops.initialize != NULL) { mutex_lock(&nvram_mutex); ret = arch_nvram_ops.initialize(); mutex_unlock(&nvram_mutex); } break; case NVRAM_SETCKS: /* just set checksum, contents unchanged (maybe useful after * checksum garbaged somehow...) */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (arch_nvram_ops.set_checksum != NULL) { mutex_lock(&nvram_mutex); ret = arch_nvram_ops.set_checksum(); mutex_unlock(&nvram_mutex); } break; #endif /* CONFIG_X86 || CONFIG_M68K */ } return ret; } static int nvram_misc_open(struct inode *inode, struct file *file) { spin_lock(&nvram_state_lock); /* Prevent multiple readers/writers if desired. */ if ((nvram_open_cnt && (file->f_flags & O_EXCL)) || (nvram_open_mode & NVRAM_EXCL)) { spin_unlock(&nvram_state_lock); return -EBUSY; } #if defined(CONFIG_X86) || defined(CONFIG_M68K) /* Prevent multiple writers if the set_checksum ioctl is implemented. */ if ((arch_nvram_ops.set_checksum != NULL) && (file->f_mode & FMODE_WRITE) && (nvram_open_mode & NVRAM_WRITE)) { spin_unlock(&nvram_state_lock); return -EBUSY; } #endif if (file->f_flags & O_EXCL) nvram_open_mode |= NVRAM_EXCL; if (file->f_mode & FMODE_WRITE) nvram_open_mode |= NVRAM_WRITE; nvram_open_cnt++; spin_unlock(&nvram_state_lock); return 0; } static int nvram_misc_release(struct inode *inode, struct file *file) { spin_lock(&nvram_state_lock); nvram_open_cnt--; /* if only one instance is open, clear the EXCL bit */ if (nvram_open_mode & NVRAM_EXCL) nvram_open_mode &= ~NVRAM_EXCL; if (file->f_mode & FMODE_WRITE) nvram_open_mode &= ~NVRAM_WRITE; spin_unlock(&nvram_state_lock); return 0; } #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) static const char * const floppy_types[] = { "none", "5.25'' 360k", "5.25'' 1.2M", "3.5'' 720k", "3.5'' 1.44M", "3.5'' 2.88M", "3.5'' 2.88M" }; static const char * const gfx_types[] = { "EGA, VGA, ... (with BIOS)", "CGA (40 cols)", "CGA (80 cols)", "monochrome", }; static void pc_nvram_proc_read(unsigned char *nvram, struct seq_file *seq, void *offset) { int checksum; int type; spin_lock_irq(&rtc_lock); checksum = __nvram_check_checksum(); spin_unlock_irq(&rtc_lock); seq_printf(seq, "Checksum status: %svalid\n", checksum ? "" : "not "); seq_printf(seq, "# floppies : %d\n", (nvram[6] & 1) ? (nvram[6] >> 6) + 1 : 0); seq_printf(seq, "Floppy 0 type : "); type = nvram[2] >> 4; if (type < ARRAY_SIZE(floppy_types)) seq_printf(seq, "%s\n", floppy_types[type]); else seq_printf(seq, "%d (unknown)\n", type); seq_printf(seq, "Floppy 1 type : "); type = nvram[2] & 0x0f; if (type < ARRAY_SIZE(floppy_types)) seq_printf(seq, "%s\n", floppy_types[type]); else seq_printf(seq, "%d (unknown)\n", type); seq_printf(seq, "HD 0 type : "); type = nvram[4] >> 4; if (type) seq_printf(seq, "%02x\n", type == 0x0f ? nvram[11] : type); else seq_printf(seq, "none\n"); seq_printf(seq, "HD 1 type : "); type = nvram[4] & 0x0f; if (type) seq_printf(seq, "%02x\n", type == 0x0f ? nvram[12] : type); else seq_printf(seq, "none\n"); seq_printf(seq, "HD type 48 data: %d/%d/%d C/H/S, precomp %d, lz %d\n", nvram[18] | (nvram[19] << 8), nvram[20], nvram[25], nvram[21] | (nvram[22] << 8), nvram[23] | (nvram[24] << 8)); seq_printf(seq, "HD type 49 data: %d/%d/%d C/H/S, precomp %d, lz %d\n", nvram[39] | (nvram[40] << 8), nvram[41], nvram[46], nvram[42] | (nvram[43] << 8), nvram[44] | (nvram[45] << 8)); seq_printf(seq, "DOS base memory: %d kB\n", nvram[7] | (nvram[8] << 8)); seq_printf(seq, "Extended memory: %d kB (configured), %d kB (tested)\n", nvram[9] | (nvram[10] << 8), nvram[34] | (nvram[35] << 8)); seq_printf(seq, "Gfx adapter : %s\n", gfx_types[(nvram[6] >> 4) & 3]); seq_printf(seq, "FPU : %sinstalled\n", (nvram[6] & 2) ? "" : "not "); return; } static int nvram_proc_read(struct seq_file *seq, void *offset) { unsigned char contents[NVRAM_BYTES]; int i = 0; spin_lock_irq(&rtc_lock); for (i = 0; i < NVRAM_BYTES; ++i) contents[i] = __nvram_read_byte(i); spin_unlock_irq(&rtc_lock); pc_nvram_proc_read(contents, seq, offset); return 0; } #endif /* CONFIG_X86 && CONFIG_PROC_FS */ static const struct file_operations nvram_misc_fops = { .owner = THIS_MODULE, .llseek = nvram_misc_llseek, .read = nvram_misc_read, .write = nvram_misc_write, .unlocked_ioctl = nvram_misc_ioctl, .open = nvram_misc_open, .release = nvram_misc_release, }; static struct miscdevice nvram_misc = { NVRAM_MINOR, "nvram", &nvram_misc_fops, }; static int __init nvram_module_init(void) { int ret; nvram_size = nvram_get_size(); if (nvram_size < 0) return nvram_size; ret = misc_register(&nvram_misc); if (ret) { pr_err("nvram: can't misc_register on minor=%d\n", NVRAM_MINOR); return ret; } #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) if (!proc_create_single("driver/nvram", 0, NULL, nvram_proc_read)) { pr_err("nvram: can't create /proc/driver/nvram\n"); misc_deregister(&nvram_misc); return -ENOMEM; } #endif pr_info("Non-volatile memory driver v" NVRAM_VERSION "\n"); return 0; } static void __exit nvram_module_exit(void) { #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) remove_proc_entry("driver/nvram", NULL); #endif misc_deregister(&nvram_misc); } module_init(nvram_module_init); module_exit(nvram_module_exit); MODULE_DESCRIPTION("CMOS/NV-RAM driver for Linux"); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(NVRAM_MINOR); MODULE_ALIAS("devname:nvram"); |
| 198 198 198 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 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 /* * Landlock LSM - Credential hooks * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #include <linux/cred.h> #include <linux/lsm_hooks.h> #include "common.h" #include "cred.h" #include "ruleset.h" #include "setup.h" static void hook_cred_transfer(struct cred *const new, const struct cred *const old) { struct landlock_ruleset *const old_dom = landlock_cred(old)->domain; if (old_dom) { landlock_get_ruleset(old_dom); landlock_cred(new)->domain = old_dom; } } static int hook_cred_prepare(struct cred *const new, const struct cred *const old, const gfp_t gfp) { hook_cred_transfer(new, old); return 0; } static void hook_cred_free(struct cred *const cred) { struct landlock_ruleset *const dom = landlock_cred(cred)->domain; if (dom) landlock_put_ruleset_deferred(dom); } static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, hook_cred_prepare), LSM_HOOK_INIT(cred_transfer, hook_cred_transfer), LSM_HOOK_INIT(cred_free, hook_cred_free), }; __init void landlock_add_cred_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } |
| 5 5 5 5 10 7 3 7 14 1 2 11 8 8 2 11 3 8 6 1 5 5 2 3 7 6 1 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/verity.c: fs-verity support for ext4 * * Copyright 2019 Google LLC */ /* * Implementation of fsverity_operations for ext4. * * ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past * the end of the file, starting at the first 64K boundary beyond i_size. This * approach works because (a) verity files are readonly, and (b) pages fully * beyond i_size aren't visible to userspace but can be read/written internally * by ext4 with only some relatively small changes to ext4. This approach * avoids having to depend on the EA_INODE feature and on rearchitecturing * ext4's xattr support to support paging multi-gigabyte xattrs into memory, and * to support encrypting xattrs. Note that the verity metadata *must* be * encrypted when the file is, since it contains hashes of the plaintext data. * * Using a 64K boundary rather than a 4K one keeps things ready for * architectures with 64K pages, and it doesn't necessarily waste space on-disk * since there can be a hole between i_size and the start of the Merkle tree. */ #include <linux/quotaops.h> #include "ext4.h" #include "ext4_extents.h" #include "ext4_jbd2.h" static inline loff_t ext4_verity_metadata_pos(const struct inode *inode) { return round_up(inode->i_size, 65536); } /* * Read some verity metadata from the inode. __vfs_read() can't be used because * we need to read beyond i_size. */ static int pagecache_read(struct inode *inode, void *buf, size_t count, loff_t pos) { while (count) { struct folio *folio; size_t n; folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT, NULL); if (IS_ERR(folio)) return PTR_ERR(folio); n = memcpy_from_file_folio(buf, folio, pos, count); folio_put(folio); buf += n; pos += n; count -= n; } return 0; } /* * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY. * kernel_write() can't be used because the file descriptor is readonly. */ static int pagecache_write(struct inode *inode, const void *buf, size_t count, loff_t pos) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; if (pos + count > inode->i_sb->s_maxbytes) return -EFBIG; while (count) { size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); struct folio *folio; void *fsdata = NULL; int res; res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata); if (res) return res; memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n); res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata); if (res < 0) return res; if (res != n) return -EIO; buf += n; pos += n; count -= n; } return 0; } static int ext4_begin_enable_verity(struct file *filp) { struct inode *inode = file_inode(filp); const int credits = 2; /* superblock and inode for ext4_orphan_add() */ handle_t *handle; int err; if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX)) return -EINVAL; if (ext4_verity_in_progress(inode)) return -EBUSY; /* * Since the file was opened readonly, we have to initialize the jbd * inode and quotas here and not rely on ->open() doing it. This must * be done before evicting the inline data. */ err = ext4_inode_attach_jinode(inode); if (err) return err; err = dquot_initialize(inode); if (err) return err; err = ext4_convert_inline_data(inode); if (err) return err; if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ext4_warning_inode(inode, "verity is only allowed on extent-based files"); return -EOPNOTSUPP; } /* * ext4 uses the last allocated block to find the verity descriptor, so * we must remove any other blocks past EOF which might confuse things. */ err = ext4_truncate(inode); if (err) return err; handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); err = ext4_orphan_add(handle, inode); if (err == 0) ext4_set_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); ext4_journal_stop(handle); return err; } /* * ext4 stores the verity descriptor beginning on the next filesystem block * boundary after the Merkle tree. Then, the descriptor size is stored in the * last 4 bytes of the last allocated filesystem block --- which is either the * block in which the descriptor ends, or the next block after that if there * weren't at least 4 bytes remaining. * * We can't simply store the descriptor in an xattr because it *must* be * encrypted when ext4 encryption is used, but ext4 encryption doesn't encrypt * xattrs. Also, if the descriptor includes a large signature blob it may be * too large to store in an xattr without the EA_INODE feature. */ static int ext4_write_verity_descriptor(struct inode *inode, const void *desc, size_t desc_size, u64 merkle_tree_size) { const u64 desc_pos = round_up(ext4_verity_metadata_pos(inode) + merkle_tree_size, i_blocksize(inode)); const u64 desc_end = desc_pos + desc_size; const __le32 desc_size_disk = cpu_to_le32(desc_size); const u64 desc_size_pos = round_up(desc_end + sizeof(desc_size_disk), i_blocksize(inode)) - sizeof(desc_size_disk); int err; err = pagecache_write(inode, desc, desc_size, desc_pos); if (err) return err; return pagecache_write(inode, &desc_size_disk, sizeof(desc_size_disk), desc_size_pos); } static int ext4_end_enable_verity(struct file *filp, const void *desc, size_t desc_size, u64 merkle_tree_size) { struct inode *inode = file_inode(filp); const int credits = 2; /* superblock and inode for ext4_orphan_del() */ handle_t *handle; struct ext4_iloc iloc; int err = 0; /* * If an error already occurred (which fs/verity/ signals by passing * desc == NULL), then only clean-up is needed. */ if (desc == NULL) goto cleanup; /* Append the verity descriptor. */ err = ext4_write_verity_descriptor(inode, desc, desc_size, merkle_tree_size); if (err) goto cleanup; /* * Write all pages (both data and verity metadata). Note that this must * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages * beyond i_size won't be written properly. For crash consistency, this * also must happen before the verity inode flag gets persisted. */ err = filemap_write_and_wait(inode->i_mapping); if (err) goto cleanup; /* * Finally, set the verity inode flag and remove the inode from the * orphan list (in a single transaction). */ handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto cleanup; } err = ext4_orphan_del(handle, inode); if (err) goto stop_and_cleanup; err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto stop_and_cleanup; ext4_set_inode_flag(inode, EXT4_INODE_VERITY); ext4_set_inode_flags(inode, false); err = ext4_mark_iloc_dirty(handle, inode, &iloc); if (err) goto stop_and_cleanup; ext4_journal_stop(handle); ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); return 0; stop_and_cleanup: ext4_journal_stop(handle); cleanup: /* * Verity failed to be enabled, so clean up by truncating any verity * metadata that was written beyond i_size (both from cache and from * disk), removing the inode from the orphan list (if it wasn't done * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS. */ truncate_inode_pages(inode->i_mapping, inode->i_size); ext4_truncate(inode); ext4_orphan_del(NULL, inode); ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); return err; } static int ext4_get_verity_descriptor_location(struct inode *inode, size_t *desc_size_ret, u64 *desc_pos_ret) { struct ext4_ext_path *path; struct ext4_extent *last_extent; u32 end_lblk; u64 desc_size_pos; __le32 desc_size_disk; u32 desc_size; u64 desc_pos; int err; /* * Descriptor size is in last 4 bytes of last allocated block. * See ext4_write_verity_descriptor(). */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { EXT4_ERROR_INODE(inode, "verity file doesn't use extents"); return -EFSCORRUPTED; } path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); last_extent = path[path->p_depth].p_ext; if (!last_extent) { EXT4_ERROR_INODE(inode, "verity file has no extents"); ext4_free_ext_path(path); return -EFSCORRUPTED; } end_lblk = le32_to_cpu(last_extent->ee_block) + ext4_ext_get_actual_len(last_extent); desc_size_pos = (u64)end_lblk << inode->i_blkbits; ext4_free_ext_path(path); if (desc_size_pos < sizeof(desc_size_disk)) goto bad; desc_size_pos -= sizeof(desc_size_disk); err = pagecache_read(inode, &desc_size_disk, sizeof(desc_size_disk), desc_size_pos); if (err) return err; desc_size = le32_to_cpu(desc_size_disk); /* * The descriptor is stored just before the desc_size_disk, but starting * on a filesystem block boundary. */ if (desc_size > INT_MAX || desc_size > desc_size_pos) goto bad; desc_pos = round_down(desc_size_pos - desc_size, i_blocksize(inode)); if (desc_pos < ext4_verity_metadata_pos(inode)) goto bad; *desc_size_ret = desc_size; *desc_pos_ret = desc_pos; return 0; bad: EXT4_ERROR_INODE(inode, "verity file corrupted; can't find descriptor"); return -EFSCORRUPTED; } static int ext4_get_verity_descriptor(struct inode *inode, void *buf, size_t buf_size) { size_t desc_size = 0; u64 desc_pos = 0; int err; err = ext4_get_verity_descriptor_location(inode, &desc_size, &desc_pos); if (err) return err; if (buf_size) { if (desc_size > buf_size) return -ERANGE; err = pagecache_read(inode, buf, desc_size, desc_pos); if (err) return err; } return desc_size; } static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { struct folio *folio; index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; folio = __filemap_get_folio(inode->i_mapping, index, FGP_ACCESSED, 0); if (IS_ERR(folio) || !folio_test_uptodate(folio)) { DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); if (!IS_ERR(folio)) folio_put(folio); else if (num_ra_pages > 1) page_cache_ra_unbounded(&ractl, num_ra_pages, 0); folio = read_mapping_folio(inode->i_mapping, index, NULL); if (IS_ERR(folio)) return ERR_CAST(folio); } return folio_file_page(folio, index); } static int ext4_write_merkle_tree_block(struct inode *inode, const void *buf, u64 pos, unsigned int size) { pos += ext4_verity_metadata_pos(inode); return pagecache_write(inode, buf, size, pos); } const struct fsverity_operations ext4_verityops = { .begin_enable_verity = ext4_begin_enable_verity, .end_enable_verity = ext4_end_enable_verity, .get_verity_descriptor = ext4_get_verity_descriptor, .read_merkle_tree_page = ext4_read_merkle_tree_page, .write_merkle_tree_block = ext4_write_merkle_tree_block, }; |
| 8 7 6 9 8 9 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_background.h" #include "bkey_buf.h" #include "btree_iter.h" #include "btree_update.h" #include "btree_write_buffer.h" #include "error.h" #include "lru.h" #include "recovery.h" /* KEY_TYPE_lru is obsolete: */ int bch2_lru_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { int ret = 0; bkey_fsck_err_on(!lru_pos_time(k.k->p), c, lru_entry_at_time_0, "lru entry at time=0"); fsck_err: return ret; } void bch2_lru_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { const struct bch_lru *lru = bkey_s_c_to_lru(k).v; prt_printf(out, "idx %llu", le64_to_cpu(lru->idx)); } void bch2_lru_pos_to_text(struct printbuf *out, struct bpos lru) { prt_printf(out, "%llu:%llu -> %llu:%llu", lru_pos_id(lru), lru_pos_time(lru), u64_to_bucket(lru.offset).inode, u64_to_bucket(lru.offset).offset); } static int __bch2_lru_set(struct btree_trans *trans, u16 lru_id, u64 dev_bucket, u64 time, bool set) { return time ? bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_pos(lru_id, dev_bucket, time), set) : 0; } int bch2_lru_del(struct btree_trans *trans, u16 lru_id, u64 dev_bucket, u64 time) { return __bch2_lru_set(trans, lru_id, dev_bucket, time, KEY_TYPE_deleted); } int bch2_lru_set(struct btree_trans *trans, u16 lru_id, u64 dev_bucket, u64 time) { return __bch2_lru_set(trans, lru_id, dev_bucket, time, KEY_TYPE_set); } int bch2_lru_change(struct btree_trans *trans, u16 lru_id, u64 dev_bucket, u64 old_time, u64 new_time) { if (old_time == new_time) return 0; return bch2_lru_del(trans, lru_id, dev_bucket, old_time) ?: bch2_lru_set(trans, lru_id, dev_bucket, new_time); } static const char * const bch2_lru_types[] = { #define x(n) #n, BCH_LRU_TYPES() #undef x NULL }; int bch2_lru_check_set(struct btree_trans *trans, u16 lru_id, u64 time, struct bkey_s_c referring_k, struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; struct btree_iter lru_iter; struct bkey_s_c lru_k = bch2_bkey_get_iter(trans, &lru_iter, BTREE_ID_lru, lru_pos(lru_id, bucket_to_u64(referring_k.k->p), time), 0); int ret = bkey_err(lru_k); if (ret) return ret; if (lru_k.k->type != KEY_TYPE_set) { ret = bch2_btree_write_buffer_maybe_flush(trans, referring_k, last_flushed); if (ret) goto err; if (fsck_err(trans, alloc_key_to_missing_lru_entry, "missing %s lru entry\n" " %s", bch2_lru_types[lru_type(lru_k)], (bch2_bkey_val_to_text(&buf, c, referring_k), buf.buf))) { ret = bch2_lru_set(trans, lru_id, bucket_to_u64(referring_k.k->p), time); if (ret) goto err; } } err: fsck_err: bch2_trans_iter_exit(trans, &lru_iter); printbuf_exit(&buf); return ret; } static int bch2_check_lru_key(struct btree_trans *trans, struct btree_iter *lru_iter, struct bkey_s_c lru_k, struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a; struct printbuf buf1 = PRINTBUF; struct printbuf buf2 = PRINTBUF; enum bch_lru_type type = lru_type(lru_k); struct bpos alloc_pos = u64_to_bucket(lru_k.k->p.offset); u64 idx; int ret; struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(c, alloc_pos); if (fsck_err_on(!ca, trans, lru_entry_to_invalid_bucket, "lru key points to nonexistent device:bucket %llu:%llu", alloc_pos.inode, alloc_pos.offset)) return bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false); k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc, alloc_pos, 0); ret = bkey_err(k); if (ret) goto err; a = bch2_alloc_to_v4(k, &a_convert); switch (type) { case BCH_LRU_read: idx = alloc_lru_idx_read(*a); break; case BCH_LRU_fragmentation: idx = alloc_lru_idx_fragmentation(*a, ca); break; } if (lru_k.k->type != KEY_TYPE_set || lru_pos_time(lru_k.k->p) != idx) { ret = bch2_btree_write_buffer_maybe_flush(trans, lru_k, last_flushed); if (ret) goto err; if (fsck_err(trans, lru_entry_bad, "incorrect lru entry: lru %s time %llu\n" " %s\n" " for %s", bch2_lru_types[type], lru_pos_time(lru_k.k->p), (bch2_bkey_val_to_text(&buf1, c, lru_k), buf1.buf), (bch2_bkey_val_to_text(&buf2, c, k), buf2.buf))) ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false); } err: fsck_err: bch2_trans_iter_exit(trans, &iter); bch2_dev_put(ca); printbuf_exit(&buf2); printbuf_exit(&buf1); return ret; } int bch2_check_lrus(struct bch_fs *c) { struct bkey_buf last_flushed; bch2_bkey_buf_init(&last_flushed); bkey_init(&last_flushed.k->k); int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_lru, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_check_lru_key(trans, &iter, k, &last_flushed))); bch2_bkey_buf_exit(&last_flushed, c); bch_err_fn(c, ret); return ret; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * stack_o2cb.c * * Code which interfaces ocfs2 with the o2cb stack. * * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/kernel.h> #include <linux/crc32.h> #include <linux/slab.h> #include <linux/module.h> /* Needed for AOP_TRUNCATED_PAGE in mlog_errno() */ #include <linux/fs.h> #include "cluster/masklog.h" #include "cluster/nodemanager.h" #include "cluster/heartbeat.h" #include "cluster/tcp.h" #include "stackglue.h" struct o2dlm_private { struct dlm_eviction_cb op_eviction_cb; }; static struct ocfs2_stack_plugin o2cb_stack; /* These should be identical */ #if (DLM_LOCK_IV != LKM_IVMODE) # error Lock modes do not match #endif #if (DLM_LOCK_NL != LKM_NLMODE) # error Lock modes do not match #endif #if (DLM_LOCK_CR != LKM_CRMODE) # error Lock modes do not match #endif #if (DLM_LOCK_CW != LKM_CWMODE) # error Lock modes do not match #endif #if (DLM_LOCK_PR != LKM_PRMODE) # error Lock modes do not match #endif #if (DLM_LOCK_PW != LKM_PWMODE) # error Lock modes do not match #endif #if (DLM_LOCK_EX != LKM_EXMODE) # error Lock modes do not match #endif static inline int mode_to_o2dlm(int mode) { BUG_ON(mode > LKM_MAXMODE); return mode; } static int flags_to_o2dlm(u32 flags) { int o2dlm_flags = 0; if (flags & DLM_LKF_NOQUEUE) o2dlm_flags |= LKM_NOQUEUE; if (flags & DLM_LKF_CANCEL) o2dlm_flags |= LKM_CANCEL; if (flags & DLM_LKF_CONVERT) o2dlm_flags |= LKM_CONVERT; if (flags & DLM_LKF_VALBLK) o2dlm_flags |= LKM_VALBLK; if (flags & DLM_LKF_IVVALBLK) o2dlm_flags |= LKM_INVVALBLK; if (flags & DLM_LKF_ORPHAN) o2dlm_flags |= LKM_ORPHAN; if (flags & DLM_LKF_FORCEUNLOCK) o2dlm_flags |= LKM_FORCE; if (flags & DLM_LKF_TIMEOUT) o2dlm_flags |= LKM_TIMEOUT; if (flags & DLM_LKF_LOCAL) o2dlm_flags |= LKM_LOCAL; return o2dlm_flags; } /* * Map an o2dlm status to standard errno values. * * o2dlm only uses a handful of these, and returns even fewer to the * caller. Still, we try to assign sane values to each error. * * The following value pairs have special meanings to dlmglue, thus * the right hand side needs to stay unique - never duplicate the * mapping elsewhere in the table! * * DLM_NORMAL: 0 * DLM_NOTQUEUED: -EAGAIN * DLM_CANCELGRANT: -EBUSY * DLM_CANCEL: -DLM_ECANCEL */ /* Keep in sync with dlmapi.h */ static int status_map[] = { [DLM_NORMAL] = 0, /* Success */ [DLM_GRANTED] = -EINVAL, [DLM_DENIED] = -EACCES, [DLM_DENIED_NOLOCKS] = -EACCES, [DLM_WORKING] = -EACCES, [DLM_BLOCKED] = -EINVAL, [DLM_BLOCKED_ORPHAN] = -EINVAL, [DLM_DENIED_GRACE_PERIOD] = -EACCES, [DLM_SYSERR] = -ENOMEM, /* It is what it is */ [DLM_NOSUPPORT] = -EPROTO, [DLM_CANCELGRANT] = -EBUSY, /* Cancel after grant */ [DLM_IVLOCKID] = -EINVAL, [DLM_SYNC] = -EINVAL, [DLM_BADTYPE] = -EINVAL, [DLM_BADRESOURCE] = -EINVAL, [DLM_MAXHANDLES] = -ENOMEM, [DLM_NOCLINFO] = -EINVAL, [DLM_NOLOCKMGR] = -EINVAL, [DLM_NOPURGED] = -EINVAL, [DLM_BADARGS] = -EINVAL, [DLM_VOID] = -EINVAL, [DLM_NOTQUEUED] = -EAGAIN, /* Trylock failed */ [DLM_IVBUFLEN] = -EINVAL, [DLM_CVTUNGRANT] = -EPERM, [DLM_BADPARAM] = -EINVAL, [DLM_VALNOTVALID] = -EINVAL, [DLM_REJECTED] = -EPERM, [DLM_ABORT] = -EINVAL, [DLM_CANCEL] = -DLM_ECANCEL, /* Successful cancel */ [DLM_IVRESHANDLE] = -EINVAL, [DLM_DEADLOCK] = -EDEADLK, [DLM_DENIED_NOASTS] = -EINVAL, [DLM_FORWARD] = -EINVAL, [DLM_TIMEOUT] = -ETIMEDOUT, [DLM_IVGROUPID] = -EINVAL, [DLM_VERS_CONFLICT] = -EOPNOTSUPP, [DLM_BAD_DEVICE_PATH] = -ENOENT, [DLM_NO_DEVICE_PERMISSION] = -EPERM, [DLM_NO_CONTROL_DEVICE] = -ENOENT, [DLM_RECOVERING] = -ENOTCONN, [DLM_MIGRATING] = -ERESTART, [DLM_MAXSTATS] = -EINVAL, }; static int dlm_status_to_errno(enum dlm_status status) { BUG_ON(status < 0 || status >= ARRAY_SIZE(status_map)); return status_map[status]; } static void o2dlm_lock_ast_wrapper(void *astarg) { struct ocfs2_dlm_lksb *lksb = astarg; lksb->lksb_conn->cc_proto->lp_lock_ast(lksb); } static void o2dlm_blocking_ast_wrapper(void *astarg, int level) { struct ocfs2_dlm_lksb *lksb = astarg; lksb->lksb_conn->cc_proto->lp_blocking_ast(lksb, level); } static void o2dlm_unlock_ast_wrapper(void *astarg, enum dlm_status status) { struct ocfs2_dlm_lksb *lksb = astarg; int error = dlm_status_to_errno(status); /* * In o2dlm, you can get both the lock_ast() for the lock being * granted and the unlock_ast() for the CANCEL failing. A * successful cancel sends DLM_NORMAL here. If the * lock grant happened before the cancel arrived, you get * DLM_CANCELGRANT. * * There's no need for the double-ast. If we see DLM_CANCELGRANT, * we just ignore it. We expect the lock_ast() to handle the * granted lock. */ if (status == DLM_CANCELGRANT) return; lksb->lksb_conn->cc_proto->lp_unlock_ast(lksb, error); } static int o2cb_dlm_lock(struct ocfs2_cluster_connection *conn, int mode, struct ocfs2_dlm_lksb *lksb, u32 flags, void *name, unsigned int namelen) { enum dlm_status status; int o2dlm_mode = mode_to_o2dlm(mode); int o2dlm_flags = flags_to_o2dlm(flags); int ret; status = dlmlock(conn->cc_lockspace, o2dlm_mode, &lksb->lksb_o2dlm, o2dlm_flags, name, namelen, o2dlm_lock_ast_wrapper, lksb, o2dlm_blocking_ast_wrapper); ret = dlm_status_to_errno(status); return ret; } static int o2cb_dlm_unlock(struct ocfs2_cluster_connection *conn, struct ocfs2_dlm_lksb *lksb, u32 flags) { enum dlm_status status; int o2dlm_flags = flags_to_o2dlm(flags); int ret; status = dlmunlock(conn->cc_lockspace, &lksb->lksb_o2dlm, o2dlm_flags, o2dlm_unlock_ast_wrapper, lksb); ret = dlm_status_to_errno(status); return ret; } static int o2cb_dlm_lock_status(struct ocfs2_dlm_lksb *lksb) { return dlm_status_to_errno(lksb->lksb_o2dlm.status); } /* * o2dlm always has a "valid" LVB. If the dlm loses track of the LVB * contents, it will zero out the LVB. Thus the caller can always trust * the contents. */ static int o2cb_dlm_lvb_valid(struct ocfs2_dlm_lksb *lksb) { return 1; } static void *o2cb_dlm_lvb(struct ocfs2_dlm_lksb *lksb) { return (void *)(lksb->lksb_o2dlm.lvb); } static void o2cb_dump_lksb(struct ocfs2_dlm_lksb *lksb) { dlm_print_one_lock(lksb->lksb_o2dlm.lockid); } /* * Check if this node is heartbeating and is connected to all other * heartbeating nodes. */ static int o2cb_cluster_check(void) { u8 node_num; int i; unsigned long hbmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; unsigned long netmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; node_num = o2nm_this_node(); if (node_num == O2NM_MAX_NODES) { printk(KERN_ERR "o2cb: This node has not been configured.\n"); return -EINVAL; } /* * o2dlm expects o2net sockets to be created. If not, then * dlm_join_domain() fails with a stack of errors which are both cryptic * and incomplete. The idea here is to detect upfront whether we have * managed to connect to all nodes or not. If not, then list the nodes * to allow the user to check the configuration (incorrect IP, firewall, * etc.) Yes, this is racy. But its not the end of the world. */ #define O2CB_MAP_STABILIZE_COUNT 60 for (i = 0; i < O2CB_MAP_STABILIZE_COUNT; ++i) { o2hb_fill_node_map(hbmap, O2NM_MAX_NODES); if (!test_bit(node_num, hbmap)) { printk(KERN_ERR "o2cb: %s heartbeat has not been " "started.\n", (o2hb_global_heartbeat_active() ? "Global" : "Local")); return -EINVAL; } o2net_fill_node_map(netmap, O2NM_MAX_NODES); /* Force set the current node to allow easy compare */ set_bit(node_num, netmap); if (bitmap_equal(hbmap, netmap, O2NM_MAX_NODES)) return 0; if (i < O2CB_MAP_STABILIZE_COUNT - 1) msleep(1000); } printk(KERN_ERR "o2cb: This node could not connect to nodes:"); i = -1; while ((i = find_next_bit(hbmap, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) { if (!test_bit(i, netmap)) printk(" %u", i); } printk(".\n"); return -ENOTCONN; } /* * Called from the dlm when it's about to evict a node. This is how the * classic stack signals node death. */ static void o2dlm_eviction_cb(int node_num, void *data) { struct ocfs2_cluster_connection *conn = data; printk(KERN_NOTICE "o2cb: o2dlm has evicted node %d from domain %.*s\n", node_num, conn->cc_namelen, conn->cc_name); conn->cc_recovery_handler(node_num, conn->cc_recovery_data); } static int o2cb_cluster_connect(struct ocfs2_cluster_connection *conn) { int rc = 0; u32 dlm_key; struct dlm_ctxt *dlm; struct o2dlm_private *priv; struct dlm_protocol_version fs_version; BUG_ON(conn == NULL); BUG_ON(conn->cc_proto == NULL); /* Ensure cluster stack is up and all nodes are connected */ rc = o2cb_cluster_check(); if (rc) { printk(KERN_ERR "o2cb: Cluster check failed. Fix errors " "before retrying.\n"); goto out; } priv = kzalloc(sizeof(struct o2dlm_private), GFP_KERNEL); if (!priv) { rc = -ENOMEM; goto out_free; } /* This just fills the structure in. It is safe to pass conn. */ dlm_setup_eviction_cb(&priv->op_eviction_cb, o2dlm_eviction_cb, conn); conn->cc_private = priv; /* used by the dlm code to make message headers unique, each * node in this domain must agree on this. */ dlm_key = crc32_le(0, conn->cc_name, conn->cc_namelen); fs_version.pv_major = conn->cc_version.pv_major; fs_version.pv_minor = conn->cc_version.pv_minor; dlm = dlm_register_domain(conn->cc_name, dlm_key, &fs_version); if (IS_ERR(dlm)) { rc = PTR_ERR(dlm); mlog_errno(rc); goto out_free; } conn->cc_version.pv_major = fs_version.pv_major; conn->cc_version.pv_minor = fs_version.pv_minor; conn->cc_lockspace = dlm; dlm_register_eviction_cb(dlm, &priv->op_eviction_cb); out_free: if (rc) kfree(conn->cc_private); out: return rc; } static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn) { struct dlm_ctxt *dlm = conn->cc_lockspace; struct o2dlm_private *priv = conn->cc_private; dlm_unregister_eviction_cb(&priv->op_eviction_cb); conn->cc_private = NULL; kfree(priv); dlm_unregister_domain(dlm); conn->cc_lockspace = NULL; return 0; } static int o2cb_cluster_this_node(struct ocfs2_cluster_connection *conn, unsigned int *node) { int node_num; node_num = o2nm_this_node(); if (node_num == O2NM_INVALID_NODE_NUM) return -ENOENT; if (node_num >= O2NM_MAX_NODES) return -EOVERFLOW; *node = node_num; return 0; } static const struct ocfs2_stack_operations o2cb_stack_ops = { .connect = o2cb_cluster_connect, .disconnect = o2cb_cluster_disconnect, .this_node = o2cb_cluster_this_node, .dlm_lock = o2cb_dlm_lock, .dlm_unlock = o2cb_dlm_unlock, .lock_status = o2cb_dlm_lock_status, .lvb_valid = o2cb_dlm_lvb_valid, .lock_lvb = o2cb_dlm_lvb, .dump_lksb = o2cb_dump_lksb, }; static struct ocfs2_stack_plugin o2cb_stack = { .sp_name = "o2cb", .sp_ops = &o2cb_stack_ops, .sp_owner = THIS_MODULE, }; static int __init o2cb_stack_init(void) { return ocfs2_stack_glue_register(&o2cb_stack); } static void __exit o2cb_stack_exit(void) { ocfs2_stack_glue_unregister(&o2cb_stack); } MODULE_AUTHOR("Oracle"); MODULE_DESCRIPTION("ocfs2 driver for the classic o2cb stack"); MODULE_LICENSE("GPL"); module_init(o2cb_stack_init); module_exit(o2cb_stack_exit); |
| 10 4 3 3 12 12 12 9 3 12 12 12 12 12 12 5 4 3 3 7 2 5 5 2 11 1 233 233 233 232 233 233 233 233 11 11 4 2 4 37 37 36 1 249 246 2 245 3 1 245 1 246 2 1 237 235 235 1 245 246 37 2 2 49 49 49 49 33 5 28 129 58 58 68 69 69 1 34 35 10 10 10 1 10 8 2 6 6 6 1 6 6 6 6 6 8 3 1 2 2 1 1 237 129 103 3 237 236 33 246 246 37 4 4 1 1 55 55 71 71 269 267 194 16 10 2 3 1 33 14 24 16 6 7 26 15 260 52 46 109 40 28 25 29 10 15 10 50 25 19 2 274 272 2 2 269 263 2 1 251 9 1 254 4 3 213 45 3 266 233 32 244 22 246 19 17 248 4 245 8 1 1 236 235 224 11 236 235 83 152 152 236 235 175 60 23 212 33 266 2 2 2 1 6 12 1 11 1 11 1 9 2 5 6 274 265 13 274 274 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_bmap.h" #include "xfs_alloc.h" #include "xfs_fsops.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_dir2.h" #include "xfs_extfree_item.h" #include "xfs_mru_cache.h" #include "xfs_inode_item.h" #include "xfs_icache.h" #include "xfs_trace.h" #include "xfs_icreate_item.h" #include "xfs_filestream.h" #include "xfs_quota.h" #include "xfs_sysfs.h" #include "xfs_ondisk.h" #include "xfs_rmap_item.h" #include "xfs_refcount_item.h" #include "xfs_bmap_item.h" #include "xfs_reflink.h" #include "xfs_pwork.h" #include "xfs_ag.h" #include "xfs_defer.h" #include "xfs_attr_item.h" #include "xfs_xattr.h" #include "xfs_iunlink_item.h" #include "xfs_dahash_test.h" #include "xfs_rtbitmap.h" #include "xfs_exchmaps_item.h" #include "xfs_parent.h" #include "xfs_rtalloc.h" #include "scrub/stats.h" #include "scrub/rcbag_btree.h" #include <linux/magic.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> static const struct super_operations xfs_super_operations; static struct dentry *xfs_debugfs; /* top-level xfs debugfs dir */ static struct kset *xfs_kset; /* top-level xfs sysfs dir */ #ifdef DEBUG static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #endif enum xfs_dax_mode { XFS_DAX_INODE = 0, XFS_DAX_ALWAYS = 1, XFS_DAX_NEVER = 2, }; /* Were quota mount options provided? Must use the upper 16 bits of qflags. */ #define XFS_QFLAGS_MNTOPTS (1U << 31) static void xfs_mount_set_dax_mode( struct xfs_mount *mp, enum xfs_dax_mode mode) { switch (mode) { case XFS_DAX_INODE: mp->m_features &= ~(XFS_FEAT_DAX_ALWAYS | XFS_FEAT_DAX_NEVER); break; case XFS_DAX_ALWAYS: mp->m_features |= XFS_FEAT_DAX_ALWAYS; mp->m_features &= ~XFS_FEAT_DAX_NEVER; break; case XFS_DAX_NEVER: mp->m_features |= XFS_FEAT_DAX_NEVER; mp->m_features &= ~XFS_FEAT_DAX_ALWAYS; break; } } static const struct constant_table dax_param_enums[] = { {"inode", XFS_DAX_INODE }, {"always", XFS_DAX_ALWAYS }, {"never", XFS_DAX_NEVER }, {} }; /* * Table driven mount option parser. */ enum { Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups, Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep, Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota, Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce, Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum, }; static const struct fs_parameter_spec xfs_fs_parameters[] = { fsparam_u32("logbufs", Opt_logbufs), fsparam_string("logbsize", Opt_logbsize), fsparam_string("logdev", Opt_logdev), fsparam_string("rtdev", Opt_rtdev), fsparam_flag("wsync", Opt_wsync), fsparam_flag("noalign", Opt_noalign), fsparam_flag("swalloc", Opt_swalloc), fsparam_u32("sunit", Opt_sunit), fsparam_u32("swidth", Opt_swidth), fsparam_flag("nouuid", Opt_nouuid), fsparam_flag("grpid", Opt_grpid), fsparam_flag("nogrpid", Opt_nogrpid), fsparam_flag("bsdgroups", Opt_bsdgroups), fsparam_flag("sysvgroups", Opt_sysvgroups), fsparam_string("allocsize", Opt_allocsize), fsparam_flag("norecovery", Opt_norecovery), fsparam_flag("inode64", Opt_inode64), fsparam_flag("inode32", Opt_inode32), fsparam_flag("ikeep", Opt_ikeep), fsparam_flag("noikeep", Opt_noikeep), fsparam_flag("largeio", Opt_largeio), fsparam_flag("nolargeio", Opt_nolargeio), fsparam_flag("attr2", Opt_attr2), fsparam_flag("noattr2", Opt_noattr2), fsparam_flag("filestreams", Opt_filestreams), fsparam_flag("quota", Opt_quota), fsparam_flag("noquota", Opt_noquota), fsparam_flag("usrquota", Opt_usrquota), fsparam_flag("grpquota", Opt_grpquota), fsparam_flag("prjquota", Opt_prjquota), fsparam_flag("uquota", Opt_uquota), fsparam_flag("gquota", Opt_gquota), fsparam_flag("pquota", Opt_pquota), fsparam_flag("uqnoenforce", Opt_uqnoenforce), fsparam_flag("gqnoenforce", Opt_gqnoenforce), fsparam_flag("pqnoenforce", Opt_pqnoenforce), fsparam_flag("qnoenforce", Opt_qnoenforce), fsparam_flag("discard", Opt_discard), fsparam_flag("nodiscard", Opt_nodiscard), fsparam_flag("dax", Opt_dax), fsparam_enum("dax", Opt_dax_enum, dax_param_enums), {} }; struct proc_xfs_info { uint64_t flag; char *str; }; static int xfs_fs_show_options( struct seq_file *m, struct dentry *root) { static struct proc_xfs_info xfs_info_set[] = { /* the few simple ones we can get from the mount struct */ { XFS_FEAT_IKEEP, ",ikeep" }, { XFS_FEAT_WSYNC, ",wsync" }, { XFS_FEAT_NOALIGN, ",noalign" }, { XFS_FEAT_SWALLOC, ",swalloc" }, { XFS_FEAT_NOUUID, ",nouuid" }, { XFS_FEAT_NORECOVERY, ",norecovery" }, { XFS_FEAT_ATTR2, ",attr2" }, { XFS_FEAT_FILESTREAMS, ",filestreams" }, { XFS_FEAT_GRPID, ",grpid" }, { XFS_FEAT_DISCARD, ",discard" }, { XFS_FEAT_LARGE_IOSIZE, ",largeio" }, { XFS_FEAT_DAX_ALWAYS, ",dax=always" }, { XFS_FEAT_DAX_NEVER, ",dax=never" }, { 0, NULL } }; struct xfs_mount *mp = XFS_M(root->d_sb); struct proc_xfs_info *xfs_infop; for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) { if (mp->m_features & xfs_infop->flag) seq_puts(m, xfs_infop->str); } seq_printf(m, ",inode%d", xfs_has_small_inums(mp) ? 32 : 64); if (xfs_has_allocsize(mp)) seq_printf(m, ",allocsize=%dk", (1 << mp->m_allocsize_log) >> 10); if (mp->m_logbufs > 0) seq_printf(m, ",logbufs=%d", mp->m_logbufs); if (mp->m_logbsize > 0) seq_printf(m, ",logbsize=%dk", mp->m_logbsize >> 10); if (mp->m_logname) seq_show_option(m, "logdev", mp->m_logname); if (mp->m_rtname) seq_show_option(m, "rtdev", mp->m_rtname); if (mp->m_dalign > 0) seq_printf(m, ",sunit=%d", (int)XFS_FSB_TO_BB(mp, mp->m_dalign)); if (mp->m_swidth > 0) seq_printf(m, ",swidth=%d", (int)XFS_FSB_TO_BB(mp, mp->m_swidth)); if (mp->m_qflags & XFS_UQUOTA_ENFD) seq_puts(m, ",usrquota"); else if (mp->m_qflags & XFS_UQUOTA_ACCT) seq_puts(m, ",uqnoenforce"); if (mp->m_qflags & XFS_PQUOTA_ENFD) seq_puts(m, ",prjquota"); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, ",pqnoenforce"); if (mp->m_qflags & XFS_GQUOTA_ENFD) seq_puts(m, ",grpquota"); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, ",gqnoenforce"); if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT)) seq_puts(m, ",noquota"); return 0; } static bool xfs_set_inode_alloc_perag( struct xfs_perag *pag, xfs_ino_t ino, xfs_agnumber_t max_metadata) { if (!xfs_is_inode32(pag_mount(pag))) { set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); return false; } if (ino > XFS_MAXINUMBER_32) { clear_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); return false; } set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); if (pag_agno(pag) < max_metadata) set_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); else clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); return true; } /* * Set parameters for inode allocation heuristics, taking into account * filesystem size and inode32/inode64 mount options; i.e. specifically * whether or not XFS_FEAT_SMALL_INUMS is set. * * Inode allocation patterns are altered only if inode32 is requested * (XFS_FEAT_SMALL_INUMS), and the filesystem is sufficiently large. * If altered, XFS_OPSTATE_INODE32 is set as well. * * An agcount independent of that in the mount structure is provided * because in the growfs case, mp->m_sb.sb_agcount is not yet updated * to the potentially higher ag count. * * Returns the maximum AG index which may contain inodes. */ xfs_agnumber_t xfs_set_inode_alloc( struct xfs_mount *mp, xfs_agnumber_t agcount) { xfs_agnumber_t index; xfs_agnumber_t maxagi = 0; xfs_sb_t *sbp = &mp->m_sb; xfs_agnumber_t max_metadata; xfs_agino_t agino; xfs_ino_t ino; /* * Calculate how much should be reserved for inodes to meet * the max inode percentage. Used only for inode32. */ if (M_IGEO(mp)->maxicount) { uint64_t icount; icount = sbp->sb_dblocks * sbp->sb_imax_pct; do_div(icount, 100); icount += sbp->sb_agblocks - 1; do_div(icount, sbp->sb_agblocks); max_metadata = icount; } else { max_metadata = agcount; } /* Get the last possible inode in the filesystem */ agino = XFS_AGB_TO_AGINO(mp, sbp->sb_agblocks - 1); ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino); /* * If user asked for no more than 32-bit inodes, and the fs is * sufficiently large, set XFS_OPSTATE_INODE32 if we must alter * the allocator to accommodate the request. */ if (xfs_has_small_inums(mp) && ino > XFS_MAXINUMBER_32) xfs_set_inode32(mp); else xfs_clear_inode32(mp); for (index = 0; index < agcount; index++) { struct xfs_perag *pag; ino = XFS_AGINO_TO_INO(mp, index, agino); pag = xfs_perag_get(mp, index); if (xfs_set_inode_alloc_perag(pag, ino, max_metadata)) maxagi++; xfs_perag_put(pag); } return xfs_is_inode32(mp) ? maxagi : agcount; } static int xfs_setup_dax_always( struct xfs_mount *mp) { if (!mp->m_ddev_targp->bt_daxdev && (!mp->m_rtdev_targp || !mp->m_rtdev_targp->bt_daxdev)) { xfs_alert(mp, "DAX unsupported by block device. Turning off DAX."); goto disable_dax; } if (mp->m_super->s_blocksize != PAGE_SIZE) { xfs_alert(mp, "DAX not supported for blocksize. Turning off DAX."); goto disable_dax; } if (xfs_has_reflink(mp) && bdev_is_partition(mp->m_ddev_targp->bt_bdev)) { xfs_alert(mp, "DAX and reflink cannot work with multi-partitions!"); return -EINVAL; } return 0; disable_dax: xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER); return 0; } STATIC int xfs_blkdev_get( xfs_mount_t *mp, const char *name, struct file **bdev_filep) { int error = 0; *bdev_filep = bdev_file_open_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, mp->m_super, &fs_holder_ops); if (IS_ERR(*bdev_filep)) { error = PTR_ERR(*bdev_filep); *bdev_filep = NULL; xfs_warn(mp, "Invalid device [%s], error=%d", name, error); } return error; } STATIC void xfs_shutdown_devices( struct xfs_mount *mp) { /* * Udev is triggered whenever anyone closes a block device or unmounts * a file systemm on a block device. * The default udev rules invoke blkid to read the fs super and create * symlinks to the bdev under /dev/disk. For this, it uses buffered * reads through the page cache. * * xfs_db also uses buffered reads to examine metadata. There is no * coordination between xfs_db and udev, which means that they can run * concurrently. Note there is no coordination between the kernel and * blkid either. * * On a system with 64k pages, the page cache can cache the superblock * and the root inode (and hence the root directory) with the same 64k * page. If udev spawns blkid after the mkfs and the system is busy * enough that it is still running when xfs_db starts up, they'll both * read from the same page in the pagecache. * * The unmount writes updated inode metadata to disk directly. The XFS * buffer cache does not use the bdev pagecache, so it needs to * invalidate that pagecache on unmount. If the above scenario occurs, * the pagecache no longer reflects what's on disk, xfs_db reads the * stale metadata, and fails to find /a. Most of the time this succeeds * because closing a bdev invalidates the page cache, but when processes * race, everyone loses. */ if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { blkdev_issue_flush(mp->m_logdev_targp->bt_bdev); invalidate_bdev(mp->m_logdev_targp->bt_bdev); } if (mp->m_rtdev_targp) { blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); invalidate_bdev(mp->m_rtdev_targp->bt_bdev); } blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); invalidate_bdev(mp->m_ddev_targp->bt_bdev); } /* * The file system configurations are: * (1) device (partition) with data and internal log * (2) logical volume with data and log subvolumes. * (3) logical volume with data, log, and realtime subvolumes. * * We only have to handle opening the log and realtime volumes here if * they are present. The data subvolume has already been opened by * get_sb_bdev() and is stored in sb->s_bdev. */ STATIC int xfs_open_devices( struct xfs_mount *mp) { struct super_block *sb = mp->m_super; struct block_device *ddev = sb->s_bdev; struct file *logdev_file = NULL, *rtdev_file = NULL; int error; /* * Open real time and log devices - order is important. */ if (mp->m_logname) { error = xfs_blkdev_get(mp, mp->m_logname, &logdev_file); if (error) return error; } if (mp->m_rtname) { error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_file); if (error) goto out_close_logdev; if (file_bdev(rtdev_file) == ddev || (logdev_file && file_bdev(rtdev_file) == file_bdev(logdev_file))) { xfs_warn(mp, "Cannot mount filesystem with identical rtdev and ddev/logdev."); error = -EINVAL; goto out_close_rtdev; } } /* * Setup xfs_mount buffer target pointers */ error = -ENOMEM; mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_file); if (!mp->m_ddev_targp) goto out_close_rtdev; if (rtdev_file) { mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_file); if (!mp->m_rtdev_targp) goto out_free_ddev_targ; } if (logdev_file && file_bdev(logdev_file) != ddev) { mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_file); if (!mp->m_logdev_targp) goto out_free_rtdev_targ; } else { mp->m_logdev_targp = mp->m_ddev_targp; /* Handle won't be used, drop it */ if (logdev_file) bdev_fput(logdev_file); } return 0; out_free_rtdev_targ: if (mp->m_rtdev_targp) xfs_free_buftarg(mp->m_rtdev_targp); out_free_ddev_targ: xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: if (rtdev_file) bdev_fput(rtdev_file); out_close_logdev: if (logdev_file) bdev_fput(logdev_file); return error; } /* * Setup xfs_mount buffer target pointers based on superblock */ STATIC int xfs_setup_devices( struct xfs_mount *mp) { int error; error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_sectsize); if (error) return error; if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { unsigned int log_sector_size = BBSIZE; if (xfs_has_sector(mp)) log_sector_size = mp->m_sb.sb_logsectsize; error = xfs_setsize_buftarg(mp->m_logdev_targp, log_sector_size); if (error) return error; } if (mp->m_rtdev_targp) { error = xfs_setsize_buftarg(mp->m_rtdev_targp, mp->m_sb.sb_sectsize); if (error) return error; } return 0; } STATIC int xfs_init_mount_workqueues( struct xfs_mount *mp) { mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), 1, mp->m_super->s_id); if (!mp->m_buf_workqueue) goto out; mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), 0, mp->m_super->s_id); if (!mp->m_unwritten_workqueue) goto out_destroy_buf; mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), 0, mp->m_super->s_id); if (!mp->m_reclaim_workqueue) goto out_destroy_unwritten; mp->m_blockgc_wq = alloc_workqueue("xfs-blockgc/%s", XFS_WQFLAGS(WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM), 0, mp->m_super->s_id); if (!mp->m_blockgc_wq) goto out_destroy_reclaim; mp->m_inodegc_wq = alloc_workqueue("xfs-inodegc/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), 1, mp->m_super->s_id); if (!mp->m_inodegc_wq) goto out_destroy_blockgc; mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", XFS_WQFLAGS(WQ_FREEZABLE), 0, mp->m_super->s_id); if (!mp->m_sync_workqueue) goto out_destroy_inodegc; return 0; out_destroy_inodegc: destroy_workqueue(mp->m_inodegc_wq); out_destroy_blockgc: destroy_workqueue(mp->m_blockgc_wq); out_destroy_reclaim: destroy_workqueue(mp->m_reclaim_workqueue); out_destroy_unwritten: destroy_workqueue(mp->m_unwritten_workqueue); out_destroy_buf: destroy_workqueue(mp->m_buf_workqueue); out: return -ENOMEM; } STATIC void xfs_destroy_mount_workqueues( struct xfs_mount *mp) { destroy_workqueue(mp->m_sync_workqueue); destroy_workqueue(mp->m_blockgc_wq); destroy_workqueue(mp->m_inodegc_wq); destroy_workqueue(mp->m_reclaim_workqueue); destroy_workqueue(mp->m_unwritten_workqueue); destroy_workqueue(mp->m_buf_workqueue); } static void xfs_flush_inodes_worker( struct work_struct *work) { struct xfs_mount *mp = container_of(work, struct xfs_mount, m_flush_inodes_work); struct super_block *sb = mp->m_super; if (down_read_trylock(&sb->s_umount)) { sync_inodes_sb(sb); up_read(&sb->s_umount); } } /* * Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK * or a page lock. We use sync_inodes_sb() here to ensure we block while waiting * for IO to complete so that we effectively throttle multiple callers to the * rate at which IO is completing. */ void xfs_flush_inodes( struct xfs_mount *mp) { /* * If flush_work() returns true then that means we waited for a flush * which was already in progress. Don't bother running another scan. */ if (flush_work(&mp->m_flush_inodes_work)) return; queue_work(mp->m_sync_workqueue, &mp->m_flush_inodes_work); flush_work(&mp->m_flush_inodes_work); } /* Catch misguided souls that try to use this interface on XFS */ STATIC struct inode * xfs_fs_alloc_inode( struct super_block *sb) { BUG(); return NULL; } /* * Now that the generic code is guaranteed not to be accessing * the linux inode, we can inactivate and reclaim the inode. */ STATIC void xfs_fs_destroy_inode( struct inode *inode) { struct xfs_inode *ip = XFS_I(inode); trace_xfs_destroy_inode(ip); ASSERT(!rwsem_is_locked(&inode->i_rwsem)); XFS_STATS_INC(ip->i_mount, vn_rele); XFS_STATS_INC(ip->i_mount, vn_remove); xfs_inode_mark_reclaimable(ip); } static void xfs_fs_dirty_inode( struct inode *inode, int flags) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; if (!(inode->i_sb->s_flags & SB_LAZYTIME)) return; /* * Only do the timestamp update if the inode is dirty (I_DIRTY_SYNC) * and has dirty timestamp (I_DIRTY_TIME). I_DIRTY_TIME can be passed * in flags possibly together with I_DIRTY_SYNC. */ if ((flags & ~I_DIRTY_TIME) != I_DIRTY_SYNC || !(flags & I_DIRTY_TIME)) return; if (xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp)) return; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP); xfs_trans_commit(tp); } /* * Slab object creation initialisation for the XFS inode. * This covers only the idempotent fields in the XFS inode; * all other fields need to be initialised on allocation * from the slab. This avoids the need to repeatedly initialise * fields in the xfs inode that left in the initialise state * when freeing the inode. */ STATIC void xfs_fs_inode_init_once( void *inode) { struct xfs_inode *ip = inode; memset(ip, 0, sizeof(struct xfs_inode)); /* vfs inode */ inode_init_once(VFS_I(ip)); /* xfs inode */ atomic_set(&ip->i_pincount, 0); spin_lock_init(&ip->i_flags_lock); init_rwsem(&ip->i_lock); } /* * We do an unlocked check for XFS_IDONTCACHE here because we are already * serialised against cache hits here via the inode->i_lock and igrab() in * xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be * racing with us, and it avoids needing to grab a spinlock here for every inode * we drop the final reference on. */ STATIC int xfs_fs_drop_inode( struct inode *inode) { struct xfs_inode *ip = XFS_I(inode); /* * If this unlinked inode is in the middle of recovery, don't * drop the inode just yet; log recovery will take care of * that. See the comment for this inode flag. */ if (ip->i_flags & XFS_IRECOVERY) { ASSERT(xlog_recovery_needed(ip->i_mount->m_log)); return 0; } return generic_drop_inode(inode); } static void xfs_mount_free( struct xfs_mount *mp) { if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) xfs_free_buftarg(mp->m_logdev_targp); if (mp->m_rtdev_targp) xfs_free_buftarg(mp->m_rtdev_targp); if (mp->m_ddev_targp) xfs_free_buftarg(mp->m_ddev_targp); debugfs_remove(mp->m_debugfs); kfree(mp->m_rtname); kfree(mp->m_logname); kfree(mp); } STATIC int xfs_fs_sync_fs( struct super_block *sb, int wait) { struct xfs_mount *mp = XFS_M(sb); int error; trace_xfs_fs_sync_fs(mp, __return_address); /* * Doing anything during the async pass would be counterproductive. */ if (!wait) return 0; error = xfs_log_force(mp, XFS_LOG_SYNC); if (error) return error; if (laptop_mode) { /* * The disk must be active because we're syncing. * We schedule log work now (now that the disk is * active) instead of later (when it might not be). */ flush_delayed_work(&mp->m_log->l_work); } /* * If we are called with page faults frozen out, it means we are about * to freeze the transaction subsystem. Take the opportunity to shut * down inodegc because once SB_FREEZE_FS is set it's too late to * prevent inactivation races with freeze. The fs doesn't get called * again by the freezing process until after SB_FREEZE_FS has been set, * so it's now or never. Same logic applies to speculative allocation * garbage collection. * * We don't care if this is a normal syncfs call that does this or * freeze that does this - we can run this multiple times without issue * and we won't race with a restart because a restart can only occur * when the state is either SB_FREEZE_FS or SB_FREEZE_COMPLETE. */ if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) { xfs_inodegc_stop(mp); xfs_blockgc_stop(mp); } return 0; } static xfs_extlen_t xfs_internal_log_size( struct xfs_mount *mp) { if (!mp->m_sb.sb_logstart) return 0; return mp->m_sb.sb_logblocks; } static void xfs_statfs_data( struct xfs_mount *mp, struct kstatfs *st) { int64_t fdblocks = percpu_counter_sum(&mp->m_fdblocks); /* make sure st->f_bfree does not underflow */ st->f_bfree = max(0LL, fdblocks - xfs_fdblocks_unavailable(mp)); /* * sb_dblocks can change during growfs, but nothing cares about reporting * the old or new value during growfs. */ st->f_blocks = mp->m_sb.sb_dblocks - xfs_internal_log_size(mp); } /* * When stat(v)fs is called on a file with the realtime bit set or a directory * with the rtinherit bit, report freespace information for the RT device * instead of the main data device. */ static void xfs_statfs_rt( struct xfs_mount *mp, struct kstatfs *st) { st->f_bfree = xfs_rtbxlen_to_blen(mp, percpu_counter_sum_positive(&mp->m_frextents)); st->f_blocks = mp->m_sb.sb_rblocks; } static void xfs_statfs_inodes( struct xfs_mount *mp, struct kstatfs *st) { uint64_t icount = percpu_counter_sum(&mp->m_icount); uint64_t ifree = percpu_counter_sum(&mp->m_ifree); uint64_t fakeinos = XFS_FSB_TO_INO(mp, st->f_bfree); st->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); if (M_IGEO(mp)->maxicount) st->f_files = min_t(typeof(st->f_files), st->f_files, M_IGEO(mp)->maxicount); /* If sb_icount overshot maxicount, report actual allocation */ st->f_files = max_t(typeof(st->f_files), st->f_files, mp->m_sb.sb_icount); /* Make sure st->f_ffree does not underflow */ st->f_ffree = max_t(int64_t, 0, st->f_files - (icount - ifree)); } STATIC int xfs_fs_statfs( struct dentry *dentry, struct kstatfs *st) { struct xfs_mount *mp = XFS_M(dentry->d_sb); struct xfs_inode *ip = XFS_I(d_inode(dentry)); /* * Expedite background inodegc but don't wait. We do not want to block * here waiting hours for a billion extent file to be truncated. */ xfs_inodegc_push(mp); st->f_type = XFS_SUPER_MAGIC; st->f_namelen = MAXNAMELEN - 1; st->f_bsize = mp->m_sb.sb_blocksize; st->f_fsid = u64_to_fsid(huge_encode_dev(mp->m_ddev_targp->bt_dev)); xfs_statfs_data(mp, st); xfs_statfs_inodes(mp, st); if (XFS_IS_REALTIME_MOUNT(mp) && (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) xfs_statfs_rt(mp, st); if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) && ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) == (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD)) xfs_qm_statvfs(ip, st); /* * XFS does not distinguish between blocks available to privileged and * unprivileged users. */ st->f_bavail = st->f_bfree; return 0; } STATIC void xfs_save_resvblks(struct xfs_mount *mp) { mp->m_resblks_save = mp->m_resblks; xfs_reserve_blocks(mp, 0); } STATIC void xfs_restore_resvblks(struct xfs_mount *mp) { uint64_t resblks; if (mp->m_resblks_save) { resblks = mp->m_resblks_save; mp->m_resblks_save = 0; } else resblks = xfs_default_resblks(mp); xfs_reserve_blocks(mp, resblks); } /* * Second stage of a freeze. The data is already frozen so we only * need to take care of the metadata. Once that's done sync the superblock * to the log to dirty it in case of a crash while frozen. This ensures that we * will recover the unlinked inode lists on the next mount. */ STATIC int xfs_fs_freeze( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); unsigned int flags; int ret; /* * The filesystem is now frozen far enough that memory reclaim * cannot safely operate on the filesystem. Hence we need to * set a GFP_NOFS context here to avoid recursion deadlocks. */ flags = memalloc_nofs_save(); xfs_save_resvblks(mp); ret = xfs_log_quiesce(mp); memalloc_nofs_restore(flags); /* * For read-write filesystems, we need to restart the inodegc on error * because we stopped it at SB_FREEZE_PAGEFAULT level and a thaw is not * going to be run to restart it now. We are at SB_FREEZE_FS level * here, so we can restart safely without racing with a stop in * xfs_fs_sync_fs(). */ if (ret && !xfs_is_readonly(mp)) { xfs_blockgc_start(mp); xfs_inodegc_start(mp); } return ret; } STATIC int xfs_fs_unfreeze( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); xfs_restore_resvblks(mp); xfs_log_work_queue(mp); /* * Don't reactivate the inodegc worker on a readonly filesystem because * inodes are sent directly to reclaim. Don't reactivate the blockgc * worker because there are no speculative preallocations on a readonly * filesystem. */ if (!xfs_is_readonly(mp)) { xfs_blockgc_start(mp); xfs_inodegc_start(mp); } return 0; } /* * This function fills in xfs_mount_t fields based on mount args. * Note: the superblock _has_ now been read in. */ STATIC int xfs_finish_flags( struct xfs_mount *mp) { /* Fail a mount where the logbuf is smaller than the log stripe */ if (xfs_has_logv2(mp)) { if (mp->m_logbsize <= 0 && mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) { mp->m_logbsize = mp->m_sb.sb_logsunit; } else if (mp->m_logbsize > 0 && mp->m_logbsize < mp->m_sb.sb_logsunit) { xfs_warn(mp, "logbuf size must be greater than or equal to log stripe size"); return -EINVAL; } } else { /* Fail a mount if the logbuf is larger than 32K */ if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) { xfs_warn(mp, "logbuf size for version 1 logs must be 16K or 32K"); return -EINVAL; } } /* * V5 filesystems always use attr2 format for attributes. */ if (xfs_has_crc(mp) && xfs_has_noattr2(mp)) { xfs_warn(mp, "Cannot mount a V5 filesystem as noattr2. " "attr2 is always enabled for V5 filesystems."); return -EINVAL; } /* * prohibit r/w mounts of read-only filesystems */ if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !xfs_is_readonly(mp)) { xfs_warn(mp, "cannot mount a read-only filesystem as read-write"); return -EROFS; } if ((mp->m_qflags & XFS_GQUOTA_ACCT) && (mp->m_qflags & XFS_PQUOTA_ACCT) && !xfs_has_pquotino(mp)) { xfs_warn(mp, "Super block does not support project and group quota together"); return -EINVAL; } return 0; } static int xfs_init_percpu_counters( struct xfs_mount *mp) { int error; error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL); if (error) return -ENOMEM; error = percpu_counter_init(&mp->m_ifree, 0, GFP_KERNEL); if (error) goto free_icount; error = percpu_counter_init(&mp->m_fdblocks, 0, GFP_KERNEL); if (error) goto free_ifree; error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL); if (error) goto free_fdblocks; error = percpu_counter_init(&mp->m_delalloc_rtextents, 0, GFP_KERNEL); if (error) goto free_delalloc; error = percpu_counter_init(&mp->m_frextents, 0, GFP_KERNEL); if (error) goto free_delalloc_rt; return 0; free_delalloc_rt: percpu_counter_destroy(&mp->m_delalloc_rtextents); free_delalloc: percpu_counter_destroy(&mp->m_delalloc_blks); free_fdblocks: percpu_counter_destroy(&mp->m_fdblocks); free_ifree: percpu_counter_destroy(&mp->m_ifree); free_icount: percpu_counter_destroy(&mp->m_icount); return -ENOMEM; } void xfs_reinit_percpu_counters( struct xfs_mount *mp) { percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount); percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree); percpu_counter_set(&mp->m_fdblocks, mp->m_sb.sb_fdblocks); percpu_counter_set(&mp->m_frextents, mp->m_sb.sb_frextents); } static void xfs_destroy_percpu_counters( struct xfs_mount *mp) { percpu_counter_destroy(&mp->m_icount); percpu_counter_destroy(&mp->m_ifree); percpu_counter_destroy(&mp->m_fdblocks); ASSERT(xfs_is_shutdown(mp) || percpu_counter_sum(&mp->m_delalloc_rtextents) == 0); percpu_counter_destroy(&mp->m_delalloc_rtextents); ASSERT(xfs_is_shutdown(mp) || percpu_counter_sum(&mp->m_delalloc_blks) == 0); percpu_counter_destroy(&mp->m_delalloc_blks); percpu_counter_destroy(&mp->m_frextents); } static int xfs_inodegc_init_percpu( struct xfs_mount *mp) { struct xfs_inodegc *gc; int cpu; mp->m_inodegc = alloc_percpu(struct xfs_inodegc); if (!mp->m_inodegc) return -ENOMEM; for_each_possible_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); gc->cpu = cpu; gc->mp = mp; init_llist_head(&gc->list); gc->items = 0; gc->error = 0; INIT_DELAYED_WORK(&gc->work, xfs_inodegc_worker); } return 0; } static void xfs_inodegc_free_percpu( struct xfs_mount *mp) { if (!mp->m_inodegc) return; free_percpu(mp->m_inodegc); } static void xfs_fs_put_super( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); xfs_notice(mp, "Unmounting Filesystem %pU", &mp->m_sb.sb_uuid); xfs_filestream_unmount(mp); xfs_unmountfs(mp); xfs_rtmount_freesb(mp); xfs_freesb(mp); xchk_mount_stats_free(mp); free_percpu(mp->m_stats.xs_stats); xfs_inodegc_free_percpu(mp); xfs_destroy_percpu_counters(mp); xfs_destroy_mount_workqueues(mp); xfs_shutdown_devices(mp); } static long xfs_fs_nr_cached_objects( struct super_block *sb, struct shrink_control *sc) { /* Paranoia: catch incorrect calls during mount setup or teardown */ if (WARN_ON_ONCE(!sb->s_fs_info)) return 0; return xfs_reclaim_inodes_count(XFS_M(sb)); } static long xfs_fs_free_cached_objects( struct super_block *sb, struct shrink_control *sc) { return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan); } static void xfs_fs_shutdown( struct super_block *sb) { xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED); } static const struct super_operations xfs_super_operations = { .alloc_inode = xfs_fs_alloc_inode, .destroy_inode = xfs_fs_destroy_inode, .dirty_inode = xfs_fs_dirty_inode, .drop_inode = xfs_fs_drop_inode, .put_super = xfs_fs_put_super, .sync_fs = xfs_fs_sync_fs, .freeze_fs = xfs_fs_freeze, .unfreeze_fs = xfs_fs_unfreeze, .statfs = xfs_fs_statfs, .show_options = xfs_fs_show_options, .nr_cached_objects = xfs_fs_nr_cached_objects, .free_cached_objects = xfs_fs_free_cached_objects, .shutdown = xfs_fs_shutdown, }; static int suffix_kstrtoint( const char *s, unsigned int base, int *res) { int last, shift_left_factor = 0, _res; char *value; int ret = 0; value = kstrdup(s, GFP_KERNEL); if (!value) return -ENOMEM; last = strlen(value) - 1; if (value[last] == 'K' || value[last] == 'k') { shift_left_factor = 10; value[last] = '\0'; } if (value[last] == 'M' || value[last] == 'm') { shift_left_factor = 20; value[last] = '\0'; } if (value[last] == 'G' || value[last] == 'g') { shift_left_factor = 30; value[last] = '\0'; } if (kstrtoint(value, base, &_res)) ret = -EINVAL; kfree(value); *res = _res << shift_left_factor; return ret; } static inline void xfs_fs_warn_deprecated( struct fs_context *fc, struct fs_parameter *param, uint64_t flag, bool value) { /* Don't print the warning if reconfiguring and current mount point * already had the flag set */ if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) && !!(XFS_M(fc->root->d_sb)->m_features & flag) == value) return; xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key); } /* * Set mount state from a mount option. * * NOTE: mp->m_super is NULL here! */ static int xfs_fs_parse_param( struct fs_context *fc, struct fs_parameter *param) { struct xfs_mount *parsing_mp = fc->s_fs_info; struct fs_parse_result result; int size = 0; int opt; BUILD_BUG_ON(XFS_QFLAGS_MNTOPTS & XFS_MOUNT_QUOTA_ALL); opt = fs_parse(fc, xfs_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_logbufs: parsing_mp->m_logbufs = result.uint_32; return 0; case Opt_logbsize: if (suffix_kstrtoint(param->string, 10, &parsing_mp->m_logbsize)) return -EINVAL; return 0; case Opt_logdev: kfree(parsing_mp->m_logname); parsing_mp->m_logname = kstrdup(param->string, GFP_KERNEL); if (!parsing_mp->m_logname) return -ENOMEM; return 0; case Opt_rtdev: kfree(parsing_mp->m_rtname); parsing_mp->m_rtname = kstrdup(param->string, GFP_KERNEL); if (!parsing_mp->m_rtname) return -ENOMEM; return 0; case Opt_allocsize: if (suffix_kstrtoint(param->string, 10, &size)) return -EINVAL; parsing_mp->m_allocsize_log = ffs(size) - 1; parsing_mp->m_features |= XFS_FEAT_ALLOCSIZE; return 0; case Opt_grpid: case Opt_bsdgroups: parsing_mp->m_features |= XFS_FEAT_GRPID; return 0; case Opt_nogrpid: case Opt_sysvgroups: parsing_mp->m_features &= ~XFS_FEAT_GRPID; return 0; case Opt_wsync: parsing_mp->m_features |= XFS_FEAT_WSYNC; return 0; case Opt_norecovery: parsing_mp->m_features |= XFS_FEAT_NORECOVERY; return 0; case Opt_noalign: parsing_mp->m_features |= XFS_FEAT_NOALIGN; return 0; case Opt_swalloc: parsing_mp->m_features |= XFS_FEAT_SWALLOC; return 0; case Opt_sunit: parsing_mp->m_dalign = result.uint_32; return 0; case Opt_swidth: parsing_mp->m_swidth = result.uint_32; return 0; case Opt_inode32: parsing_mp->m_features |= XFS_FEAT_SMALL_INUMS; return 0; case Opt_inode64: parsing_mp->m_features &= ~XFS_FEAT_SMALL_INUMS; return 0; case Opt_nouuid: parsing_mp->m_features |= XFS_FEAT_NOUUID; return 0; case Opt_largeio: parsing_mp->m_features |= XFS_FEAT_LARGE_IOSIZE; return 0; case Opt_nolargeio: parsing_mp->m_features &= ~XFS_FEAT_LARGE_IOSIZE; return 0; case Opt_filestreams: parsing_mp->m_features |= XFS_FEAT_FILESTREAMS; return 0; case Opt_noquota: parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_quota: case Opt_uquota: case Opt_usrquota: parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ENFD); parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_qnoenforce: case Opt_uqnoenforce: parsing_mp->m_qflags |= XFS_UQUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_pquota: case Opt_prjquota: parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ENFD); parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_pqnoenforce: parsing_mp->m_qflags |= XFS_PQUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_gquota: case Opt_grpquota: parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ENFD); parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_gqnoenforce: parsing_mp->m_qflags |= XFS_GQUOTA_ACCT; parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD; parsing_mp->m_qflags |= XFS_QFLAGS_MNTOPTS; return 0; case Opt_discard: parsing_mp->m_features |= XFS_FEAT_DISCARD; return 0; case Opt_nodiscard: parsing_mp->m_features &= ~XFS_FEAT_DISCARD; return 0; #ifdef CONFIG_FS_DAX case Opt_dax: xfs_mount_set_dax_mode(parsing_mp, XFS_DAX_ALWAYS); return 0; case Opt_dax_enum: xfs_mount_set_dax_mode(parsing_mp, result.uint_32); return 0; #endif /* Following mount options will be removed in September 2025 */ case Opt_ikeep: xfs_fs_warn_deprecated(fc, param, XFS_FEAT_IKEEP, true); parsing_mp->m_features |= XFS_FEAT_IKEEP; return 0; case Opt_noikeep: xfs_fs_warn_deprecated(fc, param, XFS_FEAT_IKEEP, false); parsing_mp->m_features &= ~XFS_FEAT_IKEEP; return 0; case Opt_attr2: xfs_fs_warn_deprecated(fc, param, XFS_FEAT_ATTR2, true); parsing_mp->m_features |= XFS_FEAT_ATTR2; return 0; case Opt_noattr2: xfs_fs_warn_deprecated(fc, param, XFS_FEAT_NOATTR2, true); parsing_mp->m_features |= XFS_FEAT_NOATTR2; return 0; default: xfs_warn(parsing_mp, "unknown mount option [%s].", param->key); return -EINVAL; } return 0; } static int xfs_fs_validate_params( struct xfs_mount *mp) { /* No recovery flag requires a read-only mount */ if (xfs_has_norecovery(mp) && !xfs_is_readonly(mp)) { xfs_warn(mp, "no-recovery mounts must be read-only."); return -EINVAL; } /* * We have not read the superblock at this point, so only the attr2 * mount option can set the attr2 feature by this stage. */ if (xfs_has_attr2(mp) && xfs_has_noattr2(mp)) { xfs_warn(mp, "attr2 and noattr2 cannot both be specified."); return -EINVAL; } if (xfs_has_noalign(mp) && (mp->m_dalign || mp->m_swidth)) { xfs_warn(mp, "sunit and swidth options incompatible with the noalign option"); return -EINVAL; } if (!IS_ENABLED(CONFIG_XFS_QUOTA) && (mp->m_qflags & ~XFS_QFLAGS_MNTOPTS)) { xfs_warn(mp, "quota support not available in this kernel."); return -EINVAL; } if ((mp->m_dalign && !mp->m_swidth) || (!mp->m_dalign && mp->m_swidth)) { xfs_warn(mp, "sunit and swidth must be specified together"); return -EINVAL; } if (mp->m_dalign && (mp->m_swidth % mp->m_dalign != 0)) { xfs_warn(mp, "stripe width (%d) must be a multiple of the stripe unit (%d)", mp->m_swidth, mp->m_dalign); return -EINVAL; } if (mp->m_logbufs != -1 && mp->m_logbufs != 0 && (mp->m_logbufs < XLOG_MIN_ICLOGS || mp->m_logbufs > XLOG_MAX_ICLOGS)) { xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]", mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS); return -EINVAL; } if (mp->m_logbsize != -1 && mp->m_logbsize != 0 && (mp->m_logbsize < XLOG_MIN_RECORD_BSIZE || mp->m_logbsize > XLOG_MAX_RECORD_BSIZE || !is_power_of_2(mp->m_logbsize))) { xfs_warn(mp, "invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]", mp->m_logbsize); return -EINVAL; } if (xfs_has_allocsize(mp) && (mp->m_allocsize_log > XFS_MAX_IO_LOG || mp->m_allocsize_log < XFS_MIN_IO_LOG)) { xfs_warn(mp, "invalid log iosize: %d [not %d-%d]", mp->m_allocsize_log, XFS_MIN_IO_LOG, XFS_MAX_IO_LOG); return -EINVAL; } return 0; } struct dentry * xfs_debugfs_mkdir( const char *name, struct dentry *parent) { struct dentry *child; /* Apparently we're expected to ignore error returns?? */ child = debugfs_create_dir(name, parent); if (IS_ERR(child)) return NULL; return child; } static int xfs_fs_fill_super( struct super_block *sb, struct fs_context *fc) { struct xfs_mount *mp = sb->s_fs_info; struct inode *root; int flags = 0, error; mp->m_super = sb; /* * Copy VFS mount flags from the context now that all parameter parsing * is guaranteed to have been completed by either the old mount API or * the newer fsopen/fsconfig API. */ if (fc->sb_flags & SB_RDONLY) xfs_set_readonly(mp); if (fc->sb_flags & SB_DIRSYNC) mp->m_features |= XFS_FEAT_DIRSYNC; if (fc->sb_flags & SB_SYNCHRONOUS) mp->m_features |= XFS_FEAT_WSYNC; error = xfs_fs_validate_params(mp); if (error) return error; sb_min_blocksize(sb, BBSIZE); sb->s_xattr = xfs_xattr_handlers; sb->s_export_op = &xfs_export_operations; #ifdef CONFIG_XFS_QUOTA sb->s_qcop = &xfs_quotactl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif sb->s_op = &xfs_super_operations; /* * Delay mount work if the debug hook is set. This is debug * instrumention to coordinate simulation of xfs mount failures with * VFS superblock operations */ if (xfs_globals.mount_delay) { xfs_notice(mp, "Delaying mount for %d seconds.", xfs_globals.mount_delay); msleep(xfs_globals.mount_delay * 1000); } if (fc->sb_flags & SB_SILENT) flags |= XFS_MFSI_QUIET; error = xfs_open_devices(mp); if (error) return error; if (xfs_debugfs) { mp->m_debugfs = xfs_debugfs_mkdir(mp->m_super->s_id, xfs_debugfs); } else { mp->m_debugfs = NULL; } error = xfs_init_mount_workqueues(mp); if (error) goto out_shutdown_devices; error = xfs_init_percpu_counters(mp); if (error) goto out_destroy_workqueues; error = xfs_inodegc_init_percpu(mp); if (error) goto out_destroy_counters; /* Allocate stats memory before we do operations that might use it */ mp->m_stats.xs_stats = alloc_percpu(struct xfsstats); if (!mp->m_stats.xs_stats) { error = -ENOMEM; goto out_destroy_inodegc; } error = xchk_mount_stats_alloc(mp); if (error) goto out_free_stats; error = xfs_readsb(mp, flags); if (error) goto out_free_scrub_stats; error = xfs_finish_flags(mp); if (error) goto out_free_sb; error = xfs_setup_devices(mp); if (error) goto out_free_sb; /* * V4 support is undergoing deprecation. * * Note: this has to use an open coded m_features check as xfs_has_crc * always returns false for !CONFIG_XFS_SUPPORT_V4. */ if (!(mp->m_features & XFS_FEAT_CRC)) { if (!IS_ENABLED(CONFIG_XFS_SUPPORT_V4)) { xfs_warn(mp, "Deprecated V4 format (crc=0) not supported by kernel."); error = -EINVAL; goto out_free_sb; } xfs_warn_once(mp, "Deprecated V4 format (crc=0) will not be supported after September 2030."); } /* ASCII case insensitivity is undergoing deprecation. */ if (xfs_has_asciici(mp)) { #ifdef CONFIG_XFS_SUPPORT_ASCII_CI xfs_warn_once(mp, "Deprecated ASCII case-insensitivity feature (ascii-ci=1) will not be supported after September 2030."); #else xfs_warn(mp, "Deprecated ASCII case-insensitivity feature (ascii-ci=1) not supported by kernel."); error = -EINVAL; goto out_free_sb; #endif } /* Filesystem claims it needs repair, so refuse the mount. */ if (xfs_has_needsrepair(mp)) { xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair."); error = -EFSCORRUPTED; goto out_free_sb; } /* * Don't touch the filesystem if a user tool thinks it owns the primary * superblock. mkfs doesn't clear the flag from secondary supers, so * we don't check them at all. */ if (mp->m_sb.sb_inprogress) { xfs_warn(mp, "Offline file system operation in progress!"); error = -EFSCORRUPTED; goto out_free_sb; } if (mp->m_sb.sb_blocksize > PAGE_SIZE) { size_t max_folio_size = mapping_max_folio_size_supported(); if (!xfs_has_crc(mp)) { xfs_warn(mp, "V4 Filesystem with blocksize %d bytes. Only pagesize (%ld) or less is supported.", mp->m_sb.sb_blocksize, PAGE_SIZE); error = -ENOSYS; goto out_free_sb; } if (mp->m_sb.sb_blocksize > max_folio_size) { xfs_warn(mp, "block size (%u bytes) not supported; Only block size (%zu) or less is supported", mp->m_sb.sb_blocksize, max_folio_size); error = -ENOSYS; goto out_free_sb; } xfs_warn_experimental(mp, XFS_EXPERIMENTAL_LBS); } /* Ensure this filesystem fits in the page cache limits */ if (xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_dblocks) || xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_rblocks)) { xfs_warn(mp, "file system too large to be mounted on this system."); error = -EFBIG; goto out_free_sb; } /* * XFS block mappings use 54 bits to store the logical block offset. * This should suffice to handle the maximum file size that the VFS * supports (currently 2^63 bytes on 64-bit and ULONG_MAX << PAGE_SHIFT * bytes on 32-bit), but as XFS and VFS have gotten the s_maxbytes * calculation wrong on 32-bit kernels in the past, we'll add a WARN_ON * to check this assertion. * * Avoid integer overflow by comparing the maximum bmbt offset to the * maximum pagecache offset in units of fs blocks. */ if (!xfs_verify_fileoff(mp, XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE))) { xfs_warn(mp, "MAX_LFS_FILESIZE block offset (%llu) exceeds extent map maximum (%llu)!", XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE), XFS_MAX_FILEOFF); error = -EINVAL; goto out_free_sb; } error = xfs_rtmount_readsb(mp); if (error) goto out_free_sb; error = xfs_filestream_mount(mp); if (error) goto out_free_rtsb; /* * we must configure the block size in the superblock before we run the * full mount process as the mount process can lookup and cache inodes. */ sb->s_magic = XFS_SUPER_MAGIC; sb->s_blocksize = mp->m_sb.sb_blocksize; sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_max_links = XFS_MAXLINK; sb->s_time_gran = 1; if (xfs_has_bigtime(mp)) { sb->s_time_min = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MIN); sb->s_time_max = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MAX); } else { sb->s_time_min = XFS_LEGACY_TIME_MIN; sb->s_time_max = XFS_LEGACY_TIME_MAX; } trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max); sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM; set_posix_acl_flag(sb); /* version 5 superblocks support inode version counters. */ if (xfs_has_crc(mp)) sb->s_flags |= SB_I_VERSION; if (xfs_has_dax_always(mp)) { error = xfs_setup_dax_always(mp); if (error) goto out_filestream_unmount; } if (xfs_has_discard(mp) && !bdev_max_discard_sectors(sb->s_bdev)) { xfs_warn(mp, "mounting with \"discard\" option, but the device does not support discard"); mp->m_features &= ~XFS_FEAT_DISCARD; } if (xfs_has_metadir(mp)) xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR); if (xfs_has_reflink(mp)) { if (xfs_has_realtime(mp) && !xfs_reflink_supports_rextsize(mp, mp->m_sb.sb_rextsize)) { xfs_alert(mp, "reflink not compatible with realtime extent size %u!", mp->m_sb.sb_rextsize); error = -EINVAL; goto out_filestream_unmount; } if (xfs_globals.always_cow) { xfs_info(mp, "using DEBUG-only always_cow mode."); mp->m_always_cow = true; } } if (xfs_has_exchange_range(mp)) xfs_warn_experimental(mp, XFS_EXPERIMENTAL_EXCHRANGE); if (xfs_has_parent(mp)) xfs_warn_experimental(mp, XFS_EXPERIMENTAL_PPTR); /* * If no quota mount options were provided, maybe we'll try to pick * up the quota accounting and enforcement flags from the ondisk sb. */ if (!(mp->m_qflags & XFS_QFLAGS_MNTOPTS)) xfs_set_resuming_quotaon(mp); mp->m_qflags &= ~XFS_QFLAGS_MNTOPTS; error = xfs_mountfs(mp); if (error) goto out_filestream_unmount; root = igrab(VFS_I(mp->m_rootip)); if (!root) { error = -ENOENT; goto out_unmount; } sb->s_root = d_make_root(root); if (!sb->s_root) { error = -ENOMEM; goto out_unmount; } return 0; out_filestream_unmount: xfs_filestream_unmount(mp); out_free_rtsb: xfs_rtmount_freesb(mp); out_free_sb: xfs_freesb(mp); out_free_scrub_stats: xchk_mount_stats_free(mp); out_free_stats: free_percpu(mp->m_stats.xs_stats); out_destroy_inodegc: xfs_inodegc_free_percpu(mp); out_destroy_counters: xfs_destroy_percpu_counters(mp); out_destroy_workqueues: xfs_destroy_mount_workqueues(mp); out_shutdown_devices: xfs_shutdown_devices(mp); return error; out_unmount: xfs_filestream_unmount(mp); xfs_unmountfs(mp); goto out_free_rtsb; } static int xfs_fs_get_tree( struct fs_context *fc) { return get_tree_bdev(fc, xfs_fs_fill_super); } static int xfs_remount_rw( struct xfs_mount *mp) { struct xfs_sb *sbp = &mp->m_sb; int error; if (xfs_has_norecovery(mp)) { xfs_warn(mp, "ro->rw transition prohibited on norecovery mount"); return -EINVAL; } if (xfs_sb_is_v5(sbp) && xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_warn(mp, "ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem", (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_UNKNOWN)); return -EINVAL; } xfs_clear_readonly(mp); /* * If this is the first remount to writeable state we might have some * superblock changes to update. */ if (mp->m_update_sb) { error = xfs_sync_sb(mp, false); if (error) { xfs_warn(mp, "failed to write sb changes"); return error; } mp->m_update_sb = false; } /* * Fill out the reserve pool if it is empty. Use the stashed value if * it is non-zero, otherwise go with the default. */ xfs_restore_resvblks(mp); xfs_log_work_queue(mp); xfs_blockgc_start(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); if (error && error != -ENOSPC) return error; /* Re-enable the background inode inactivation worker. */ xfs_inodegc_start(mp); return 0; } static int xfs_remount_ro( struct xfs_mount *mp) { struct xfs_icwalk icw = { .icw_flags = XFS_ICWALK_FLAG_SYNC, }; int error; /* Flush all the dirty data to disk. */ error = sync_filesystem(mp->m_super); if (error) return error; /* * Cancel background eofb scanning so it cannot race with the final * log force+buftarg wait and deadlock the remount. */ xfs_blockgc_stop(mp); /* * Clear out all remaining COW staging extents and speculative post-EOF * preallocations so that we don't leave inodes requiring inactivation * cleanups during reclaim on a read-only mount. We must process every * cached inode, so this requires a synchronous cache scan. */ error = xfs_blockgc_free_space(mp, &icw); if (error) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } /* * Stop the inodegc background worker. xfs_fs_reconfigure already * flushed all pending inodegc work when it sync'd the filesystem. * The VFS holds s_umount, so we know that inodes cannot enter * xfs_fs_destroy_inode during a remount operation. In readonly mode * we send inodes straight to reclaim, so no inodes will be queued. */ xfs_inodegc_stop(mp); /* Free the per-AG metadata reservation pool. */ xfs_fs_unreserve_ag_blocks(mp); /* * Before we sync the metadata, we need to free up the reserve block * pool so that the used block count in the superblock on disk is * correct at the end of the remount. Stash the current* reserve pool * size so that if we get remounted rw, we can return it to the same * size. */ xfs_save_resvblks(mp); xfs_log_clean(mp); xfs_set_readonly(mp); return 0; } /* * Logically we would return an error here to prevent users from believing * they might have changed mount options using remount which can't be changed. * * But unfortunately mount(8) adds all options from mtab and fstab to the mount * arguments in some cases so we can't blindly reject options, but have to * check for each specified option if it actually differs from the currently * set option and only reject it if that's the case. * * Until that is implemented we return success for every remount request, and * silently ignore all options that we can't actually change. */ static int xfs_fs_reconfigure( struct fs_context *fc) { struct xfs_mount *mp = XFS_M(fc->root->d_sb); struct xfs_mount *new_mp = fc->s_fs_info; int flags = fc->sb_flags; int error; new_mp->m_qflags &= ~XFS_QFLAGS_MNTOPTS; /* version 5 superblocks always support version counters. */ if (xfs_has_crc(mp)) fc->sb_flags |= SB_I_VERSION; error = xfs_fs_validate_params(new_mp); if (error) return error; /* inode32 -> inode64 */ if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) { mp->m_features &= ~XFS_FEAT_SMALL_INUMS; mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount); } /* inode64 -> inode32 */ if (!xfs_has_small_inums(mp) && xfs_has_small_inums(new_mp)) { mp->m_features |= XFS_FEAT_SMALL_INUMS; mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount); } /* ro -> rw */ if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) { error = xfs_remount_rw(mp); if (error) return error; } /* rw -> ro */ if (!xfs_is_readonly(mp) && (flags & SB_RDONLY)) { error = xfs_remount_ro(mp); if (error) return error; } return 0; } static void xfs_fs_free( struct fs_context *fc) { struct xfs_mount *mp = fc->s_fs_info; /* * mp is stored in the fs_context when it is initialized. * mp is transferred to the superblock on a successful mount, * but if an error occurs before the transfer we have to free * it here. */ if (mp) xfs_mount_free(mp); } static const struct fs_context_operations xfs_context_ops = { .parse_param = xfs_fs_parse_param, .get_tree = xfs_fs_get_tree, .reconfigure = xfs_fs_reconfigure, .free = xfs_fs_free, }; /* * WARNING: do not initialise any parameters in this function that depend on * mount option parsing having already been performed as this can be called from * fsopen() before any parameters have been set. */ static int xfs_init_fs_context( struct fs_context *fc) { struct xfs_mount *mp; int i; mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL | __GFP_NOFAIL); if (!mp) return -ENOMEM; spin_lock_init(&mp->m_sb_lock); for (i = 0; i < XG_TYPE_MAX; i++) xa_init(&mp->m_groups[i].xa); mutex_init(&mp->m_growlock); INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker); INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); mp->m_kobj.kobject.kset = xfs_kset; /* * We don't create the finobt per-ag space reservation until after log * recovery, so we must set this to true so that an ifree transaction * started during log recovery will not depend on space reservations * for finobt expansion. */ mp->m_finobt_nores = true; /* * These can be overridden by the mount option parsing. */ mp->m_logbufs = -1; mp->m_logbsize = -1; mp->m_allocsize_log = 16; /* 64k */ xfs_hooks_init(&mp->m_dir_update_hooks); fc->s_fs_info = mp; fc->ops = &xfs_context_ops; return 0; } static void xfs_kill_sb( struct super_block *sb) { kill_block_super(sb); xfs_mount_free(XFS_M(sb)); } static struct file_system_type xfs_fs_type = { .owner = THIS_MODULE, .name = "xfs", .init_fs_context = xfs_init_fs_context, .parameters = xfs_fs_parameters, .kill_sb = xfs_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, }; MODULE_ALIAS_FS("xfs"); STATIC int __init xfs_init_caches(void) { int error; xfs_buf_cache = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT, NULL); if (!xfs_buf_cache) goto out; xfs_log_ticket_cache = kmem_cache_create("xfs_log_ticket", sizeof(struct xlog_ticket), 0, 0, NULL); if (!xfs_log_ticket_cache) goto out_destroy_buf_cache; error = xfs_btree_init_cur_caches(); if (error) goto out_destroy_log_ticket_cache; error = rcbagbt_init_cur_cache(); if (error) goto out_destroy_btree_cur_cache; error = xfs_defer_init_item_caches(); if (error) goto out_destroy_rcbagbt_cur_cache; xfs_da_state_cache = kmem_cache_create("xfs_da_state", sizeof(struct xfs_da_state), 0, 0, NULL); if (!xfs_da_state_cache) goto out_destroy_defer_item_cache; xfs_ifork_cache = kmem_cache_create("xfs_ifork", sizeof(struct xfs_ifork), 0, 0, NULL); if (!xfs_ifork_cache) goto out_destroy_da_state_cache; xfs_trans_cache = kmem_cache_create("xfs_trans", sizeof(struct xfs_trans), 0, 0, NULL); if (!xfs_trans_cache) goto out_destroy_ifork_cache; /* * The size of the cache-allocated buf log item is the maximum * size possible under XFS. This wastes a little bit of memory, * but it is much faster. */ xfs_buf_item_cache = kmem_cache_create("xfs_buf_item", sizeof(struct xfs_buf_log_item), 0, 0, NULL); if (!xfs_buf_item_cache) goto out_destroy_trans_cache; xfs_efd_cache = kmem_cache_create("xfs_efd_item", xfs_efd_log_item_sizeof(XFS_EFD_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_efd_cache) goto out_destroy_buf_item_cache; xfs_efi_cache = kmem_cache_create("xfs_efi_item", xfs_efi_log_item_sizeof(XFS_EFI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_efi_cache) goto out_destroy_efd_cache; xfs_inode_cache = kmem_cache_create("xfs_inode", sizeof(struct xfs_inode), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), xfs_fs_inode_init_once); if (!xfs_inode_cache) goto out_destroy_efi_cache; xfs_ili_cache = kmem_cache_create("xfs_ili", sizeof(struct xfs_inode_log_item), 0, SLAB_RECLAIM_ACCOUNT, NULL); if (!xfs_ili_cache) goto out_destroy_inode_cache; xfs_icreate_cache = kmem_cache_create("xfs_icr", sizeof(struct xfs_icreate_item), 0, 0, NULL); if (!xfs_icreate_cache) goto out_destroy_ili_cache; xfs_rud_cache = kmem_cache_create("xfs_rud_item", sizeof(struct xfs_rud_log_item), 0, 0, NULL); if (!xfs_rud_cache) goto out_destroy_icreate_cache; xfs_rui_cache = kmem_cache_create("xfs_rui_item", xfs_rui_log_item_sizeof(XFS_RUI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_rui_cache) goto out_destroy_rud_cache; xfs_cud_cache = kmem_cache_create("xfs_cud_item", sizeof(struct xfs_cud_log_item), 0, 0, NULL); if (!xfs_cud_cache) goto out_destroy_rui_cache; xfs_cui_cache = kmem_cache_create("xfs_cui_item", xfs_cui_log_item_sizeof(XFS_CUI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_cui_cache) goto out_destroy_cud_cache; xfs_bud_cache = kmem_cache_create("xfs_bud_item", sizeof(struct xfs_bud_log_item), 0, 0, NULL); if (!xfs_bud_cache) goto out_destroy_cui_cache; xfs_bui_cache = kmem_cache_create("xfs_bui_item", xfs_bui_log_item_sizeof(XFS_BUI_MAX_FAST_EXTENTS), 0, 0, NULL); if (!xfs_bui_cache) goto out_destroy_bud_cache; xfs_attrd_cache = kmem_cache_create("xfs_attrd_item", sizeof(struct xfs_attrd_log_item), 0, 0, NULL); if (!xfs_attrd_cache) goto out_destroy_bui_cache; xfs_attri_cache = kmem_cache_create("xfs_attri_item", sizeof(struct xfs_attri_log_item), 0, 0, NULL); if (!xfs_attri_cache) goto out_destroy_attrd_cache; xfs_iunlink_cache = kmem_cache_create("xfs_iul_item", sizeof(struct xfs_iunlink_item), 0, 0, NULL); if (!xfs_iunlink_cache) goto out_destroy_attri_cache; xfs_xmd_cache = kmem_cache_create("xfs_xmd_item", sizeof(struct xfs_xmd_log_item), 0, 0, NULL); if (!xfs_xmd_cache) goto out_destroy_iul_cache; xfs_xmi_cache = kmem_cache_create("xfs_xmi_item", sizeof(struct xfs_xmi_log_item), 0, 0, NULL); if (!xfs_xmi_cache) goto out_destroy_xmd_cache; xfs_parent_args_cache = kmem_cache_create("xfs_parent_args", sizeof(struct xfs_parent_args), 0, 0, NULL); if (!xfs_parent_args_cache) goto out_destroy_xmi_cache; return 0; out_destroy_xmi_cache: kmem_cache_destroy(xfs_xmi_cache); out_destroy_xmd_cache: kmem_cache_destroy(xfs_xmd_cache); out_destroy_iul_cache: kmem_cache_destroy(xfs_iunlink_cache); out_destroy_attri_cache: kmem_cache_destroy(xfs_attri_cache); out_destroy_attrd_cache: kmem_cache_destroy(xfs_attrd_cache); out_destroy_bui_cache: kmem_cache_destroy(xfs_bui_cache); out_destroy_bud_cache: kmem_cache_destroy(xfs_bud_cache); out_destroy_cui_cache: kmem_cache_destroy(xfs_cui_cache); out_destroy_cud_cache: kmem_cache_destroy(xfs_cud_cache); out_destroy_rui_cache: kmem_cache_destroy(xfs_rui_cache); out_destroy_rud_cache: kmem_cache_destroy(xfs_rud_cache); out_destroy_icreate_cache: kmem_cache_destroy(xfs_icreate_cache); out_destroy_ili_cache: kmem_cache_destroy(xfs_ili_cache); out_destroy_inode_cache: kmem_cache_destroy(xfs_inode_cache); out_destroy_efi_cache: kmem_cache_destroy(xfs_efi_cache); out_destroy_efd_cache: kmem_cache_destroy(xfs_efd_cache); out_destroy_buf_item_cache: kmem_cache_destroy(xfs_buf_item_cache); out_destroy_trans_cache: kmem_cache_destroy(xfs_trans_cache); out_destroy_ifork_cache: kmem_cache_destroy(xfs_ifork_cache); out_destroy_da_state_cache: kmem_cache_destroy(xfs_da_state_cache); out_destroy_defer_item_cache: xfs_defer_destroy_item_caches(); out_destroy_rcbagbt_cur_cache: rcbagbt_destroy_cur_cache(); out_destroy_btree_cur_cache: xfs_btree_destroy_cur_caches(); out_destroy_log_ticket_cache: kmem_cache_destroy(xfs_log_ticket_cache); out_destroy_buf_cache: kmem_cache_destroy(xfs_buf_cache); out: return -ENOMEM; } STATIC void xfs_destroy_caches(void) { /* * Make sure all delayed rcu free are flushed before we * destroy caches. */ rcu_barrier(); kmem_cache_destroy(xfs_parent_args_cache); kmem_cache_destroy(xfs_xmd_cache); kmem_cache_destroy(xfs_xmi_cache); kmem_cache_destroy(xfs_iunlink_cache); kmem_cache_destroy(xfs_attri_cache); kmem_cache_destroy(xfs_attrd_cache); kmem_cache_destroy(xfs_bui_cache); kmem_cache_destroy(xfs_bud_cache); kmem_cache_destroy(xfs_cui_cache); kmem_cache_destroy(xfs_cud_cache); kmem_cache_destroy(xfs_rui_cache); kmem_cache_destroy(xfs_rud_cache); kmem_cache_destroy(xfs_icreate_cache); kmem_cache_destroy(xfs_ili_cache); kmem_cache_destroy(xfs_inode_cache); kmem_cache_destroy(xfs_efi_cache); kmem_cache_destroy(xfs_efd_cache); kmem_cache_destroy(xfs_buf_item_cache); kmem_cache_destroy(xfs_trans_cache); kmem_cache_destroy(xfs_ifork_cache); kmem_cache_destroy(xfs_da_state_cache); xfs_defer_destroy_item_caches(); rcbagbt_destroy_cur_cache(); xfs_btree_destroy_cur_caches(); kmem_cache_destroy(xfs_log_ticket_cache); kmem_cache_destroy(xfs_buf_cache); } STATIC int __init xfs_init_workqueues(void) { /* * The allocation workqueue can be used in memory reclaim situations * (writepage path), and parallelism is only limited by the number of * AGs in all the filesystems mounted. Hence use the default large * max_active value for this workqueue. */ xfs_alloc_wq = alloc_workqueue("xfsalloc", XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 0); if (!xfs_alloc_wq) return -ENOMEM; xfs_discard_wq = alloc_workqueue("xfsdiscard", XFS_WQFLAGS(WQ_UNBOUND), 0); if (!xfs_discard_wq) goto out_free_alloc_wq; return 0; out_free_alloc_wq: destroy_workqueue(xfs_alloc_wq); return -ENOMEM; } STATIC void xfs_destroy_workqueues(void) { destroy_workqueue(xfs_discard_wq); destroy_workqueue(xfs_alloc_wq); } STATIC int __init init_xfs_fs(void) { int error; xfs_check_ondisk_structs(); error = xfs_dahash_test(); if (error) return error; printk(KERN_INFO XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled\n"); xfs_dir_startup(); error = xfs_init_caches(); if (error) goto out; error = xfs_init_workqueues(); if (error) goto out_destroy_caches; error = xfs_mru_cache_init(); if (error) goto out_destroy_wq; error = xfs_init_procfs(); if (error) goto out_mru_cache_uninit; error = xfs_sysctl_register(); if (error) goto out_cleanup_procfs; xfs_debugfs = xfs_debugfs_mkdir("xfs", NULL); xfs_kset = kset_create_and_add("xfs", NULL, fs_kobj); if (!xfs_kset) { error = -ENOMEM; goto out_debugfs_unregister; } xfsstats.xs_kobj.kobject.kset = xfs_kset; xfsstats.xs_stats = alloc_percpu(struct xfsstats); if (!xfsstats.xs_stats) { error = -ENOMEM; goto out_kset_unregister; } error = xfs_sysfs_init(&xfsstats.xs_kobj, &xfs_stats_ktype, NULL, "stats"); if (error) goto out_free_stats; error = xchk_global_stats_setup(xfs_debugfs); if (error) goto out_remove_stats_kobj; #ifdef DEBUG xfs_dbg_kobj.kobject.kset = xfs_kset; error = xfs_sysfs_init(&xfs_dbg_kobj, &xfs_dbg_ktype, NULL, "debug"); if (error) goto out_remove_scrub_stats; #endif error = xfs_qm_init(); if (error) goto out_remove_dbg_kobj; error = register_filesystem(&xfs_fs_type); if (error) goto out_qm_exit; return 0; out_qm_exit: xfs_qm_exit(); out_remove_dbg_kobj: #ifdef DEBUG xfs_sysfs_del(&xfs_dbg_kobj); out_remove_scrub_stats: #endif xchk_global_stats_teardown(); out_remove_stats_kobj: xfs_sysfs_del(&xfsstats.xs_kobj); out_free_stats: free_percpu(xfsstats.xs_stats); out_kset_unregister: kset_unregister(xfs_kset); out_debugfs_unregister: debugfs_remove(xfs_debugfs); xfs_sysctl_unregister(); out_cleanup_procfs: xfs_cleanup_procfs(); out_mru_cache_uninit: xfs_mru_cache_uninit(); out_destroy_wq: xfs_destroy_workqueues(); out_destroy_caches: xfs_destroy_caches(); out: return error; } STATIC void __exit exit_xfs_fs(void) { xfs_qm_exit(); unregister_filesystem(&xfs_fs_type); #ifdef DEBUG xfs_sysfs_del(&xfs_dbg_kobj); #endif xchk_global_stats_teardown(); xfs_sysfs_del(&xfsstats.xs_kobj); free_percpu(xfsstats.xs_stats); kset_unregister(xfs_kset); debugfs_remove(xfs_debugfs); xfs_sysctl_unregister(); xfs_cleanup_procfs(); xfs_mru_cache_uninit(); xfs_destroy_workqueues(); xfs_destroy_caches(); xfs_uuid_table_free(); } module_init(init_xfs_fs); module_exit(exit_xfs_fs); MODULE_AUTHOR("Silicon Graphics, Inc."); MODULE_DESCRIPTION(XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled"); MODULE_LICENSE("GPL"); |
| 220 3469 3081 1229 50 1107 1268 11 113 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up(struct file_lock *fl) { wake_up(&fl->c.flc_wait); } static inline bool locks_can_async_lock(const struct file_operations *fops) { return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 102 103 104 2 2 2 2 2 1 1 1 1 8 1 1 5 5 1 4 6 5 5 5 2 2 1 2 2 5 5 5 5 5 4 4 5 5 18 7 13 5 15 11 8 8 8 8 1 1 1 21 21 3 18 15 17 1 18 15 15 15 16 16 16 16 2 14 14 16 12 7 12 6 7 7 7 7 2 2 2 2 5 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2006 Silicon Graphics, Inc. * Copyright (c) 2012 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_trans.h" #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" #include "xfs_rtalloc.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_iomap.h" #include "xfs_reflink.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" /* Kernel only BMAP related definitions and functions */ /* * Convert the given file system block to a disk block. We have to treat it * differently based on whether the file is a real time file or not, because the * bmap code does. */ xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb) { if (XFS_IS_REALTIME_INODE(ip)) return xfs_rtb_to_daddr(ip->i_mount, fsb); return XFS_FSB_TO_DADDR(ip->i_mount, fsb); } /* * Routine to zero an extent on disk allocated to the specific inode. */ int xfs_zero_extent( struct xfs_inode *ip, xfs_fsblock_t start_fsb, xfs_off_t count_fsb) { return blkdev_issue_zeroout(xfs_inode_buftarg(ip)->bt_bdev, xfs_fsb_to_db(ip, start_fsb), XFS_FSB_TO_BB(ip->i_mount, count_fsb), GFP_KERNEL, 0); } /* * Extent tree block counting routines. */ /* * Count leaf blocks given a range of extent records. Delayed allocation * extents are not counted towards the totals. */ xfs_extnum_t xfs_bmap_count_leaves( struct xfs_ifork *ifp, xfs_filblks_t *count) { struct xfs_iext_cursor icur; struct xfs_bmbt_irec got; xfs_extnum_t numrecs = 0; for_each_xfs_iext(ifp, &icur, &got) { if (!isnullstartblock(got.br_startblock)) { *count += got.br_blockcount; numrecs++; } } return numrecs; } /* * Count fsblocks of the given fork. Delayed allocation extents are * not counted towards the totals. */ int xfs_bmap_count_blocks( struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, xfs_extnum_t *nextents, xfs_filblks_t *count) { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; xfs_filblks_t btblocks = 0; int error; *nextents = 0; *count = 0; if (!ifp) return 0; switch (ifp->if_format) { case XFS_DINODE_FMT_BTREE: error = xfs_iread_extents(tp, ip, whichfork); if (error) return error; cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); error = xfs_btree_count_blocks(cur, &btblocks); xfs_btree_del_cursor(cur, error); if (error) return error; /* * xfs_btree_count_blocks includes the root block contained in * the inode fork in @btblocks, so subtract one because we're * only interested in allocated disk blocks. */ *count += btblocks - 1; fallthrough; case XFS_DINODE_FMT_EXTENTS: *nextents = xfs_bmap_count_leaves(ifp, count); break; } return 0; } static int xfs_getbmap_report_one( struct xfs_inode *ip, struct getbmapx *bmv, struct kgetbmap *out, int64_t bmv_end, struct xfs_bmbt_irec *got) { struct kgetbmap *p = out + bmv->bmv_entries; bool shared = false; int error; error = xfs_reflink_trim_around_shared(ip, got, &shared); if (error) return error; if (isnullstartblock(got->br_startblock) || got->br_startblock == DELAYSTARTBLOCK) { /* * Take the flush completion as being a point-in-time snapshot * where there are no delalloc extents, and if any new ones * have been created racily, just skip them as being 'after' * the flush and so don't get reported. */ if (!(bmv->bmv_iflags & BMV_IF_DELALLOC)) return 0; p->bmv_oflags |= BMV_OF_DELALLOC; p->bmv_block = -2; } else { p->bmv_block = xfs_fsb_to_db(ip, got->br_startblock); } if (got->br_state == XFS_EXT_UNWRITTEN && (bmv->bmv_iflags & BMV_IF_PREALLOC)) p->bmv_oflags |= BMV_OF_PREALLOC; if (shared) p->bmv_oflags |= BMV_OF_SHARED; p->bmv_offset = XFS_FSB_TO_BB(ip->i_mount, got->br_startoff); p->bmv_length = XFS_FSB_TO_BB(ip->i_mount, got->br_blockcount); bmv->bmv_offset = p->bmv_offset + p->bmv_length; bmv->bmv_length = max(0LL, bmv_end - bmv->bmv_offset); bmv->bmv_entries++; return 0; } static void xfs_getbmap_report_hole( struct xfs_inode *ip, struct getbmapx *bmv, struct kgetbmap *out, int64_t bmv_end, xfs_fileoff_t bno, xfs_fileoff_t end) { struct kgetbmap *p = out + bmv->bmv_entries; if (bmv->bmv_iflags & BMV_IF_NO_HOLES) return; p->bmv_block = -1; p->bmv_offset = XFS_FSB_TO_BB(ip->i_mount, bno); p->bmv_length = XFS_FSB_TO_BB(ip->i_mount, end - bno); bmv->bmv_offset = p->bmv_offset + p->bmv_length; bmv->bmv_length = max(0LL, bmv_end - bmv->bmv_offset); bmv->bmv_entries++; } static inline bool xfs_getbmap_full( struct getbmapx *bmv) { return bmv->bmv_length == 0 || bmv->bmv_entries >= bmv->bmv_count - 1; } static bool xfs_getbmap_next_rec( struct xfs_bmbt_irec *rec, xfs_fileoff_t total_end) { xfs_fileoff_t end = rec->br_startoff + rec->br_blockcount; if (end == total_end) return false; rec->br_startoff += rec->br_blockcount; if (!isnullstartblock(rec->br_startblock) && rec->br_startblock != DELAYSTARTBLOCK) rec->br_startblock += rec->br_blockcount; rec->br_blockcount = total_end - end; return true; } /* * Get inode's extents as described in bmv, and format for output. * Calls formatter to fill the user's buffer until all extents * are mapped, until the passed-in bmv->bmv_count slots have * been filled, or until the formatter short-circuits the loop, * if it is tracking filled-in extents on its own. */ int /* error code */ xfs_getbmap( struct xfs_inode *ip, struct getbmapx *bmv, /* user bmap structure */ struct kgetbmap *out) { struct xfs_mount *mp = ip->i_mount; int iflags = bmv->bmv_iflags; int whichfork, lock, error = 0; int64_t bmv_end, max_len; xfs_fileoff_t bno, first_bno; struct xfs_ifork *ifp; struct xfs_bmbt_irec got, rec; xfs_filblks_t len; struct xfs_iext_cursor icur; if (bmv->bmv_iflags & ~BMV_IF_VALID) return -EINVAL; #ifndef DEBUG /* Only allow CoW fork queries if we're debugging. */ if (iflags & BMV_IF_COWFORK) return -EINVAL; #endif if ((iflags & BMV_IF_ATTRFORK) && (iflags & BMV_IF_COWFORK)) return -EINVAL; if (bmv->bmv_length < -1) return -EINVAL; bmv->bmv_entries = 0; if (bmv->bmv_length == 0) return 0; if (iflags & BMV_IF_ATTRFORK) whichfork = XFS_ATTR_FORK; else if (iflags & BMV_IF_COWFORK) whichfork = XFS_COW_FORK; else whichfork = XFS_DATA_FORK; xfs_ilock(ip, XFS_IOLOCK_SHARED); switch (whichfork) { case XFS_ATTR_FORK: lock = xfs_ilock_attr_map_shared(ip); if (!xfs_inode_has_attr_fork(ip)) goto out_unlock_ilock; max_len = 1LL << 32; break; case XFS_COW_FORK: lock = XFS_ILOCK_SHARED; xfs_ilock(ip, lock); /* No CoW fork? Just return */ if (!xfs_ifork_ptr(ip, whichfork)) goto out_unlock_ilock; if (xfs_get_cowextsz_hint(ip)) max_len = mp->m_super->s_maxbytes; else max_len = XFS_ISIZE(ip); break; case XFS_DATA_FORK: if (!(iflags & BMV_IF_DELALLOC) && (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_disk_size)) { error = filemap_write_and_wait(VFS_I(ip)->i_mapping); if (error) goto out_unlock_iolock; /* * Even after flushing the inode, there can still be * delalloc blocks on the inode beyond EOF due to * speculative preallocation. These are not removed * until the release function is called or the inode * is inactivated. Hence we cannot assert here that * ip->i_delayed_blks == 0. */ } if (xfs_get_extsz_hint(ip) || (ip->i_diflags & XFS_DIFLAG_PREALLOC)) max_len = mp->m_super->s_maxbytes; else max_len = XFS_ISIZE(ip); lock = xfs_ilock_data_map_shared(ip); break; } ifp = xfs_ifork_ptr(ip, whichfork); switch (ifp->if_format) { case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: break; case XFS_DINODE_FMT_LOCAL: /* Local format inode forks report no extents. */ goto out_unlock_ilock; default: error = -EINVAL; goto out_unlock_ilock; } if (bmv->bmv_length == -1) { max_len = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, max_len)); bmv->bmv_length = max(0LL, max_len - bmv->bmv_offset); } bmv_end = bmv->bmv_offset + bmv->bmv_length; first_bno = bno = XFS_BB_TO_FSBT(mp, bmv->bmv_offset); len = XFS_BB_TO_FSB(mp, bmv->bmv_length); error = xfs_iread_extents(NULL, ip, whichfork); if (error) goto out_unlock_ilock; if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) { /* * Report a whole-file hole if the delalloc flag is set to * stay compatible with the old implementation. */ if (iflags & BMV_IF_DELALLOC) xfs_getbmap_report_hole(ip, bmv, out, bmv_end, bno, XFS_B_TO_FSB(mp, XFS_ISIZE(ip))); goto out_unlock_ilock; } while (!xfs_getbmap_full(bmv)) { xfs_trim_extent(&got, first_bno, len); /* * Report an entry for a hole if this extent doesn't directly * follow the previous one. */ if (got.br_startoff > bno) { xfs_getbmap_report_hole(ip, bmv, out, bmv_end, bno, got.br_startoff); if (xfs_getbmap_full(bmv)) break; } /* * In order to report shared extents accurately, we report each * distinct shared / unshared part of a single bmbt record with * an individual getbmapx record. */ bno = got.br_startoff + got.br_blockcount; rec = got; do { error = xfs_getbmap_report_one(ip, bmv, out, bmv_end, &rec); if (error || xfs_getbmap_full(bmv)) goto out_unlock_ilock; } while (xfs_getbmap_next_rec(&rec, bno)); if (!xfs_iext_next_extent(ifp, &icur, &got)) { xfs_fileoff_t end = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); if (bmv->bmv_entries > 0) out[bmv->bmv_entries - 1].bmv_oflags |= BMV_OF_LAST; if (whichfork != XFS_ATTR_FORK && bno < end && !xfs_getbmap_full(bmv)) { xfs_getbmap_report_hole(ip, bmv, out, bmv_end, bno, end); } break; } if (bno >= first_bno + len) break; } out_unlock_ilock: xfs_iunlock(ip, lock); out_unlock_iolock: xfs_iunlock(ip, XFS_IOLOCK_SHARED); return error; } /* * Dead simple method of punching delalyed allocation blocks from a range in * the inode. This will always punch out both the start and end blocks, even * if the ranges only partially overlap them, so it is up to the caller to * ensure that partial blocks are not passed in. */ void xfs_bmap_punch_delalloc_range( struct xfs_inode *ip, int whichfork, xfs_off_t start_byte, xfs_off_t end_byte) { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, start_byte); xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, end_byte); struct xfs_bmbt_irec got, del; struct xfs_iext_cursor icur; ASSERT(!xfs_need_iread_extents(ifp)); xfs_ilock(ip, XFS_ILOCK_EXCL); if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got)) goto out_unlock; while (got.br_startoff + got.br_blockcount > start_fsb) { del = got; xfs_trim_extent(&del, start_fsb, end_fsb - start_fsb); /* * A delete can push the cursor forward. Step back to the * previous extent on non-delalloc or extents outside the * target range. */ if (!del.br_blockcount || !isnullstartblock(del.br_startblock)) { if (!xfs_iext_prev_extent(ifp, &icur, &got)) break; continue; } xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del); if (!xfs_iext_get_extent(ifp, &icur, &got)) break; } if (whichfork == XFS_COW_FORK && !ifp->if_bytes) xfs_inode_clear_cowblocks_tag(ip); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); } /* * Test whether it is appropriate to check an inode for and free post EOF * blocks. */ bool xfs_can_free_eofblocks( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; bool found_blocks = false; xfs_fileoff_t end_fsb; xfs_fileoff_t last_fsb; struct xfs_bmbt_irec imap; struct xfs_iext_cursor icur; /* * Caller must either hold the exclusive io lock; or be inactivating * the inode, which guarantees there are no other users of the inode. */ if (!(VFS_I(ip)->i_state & I_FREEING)) xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); /* prealloc/delalloc exists only on regular files */ if (!S_ISREG(VFS_I(ip)->i_mode)) return false; /* * Zero sized files with no cached pages and delalloc blocks will not * have speculative prealloc/delalloc blocks to remove. */ if (VFS_I(ip)->i_size == 0 && VFS_I(ip)->i_mapping->nrpages == 0 && ip->i_delayed_blks == 0) return false; /* If we haven't read in the extent list, then don't do it now. */ if (xfs_need_iread_extents(&ip->i_df)) return false; /* * Do not free real extents in preallocated files unless the file has * delalloc blocks and we are forced to remove them. */ if ((ip->i_diflags & XFS_DIFLAG_PREALLOC) && !ip->i_delayed_blks) return false; /* * Do not try to free post-EOF blocks if EOF is beyond the end of the * range supported by the page cache, because the truncation will loop * forever. */ end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip)); if (xfs_inode_has_bigrtalloc(ip)) end_fsb = xfs_fileoff_roundup_rtx(mp, end_fsb); last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes); if (last_fsb <= end_fsb) return false; /* * Check if there is an post-EOF extent to free. If there are any * delalloc blocks attached to the inode (data fork delalloc * reservations or CoW extents of any kind), we need to free them so * that inactivation doesn't fail to erase them. */ xfs_ilock(ip, XFS_ILOCK_SHARED); if (ip->i_delayed_blks || xfs_iext_lookup_extent(ip, &ip->i_df, end_fsb, &icur, &imap)) found_blocks = true; xfs_iunlock(ip, XFS_ILOCK_SHARED); return found_blocks; } /* * This is called to free any blocks beyond eof. The caller must hold * IOLOCK_EXCL unless we are in the inode reclaim path and have the only * reference to the inode. */ int xfs_free_eofblocks( struct xfs_inode *ip) { struct xfs_trans *tp; struct xfs_mount *mp = ip->i_mount; int error; /* Attach the dquots to the inode up front. */ error = xfs_qm_dqattach(ip); if (error) return error; /* Wait on dio to ensure i_size has settled. */ inode_dio_wait(VFS_I(ip)); /* * For preallocated files only free delayed allocations. * * Note that this means we also leave speculative preallocations in * place for preallocated files. */ if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) { if (ip->i_delayed_blks) { xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize), LLONG_MAX); } xfs_inode_clear_eofblocks_tag(ip); return 0; } error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { ASSERT(xfs_is_shutdown(mp)); return error; } xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); /* * Do not update the on-disk file size. If we update the on-disk file * size and then the system crashes before the contents of the file are * flushed to disk then the files may be full of holes (ie NULL files * bug). */ error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK, XFS_ISIZE(ip), XFS_BMAPI_NODISCARD); if (error) goto err_cancel; error = xfs_trans_commit(tp); if (error) goto out_unlock; xfs_inode_clear_eofblocks_tag(ip); goto out_unlock; err_cancel: /* * If we get an error at this point we simply don't * bother truncating the file. */ xfs_trans_cancel(tp); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } int xfs_alloc_file_space( struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len) { xfs_mount_t *mp = ip->i_mount; xfs_off_t count; xfs_filblks_t allocatesize_fsb; xfs_extlen_t extsz, temp; xfs_fileoff_t startoffset_fsb; xfs_fileoff_t endoffset_fsb; int rt; xfs_trans_t *tp; xfs_bmbt_irec_t imaps[1], *imapp; int error; if (xfs_is_always_cow_inode(ip)) return 0; trace_xfs_alloc_file_space(ip); if (xfs_is_shutdown(mp)) return -EIO; error = xfs_qm_dqattach(ip); if (error) return error; if (len <= 0) return -EINVAL; rt = XFS_IS_REALTIME_INODE(ip); extsz = xfs_get_extsz_hint(ip); count = len; imapp = &imaps[0]; startoffset_fsb = XFS_B_TO_FSBT(mp, offset); endoffset_fsb = XFS_B_TO_FSB(mp, offset + count); allocatesize_fsb = endoffset_fsb - startoffset_fsb; /* * Allocate file space until done or until there is an error */ while (allocatesize_fsb && !error) { xfs_fileoff_t s, e; unsigned int dblocks, rblocks, resblks; int nimaps = 1; /* * Determine space reservations for data/realtime. */ if (unlikely(extsz)) { s = startoffset_fsb; do_div(s, extsz); s *= extsz; e = startoffset_fsb + allocatesize_fsb; div_u64_rem(startoffset_fsb, extsz, &temp); if (temp) e += temp; div_u64_rem(e, extsz, &temp); if (temp) e += extsz - temp; } else { s = 0; e = allocatesize_fsb; } /* * The transaction reservation is limited to a 32-bit block * count, hence we need to limit the number of blocks we are * trying to reserve to avoid an overflow. We can't allocate * more than @nimaps extents, and an extent is limited on disk * to XFS_BMBT_MAX_EXTLEN (21 bits), so use that to enforce the * limit. */ resblks = min_t(xfs_fileoff_t, (e - s), (XFS_MAX_BMBT_EXTLEN * nimaps)); if (unlikely(rt)) { dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); rblocks = resblks; } else { dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks); rblocks = 0; } error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, rblocks, false, &tp); if (error) break; error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK, XFS_IEXT_ADD_NOSPLIT_CNT); if (error) goto error; /* * If the allocator cannot find a single free extent large * enough to cover the start block of the requested range, * xfs_bmapi_write will return -ENOSR. * * In that case we simply need to keep looping with the same * startoffset_fsb so that one of the following allocations * will eventually reach the requested range. */ error = xfs_bmapi_write(tp, ip, startoffset_fsb, allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp, &nimaps); if (error) { if (error != -ENOSR) goto error; error = 0; } else { startoffset_fsb += imapp->br_blockcount; allocatesize_fsb -= imapp->br_blockcount; } ip->i_diflags |= XFS_DIFLAG_PREALLOC; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); } return error; error: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } static int xfs_unmap_extent( struct xfs_inode *ip, xfs_fileoff_t startoffset_fsb, xfs_filblks_t len_fsb, int *done) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; uint resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); int error; error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, false, &tp); if (error) return error; error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK, XFS_IEXT_PUNCH_HOLE_CNT); if (error) goto out_trans_cancel; error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done); if (error) goto out_trans_cancel; error = xfs_trans_commit(tp); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; out_trans_cancel: xfs_trans_cancel(tp); goto out_unlock; } /* Caller must first wait for the completion of any pending DIOs if required. */ int xfs_flush_unmap_range( struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len) { struct inode *inode = VFS_I(ip); xfs_off_t rounding, start, end; int error; /* * Make sure we extend the flush out to extent alignment * boundaries so any extent range overlapping the start/end * of the modification we are about to do is clean and idle. */ rounding = max_t(xfs_off_t, xfs_inode_alloc_unitsize(ip), PAGE_SIZE); start = rounddown_64(offset, rounding); end = roundup_64(offset + len, rounding) - 1; error = filemap_write_and_wait_range(inode->i_mapping, start, end); if (error) return error; truncate_pagecache_range(inode, start, end); return 0; } int xfs_free_file_space( struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len) { struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t startoffset_fsb; xfs_fileoff_t endoffset_fsb; int done = 0, error; trace_xfs_free_file_space(ip); error = xfs_qm_dqattach(ip); if (error) return error; if (len <= 0) /* if nothing being freed */ return 0; /* * Now AIO and DIO has drained we flush and (if necessary) invalidate * the cached range over the first operation we are about to run. */ error = xfs_flush_unmap_range(ip, offset, len); if (error) return error; startoffset_fsb = XFS_B_TO_FSB(mp, offset); endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len); /* We can only free complete realtime extents. */ if (xfs_inode_has_bigrtalloc(ip)) { startoffset_fsb = xfs_fileoff_roundup_rtx(mp, startoffset_fsb); endoffset_fsb = xfs_fileoff_rounddown_rtx(mp, endoffset_fsb); } /* * Need to zero the stuff we're not freeing, on disk. */ if (endoffset_fsb > startoffset_fsb) { while (!done) { error = xfs_unmap_extent(ip, startoffset_fsb, endoffset_fsb - startoffset_fsb, &done); if (error) return error; } } /* * Now that we've unmap all full blocks we'll have to zero out any * partial block at the beginning and/or end. xfs_zero_range is smart * enough to skip any holes, including those we just created, but we * must take care not to zero beyond EOF and enlarge i_size. */ if (offset >= XFS_ISIZE(ip)) return 0; if (offset + len > XFS_ISIZE(ip)) len = XFS_ISIZE(ip) - offset; error = xfs_zero_range(ip, offset, len, NULL); if (error) return error; /* * If we zeroed right up to EOF and EOF straddles a page boundary we * must make sure that the post-EOF area is also zeroed because the * page could be mmap'd and xfs_zero_range doesn't do that for us. * Writeback of the eof page will do this, albeit clumsily. */ if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) { error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, round_down(offset + len, PAGE_SIZE), LLONG_MAX); } return error; } static int xfs_prepare_shift( struct xfs_inode *ip, loff_t offset) { unsigned int rounding; int error; /* * Trim eofblocks to avoid shifting uninitialized post-eof preallocation * into the accessible region of the file. */ if (xfs_can_free_eofblocks(ip)) { error = xfs_free_eofblocks(ip); if (error) return error; } /* * Shift operations must stabilize the start block offset boundary along * with the full range of the operation. If we don't, a COW writeback * completion could race with an insert, front merge with the start * extent (after split) during the shift and corrupt the file. Start * with the allocation unit just prior to the start to stabilize the * boundary. */ rounding = xfs_inode_alloc_unitsize(ip); offset = rounddown_64(offset, rounding); if (offset) offset -= rounding; /* * Writeback and invalidate cache for the remainder of the file as we're * about to shift down every extent from offset to EOF. */ error = xfs_flush_unmap_range(ip, offset, XFS_ISIZE(ip)); if (error) return error; /* * Clean out anything hanging around in the cow fork now that * we've flushed all the dirty data out to disk to avoid having * CoW extents at the wrong offsets. */ if (xfs_inode_has_cow_data(ip)) { error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, true); if (error) return error; } return 0; } /* * xfs_collapse_file_space() * This routine frees disk space and shift extent for the given file. * The first thing we do is to free data blocks in the specified range * by calling xfs_free_file_space(). It would also sync dirty data * and invalidate page cache over the region on which collapse range * is working. And Shift extent records to the left to cover a hole. * RETURNS: * 0 on success * errno on error * */ int xfs_collapse_file_space( struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error; xfs_fileoff_t next_fsb = XFS_B_TO_FSB(mp, offset + len); xfs_fileoff_t shift_fsb = XFS_B_TO_FSB(mp, len); bool done = false; xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL); trace_xfs_collapse_file_space(ip); error = xfs_free_file_space(ip, offset, len); if (error) return error; error = xfs_prepare_shift(ip, offset); if (error) return error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp); if (error) return error; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); while (!done) { error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb, &done); if (error) goto out_trans_cancel; if (done) break; /* finish any deferred frees and roll the transaction */ error = xfs_defer_finish(&tp); if (error) goto out_trans_cancel; } error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; out_trans_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } /* * xfs_insert_file_space() * This routine create hole space by shifting extents for the given file. * The first thing we do is to sync dirty data and invalidate page cache * over the region on which insert range is working. And split an extent * to two extents at given offset by calling xfs_bmap_split_extent. * And shift all extent records which are laying between [offset, * last allocated extent] to the right to reserve hole range. * RETURNS: * 0 on success * errno on error */ int xfs_insert_file_space( struct xfs_inode *ip, loff_t offset, loff_t len) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error; xfs_fileoff_t stop_fsb = XFS_B_TO_FSB(mp, offset); xfs_fileoff_t next_fsb = NULLFSBLOCK; xfs_fileoff_t shift_fsb = XFS_B_TO_FSB(mp, len); bool done = false; xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL); trace_xfs_insert_file_space(ip); error = xfs_bmap_can_insert_extents(ip, stop_fsb, shift_fsb); if (error) return error; error = xfs_prepare_shift(ip, offset); if (error) return error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp); if (error) return error; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK, XFS_IEXT_PUNCH_HOLE_CNT); if (error) goto out_trans_cancel; /* * The extent shifting code works on extent granularity. So, if stop_fsb * is not the starting block of extent, we need to split the extent at * stop_fsb. */ error = xfs_bmap_split_extent(tp, ip, stop_fsb); if (error) goto out_trans_cancel; do { error = xfs_defer_finish(&tp); if (error) goto out_trans_cancel; error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb, &done, stop_fsb); if (error) goto out_trans_cancel; } while (!done); error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; out_trans_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } /* * We need to check that the format of the data fork in the temporary inode is * valid for the target inode before doing the swap. This is not a problem with * attr1 because of the fixed fork offset, but attr2 has a dynamically sized * data fork depending on the space the attribute fork is taking so we can get * invalid formats on the target inode. * * E.g. target has space for 7 extents in extent format, temp inode only has * space for 6. If we defragment down to 7 extents, then the tmp format is a * btree, but when swapped it needs to be in extent format. Hence we can't just * blindly swap data forks on attr2 filesystems. * * Note that we check the swap in both directions so that we don't end up with * a corrupt temporary inode, either. * * Note that fixing the way xfs_fsr sets up the attribute fork in the source * inode will prevent this situation from occurring, so all we do here is * reject and log the attempt. basically we are putting the responsibility on * userspace to get this right. */ static int xfs_swap_extents_check_format( struct xfs_inode *ip, /* target inode */ struct xfs_inode *tip) /* tmp inode */ { struct xfs_ifork *ifp = &ip->i_df; struct xfs_ifork *tifp = &tip->i_df; /* User/group/project quota ids must match if quotas are enforced. */ if (XFS_IS_QUOTA_ON(ip->i_mount) && (!uid_eq(VFS_I(ip)->i_uid, VFS_I(tip)->i_uid) || !gid_eq(VFS_I(ip)->i_gid, VFS_I(tip)->i_gid) || ip->i_projid != tip->i_projid)) return -EINVAL; /* Should never get a local format */ if (ifp->if_format == XFS_DINODE_FMT_LOCAL || tifp->if_format == XFS_DINODE_FMT_LOCAL) return -EINVAL; /* * if the target inode has less extents that then temporary inode then * why did userspace call us? */ if (ifp->if_nextents < tifp->if_nextents) return -EINVAL; /* * If we have to use the (expensive) rmap swap method, we can * handle any number of extents and any format. */ if (xfs_has_rmapbt(ip->i_mount)) return 0; /* * if the target inode is in extent form and the temp inode is in btree * form then we will end up with the target inode in the wrong format * as we already know there are less extents in the temp inode. */ if (ifp->if_format == XFS_DINODE_FMT_EXTENTS && tifp->if_format == XFS_DINODE_FMT_BTREE) return -EINVAL; /* Check temp in extent form to max in target */ if (tifp->if_format == XFS_DINODE_FMT_EXTENTS && tifp->if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)) return -EINVAL; /* Check target in extent form to max in temp */ if (ifp->if_format == XFS_DINODE_FMT_EXTENTS && ifp->if_nextents > XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK)) return -EINVAL; /* * If we are in a btree format, check that the temp root block will fit * in the target and that it has enough extents to be in btree format * in the target. * * Note that we have to be careful to allow btree->extent conversions * (a common defrag case) which will occur when the temp inode is in * extent format... */ if (tifp->if_format == XFS_DINODE_FMT_BTREE) { if (xfs_inode_has_attr_fork(ip) && xfs_bmap_bmdr_space(tifp->if_broot) > xfs_inode_fork_boff(ip)) return -EINVAL; if (tifp->if_nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)) return -EINVAL; } /* Reciprocal target->temp btree format checks */ if (ifp->if_format == XFS_DINODE_FMT_BTREE) { if (xfs_inode_has_attr_fork(tip) && xfs_bmap_bmdr_space(ip->i_df.if_broot) > xfs_inode_fork_boff(tip)) return -EINVAL; if (ifp->if_nextents <= XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK)) return -EINVAL; } return 0; } static int xfs_swap_extent_flush( struct xfs_inode *ip) { int error; error = filemap_write_and_wait(VFS_I(ip)->i_mapping); if (error) return error; truncate_pagecache_range(VFS_I(ip), 0, -1); /* Verify O_DIRECT for ftmp */ if (VFS_I(ip)->i_mapping->nrpages) return -EINVAL; return 0; } /* * Move extents from one file to another, when rmap is enabled. */ STATIC int xfs_swap_extent_rmap( struct xfs_trans **tpp, struct xfs_inode *ip, struct xfs_inode *tip) { struct xfs_trans *tp = *tpp; struct xfs_bmbt_irec irec; struct xfs_bmbt_irec uirec; struct xfs_bmbt_irec tirec; xfs_fileoff_t offset_fsb; xfs_fileoff_t end_fsb; xfs_filblks_t count_fsb; int error; xfs_filblks_t ilen; xfs_filblks_t rlen; int nimaps; uint64_t tip_flags2; /* * If the source file has shared blocks, we must flag the donor * file as having shared blocks so that we get the shared-block * rmap functions when we go to fix up the rmaps. The flags * will be switch for reals later. */ tip_flags2 = tip->i_diflags2; if (ip->i_diflags2 & XFS_DIFLAG2_REFLINK) tip->i_diflags2 |= XFS_DIFLAG2_REFLINK; offset_fsb = 0; end_fsb = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip))); count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); while (count_fsb) { /* Read extent from the donor file */ nimaps = 1; error = xfs_bmapi_read(tip, offset_fsb, count_fsb, &tirec, &nimaps, 0); if (error) goto out; ASSERT(nimaps == 1); ASSERT(tirec.br_startblock != DELAYSTARTBLOCK); trace_xfs_swap_extent_rmap_remap(tip, &tirec); ilen = tirec.br_blockcount; /* Unmap the old blocks in the source file. */ while (tirec.br_blockcount) { ASSERT(tp->t_highest_agno == NULLAGNUMBER); trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec); /* Read extent from the source file */ nimaps = 1; error = xfs_bmapi_read(ip, tirec.br_startoff, tirec.br_blockcount, &irec, &nimaps, 0); if (error) goto out; ASSERT(nimaps == 1); ASSERT(tirec.br_startoff == irec.br_startoff); trace_xfs_swap_extent_rmap_remap_piece(ip, &irec); /* Trim the extent. */ uirec = tirec; uirec.br_blockcount = rlen = min_t(xfs_filblks_t, tirec.br_blockcount, irec.br_blockcount); trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec); if (xfs_bmap_is_real_extent(&uirec)) { error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK, XFS_IEXT_SWAP_RMAP_CNT); if (error) goto out; } if (xfs_bmap_is_real_extent(&irec)) { error = xfs_iext_count_extend(tp, tip, XFS_DATA_FORK, XFS_IEXT_SWAP_RMAP_CNT); if (error) goto out; } /* Remove the mapping from the donor file. */ xfs_bmap_unmap_extent(tp, tip, XFS_DATA_FORK, &uirec); /* Remove the mapping from the source file. */ xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &irec); /* Map the donor file's blocks into the source file. */ xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, &uirec); /* Map the source file's blocks into the donor file. */ xfs_bmap_map_extent(tp, tip, XFS_DATA_FORK, &irec); error = xfs_defer_finish(tpp); tp = *tpp; if (error) goto out; tirec.br_startoff += rlen; if (tirec.br_startblock != HOLESTARTBLOCK && tirec.br_startblock != DELAYSTARTBLOCK) tirec.br_startblock += rlen; tirec.br_blockcount -= rlen; } /* Roll on... */ count_fsb -= ilen; offset_fsb += ilen; } tip->i_diflags2 = tip_flags2; return 0; out: trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_); tip->i_diflags2 = tip_flags2; return error; } /* Swap the extents of two files by swapping data forks. */ STATIC int xfs_swap_extent_forks( struct xfs_trans *tp, struct xfs_inode *ip, struct xfs_inode *tip, int *src_log_flags, int *target_log_flags) { xfs_filblks_t aforkblks = 0; xfs_filblks_t taforkblks = 0; xfs_extnum_t junk; uint64_t tmp; int error; /* * Count the number of extended attribute blocks */ if (xfs_inode_has_attr_fork(ip) && ip->i_af.if_nextents > 0 && ip->i_af.if_format != XFS_DINODE_FMT_LOCAL) { error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk, &aforkblks); if (error) return error; } if (xfs_inode_has_attr_fork(tip) && tip->i_af.if_nextents > 0 && tip->i_af.if_format != XFS_DINODE_FMT_LOCAL) { error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk, &taforkblks); if (error) return error; } /* * Btree format (v3) inodes have the inode number stamped in the bmbt * block headers. We can't start changing the bmbt blocks until the * inode owner change is logged so recovery does the right thing in the * event of a crash. Set the owner change log flags now and leave the * bmbt scan as the last step. */ if (xfs_has_v3inodes(ip->i_mount)) { if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE) (*target_log_flags) |= XFS_ILOG_DOWNER; if (tip->i_df.if_format == XFS_DINODE_FMT_BTREE) (*src_log_flags) |= XFS_ILOG_DOWNER; } /* * Swap the data forks of the inodes */ swap(ip->i_df, tip->i_df); /* * Fix the on-disk inode values */ tmp = (uint64_t)ip->i_nblocks; ip->i_nblocks = tip->i_nblocks - taforkblks + aforkblks; tip->i_nblocks = tmp + taforkblks - aforkblks; /* * The extents in the source inode could still contain speculative * preallocation beyond EOF (e.g. the file is open but not modified * while defrag is in progress). In that case, we need to copy over the * number of delalloc blocks the data fork in the source inode is * tracking beyond EOF so that when the fork is truncated away when the * temporary inode is unlinked we don't underrun the i_delayed_blks * counter on that inode. */ ASSERT(tip->i_delayed_blks == 0); tip->i_delayed_blks = ip->i_delayed_blks; ip->i_delayed_blks = 0; switch (ip->i_df.if_format) { case XFS_DINODE_FMT_EXTENTS: (*src_log_flags) |= XFS_ILOG_DEXT; break; case XFS_DINODE_FMT_BTREE: ASSERT(!xfs_has_v3inodes(ip->i_mount) || (*src_log_flags & XFS_ILOG_DOWNER)); (*src_log_flags) |= XFS_ILOG_DBROOT; break; } switch (tip->i_df.if_format) { case XFS_DINODE_FMT_EXTENTS: (*target_log_flags) |= XFS_ILOG_DEXT; break; case XFS_DINODE_FMT_BTREE: (*target_log_flags) |= XFS_ILOG_DBROOT; ASSERT(!xfs_has_v3inodes(ip->i_mount) || (*target_log_flags & XFS_ILOG_DOWNER)); break; } return 0; } /* * Fix up the owners of the bmbt blocks to refer to the current inode. The * change owner scan attempts to order all modified buffers in the current * transaction. In the event of ordered buffer failure, the offending buffer is * physically logged as a fallback and the scan returns -EAGAIN. We must roll * the transaction in this case to replenish the fallback log reservation and * restart the scan. This process repeats until the scan completes. */ static int xfs_swap_change_owner( struct xfs_trans **tpp, struct xfs_inode *ip, struct xfs_inode *tmpip) { int error; struct xfs_trans *tp = *tpp; do { error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino, NULL); /* success or fatal error */ if (error != -EAGAIN) break; error = xfs_trans_roll(tpp); if (error) break; tp = *tpp; /* * Redirty both inodes so they can relog and keep the log tail * moving forward. */ xfs_trans_ijoin(tp, ip, 0); xfs_trans_ijoin(tp, tmpip, 0); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE); } while (true); return error; } int xfs_swap_extents( struct xfs_inode *ip, /* target inode */ struct xfs_inode *tip, /* tmp inode */ struct xfs_swapext *sxp) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; struct xfs_bstat *sbp = &sxp->sx_stat; int src_log_flags, target_log_flags; int error = 0; uint64_t f; int resblks = 0; unsigned int flags = 0; struct timespec64 ctime, mtime; /* * Lock the inodes against other IO, page faults and truncate to * begin with. Then we can ensure the inodes are flushed and have no * page cache safely. Once we have done this we can take the ilocks and * do the rest of the checks. */ lock_two_nondirectories(VFS_I(ip), VFS_I(tip)); filemap_invalidate_lock_two(VFS_I(ip)->i_mapping, VFS_I(tip)->i_mapping); /* Verify that both files have the same format */ if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) { error = -EINVAL; goto out_unlock; } /* Verify both files are either real-time or non-realtime */ if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) { error = -EINVAL; goto out_unlock; } /* * The rmapbt implementation is unable to resume a swapext operation * after a crash if the allocation unit size is larger than a block. * This (deprecated) interface will not be upgraded to handle this * situation. Defragmentation must be performed with the commit range * ioctl. */ if (XFS_IS_REALTIME_INODE(ip) && xfs_has_rtgroups(ip->i_mount)) { error = -EOPNOTSUPP; goto out_unlock; } error = xfs_qm_dqattach(ip); if (error) goto out_unlock; error = xfs_qm_dqattach(tip); if (error) goto out_unlock; error = xfs_swap_extent_flush(ip); if (error) goto out_unlock; error = xfs_swap_extent_flush(tip); if (error) goto out_unlock; if (xfs_inode_has_cow_data(tip)) { error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true); if (error) goto out_unlock; } /* * Extent "swapping" with rmap requires a permanent reservation and * a block reservation because it's really just a remap operation * performed with log redo items! */ if (xfs_has_rmapbt(mp)) { int w = XFS_DATA_FORK; uint32_t ipnext = ip->i_df.if_nextents; uint32_t tipnext = tip->i_df.if_nextents; /* * Conceptually this shouldn't affect the shape of either bmbt, * but since we atomically move extents one by one, we reserve * enough space to rebuild both trees. */ resblks = XFS_SWAP_RMAP_SPACE_RES(mp, ipnext, w); resblks += XFS_SWAP_RMAP_SPACE_RES(mp, tipnext, w); /* * If either inode straddles a bmapbt block allocation boundary, * the rmapbt algorithm triggers repeated allocs and frees as * extents are remapped. This can exhaust the block reservation * prematurely and cause shutdown. Return freed blocks to the * transaction reservation to counter this behavior. */ flags |= XFS_TRANS_RES_FDBLKS; } error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, flags, &tp); if (error) goto out_unlock; /* * Lock and join the inodes to the tansaction so that transaction commit * or cancel will unlock the inodes from this point onwards. */ xfs_lock_two_inodes(ip, XFS_ILOCK_EXCL, tip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); xfs_trans_ijoin(tp, tip, 0); /* Verify all data are being swapped */ if (sxp->sx_offset != 0 || sxp->sx_length != ip->i_disk_size || sxp->sx_length != tip->i_disk_size) { error = -EFAULT; goto out_trans_cancel; } trace_xfs_swap_extent_before(ip, 0); trace_xfs_swap_extent_before(tip, 1); /* check inode formats now that data is flushed */ error = xfs_swap_extents_check_format(ip, tip); if (error) { xfs_notice(mp, "%s: inode 0x%llx format is incompatible for exchanging.", __func__, ip->i_ino); goto out_trans_cancel; } /* * Compare the current change & modify times with that * passed in. If they differ, we abort this swap. * This is the mechanism used to ensure the calling * process that the file was not changed out from * under it. */ ctime = inode_get_ctime(VFS_I(ip)); mtime = inode_get_mtime(VFS_I(ip)); if ((sbp->bs_ctime.tv_sec != ctime.tv_sec) || (sbp->bs_ctime.tv_nsec != ctime.tv_nsec) || (sbp->bs_mtime.tv_sec != mtime.tv_sec) || (sbp->bs_mtime.tv_nsec != mtime.tv_nsec)) { error = -EBUSY; goto out_trans_cancel; } /* * Note the trickiness in setting the log flags - we set the owner log * flag on the opposite inode (i.e. the inode we are setting the new * owner to be) because once we swap the forks and log that, log * recovery is going to see the fork as owned by the swapped inode, * not the pre-swapped inodes. */ src_log_flags = XFS_ILOG_CORE; target_log_flags = XFS_ILOG_CORE; if (xfs_has_rmapbt(mp)) error = xfs_swap_extent_rmap(&tp, ip, tip); else error = xfs_swap_extent_forks(tp, ip, tip, &src_log_flags, &target_log_flags); if (error) goto out_trans_cancel; /* Do we have to swap reflink flags? */ if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^ (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) { f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK; ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK; tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK; } /* Swap the cow forks. */ if (xfs_has_reflink(mp)) { ASSERT(!ip->i_cowfp || ip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS); ASSERT(!tip->i_cowfp || tip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS); swap(ip->i_cowfp, tip->i_cowfp); if (ip->i_cowfp && ip->i_cowfp->if_bytes) xfs_inode_set_cowblocks_tag(ip); else xfs_inode_clear_cowblocks_tag(ip); if (tip->i_cowfp && tip->i_cowfp->if_bytes) xfs_inode_set_cowblocks_tag(tip); else xfs_inode_clear_cowblocks_tag(tip); } xfs_trans_log_inode(tp, ip, src_log_flags); xfs_trans_log_inode(tp, tip, target_log_flags); /* * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems * have inode number owner values in the bmbt blocks that still refer to * the old inode. Scan each bmbt to fix up the owner values with the * inode number of the current inode. */ if (src_log_flags & XFS_ILOG_DOWNER) { error = xfs_swap_change_owner(&tp, ip, tip); if (error) goto out_trans_cancel; } if (target_log_flags & XFS_ILOG_DOWNER) { error = xfs_swap_change_owner(&tp, tip, ip); if (error) goto out_trans_cancel; } /* * If this is a synchronous mount, make sure that the * transaction goes to disk before returning to the user. */ if (xfs_has_wsync(mp)) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); trace_xfs_swap_extent_after(ip, 0); trace_xfs_swap_extent_after(tip, 1); out_unlock_ilock: xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_iunlock(tip, XFS_ILOCK_EXCL); out_unlock: filemap_invalidate_unlock_two(VFS_I(ip)->i_mapping, VFS_I(tip)->i_mapping); unlock_two_nondirectories(VFS_I(ip), VFS_I(tip)); return error; out_trans_cancel: xfs_trans_cancel(tp); goto out_unlock_ilock; } |
| 3 3 5 5 235 234 299 299 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * Some part derived from fs/eventfd.c (anon inode setup) and * mm/ksm.c (mm hashing). */ #include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/file.h> #include <linux/bug.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/userfaultfd_k.h> #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/swapops.h> #include <linux/miscdevice.h> #include <linux/uio.h> static int sysctl_unprivileged_userfaultfd __read_mostly; #ifdef CONFIG_SYSCTL static struct ctl_table vm_userfaultfd_table[] = { { .procname = "unprivileged_userfaultfd", .data = &sysctl_unprivileged_userfaultfd, .maxlen = sizeof(sysctl_unprivileged_userfaultfd), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; #endif static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init; struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; struct list_head list; }; struct userfaultfd_unmap_ctx { struct userfaultfd_ctx *ctx; unsigned long start; unsigned long end; struct list_head list; }; struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; struct userfaultfd_wake_range { unsigned long start; unsigned long len; }; /* internal indication that UFFD_API ioctl was successfully executed */ #define UFFD_FEATURE_INITIALIZED (1u << 31) static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) { return ctx->features & UFFD_FEATURE_INITIALIZED; } static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx) { return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC); } /* * Whether WP_UNPOPULATED is enabled on the uffd context. It is only * meaningful when userfaultfd_wp()==true on the vma and when it's * anonymous. */ bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) { struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return false; return ctx->features & UFFD_FEATURE_WP_UNPOPULATED; } static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; int ret; struct userfaultfd_wait_queue *uwq; unsigned long start, len; uwq = container_of(wq, struct userfaultfd_wait_queue, wq); ret = 0; /* len == 0 means wake all */ start = range->start; len = range->len; if (len && (start > uwq->msg.arg.pagefault.address || start + len <= uwq->msg.arg.pagefault.address)) goto out; WRITE_ONCE(uwq->waken, true); /* * The Program-Order guarantees provided by the scheduler * ensure uwq->waken is visible before the task is woken. */ ret = wake_up_state(wq->private, mode); if (ret) { /* * Wake only once, autoremove behavior. * * After the effect of list_del_init is visible to the other * CPUs, the waitqueue may disappear from under us, see the * !list_empty_careful() in handle_userfault(). * * try_to_wake_up() has an implicit smp_mb(), and the * wq->private is read before calling the extern function * "wake_up_state" (which in turns calls try_to_wake_up). */ list_del_init(&wq->entry); } out: return ret; } /** * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { refcount_inc(&ctx->refcount); } /** * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to userfaultfd context. * * The userfaultfd context reference must have been previously acquired either * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget(). */ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) { if (refcount_dec_and_test(&ctx->refcount)) { VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->event_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } } static inline void msg_init(struct uffd_msg *msg) { BUILD_BUG_ON(sizeof(struct uffd_msg) != 32); /* * Must use memset to zero out the paddings or kernel data is * leaked to userland. */ memset(msg, 0, sizeof(struct uffd_msg)); } static inline struct uffd_msg userfault_msg(unsigned long address, unsigned long real_address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ? real_address : address; /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. * - Neither of these flags being set indicates a MISSING fault. * * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write * fault. Otherwise, it was a read fault. */ if (flags & FAULT_FLAG_WRITE) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; if (reason & VM_UFFD_MINOR) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } #ifdef CONFIG_HUGETLB_PAGE /* * Same functionality as userfaultfd_must_wait below with modifications for * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct vm_area_struct *vma = vmf->vma; pte_t *ptep, pte; bool ret = true; assert_fault_locked(vmf); ptep = hugetlb_walk(vma, vmf->address, vma_mmu_pagesize(vma)); if (!ptep) goto out; ret = false; pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ if (huge_pte_none_mostly(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; out: return ret; } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { return false; /* should never get here */ } #endif /* CONFIG_HUGETLB_PAGE */ /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any * userfault that has already been resolved, if userfaultfd_read_iter and * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different * threads. */ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct mm_struct *mm = ctx->mm; unsigned long address = vmf->address; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; pte_t ptent; bool ret = true; assert_fault_locked(vmf); pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); again: _pmd = pmdp_get_lockless(pmd); if (pmd_none(_pmd)) goto out; ret = false; if (!pmd_present(_pmd) || pmd_devmap(_pmd)) goto out; if (pmd_trans_huge(_pmd)) { if (!pmd_write(_pmd) && (reason & VM_UFFD_WP)) ret = true; goto out; } pte = pte_offset_map(pmd, address); if (!pte) { ret = true; goto again; } /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ ptent = ptep_get(pte); if (pte_none_mostly(ptent)) ret = true; if (!pte_write(ptent) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); out: return ret; } static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) { if (flags & FAULT_FLAG_INTERRUPTIBLE) return TASK_INTERRUPTIBLE; if (flags & FAULT_FLAG_KILLABLE) return TASK_KILLABLE; return TASK_UNINTERRUPTIBLE; } /* * The locking rules involved in returning VM_FAULT_RETRY depending on * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and * FAULT_FLAG_KILLABLE are not straightforward. The "Caution" * recommendation in __lock_page_or_retry is not an understatement. * * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is * not set. * * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not * set, VM_FAULT_RETRY can still be returned if and only if there are * fatal_signal_pending()s, and the mmap_lock must be released before * returning it. */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; bool must_wait; unsigned int blocking_state; /* * We don't do userfault handling for the final child pid update * and when coredumping (faults triggered by get_dump_page()). */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; assert_fault_locked(vmf); ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; BUG_ON(ctx->mm != mm); /* Any unrecognized flag is a bug. */ VM_BUG_ON(reason & ~__VM_UFFD_FLAGS); /* 0 or > 1 flags set is a bug; we expect exactly 1. */ VM_BUG_ON(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY)) goto out; /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_lock. */ if (unlikely(READ_ONCE(ctx->released))) { /* * Don't return VM_FAULT_SIGBUS in this case, so a non * cooperative manager can close the uffd after the * last UFFDIO_COPY, without risking to trigger an * involuntary SIGBUS if the process was starting the * userfaultfd while the userfaultfd was still armed * (but after the last UFFDIO_COPY). If the uffd * wasn't already closed when the userfault reached * this point, that would normally be solved by * userfaultfd_must_wait returning 'false'. * * If we were to return VM_FAULT_SIGBUS here, the non * cooperative manager would be instead forced to * always call UFFDIO_UNREGISTER before it can safely * close the uffd. */ ret = VM_FAULT_NOPAGE; goto out; } /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY * even if FAULT_FLAG_TRIED is set without leading to gup() * -EBUSY failures, if the userfaultfd is to be extended for * VM_UFFD_WP tracking and we intend to arm the userfault * without first stopping userland access to the memory. For * VM_UFFD_MISSING userfaults this is enough for now. */ if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) { /* * Validate the invariant that nowait must allow retry * to be sure not to return SIGBUS erroneously on * nowait invocations. */ BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT); #ifdef CONFIG_DEBUG_VM if (printk_ratelimit()) { printk(KERN_WARNING "FAULT_FLAG_ALLOW_RETRY missing %x\n", vmf->flags); dump_stack(); } #endif goto out; } /* * Handle nowait, not much to do other than tell it to retry * and wait. */ ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out; /* take the reference before dropping the mmap_lock */ userfaultfd_ctx_get(ctx); init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags, reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; blocking_state = userfaultfd_get_blocking_state(vmf->flags); /* * Take the vma lock now, in order to safely call * userfaultfd_huge_must_wait() later. Since acquiring the * (sleepable) vma lock can modify the current task state, that * must be before explicitly calling set_current_state(). */ if (is_vm_hugetlb_page(vma)) hugetlb_vma_lock_read(vma); spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq); /* * The smp_mb() after __set_current_state prevents the reads * following the spin_unlock to happen before the list_add in * __add_wait_queue. */ set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); if (!is_vm_hugetlb_page(vma)) must_wait = userfaultfd_must_wait(ctx, vmf, reason); else must_wait = userfaultfd_huge_must_wait(ctx, vmf, reason); if (is_vm_hugetlb_page(vma)) hugetlb_vma_unlock_read(vma); release_fault_lock(vmf); if (likely(must_wait && !READ_ONCE(ctx->released))) { wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); } __set_current_state(TASK_RUNNING); /* * Here we race with the list_del; list_add in * userfaultfd_ctx_read(), however because we don't ever run * list_del_init() to refile across the two lists, the prev * and next pointers will never point to self. list_add also * would never let any of the two pointers to point to * self. So list_empty_careful won't risk to see both pointers * pointing to self at any time during the list refile. The * only case where list_del_init() is called is the full * removal in the wake function and there we don't re-list_add * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ if (!list_empty_careful(&uwq.wq.entry)) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ list_del(&uwq.wq.entry); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ userfaultfd_ctx_put(ctx); out: return ret; } static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { struct userfaultfd_ctx *release_new_ctx; if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); release_new_ctx = NULL; spin_lock_irq(&ctx->event_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->event_wqh, &ewq->wq); for (;;) { set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but * __remove_wait_queue ignores the head * parameter. It would be a problem if it * didn't. */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; release_new_ctx = new; } break; } spin_unlock_irq(&ctx->event_wqh.lock); wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); spin_lock_irq(&ctx->event_wqh.lock); } __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { userfaultfd_release_new(release_new_ctx); userfaultfd_ctx_put(release_new_ctx); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ out: atomic_dec(&ctx->mmap_changing); VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { ewq->msg.event = 0; wake_up_locked(&ctx->event_wqh); __remove_wait_queue(&ctx->event_wqh, &ewq->wq); } int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) { struct userfaultfd_ctx *ctx = NULL, *octx; struct userfaultfd_fork_ctx *fctx; octx = vma->vm_userfaultfd_ctx.ctx; if (!octx) return 0; if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) { userfaultfd_reset_ctx(vma); return 0; } list_for_each_entry(fctx, fcs, list) if (fctx->orig == octx) { ctx = fctx->new; break; } if (!ctx) { fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); if (!fctx) return -ENOMEM; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) { kfree(fctx); return -ENOMEM; } refcount_set(&ctx->refcount, 1); ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); down_write(&octx->map_changing_lock); atomic_inc(&octx->mmap_changing); up_write(&octx->map_changing_lock); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); } vma->vm_userfaultfd_ctx.ctx = ctx; return 0; } static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } } void dup_userfaultfd_fail(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; /* * An error has occurred on fork, we will tear memory down, but have * allocated memory for fctx's and raised reference counts for both the * original and child contexts (and on the mm for each as a result). * * These would ordinarily be taken care of by a user handling the event, * but we are no longer doing so, so manually clean up here. * * mm tear down will take care of cleaning up VMA contexts. */ list_for_each_entry_safe(fctx, n, fcs, list) { struct userfaultfd_ctx *octx = fctx->orig; struct userfaultfd_ctx *ctx = fctx->new; atomic_dec(&octx->mmap_changing); VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0); userfaultfd_ctx_put(octx); userfaultfd_ctx_put(ctx); list_del(&fctx->list); kfree(fctx); } } void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { struct userfaultfd_ctx *ctx; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return; if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); } else { /* Drop uffd context if remap feature not enabled */ userfaultfd_reset_ctx(vma); } } void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, unsigned long from, unsigned long to, unsigned long len) { struct userfaultfd_ctx *ctx = vm_ctx->ctx; struct userfaultfd_wait_queue ewq; if (!ctx) return; if (to & ~PAGE_MASK) { userfaultfd_ctx_put(ctx); return; } msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMAP; ewq.msg.arg.remap.from = from; ewq.msg.arg.remap.to = to; ewq.msg.arg.remap.len = len; userfaultfd_event_wait_completion(ctx, &ewq); } bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue ewq; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) return true; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); mmap_read_unlock(mm); msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; ewq.msg.arg.remove.start = start; ewq.msg.arg.remove.end = end; userfaultfd_event_wait_completion(ctx, &ewq); return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, unsigned long start, unsigned long end) { struct userfaultfd_unmap_ctx *unmap_ctx; list_for_each_entry(unmap_ctx, unmaps, list) if (unmap_ctx->ctx == ctx && unmap_ctx->start == start && unmap_ctx->end == end) return true; return false; } int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *unmaps) { struct userfaultfd_unmap_ctx *unmap_ctx; struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || has_unmap_ctx(ctx, unmaps, start, end)) return 0; unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); if (!unmap_ctx) return -ENOMEM; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; list_add_tail(&unmap_ctx->list, unmaps); return 0; } void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { struct userfaultfd_unmap_ctx *ctx, *n; struct userfaultfd_wait_queue ewq; list_for_each_entry_safe(ctx, n, uf, list) { msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_UNMAP; ewq.msg.arg.remove.start = ctx->start; ewq.msg.arg.remove.end = ctx->end; userfaultfd_event_wait_completion(ctx->ctx, &ewq); list_del(&ctx->list); kfree(ctx); } } static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; struct mm_struct *mm = ctx->mm; /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; WRITE_ONCE(ctx->released, true); userfaultfd_release_all(mm, ctx); /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on * the fault_*wqh. */ spin_lock_irq(&ctx->fault_pending_wqh.lock); __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); wake_up_poll(&ctx->fd_wqh, EPOLLHUP); userfaultfd_ctx_put(ctx); return 0; } /* fault_pending_wqh.lock must be hold by the caller */ static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; lockdep_assert_held(&wqh->lock); uwq = NULL; if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } static inline struct userfaultfd_wait_queue *find_userfault( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->fault_pending_wqh); } static inline struct userfaultfd_wait_queue *find_userfault_evt( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->event_wqh); } static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; __poll_t ret; poll_wait(file, &ctx->fd_wqh, wait); if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; /* * poll() never guarantees that read won't block. * userfaults can be waken before they're read(). */ if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; /* * lockless access to see if there are pending faults * __pollwait last action is the add_wait_queue but * the spin_unlock would allow the waitqueue_active to * pass above the actual list_add inside * add_wait_queue critical section. So use a full * memory barrier to serialize the list_add write of * add_wait_queue() with the waitqueue_active read * below. */ ret = 0; smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = EPOLLIN; else if (waitqueue_active(&ctx->event_wqh)) ret = EPOLLIN; return ret; } static const struct file_operations userfaultfd_fops; static int resolve_userfault_fork(struct userfaultfd_ctx *new, struct inode *inode, struct uffd_msg *msg) { int fd; fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new, O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; msg->arg.reserved.reserved1 = 0; msg->arg.fork.ufd = fd; return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, struct uffd_msg *msg, struct inode *inode) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; /* * Handling fork event requires sleeping operations, so * we drop the event_wqh lock, then do these ops, then * lock it back and wake up the waiter. While the lock is * dropped the ewq may go away so we keep track of it * carefully. */ LIST_HEAD(fork_event); struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock_irq(&ctx->fd_wqh.lock); __add_wait_queue(&ctx->fd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); spin_lock(&ctx->fault_pending_wqh.lock); uwq = find_userfault(ctx); if (uwq) { /* * Use a seqcount to repeat the lockless check * in wake_userfault() to avoid missing * wakeups because during the refile both * waitqueue could become empty if this is the * only userfault. */ write_seqcount_begin(&ctx->refile_seq); /* * The fault_pending_wqh.lock prevents the uwq * to disappear from under us. * * Refile this userfault from * fault_pending_wqh to fault_wqh, it's not * pending anymore after we read it. * * Use list_del() by hand (as * userfaultfd_wake_function also uses * list_del_init() by hand) to be sure nobody * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ list_del(&uwq->wq.entry); add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); /* careful to always initialize msg if ret == 0 */ *msg = uwq->msg; spin_unlock(&ctx->fault_pending_wqh.lock); ret = 0; break; } spin_unlock(&ctx->fault_pending_wqh.lock); spin_lock(&ctx->event_wqh.lock); uwq = find_userfault_evt(ctx); if (uwq) { *msg = uwq->msg; if (uwq->msg.event == UFFD_EVENT_FORK) { fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); /* * fork_nctx can be freed as soon as * we drop the lock, unless we take a * reference on it. */ userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } userfaultfd_event_complete(ctx, uwq); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } spin_unlock(&ctx->event_wqh.lock); if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (no_wait) { ret = -EAGAIN; break; } spin_unlock_irq(&ctx->fd_wqh.lock); schedule(); spin_lock_irq(&ctx->fd_wqh.lock); } __remove_wait_queue(&ctx->fd_wqh, &wait); __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->fd_wqh.lock); if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(fork_nctx, inode, msg); spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* * The fork thread didn't abort, so we can * drop the temporary refcount. */ userfaultfd_ctx_put(fork_nctx); uwq = list_first_entry(&fork_event, typeof(*uwq), wq.entry); /* * If fork_event list wasn't empty and in turn * the event wasn't already released by fork * (the event is allocated on fork kernel * stack), put the event back to its place in * the event_wq. fork_event head will be freed * as soon as we return so the event cannot * stay queued there no matter the current * "ret" value. */ list_del(&uwq->wq.entry); __add_wait_queue(&ctx->event_wqh, &uwq->wq); /* * Leave the event in the waitqueue and report * error to userland if we failed to resolve * the userfault fork. */ if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); } else { /* * Here the fork thread aborted and the * refcount from the fork thread on fork_nctx * has already been released. We still hold * the reference we took before releasing the * lock above. If resolve_userfault_fork * failed we've to drop it because the * fork_nctx has to be freed in such case. If * it succeeded we'll hold it because the new * uffd references it. */ if (ret) userfaultfd_ctx_put(fork_nctx); } spin_unlock_irq(&ctx->event_wqh.lock); } return ret; } static ssize_t userfaultfd_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct userfaultfd_ctx *ctx = file->private_data; ssize_t _ret, ret = 0; struct uffd_msg msg; struct inode *inode = file_inode(file); bool no_wait; if (!userfaultfd_is_initialized(ctx)) return -EINVAL; no_wait = file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT; for (;;) { if (iov_iter_count(to) < sizeof(msg)) return ret ? ret : -EINVAL; _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode); if (_ret < 0) return ret ? ret : _ret; _ret = !copy_to_iter_full(&msg, sizeof(msg), to); if (_ret) return ret ? ret : -EFAULT; ret += sizeof(msg); /* * Allow to read more than one fault at time but only * block if waiting for the very first one. */ no_wait = true; } } static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { unsigned seq; bool need_wakeup; /* * To be sure waitqueue_active() is not reordered by the CPU * before the pagetable update, use an explicit SMP memory * barrier here. PT lock release or mmap_read_unlock(mm) still * have release semantics that can allow the * waitqueue_active() to be reordered before the pte update. */ smp_mb(); /* * Use waitqueue_active because it's very frequent to * change the address space atomically even if there are no * userfaults yet. So we take the spinlock only when we're * sure we've userfaults to wake. */ do { seq = read_seqcount_begin(&ctx->refile_seq); need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) || waitqueue_active(&ctx->fault_wqh); cond_resched(); } while (read_seqcount_retry(&ctx->refile_seq, seq)); if (need_wakeup) __wake_userfault(ctx, range); } static __always_inline int validate_unaligned_range( struct mm_struct *mm, __u64 start, __u64 len) { __u64 task_size = mm->task_size; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; if (start < mmap_min_addr) return -EINVAL; if (start >= task_size) return -EINVAL; if (len > task_size - start) return -EINVAL; if (start + len <= start) return -EINVAL; return 0; } static __always_inline int validate_range(struct mm_struct *mm, __u64 start, __u64 len) { if (start & ~PAGE_MASK) return -EINVAL; return validate_unaligned_range(mm, start, len); } static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *cur; int ret; struct uffdio_register uffdio_register; struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags; bool found; bool basic_ioctls; unsigned long start, end; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); user_uffdio_register = (struct uffdio_register __user *) arg; ret = -EFAULT; if (copy_from_user(&uffdio_register, user_uffdio_register, sizeof(uffdio_register)-sizeof(__u64))) goto out; ret = -EINVAL; if (!uffdio_register.mode) goto out; if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP goto out; #endif vm_flags |= VM_UFFD_WP; } if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; #endif vm_flags |= VM_UFFD_MINOR; } ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; start = uffdio_register.range.start; end = start + uffdio_register.range.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; ret = -EINVAL; mmap_write_lock(mm); vma_iter_init(&vmi, mm, start); vma = vma_find(&vmi, end); if (!vma) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; basic_ioctls = false; cur = vma; do { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; if (!vma_can_userfault(cur, vm_flags, wp_async)) goto out_unlock; /* * UFFDIO_COPY will fill file holes even without * PROT_WRITE. This check enforces that if this is a * MAP_SHARED, the process has write permission to the backing * file. If VM_MAYWRITE is set it also enforces that on a * MAP_SHARED vma: there is no F_WRITE_SEAL and no further * F_WRITE_SEAL can be taken until the vma is destroyed. */ ret = -EPERM; if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) goto out_unlock; /* * If this vma contains ending address, and huge pages * check alignment. */ if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && end > cur->vm_start) { unsigned long vma_hpagesize = vma_kernel_pagesize(cur); ret = -EINVAL; if (end & (vma_hpagesize - 1)) goto out_unlock; } if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE)) goto out_unlock; /* * Check that this vma isn't already owned by a * different userfaultfd. We can't allow more than one * userfaultfd to own a single vma simultaneously or we * wouldn't know which one to deliver the userfaults to. */ ret = -EBUSY; if (cur->vm_userfaultfd_ctx.ctx && cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; /* * Note vmas containing huge pages */ if (is_vm_hugetlb_page(cur)) basic_ioctls = true; found = true; } for_each_vma_range(vmi, cur, end); BUG_ON(!found); ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end, wp_async); out_unlock: mmap_write_unlock(mm); mmput(mm); if (!ret) { __u64 ioctls_out; ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS; /* * Declare the WP ioctl only if the WP mode is * specified and all checks passed with the range */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)) ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT); /* CONTINUE ioctl is only supported for MINOR ranges. */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR)) ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE); /* * Now that we scanned all vmas we can already tell * userland which ioctls methods are guaranteed to * succeed on this range. */ if (put_user(ioctls_out, &user_uffdio_register->ioctls)) ret = -EFAULT; } out: return ret; } static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_range uffdio_unregister; bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; start = uffdio_unregister.start; end = start + uffdio_unregister.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); ret = -EINVAL; vma_iter_init(&vmi, mm, start); vma = vma_find(&vmi, end); if (!vma) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; cur = vma; do { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Check not compatible vmas, not strictly required * here as not compatible vmas cannot have an * userfaultfd_ctx registered on them, but this * provides for more strict behavior to notice * unregistration errors. */ if (!vma_can_userfault(cur, cur->vm_flags, wp_async)) goto out_unlock; found = true; } for_each_vma_range(vmi, cur, end); BUG_ON(!found); vma_iter_set(&vmi, start); prev = vma_prev(&vmi); if (vma->vm_start < start) prev = vma; ret = 0; for_each_vma_range(vmi, vma, end) { cond_resched(); BUG_ON(!vma_can_userfault(vma, vma->vm_flags, wp_async)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (!vma->vm_userfaultfd_ctx.ctx) goto skip; WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); if (userfaultfd_missing(vma)) { /* * Wake any concurrent pending userfault while * we unregister, so they will not hang * permanently and it avoids userland to call * UFFDIO_WAKE explicitly. */ struct userfaultfd_wake_range range; range.start = start; range.len = vma_end - start; wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } vma = userfaultfd_clear_vma(&vmi, prev, vma, start, vma_end); if (IS_ERR(vma)) { ret = PTR_ERR(vma); break; } skip: prev = vma; start = vma->vm_end; } out_unlock: mmap_write_unlock(mm); mmput(mm); out: return ret; } /* * userfaultfd_wake may be used in combination with the * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches. */ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_range uffdio_wake; struct userfaultfd_wake_range range; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; range.start = uffdio_wake.start; range.len = uffdio_wake.len; /* * len == 0 means wake all and we don't want to wake all here, * so check it again to be sure. */ VM_BUG_ON(!range.len); wake_userfault(ctx, &range); ret = 0; out: return ret; } static int userfaultfd_copy(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_copy uffdio_copy; struct uffdio_copy __user *user_uffdio_copy; struct userfaultfd_wake_range range; uffd_flags_t flags = 0; user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, /* don't copy "copy" last field */ sizeof(uffdio_copy)-sizeof(__s64))) goto out; ret = validate_unaligned_range(ctx->mm, uffdio_copy.src, uffdio_copy.len); if (ret) goto out; ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; ret = -EINVAL; if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len, flags); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; if (ret < 0) goto out; BUG_ON(!ret); /* len == 0 would wake all */ range.len = ret; if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) { range.start = uffdio_copy.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_copy.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_zeropage uffdio_zeropage; struct uffdio_zeropage __user *user_uffdio_zeropage; struct userfaultfd_wake_range range; user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, /* don't copy "zeropage" last field */ sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start, uffdio_zeropage.range.len); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) { range.start = uffdio_zeropage.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_writeprotect uffdio_wp; struct uffdio_writeprotect __user *user_uffdio_wp; struct userfaultfd_wake_range range; bool mode_wp, mode_dontwake; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; if (copy_from_user(&uffdio_wp, user_uffdio_wp, sizeof(struct uffdio_writeprotect))) return -EFAULT; ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE | UFFDIO_WRITEPROTECT_MODE_WP)) return -EINVAL; mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP; mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE; if (mode_wp && mode_dontwake) return -EINVAL; if (mmget_not_zero(ctx->mm)) { ret = mwriteprotect_range(ctx, uffdio_wp.range.start, uffdio_wp.range.len, mode_wp); mmput(ctx->mm); } else { return -ESRCH; } if (ret) return ret; if (!mode_wp && !mode_dontwake) { range.start = uffdio_wp.range.start; range.len = uffdio_wp.range.len; wake_userfault(ctx, &range); } return ret; } static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_continue uffdio_continue; struct uffdio_continue __user *user_uffdio_continue; struct userfaultfd_wake_range range; uffd_flags_t flags = 0; user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, /* don't copy the output fields */ sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE | UFFDIO_CONTINUE_MODE_WP)) goto out; if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_continue(ctx, uffdio_continue.range.start, uffdio_continue.range.len, flags); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) { range.start = uffdio_continue.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN; out: return ret; } static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_poison uffdio_poison; struct uffdio_poison __user *user_uffdio_poison; struct userfaultfd_wake_range range; user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, /* don't copy the output fields */ sizeof(uffdio_poison) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_poison.range.start, uffdio_poison.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_poison.mode & ~UFFDIO_POISON_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_poison(ctx, uffdio_poison.range.start, uffdio_poison.range.len, 0); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_poison->updated))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_poison.mode & UFFDIO_POISON_MODE_DONTWAKE)) { range.start = uffdio_poison.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_poison.range.len ? 0 : -EAGAIN; out: return ret; } bool userfaultfd_wp_async(struct vm_area_struct *vma) { return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx); } static inline unsigned int uffd_ctx_features(__u64 user_features) { /* * For the current set of features the bits just coincide. Set * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } static int userfaultfd_move(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_move uffdio_move; struct uffdio_move __user *user_uffdio_move; struct userfaultfd_wake_range range; struct mm_struct *mm = ctx->mm; user_uffdio_move = (struct uffdio_move __user *) arg; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */ sizeof(uffdio_move)-sizeof(__s64))) return -EFAULT; /* Do not allow cross-mm moves. */ if (mm != current->mm) return -EINVAL; ret = validate_range(mm, uffdio_move.dst, uffdio_move.len); if (ret) return ret; ret = validate_range(mm, uffdio_move.src, uffdio_move.len); if (ret) return ret; if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES| UFFDIO_MOVE_MODE_DONTWAKE)) return -EINVAL; if (mmget_not_zero(mm)) { ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src, uffdio_move.len, uffdio_move.mode); mmput(mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_move->move))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ VM_WARN_ON(!ret); range.len = ret; if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) { range.start = uffdio_move.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_move.len ? 0 : -EAGAIN; out: return ret; } /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API * version or -EINVAL if unknown. */ static int userfaultfd_api(struct userfaultfd_ctx *ctx, unsigned long arg) { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; unsigned int ctx_features; int ret; __u64 features; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; features = uffdio_api.features; ret = -EINVAL; if (uffdio_api.api != UFFD_API) goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; /* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */ if (features & UFFD_FEATURE_WP_ASYNC) features |= UFFD_FEATURE_WP_UNPOPULATED; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR uffdio_api.features &= ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); #endif #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif #ifndef CONFIG_PTE_MARKER_UFFD_WP uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED; uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC; #endif ret = -EINVAL; if (features & ~uffdio_api.features) goto err_out; uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; /* only enable the requested features for this uffd context */ ctx_features = uffd_ctx_features(features); ret = -EINVAL; if (cmpxchg(&ctx->features, 0, ctx_features) != 0) goto err_out; ret = 0; out: return ret; err_out: memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) ret = -EFAULT; goto out; } static long userfaultfd_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { case UFFDIO_API: ret = userfaultfd_api(ctx, arg); break; case UFFDIO_REGISTER: ret = userfaultfd_register(ctx, arg); break; case UFFDIO_UNREGISTER: ret = userfaultfd_unregister(ctx, arg); break; case UFFDIO_WAKE: ret = userfaultfd_wake(ctx, arg); break; case UFFDIO_COPY: ret = userfaultfd_copy(ctx, arg); break; case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; case UFFDIO_MOVE: ret = userfaultfd_move(ctx, arg); break; case UFFDIO_WRITEPROTECT: ret = userfaultfd_writeprotect(ctx, arg); break; case UFFDIO_CONTINUE: ret = userfaultfd_continue(ctx, arg); break; case UFFDIO_POISON: ret = userfaultfd_poison(ctx, arg); break; } return ret; } #ifdef CONFIG_PROC_FS static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; wait_queue_entry_t *wq; unsigned long pending = 0, total = 0; spin_lock_irq(&ctx->fault_pending_wqh.lock); list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { pending++; total++; } list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { total++; } spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* * If more protocols will be added, there will be all shown * separated by a space. Like this: * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif static const struct file_operations userfaultfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = userfaultfd_show_fdinfo, #endif .release = userfaultfd_release, .poll = userfaultfd_poll, .read_iter = userfaultfd_read_iter, .unlocked_ioctl = userfaultfd_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static void init_once_userfaultfd_ctx(void *mem) { struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem; init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } static int new_userfaultfd(int flags) { struct userfaultfd_ctx *ctx; struct file *file; int fd; BUG_ON(!current->mm); /* Check the UFFD_* constants for consistency. */ BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS); BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK); if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY)) return -EINVAL; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) return -ENOMEM; refcount_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; fd = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS); if (fd < 0) goto err_out; /* Create a new inode so that the LSM can block the creation. */ file = anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx, O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (IS_ERR(file)) { put_unused_fd(fd); fd = PTR_ERR(file); goto err_out; } /* prevent the mm struct to be freed */ mmgrab(ctx->mm); file->f_mode |= FMODE_NOWAIT; fd_install(fd, file); return fd; err_out: kmem_cache_free(userfaultfd_ctx_cachep, ctx); return fd; } static inline bool userfaultfd_syscall_allowed(int flags) { /* Userspace-only page faults are always allowed */ if (flags & UFFD_USER_MODE_ONLY) return true; /* * The user is requesting a userfaultfd which can handle kernel faults. * Privileged users are always allowed to do this. */ if (capable(CAP_SYS_PTRACE)) return true; /* Otherwise, access to kernel fault handling is sysctl controlled. */ return sysctl_unprivileged_userfaultfd; } SYSCALL_DEFINE1(userfaultfd, int, flags) { if (!userfaultfd_syscall_allowed(flags)) return -EPERM; return new_userfaultfd(flags); } static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags) { if (cmd != USERFAULTFD_IOC_NEW) return -EINVAL; return new_userfaultfd(flags); } static const struct file_operations userfaultfd_dev_fops = { .unlocked_ioctl = userfaultfd_dev_ioctl, .compat_ioctl = userfaultfd_dev_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice userfaultfd_misc = { .minor = MISC_DYNAMIC_MINOR, .name = "userfaultfd", .fops = &userfaultfd_dev_fops }; static int __init userfaultfd_init(void) { int ret; ret = misc_register(&userfaultfd_misc); if (ret) return ret; userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache", sizeof(struct userfaultfd_ctx), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_userfaultfd_table); #endif return 0; } __initcall(userfaultfd_init); |
| 78 21 57 39 154 90 159 5 1 1 1 159 267 159 107 1 12 97 332 333 22 249 240 333 333 1 13 51 68 66 11 3 67 7 62 72 66 1 69 2 1 68 81 9 81 72 1 1 3 70 7 64 23 1 1 62 1 61 38 23 73 38 31 4 6 2 3 2 2 1 1 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * Directory handling functions for NTFS-based filesystems. * */ #include <linux/fs.h> #include <linux/nls.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* Convert little endian UTF-16 to NLS string. */ int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const __le16 *name, u32 len, u8 *buf, int buf_len) { int ret, warn; u8 *op; struct nls_table *nls = sbi->options->nls; static_assert(sizeof(wchar_t) == sizeof(__le16)); if (!nls) { /* UTF-16 -> UTF-8 */ ret = utf16s_to_utf8s((wchar_t *)name, len, UTF16_LITTLE_ENDIAN, buf, buf_len); buf[ret] = '\0'; return ret; } op = buf; warn = 0; while (len--) { u16 ec; int charlen; char dump[5]; if (buf_len < NLS_MAX_CHARSET_SIZE) { ntfs_warn(sbi->sb, "filename was truncated while converting."); break; } ec = le16_to_cpu(*name++); charlen = nls->uni2char(ec, op, buf_len); if (charlen > 0) { op += charlen; buf_len -= charlen; continue; } *op++ = '_'; buf_len -= 1; if (warn) continue; warn = 1; hex_byte_pack(&dump[0], ec >> 8); hex_byte_pack(&dump[2], ec); dump[4] = 0; ntfs_err(sbi->sb, "failed to convert \"%s\" to %s", dump, nls->charset); } *op = '\0'; return op - buf; } // clang-format off #define PLANE_SIZE 0x00010000 #define SURROGATE_PAIR 0x0000d800 #define SURROGATE_LOW 0x00000400 #define SURROGATE_BITS 0x000003ff // clang-format on /* * put_utf16 - Modified version of put_utf16 from fs/nls/nls_base.c * * Function is sparse warnings free. */ static inline void put_utf16(wchar_t *s, unsigned int c, enum utf16_endian endian) { static_assert(sizeof(wchar_t) == sizeof(__le16)); static_assert(sizeof(wchar_t) == sizeof(__be16)); switch (endian) { default: *s = (wchar_t)c; break; case UTF16_LITTLE_ENDIAN: *(__le16 *)s = __cpu_to_le16(c); break; case UTF16_BIG_ENDIAN: *(__be16 *)s = __cpu_to_be16(c); break; } } /* * _utf8s_to_utf16s * * Modified version of 'utf8s_to_utf16s' allows to * detect -ENAMETOOLONG without writing out of expected maximum. */ static int _utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian, wchar_t *pwcs, int maxout) { u16 *op; int size; unicode_t u; op = pwcs; while (inlen > 0 && *s) { if (*s & 0x80) { size = utf8_to_utf32(s, inlen, &u); if (size < 0) return -EINVAL; s += size; inlen -= size; if (u >= PLANE_SIZE) { if (maxout < 2) return -ENAMETOOLONG; u -= PLANE_SIZE; put_utf16(op++, SURROGATE_PAIR | ((u >> 10) & SURROGATE_BITS), endian); put_utf16(op++, SURROGATE_PAIR | SURROGATE_LOW | (u & SURROGATE_BITS), endian); maxout -= 2; } else { if (maxout < 1) return -ENAMETOOLONG; put_utf16(op++, u, endian); maxout--; } } else { if (maxout < 1) return -ENAMETOOLONG; put_utf16(op++, *s++, endian); inlen--; maxout--; } } return op - pwcs; } /* * ntfs_nls_to_utf16 - Convert input string to UTF-16. * @name: Input name. * @name_len: Input name length. * @uni: Destination memory. * @max_ulen: Destination memory. * @endian: Endian of target UTF-16 string. * * This function is called: * - to create NTFS name * - to create symlink * * Return: UTF-16 string length or error (if negative). */ int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len, struct cpu_str *uni, u32 max_ulen, enum utf16_endian endian) { int ret, slen; const u8 *end; struct nls_table *nls = sbi->options->nls; u16 *uname = uni->name; static_assert(sizeof(wchar_t) == sizeof(u16)); if (!nls) { /* utf8 -> utf16 */ ret = _utf8s_to_utf16s(name, name_len, endian, uname, max_ulen); uni->len = ret; return ret; } for (ret = 0, end = name + name_len; name < end; ret++, name += slen) { if (ret >= max_ulen) return -ENAMETOOLONG; slen = nls->char2uni(name, end - name, uname + ret); if (!slen) return -EINVAL; if (slen < 0) return slen; } #ifdef __BIG_ENDIAN if (endian == UTF16_LITTLE_ENDIAN) { int i = ret; while (i--) { __cpu_to_le16s(uname); uname++; } } #else if (endian == UTF16_BIG_ENDIAN) { int i = ret; while (i--) { __cpu_to_be16s(uname); uname++; } } #endif uni->len = ret; return ret; } /* * dir_search_u - Helper function. */ struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, struct ntfs_fnd *fnd) { int err = 0; struct super_block *sb = dir->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(dir); struct NTFS_DE *e; int diff; struct inode *inode = NULL; struct ntfs_fnd *fnd_a = NULL; if (!fnd) { fnd_a = fnd_get(); if (!fnd_a) { err = -ENOMEM; goto out; } fnd = fnd_a; } err = indx_find(&ni->dir, ni, NULL, uni, 0, sbi, &diff, &e, fnd); if (err) goto out; if (diff) { err = -ENOENT; goto out; } inode = ntfs_iget5(sb, &e->ref, uni); if (!IS_ERR(inode) && is_bad_inode(inode)) { iput(inode); err = -EINVAL; } out: fnd_put(fnd_a); return err == -ENOENT ? NULL : err ? ERR_PTR(err) : inode; } /* * returns false if 'ctx' if full */ static inline bool ntfs_dir_emit(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, const struct NTFS_DE *e, u8 *name, struct dir_context *ctx) { const struct ATTR_FILE_NAME *fname; unsigned long ino; int name_len; u32 dt_type; fname = Add2Ptr(e, sizeof(struct NTFS_DE)); if (fname->type == FILE_NAME_DOS) return true; if (!mi_is_ref(&ni->mi, &fname->home)) return true; ino = ino_get(&e->ref); if (ino == MFT_REC_ROOT) return true; /* Skip meta files. Unless option to show metafiles is set. */ if (!sbi->options->showmeta && ntfs_is_meta_file(sbi, ino)) return true; if (sbi->options->nohidden && (fname->dup.fa & FILE_ATTRIBUTE_HIDDEN)) return true; name_len = ntfs_utf16_to_nls(sbi, fname->name, fname->name_len, name, PATH_MAX); if (name_len <= 0) { ntfs_warn(sbi->sb, "failed to convert name for inode %lx.", ino); return true; } /* * NTFS: symlinks are "dir + reparse" or "file + reparse" * Unfortunately reparse attribute is used for many purposes (several dozens). * It is not possible here to know is this name symlink or not. * To get exactly the type of name we should to open inode (read mft). * getattr for opened file (fstat) correctly returns symlink. */ dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; /* * It is not reliable to detect the type of name using duplicated information * stored in parent directory. * The only correct way to get the type of name - read MFT record and find ATTR_STD. * The code below is not good idea. * It does additional locks/reads just to get the type of name. * Should we use additional mount option to enable branch below? */ if (((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) || fname->dup.ea_size) && ino != ni->mi.rno) { struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL); if (!IS_ERR_OR_NULL(inode)) { dt_type = fs_umode_to_dtype(inode->i_mode); iput(inode); } } return dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } /* * ntfs_read_hdr - Helper function for ntfs_readdir(). * * returns 0 if ok. * returns -EINVAL if directory is corrupted. * returns +1 if 'ctx' is full. */ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, const struct INDEX_HDR *hdr, u64 vbo, u64 pos, u8 *name, struct dir_context *ctx) { const struct NTFS_DE *e; u32 e_size; u32 end = le32_to_cpu(hdr->used); u32 off = le32_to_cpu(hdr->de_off); for (;; off += e_size) { if (off + sizeof(struct NTFS_DE) > end) return -EINVAL; e = Add2Ptr(hdr, off); e_size = le16_to_cpu(e->size); if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) return -EINVAL; if (de_is_last(e)) return 0; /* Skip already enumerated. */ if (vbo + off < pos) continue; if (le16_to_cpu(e->key_size) < SIZEOF_ATTRIBUTE_FILENAME) return -EINVAL; ctx->pos = vbo + off; /* Submit the name to the filldir callback. */ if (!ntfs_dir_emit(sbi, ni, e, name, ctx)) { /* ctx is full. */ return +1; } } } /* * ntfs_readdir - file_operations::iterate_shared * * Use non sorted enumeration. * We have an example of broken volume where sorted enumeration * counts each name twice. */ static int ntfs_readdir(struct file *file, struct dir_context *ctx) { const struct INDEX_ROOT *root; u64 vbo; size_t bit; loff_t eod; int err = 0; struct inode *dir = file_inode(file); struct ntfs_inode *ni = ntfs_i(dir); struct super_block *sb = dir->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; loff_t i_size = i_size_read(dir); u32 pos = ctx->pos; u8 *name = NULL; struct indx_node *node = NULL; u8 index_bits = ni->dir.index_bits; /* Name is a buffer of PATH_MAX length. */ static_assert(NTFS_NAME_LEN * 4 < PATH_MAX); eod = i_size + sbi->record_size; if (pos >= eod) return 0; if (!dir_emit_dots(file, ctx)) return 0; /* Allocate PATH_MAX bytes. */ name = __getname(); if (!name) return -ENOMEM; if (!ni->mi_loaded && ni->attr_list.size) { /* * Directory inode is locked for read. * Load all subrecords to avoid 'write' access to 'ni' during * directory reading. */ ni_lock(ni); if (!ni->mi_loaded && ni->attr_list.size) { err = ni_load_all_mi(ni); if (!err) ni->mi_loaded = true; } ni_unlock(ni); if (err) goto out; } root = indx_get_root(&ni->dir, ni, NULL, NULL); if (!root) { err = -EINVAL; goto out; } if (pos >= sbi->record_size) { bit = (pos - sbi->record_size) >> index_bits; } else { err = ntfs_read_hdr(sbi, ni, &root->ihdr, 0, pos, name, ctx); if (err) goto out; bit = 0; } if (!i_size) { ctx->pos = eod; goto out; } for (;;) { vbo = (u64)bit << index_bits; if (vbo >= i_size) { ctx->pos = eod; goto out; } err = indx_used_bit(&ni->dir, ni, &bit); if (err) goto out; if (bit == MINUS_ONE_T) { ctx->pos = eod; goto out; } vbo = (u64)bit << index_bits; if (vbo >= i_size) { err = -EINVAL; goto out; } err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, &node); if (err) goto out; err = ntfs_read_hdr(sbi, ni, &node->index->ihdr, vbo + sbi->record_size, pos, name, ctx); if (err) goto out; bit += 1; } out: __putname(name); put_indx_node(node); if (err == 1) { /* 'ctx' is full. */ err = 0; } else if (err == -ENOENT) { err = 0; ctx->pos = pos; } else if (err < 0) { if (err == -EINVAL) ntfs_inode_err(dir, "directory corrupted"); ctx->pos = eod; } return err; } static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, size_t *files) { int err = 0; struct ntfs_inode *ni = ntfs_i(dir); struct NTFS_DE *e = NULL; struct INDEX_ROOT *root; struct INDEX_HDR *hdr; const struct ATTR_FILE_NAME *fname; u32 e_size, off, end; size_t drs = 0, fles = 0, bit = 0; struct indx_node *node = NULL; size_t max_indx = i_size_read(&ni->vfs_inode) >> ni->dir.index_bits; if (is_empty) *is_empty = true; root = indx_get_root(&ni->dir, ni, NULL, NULL); if (!root) return -EINVAL; hdr = &root->ihdr; for (;;) { end = le32_to_cpu(hdr->used); off = le32_to_cpu(hdr->de_off); for (; off + sizeof(struct NTFS_DE) <= end; off += e_size) { e = Add2Ptr(hdr, off); e_size = le16_to_cpu(e->size); if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) { /* Looks like corruption. */ break; } if (de_is_last(e)) break; fname = de_get_fname(e); if (!fname) continue; if (fname->type == FILE_NAME_DOS) continue; if (is_empty) { *is_empty = false; if (!dirs && !files) goto out; } if (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) drs += 1; else fles += 1; } if (bit >= max_indx) goto out; err = indx_used_bit(&ni->dir, ni, &bit); if (err) goto out; if (bit == MINUS_ONE_T) goto out; if (bit >= max_indx) goto out; err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, &node); if (err) goto out; hdr = &node->index->ihdr; bit += 1; } out: put_indx_node(node); if (dirs) *dirs = drs; if (files) *files = fles; return err; } bool dir_is_empty(struct inode *dir) { bool is_empty = false; ntfs_dir_count(dir, &is_empty, NULL, NULL); return is_empty; } // clang-format off const struct file_operations ntfs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = ntfs_readdir, .fsync = generic_file_fsync, .open = ntfs_file_open, .unlocked_ioctl = ntfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ntfs_compat_ioctl, #endif }; #if IS_ENABLED(CONFIG_NTFS_FS) const struct file_operations ntfs_legacy_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = ntfs_readdir, .open = ntfs_file_open, }; #endif // clang-format on |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. NET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Ethernet handlers. * * Version: @(#)eth.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Relocated to include/linux where it belongs by Alan Cox * <gw4pts@gw4pts.ampr.org> */ #ifndef _LINUX_ETHERDEVICE_H #define _LINUX_ETHERDEVICE_H #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> #include <linux/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); int device_get_ethdev_address(struct device *dev, struct net_device *netdev); int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); __be16 eth_header_parse_protocol(const struct sk_buff *skb); int eth_prepare_mac_addr_change(struct net_device *dev, void *p); void eth_commit_mac_addr_change(struct net_device *dev, void *p); int eth_mac_addr(struct net_device *dev, void *p); int eth_validate_addr(struct net_device *dev); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. */ static inline bool is_link_local_ether_addr(const u8 *addr) { __be16 *a = (__be16 *)addr; static const __be16 *b = (const __be16 *)eth_reserved_addr_base; static const __be16 m = cpu_to_be16(0xfff0); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif } /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ static inline bool is_zero_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0; #else return (*(const u16 *)(addr + 0) | *(const u16 *)(addr + 2) | *(const u16 *)(addr + 4)) == 0; #endif } /** * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 a = *(const u32 *)addr; #else u16 a = *(const u16 *)addr; #endif #ifdef __BIG_ENDIAN return 0x01 & (a >> ((sizeof(a) * 8) - 8)); #else return 0x01 & a; #endif } static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN return 0x01 & ((*(const u64 *)addr) >> 56); #else return 0x01 & (*(const u64 *)addr); #endif #else return is_multicast_ether_addr(addr); #endif } /** * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { return 0x02 & addr[0]; } /** * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ static inline bool is_broadcast_ether_addr(const u8 *addr) { return (*(const u16 *)(addr + 0) & *(const u16 *)(addr + 2) & *(const u16 *)(addr + 4)) == 0xffff; } /** * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { return !is_multicast_ether_addr(addr); } /** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address * * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * * Return: true if the address is valid. * * Please note: addr must be aligned to u16. */ static inline bool is_valid_ether_addr(const u8 *addr) { /* FF:FF:FF:FF:FF:FF is a multicast address so we don't need to * explicitly check for it here. */ return !is_multicast_ether_addr(addr) && !is_zero_ether_addr(addr); } /** * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol * @proto: Ethertype/length value to be tested * * Check that the value from the Ethertype/length field is a valid Ethertype. * * Return: true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { #ifndef __BIG_ENDIAN /* if CPU is little endian mask off bits representing LSB */ proto &= htons(0xFF00); #endif /* cast both to u16 and compare since LSB can be ignored */ return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); } /** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * * Generate a random Ethernet address (MAC) that is not multicast * and has the local assigned bit set. */ static inline void eth_random_addr(u8 *addr) { get_random_bytes(addr, ETH_ALEN); addr[0] &= 0xfe; /* clear multicast bit */ addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the broadcast address to the given address array. */ static inline void eth_broadcast_addr(u8 *addr) { memset(addr, 0xff, ETH_ALEN); } /** * eth_zero_addr - Assign zero address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the zero address to the given address array. */ static inline void eth_zero_addr(u8 *addr) { memset(addr, 0x00, ETH_ALEN); } /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag * @dev: pointer to net_device structure * * Generate a random Ethernet address (MAC) to be used by a net device * and set addr_assign_type so the state can be read by sysfs and be * used by userspace. */ static inline void eth_hw_addr_random(struct net_device *dev) { u8 addr[ETH_ALEN]; eth_random_addr(addr); __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; } /** * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr * @ha: pointer to hardware address * * Calculate CRC from a hardware address as basis for filter hashes. */ static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) { return ether_crc(ETH_ALEN, ha->addr); } /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination * @src: Pointer to a six-byte array Ethernet address source * * Please note: dst & src must both be aligned to u16. */ static inline void ether_addr_copy(u8 *dst, const u8 *src) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) *(u32 *)dst = *(const u32 *)src; *(u16 *)(dst + 4) = *(const u16 *)(src + 4); #else u16 *a = (u16 *)dst; const u16 *b = (const u16 *)src; a[0] = b[0]; a[1] = b[1]; a[2] = b[2]; #endif } /** * eth_hw_addr_set - Assign Ethernet address to a net_device * @dev: pointer to net_device structure * @addr: address to assign * * Assign given address to the net_device, addr_assign_type is not changed. */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, ETH_ALEN); } /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to * @src: pointer to net_device to copy dev_addr from * * Copy the Ethernet address from one net_device to another along with * the address attributes (addr_assign_type). */ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; eth_hw_addr_set(dst, src->dev_addr); } /** * ether_addr_equal - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: addr1 & addr2 must both be aligned to u16. */ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); return fold == 0; #else const u16 *a = (const u16 *)addr1; const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0; #endif } /** * ether_addr_equal_64bits - Compare two Ethernet addresses * @addr1: Pointer to an array of 8 bytes * @addr2: Pointer to an other array of 8 bytes * * Compare two Ethernet addresses, returns true if equal, false otherwise. * * The function doesn't need any conditional branches and possibly uses * word memory accesses on CPU allowing cheap unaligned memory reads. * arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 } * * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); #ifdef __BIG_ENDIAN return (fold >> 16) == 0; #else return (fold << 16) == 0; #endif #else return ether_addr_equal(addr1, addr2); #endif } /** * ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: Use only when any Ethernet address may not be u16 aligned. */ static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ether_addr_equal(addr1, addr2); #else return memcmp(addr1, addr2, ETH_ALEN) == 0; #endif } /** * ether_addr_equal_masked - Compare two Ethernet addresses with a mask * @addr1: Pointer to a six-byte array containing the 1st Ethernet address * @addr2: Pointer to a six-byte array containing the 2nd Ethernet address * @mask: Pointer to a six-byte array containing the Ethernet address bitmask * * Compare two Ethernet addresses with a mask, returns true if for every bit * set in the bitmask the equivalent bits in the ethernet addresses are equal. * Using a mask with all bits set is a slower ether_addr_equal. */ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, const u8 *mask) { int i; for (i = 0; i < ETH_ALEN; i++) { if ((addr1[i] ^ addr2[i]) & mask[i]) return false; } return true; } static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) { return ether_addr_is_ipv4_mcast(addr) || ether_addr_is_ipv6_mcast(addr); } /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { u64 u = 0; int i; for (i = 0; i < ETH_ALEN; i++) u = u << 8 | addr[i]; return u; } /** * u64_to_ether_addr - Convert a u64 to an Ethernet address. * @u: u64 to convert to an Ethernet MAC address * @addr: Pointer to a six-byte array to contain the Ethernet address */ static inline void u64_to_ether_addr(u64 u, u8 *addr) { int i; for (i = ETH_ALEN - 1; i >= 0; i--) { addr[i] = u & 0xff; u = u >> 8; } } /** * eth_addr_dec - Decrement the given MAC address * * @addr: Pointer to a six-byte array containing Ethernet address to decrement */ static inline void eth_addr_dec(u8 *addr) { u64 u = ether_addr_to_u64(addr); u--; u64_to_ether_addr(u, addr); } /** * eth_addr_inc() - Increment the given MAC address. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_inc(u8 *addr) { u64 u = ether_addr_to_u64(addr); u++; u64_to_ether_addr(u, addr); } /** * eth_addr_add() - Add (or subtract) an offset to/from the given MAC address. * * @offset: Offset to add. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_add(u8 *addr, long offset) { u64 u = ether_addr_to_u64(addr); u += offset; u64_to_ether_addr(u, addr); } /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address * * Compare passed address with all addresses of the device. Return true if the * address if one of the device addresses. * * Note that this function calls ether_addr_equal_64bits() so take care of * the right padding. */ static inline bool is_etherdev_addr(const struct net_device *dev, const u8 addr[6 + 2]) { struct netdev_hw_addr *ha; bool res = false; rcu_read_lock(); for_each_dev_addr(dev, ha) { res = ether_addr_equal_64bits(addr, ha->addr); if (res) break; } rcu_read_unlock(); return res; } #endif /* __KERNEL__ */ /** * compare_ether_header - Compare two Ethernet headers * @a: Pointer to Ethernet header * @b: Pointer to Ethernet header * * Compare two Ethernet headers, returns 0 if equal. * This assumes that the network header (i.e., IP header) is 4-byte * aligned OR the platform can handle unaligned access. This is the * case for all packets coming into netif_receive_skb or similar * entry points. */ static inline unsigned long compare_ether_header(const void *a, const void *b) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 unsigned long fold; /* * We want to compare 14 bytes: * [a0 ... a13] ^ [b0 ... b13] * Use two long XOR, ORed together, with an overlap of two bytes. * [a0 a1 a2 a3 a4 a5 a6 a7 ] ^ [b0 b1 b2 b3 b4 b5 b6 b7 ] | * [a6 a7 a8 a9 a10 a11 a12 a13] ^ [b6 b7 b8 b9 b10 b11 b12 b13] * This means the [a6 a7] ^ [b6 b7] part is done two times. */ fold = *(unsigned long *)a ^ *(unsigned long *)b; fold |= *(unsigned long *)(a + 6) ^ *(unsigned long *)(b + 6); return fold; #else u32 *a32 = (u32 *)((u8 *)a + 2); u32 *b32 = (u32 *)((u8 *)b + 2); return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) | (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]); #endif } /** * eth_hw_addr_gen - Generate and assign Ethernet address to a port * @dev: pointer to port's net_device structure * @base_addr: base Ethernet address * @id: offset to add to the base address * * Generate a MAC address using a base address and an offset and assign it * to a net_device. Commonly used by switch drivers which need to compute * addresses for all their ports. addr_assign_type is not changed. */ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, unsigned int id) { u64 u = ether_addr_to_u64(base_addr); u8 addr[ETH_ALEN]; u += id; u64_to_ether_addr(u, addr); eth_hw_addr_set(dev, addr); } /** * eth_skb_pkt_type - Assign packet type if destination address does not match * @skb: Assigned a packet type if address does not match @dev address * @dev: Network device used to compare packet address against * * If the destination MAC address of the packet does not match the network * device address, assign an appropriate packet type. */ static inline void eth_skb_pkt_type(struct sk_buff *skb, const struct net_device *dev) { const struct ethhdr *eth = eth_hdr(skb); if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; } else { skb->pkt_type = PACKET_OTHERHOST; } } } static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) { struct ethhdr *eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); return eth; } /** * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function * takes short frames and pads them with zeros up to the 60 byte limit. */ static inline int eth_skb_pad(struct sk_buff *skb) { return skb_put_padto(skb, ETH_ZLEN); } #endif /* _LINUX_ETHERDEVICE_H */ |
| 1 65 211 229 228 163 230 231 1 228 228 88 88 88 88 77 10 88 88 88 258 88 88 88 21 21 88 88 88 88 69 88 87 88 88 88 77 10 88 88 88 88 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_attr_sf.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_bmap.h" #include "xfs_bmap_btree.h" #include "xfs_attr.h" #include "xfs_attr_leaf.h" #include "xfs_attr_remote.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_trace.h" #include "xfs_attr_item.h" #include "xfs_xattr.h" #include "xfs_parent.h" struct kmem_cache *xfs_attr_intent_cache; /* * xfs_attr.c * * Provide the external interfaces to manage attribute lists. */ /*======================================================================== * Function prototypes for the kernel. *========================================================================*/ /* * Internal routines when attribute list fits inside the inode. */ STATIC int xfs_attr_shortform_addname(xfs_da_args_t *args); /* * Internal routines when attribute list is one block. */ STATIC int xfs_attr_leaf_get(xfs_da_args_t *args); STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args); STATIC int xfs_attr_leaf_hasname(struct xfs_da_args *args, struct xfs_buf **bp); /* * Internal routines when attribute list is more than one block. */ STATIC int xfs_attr_node_get(xfs_da_args_t *args); STATIC void xfs_attr_restore_rmt_blk(struct xfs_da_args *args); static int xfs_attr_node_try_addname(struct xfs_attr_intent *attr); STATIC int xfs_attr_node_addname_find_attr(struct xfs_attr_intent *attr); STATIC int xfs_attr_node_remove_attr(struct xfs_attr_intent *attr); STATIC int xfs_attr_node_lookup(struct xfs_da_args *args, struct xfs_da_state *state); int xfs_inode_hasattr( struct xfs_inode *ip) { if (!xfs_inode_has_attr_fork(ip)) return 0; if (ip->i_af.if_format == XFS_DINODE_FMT_EXTENTS && ip->i_af.if_nextents == 0) return 0; return 1; } /* * Returns true if the there is exactly only block in the attr fork, in which * case the attribute fork consists of a single leaf block entry. */ bool xfs_attr_is_leaf( struct xfs_inode *ip) { struct xfs_ifork *ifp = &ip->i_af; struct xfs_iext_cursor icur; struct xfs_bmbt_irec imap; ASSERT(!xfs_need_iread_extents(ifp)); if (ifp->if_nextents != 1 || ifp->if_format != XFS_DINODE_FMT_EXTENTS) return false; xfs_iext_first(ifp, &icur); xfs_iext_get_extent(ifp, &icur, &imap); return imap.br_startoff == 0 && imap.br_blockcount == 1; } /* * XXX (dchinner): name path state saving and refilling is an optimisation to * avoid needing to look up name entries after rolling transactions removing * remote xattr blocks between the name entry lookup and name entry removal. * This optimisation got sidelined when combining the set and remove state * machines, but the code has been left in place because it is worthwhile to * restore the optimisation once the combined state machine paths have settled. * * This comment is a public service announcement to remind Future Dave that he * still needs to restore this code to working order. */ #if 0 /* * Fill in the disk block numbers in the state structure for the buffers * that are attached to the state structure. * This is done so that we can quickly reattach ourselves to those buffers * after some set of transaction commits have released these buffers. */ static int xfs_attr_fillstate(xfs_da_state_t *state) { xfs_da_state_path_t *path; xfs_da_state_blk_t *blk; int level; trace_xfs_attr_fillstate(state->args); /* * Roll down the "path" in the state structure, storing the on-disk * block number for those buffers in the "path". */ path = &state->path; ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH)); for (blk = path->blk, level = 0; level < path->active; blk++, level++) { if (blk->bp) { blk->disk_blkno = xfs_buf_daddr(blk->bp); blk->bp = NULL; } else { blk->disk_blkno = 0; } } /* * Roll down the "altpath" in the state structure, storing the on-disk * block number for those buffers in the "altpath". */ path = &state->altpath; ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH)); for (blk = path->blk, level = 0; level < path->active; blk++, level++) { if (blk->bp) { blk->disk_blkno = xfs_buf_daddr(blk->bp); blk->bp = NULL; } else { blk->disk_blkno = 0; } } return 0; } /* * Reattach the buffers to the state structure based on the disk block * numbers stored in the state structure. * This is done after some set of transaction commits have released those * buffers from our grip. */ static int xfs_attr_refillstate(xfs_da_state_t *state) { xfs_da_state_path_t *path; xfs_da_state_blk_t *blk; int level, error; trace_xfs_attr_refillstate(state->args); /* * Roll down the "path" in the state structure, storing the on-disk * block number for those buffers in the "path". */ path = &state->path; ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH)); for (blk = path->blk, level = 0; level < path->active; blk++, level++) { if (blk->disk_blkno) { error = xfs_da3_node_read_mapped(state->args->trans, state->args->dp, blk->disk_blkno, &blk->bp, XFS_ATTR_FORK); if (error) return error; } else { blk->bp = NULL; } } /* * Roll down the "altpath" in the state structure, storing the on-disk * block number for those buffers in the "altpath". */ path = &state->altpath; ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH)); for (blk = path->blk, level = 0; level < path->active; blk++, level++) { if (blk->disk_blkno) { error = xfs_da3_node_read_mapped(state->args->trans, state->args->dp, blk->disk_blkno, &blk->bp, XFS_ATTR_FORK); if (error) return error; } else { blk->bp = NULL; } } return 0; } #else static int xfs_attr_fillstate(xfs_da_state_t *state) { return 0; } #endif /*======================================================================== * Overall external interface routines. *========================================================================*/ /* * Retrieve an extended attribute and its value. Must have ilock. * Returns 0 on successful retrieval, otherwise an error. */ int xfs_attr_get_ilocked( struct xfs_da_args *args) { int error; xfs_assert_ilocked(args->dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); if (!xfs_inode_hasattr(args->dp)) return -ENOATTR; /* * The incore attr fork iext tree must be loaded for xfs_attr_is_leaf * to work correctly. */ error = xfs_iread_extents(args->trans, args->dp, XFS_ATTR_FORK); if (error) return error; if (args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) return xfs_attr_shortform_getvalue(args); if (xfs_attr_is_leaf(args->dp)) return xfs_attr_leaf_get(args); return xfs_attr_node_get(args); } /* * Retrieve an extended attribute by name, and its value if requested. * * If args->valuelen is zero, then the caller does not want the value, just an * indication whether the attribute exists and the size of the value if it * exists. The size is returned in args.valuelen. * * If args->value is NULL but args->valuelen is non-zero, allocate the buffer * for the value after existence of the attribute has been determined. The * caller always has to free args->value if it is set, no matter if this * function was successful or not. * * If the attribute is found, but exceeds the size limit set by the caller in * args->valuelen, return -ERANGE with the size of the attribute that was found * in args->valuelen. */ int xfs_attr_get( struct xfs_da_args *args) { uint lock_mode; int error; XFS_STATS_INC(args->dp->i_mount, xs_attr_get); if (xfs_is_shutdown(args->dp->i_mount)) return -EIO; if (!args->owner) args->owner = args->dp->i_ino; args->geo = args->dp->i_mount->m_attr_geo; args->whichfork = XFS_ATTR_FORK; xfs_attr_sethash(args); /* Entirely possible to look up a name which doesn't exist */ args->op_flags = XFS_DA_OP_OKNOENT; lock_mode = xfs_ilock_attr_map_shared(args->dp); error = xfs_attr_get_ilocked(args); xfs_iunlock(args->dp, lock_mode); return error; } /* * Calculate how many blocks we need for the new attribute, */ int xfs_attr_calc_size( struct xfs_da_args *args, int *local) { struct xfs_mount *mp = args->dp->i_mount; int size; int nblks; /* * Determine space new attribute will use, and if it would be * "local" or "remote" (note: local != inline). */ size = xfs_attr_leaf_newentsize(args, local); nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK); if (*local) { if (size > (args->geo->blksize / 2)) { /* Double split possible */ nblks *= 2; } } else { /* * Out of line attribute, cannot double split, but * make room for the attribute value itself. */ uint dblocks = xfs_attr3_rmt_blocks(mp, args->valuelen); nblks += dblocks; nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK); } return nblks; } /* Initialize transaction reservation for an xattr set/replace/upsert */ inline struct xfs_trans_res xfs_attr_set_resv( const struct xfs_da_args *args) { struct xfs_mount *mp = args->dp->i_mount; struct xfs_trans_res ret = { .tr_logres = M_RES(mp)->tr_attrsetm.tr_logres + M_RES(mp)->tr_attrsetrt.tr_logres * args->total, .tr_logcount = XFS_ATTRSET_LOG_COUNT, .tr_logflags = XFS_TRANS_PERM_LOG_RES, }; return ret; } /* * Add an attr to a shortform fork. If there is no space, * xfs_attr_shortform_addname() will convert to leaf format and return -ENOSPC. * to use. */ STATIC int xfs_attr_try_sf_addname( struct xfs_inode *dp, struct xfs_da_args *args) { int error; /* * Build initial attribute list (if required). */ if (dp->i_af.if_format == XFS_DINODE_FMT_EXTENTS) xfs_attr_shortform_create(args); error = xfs_attr_shortform_addname(args); if (error == -ENOSPC) return error; /* * Commit the shortform mods, and we're done. * NOTE: this is also the error path (EEXIST, etc). */ if (!error) xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); if (xfs_has_wsync(dp->i_mount)) xfs_trans_set_sync(args->trans); return error; } static int xfs_attr_sf_addname( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; struct xfs_inode *dp = args->dp; int error = 0; error = xfs_attr_try_sf_addname(dp, args); if (error != -ENOSPC) { ASSERT(!error || error == -EEXIST); attr->xattri_dela_state = XFS_DAS_DONE; goto out; } /* * It won't fit in the shortform, transform to a leaf block. GROT: * another possible req'mt for a double-split btree op. */ error = xfs_attr_shortform_to_leaf(args); if (error) return error; attr->xattri_dela_state = XFS_DAS_LEAF_ADD; out: trace_xfs_attr_sf_addname_return(attr->xattri_dela_state, args->dp); return error; } /* Compute the hash value for a user/root/secure extended attribute */ xfs_dahash_t xfs_attr_hashname( const uint8_t *name, int namelen) { return xfs_da_hashname(name, namelen); } /* Compute the hash value for any extended attribute from any namespace. */ xfs_dahash_t xfs_attr_hashval( struct xfs_mount *mp, unsigned int attr_flags, const uint8_t *name, int namelen, const void *value, int valuelen) { ASSERT(xfs_attr_check_namespace(attr_flags)); if (attr_flags & XFS_ATTR_PARENT) return xfs_parent_hashattr(mp, name, namelen, value, valuelen); return xfs_attr_hashname(name, namelen); } /* Save the current remote block info and clear the current pointers. */ static void xfs_attr_save_rmt_blk( struct xfs_da_args *args) { args->blkno2 = args->blkno; args->index2 = args->index; args->rmtblkno2 = args->rmtblkno; args->rmtblkcnt2 = args->rmtblkcnt; args->rmtvaluelen2 = args->rmtvaluelen; args->rmtblkno = 0; args->rmtblkcnt = 0; args->rmtvaluelen = 0; } /* Set stored info about a remote block */ static void xfs_attr_restore_rmt_blk( struct xfs_da_args *args) { args->blkno = args->blkno2; args->index = args->index2; args->rmtblkno = args->rmtblkno2; args->rmtblkcnt = args->rmtblkcnt2; args->rmtvaluelen = args->rmtvaluelen2; } /* * PPTR_REPLACE operations require the caller to set the old and new names and * values explicitly. Update the canonical fields to the new name and value * here now that the removal phase has finished. */ static void xfs_attr_update_pptr_replace_args( struct xfs_da_args *args) { ASSERT(args->new_namelen > 0); args->name = args->new_name; args->namelen = args->new_namelen; args->value = args->new_value; args->valuelen = args->new_valuelen; xfs_attr_sethash(args); } /* * Handle the state change on completion of a multi-state attr operation. * * If the XFS_DA_OP_REPLACE flag is set, this means the operation was the first * modification in a attr replace operation and we still have to do the second * state, indicated by @replace_state. * * We consume the XFS_DA_OP_REPLACE flag so that when we are called again on * completion of the second half of the attr replace operation we correctly * signal that it is done. */ static enum xfs_delattr_state xfs_attr_complete_op( struct xfs_attr_intent *attr, enum xfs_delattr_state replace_state) { struct xfs_da_args *args = attr->xattri_da_args; if (!(args->op_flags & XFS_DA_OP_REPLACE)) replace_state = XFS_DAS_DONE; else if (xfs_attr_intent_op(attr) == XFS_ATTRI_OP_FLAGS_PPTR_REPLACE) xfs_attr_update_pptr_replace_args(args); args->op_flags &= ~XFS_DA_OP_REPLACE; args->attr_filter &= ~XFS_ATTR_INCOMPLETE; return replace_state; } /* * Try to add an attribute to an inode in leaf form. */ static int xfs_attr_leaf_addname( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; struct xfs_buf *bp; int error; ASSERT(xfs_attr_is_leaf(args->dp)); error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp); if (error) return error; /* * Look up the xattr name to set the insertion point for the new xattr. */ error = xfs_attr3_leaf_lookup_int(bp, args); switch (error) { case -ENOATTR: if (args->op_flags & XFS_DA_OP_REPLACE) goto out_brelse; break; case -EEXIST: if (!(args->op_flags & XFS_DA_OP_REPLACE)) goto out_brelse; trace_xfs_attr_leaf_replace(args); /* * Save the existing remote attr state so that the current * values reflect the state of the new attribute we are about to * add, not the attribute we just found and will remove later. */ xfs_attr_save_rmt_blk(args); break; case 0: break; default: goto out_brelse; } /* * We need to commit and roll if we need to allocate remote xattr blocks * or perform more xattr manipulations. Otherwise there is nothing more * to do and we can return success. */ if (!xfs_attr3_leaf_add(bp, args)) { error = xfs_attr3_leaf_to_node(args); if (error) return error; attr->xattri_dela_state = XFS_DAS_NODE_ADD; } else if (args->rmtblkno) { attr->xattri_dela_state = XFS_DAS_LEAF_SET_RMT; } else { attr->xattri_dela_state = xfs_attr_complete_op(attr, XFS_DAS_LEAF_REPLACE); } trace_xfs_attr_leaf_addname_return(attr->xattri_dela_state, args->dp); return 0; out_brelse: xfs_trans_brelse(args->trans, bp); return error; } /* * Add an entry to a node format attr tree. * * Note that we might still have a leaf here - xfs_attr_is_leaf() cannot tell * the difference between leaf + remote attr blocks and a node format tree, * so we may still end up having to convert from leaf to node format here. */ static int xfs_attr_node_addname( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; int error; error = xfs_attr_node_addname_find_attr(attr); if (error) return error; error = xfs_attr_node_try_addname(attr); if (error == 1) { error = xfs_attr3_leaf_to_node(args); if (error) return error; /* * No state change, we really are in node form now * but we need the transaction rolled to continue. */ goto out; } if (error) return error; if (args->rmtblkno) attr->xattri_dela_state = XFS_DAS_NODE_SET_RMT; else attr->xattri_dela_state = xfs_attr_complete_op(attr, XFS_DAS_NODE_REPLACE); out: trace_xfs_attr_node_addname_return(attr->xattri_dela_state, args->dp); return error; } static int xfs_attr_rmtval_alloc( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; int error = 0; /* * If there was an out-of-line value, allocate the blocks we * identified for its storage and copy the value. This is done * after we create the attribute so that we don't overflow the * maximum size of a transaction and/or hit a deadlock. */ if (attr->xattri_blkcnt > 0) { error = xfs_attr_rmtval_set_blk(attr); if (error) return error; /* Roll the transaction only if there is more to allocate. */ if (attr->xattri_blkcnt > 0) goto out; } error = xfs_attr_rmtval_set_value(args); if (error) return error; attr->xattri_dela_state = xfs_attr_complete_op(attr, ++attr->xattri_dela_state); /* * If we are not doing a rename, we've finished the operation but still * have to clear the incomplete flag protecting the new attr from * exposing partially initialised state if we crash during creation. */ if (attr->xattri_dela_state == XFS_DAS_DONE) error = xfs_attr3_leaf_clearflag(args); out: trace_xfs_attr_rmtval_alloc(attr->xattri_dela_state, args->dp); return error; } /* * Mark an attribute entry INCOMPLETE and save pointers to the relevant buffers * for later deletion of the entry. */ static int xfs_attr_leaf_mark_incomplete( struct xfs_da_args *args, struct xfs_da_state *state) { int error; /* * Fill in disk block numbers in the state structure * so that we can get the buffers back after we commit * several transactions in the following calls. */ error = xfs_attr_fillstate(state); if (error) return error; /* * Mark the attribute as INCOMPLETE */ return xfs_attr3_leaf_setflag(args); } /* Ensure the da state of an xattr deferred work item is ready to go. */ static inline void xfs_attr_item_init_da_state( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; if (!attr->xattri_da_state) attr->xattri_da_state = xfs_da_state_alloc(args); else xfs_da_state_reset(attr->xattri_da_state, args); } /* * Initial setup for xfs_attr_node_removename. Make sure the attr is there and * the blocks are valid. Attr keys with remote blocks will be marked * incomplete. */ static int xfs_attr_node_removename_setup( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; struct xfs_da_state *state; int error; xfs_attr_item_init_da_state(attr); error = xfs_attr_node_lookup(args, attr->xattri_da_state); if (error != -EEXIST) goto out; error = 0; state = attr->xattri_da_state; ASSERT(state->path.blk[state->path.active - 1].bp != NULL); ASSERT(state->path.blk[state->path.active - 1].magic == XFS_ATTR_LEAF_MAGIC); error = xfs_attr_leaf_mark_incomplete(args, state); if (error) goto out; if (args->rmtblkno > 0) error = xfs_attr_rmtval_invalidate(args); out: if (error) { xfs_da_state_free(attr->xattri_da_state); attr->xattri_da_state = NULL; } return error; } /* * Remove the original attr we have just replaced. This is dependent on the * original lookup and insert placing the old attr in args->blkno/args->index * and the new attr in args->blkno2/args->index2. */ static int xfs_attr_leaf_remove_attr( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; struct xfs_inode *dp = args->dp; struct xfs_buf *bp = NULL; int forkoff; int error; error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, args->blkno, &bp); if (error) return error; xfs_attr3_leaf_remove(bp, args); forkoff = xfs_attr_shortform_allfit(bp, dp); if (forkoff) error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ return error; } /* * Shrink an attribute from leaf to shortform. Used by the node format remove * path when the node format collapses to a single block and so we have to check * if it can be collapsed further. */ static int xfs_attr_leaf_shrink( struct xfs_da_args *args) { struct xfs_inode *dp = args->dp; struct xfs_buf *bp; int forkoff; int error; if (!xfs_attr_is_leaf(dp)) return 0; error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp); if (error) return error; forkoff = xfs_attr_shortform_allfit(bp, dp); if (forkoff) { error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ } else { xfs_trans_brelse(args->trans, bp); } return error; } /* * Run the attribute operation specified in @attr. * * This routine is meant to function as a delayed operation and will set the * state to XFS_DAS_DONE when the operation is complete. Calling functions will * need to handle this, and recall the function until either an error or * XFS_DAS_DONE is detected. */ int xfs_attr_set_iter( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; int error = 0; /* State machine switch */ next_state: switch (attr->xattri_dela_state) { case XFS_DAS_UNINIT: ASSERT(0); return -EFSCORRUPTED; case XFS_DAS_SF_ADD: return xfs_attr_sf_addname(attr); case XFS_DAS_LEAF_ADD: return xfs_attr_leaf_addname(attr); case XFS_DAS_NODE_ADD: return xfs_attr_node_addname(attr); case XFS_DAS_SF_REMOVE: error = xfs_attr_sf_removename(args); attr->xattri_dela_state = xfs_attr_complete_op(attr, xfs_attr_init_add_state(args)); break; case XFS_DAS_LEAF_REMOVE: error = xfs_attr_leaf_removename(args); attr->xattri_dela_state = xfs_attr_complete_op(attr, xfs_attr_init_add_state(args)); break; case XFS_DAS_NODE_REMOVE: error = xfs_attr_node_removename_setup(attr); if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY)) { attr->xattri_dela_state = xfs_attr_complete_op(attr, xfs_attr_init_add_state(args)); error = 0; break; } if (error) return error; attr->xattri_dela_state = XFS_DAS_NODE_REMOVE_RMT; if (args->rmtblkno == 0) attr->xattri_dela_state++; break; case XFS_DAS_LEAF_SET_RMT: case XFS_DAS_NODE_SET_RMT: error = xfs_attr_rmtval_find_space(attr); if (error) return error; attr->xattri_dela_state++; fallthrough; case XFS_DAS_LEAF_ALLOC_RMT: case XFS_DAS_NODE_ALLOC_RMT: error = xfs_attr_rmtval_alloc(attr); if (error) return error; if (attr->xattri_dela_state == XFS_DAS_DONE) break; goto next_state; case XFS_DAS_LEAF_REPLACE: case XFS_DAS_NODE_REPLACE: /* * We must "flip" the incomplete flags on the "new" and "old" * attribute/value pairs so that one disappears and one appears * atomically. */ error = xfs_attr3_leaf_flipflags(args); if (error) return error; /* * We must commit the flag value change now to make it atomic * and then we can start the next trans in series at REMOVE_OLD. */ attr->xattri_dela_state++; break; case XFS_DAS_LEAF_REMOVE_OLD: case XFS_DAS_NODE_REMOVE_OLD: /* * If we have a remote attr, start the process of removing it * by invalidating any cached buffers. * * If we don't have a remote attr, we skip the remote block * removal state altogether with a second state increment. */ xfs_attr_restore_rmt_blk(args); if (args->rmtblkno) { error = xfs_attr_rmtval_invalidate(args); if (error) return error; } else { attr->xattri_dela_state++; } attr->xattri_dela_state++; goto next_state; case XFS_DAS_LEAF_REMOVE_RMT: case XFS_DAS_NODE_REMOVE_RMT: error = xfs_attr_rmtval_remove(attr); if (error == -EAGAIN) { error = 0; break; } if (error) return error; /* * We've finished removing the remote attr blocks, so commit the * transaction and move on to removing the attr name from the * leaf/node block. Removing the attr might require a full * transaction reservation for btree block freeing, so we * can't do that in the same transaction where we removed the * remote attr blocks. */ attr->xattri_dela_state++; break; case XFS_DAS_LEAF_REMOVE_ATTR: error = xfs_attr_leaf_remove_attr(attr); attr->xattri_dela_state = xfs_attr_complete_op(attr, xfs_attr_init_add_state(args)); break; case XFS_DAS_NODE_REMOVE_ATTR: error = xfs_attr_node_remove_attr(attr); if (!error) error = xfs_attr_leaf_shrink(args); attr->xattri_dela_state = xfs_attr_complete_op(attr, xfs_attr_init_add_state(args)); break; default: ASSERT(0); break; } trace_xfs_attr_set_iter_return(attr->xattri_dela_state, args->dp); return error; } /* * Return EEXIST if attr is found, or ENOATTR if not */ static int xfs_attr_lookup( struct xfs_da_args *args) { struct xfs_inode *dp = args->dp; struct xfs_buf *bp = NULL; struct xfs_da_state *state; int error; if (!xfs_inode_hasattr(dp)) return -ENOATTR; if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) { if (xfs_attr_sf_findname(args)) return -EEXIST; return -ENOATTR; } /* Prerequisite for xfs_attr_is_leaf */ error = xfs_iread_extents(args->trans, args->dp, XFS_ATTR_FORK); if (error) return error; if (xfs_attr_is_leaf(dp)) { error = xfs_attr_leaf_hasname(args, &bp); if (bp) xfs_trans_brelse(args->trans, bp); return error; } state = xfs_da_state_alloc(args); error = xfs_attr_node_lookup(args, state); xfs_da_state_free(state); return error; } int xfs_attr_add_fork( struct xfs_inode *ip, /* incore inode pointer */ int size, /* space new attribute needs */ int rsvd) /* xact may use reserved blks */ { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; /* transaction pointer */ unsigned int blks; /* space reservation */ int error; /* error return value */ if (!xfs_is_metadir_inode(ip)) ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); blks = XFS_ADDAFORK_SPACE_RES(mp); error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0, rsvd, &tp); if (error) return error; if (xfs_inode_has_attr_fork(ip)) goto trans_cancel; error = xfs_bmap_add_attrfork(tp, ip, size, rsvd); if (error) goto trans_cancel; error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; trans_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } /* * Make a change to the xattr structure. * * The caller must have initialized @args, attached dquots, and must not hold * any ILOCKs. Reserved data blocks may be used if @rsvd is set. * * Returns -EEXIST for XFS_ATTRUPDATE_CREATE if the name already exists. * Returns -ENOATTR for XFS_ATTRUPDATE_REMOVE if the name does not exist. * Returns 0 on success, or a negative errno if something else went wrong. */ int xfs_attr_set( struct xfs_da_args *args, enum xfs_attr_update op, bool rsvd) { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_trans_res tres; int error, local; int rmt_blks = 0; unsigned int total = 0; ASSERT(!args->trans); switch (op) { case XFS_ATTRUPDATE_UPSERT: case XFS_ATTRUPDATE_CREATE: case XFS_ATTRUPDATE_REPLACE: XFS_STATS_INC(mp, xs_attr_set); args->total = xfs_attr_calc_size(args, &local); /* * If the inode doesn't have an attribute fork, add one. * (inode must not be locked when we call this routine) */ if (xfs_inode_has_attr_fork(dp) == 0) { int sf_size = sizeof(struct xfs_attr_sf_hdr) + xfs_attr_sf_entsize_byname(args->namelen, args->valuelen); error = xfs_attr_add_fork(dp, sf_size, rsvd); if (error) return error; } if (!local) rmt_blks = xfs_attr3_rmt_blocks(mp, args->valuelen); tres = xfs_attr_set_resv(args); total = args->total; break; case XFS_ATTRUPDATE_REMOVE: XFS_STATS_INC(mp, xs_attr_remove); rmt_blks = xfs_attr3_max_rmt_blocks(mp); tres = M_RES(mp)->tr_attrrm; total = XFS_ATTRRM_SPACE_RES(mp); break; } /* * Root fork attributes can use reserved data blocks for this * operation if necessary */ error = xfs_trans_alloc_inode(dp, &tres, total, 0, rsvd, &args->trans); if (error) return error; if (op != XFS_ATTRUPDATE_REMOVE || xfs_inode_hasattr(dp)) { error = xfs_iext_count_extend(args->trans, dp, XFS_ATTR_FORK, XFS_IEXT_ATTR_MANIP_CNT(rmt_blks)); if (error) goto out_trans_cancel; } error = xfs_attr_lookup(args); switch (error) { case -EEXIST: if (op == XFS_ATTRUPDATE_REMOVE) { /* if no value, we are performing a remove operation */ xfs_attr_defer_add(args, XFS_ATTR_DEFER_REMOVE); break; } /* Pure create fails if the attr already exists */ if (op == XFS_ATTRUPDATE_CREATE) goto out_trans_cancel; xfs_attr_defer_add(args, XFS_ATTR_DEFER_REPLACE); break; case -ENOATTR: /* Can't remove what isn't there. */ if (op == XFS_ATTRUPDATE_REMOVE) goto out_trans_cancel; /* Pure replace fails if no existing attr to replace. */ if (op == XFS_ATTRUPDATE_REPLACE) goto out_trans_cancel; xfs_attr_defer_add(args, XFS_ATTR_DEFER_SET); break; default: goto out_trans_cancel; } /* * If this is a synchronous mount, make sure that the * transaction goes to disk before returning to the user. */ if (xfs_has_wsync(mp)) xfs_trans_set_sync(args->trans); xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); /* * Commit the last in the sequence of transactions. */ xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE); error = xfs_trans_commit(args->trans); out_unlock: xfs_iunlock(dp, XFS_ILOCK_EXCL); args->trans = NULL; return error; out_trans_cancel: if (args->trans) xfs_trans_cancel(args->trans); goto out_unlock; } /*======================================================================== * External routines when attribute list is inside the inode *========================================================================*/ int xfs_attr_sf_totsize(struct xfs_inode *dp) { struct xfs_attr_sf_hdr *sf = dp->i_af.if_data; return be16_to_cpu(sf->totsize); } /* * Add a name to the shortform attribute list structure * This is the external routine. */ static int xfs_attr_shortform_addname( struct xfs_da_args *args) { int newsize, forkoff; trace_xfs_attr_sf_addname(args); if (xfs_attr_sf_findname(args)) { int error; ASSERT(args->op_flags & XFS_DA_OP_REPLACE); error = xfs_attr_sf_removename(args); if (error) return error; /* * Since we have removed the old attr, clear XFS_DA_OP_REPLACE * so that the new attr doesn't fit in shortform format, the * leaf format add routine won't trip over the attr not being * around. */ args->op_flags &= ~XFS_DA_OP_REPLACE; } else { ASSERT(!(args->op_flags & XFS_DA_OP_REPLACE)); } if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX || args->valuelen >= XFS_ATTR_SF_ENTSIZE_MAX) return -ENOSPC; newsize = xfs_attr_sf_totsize(args->dp); newsize += xfs_attr_sf_entsize_byname(args->namelen, args->valuelen); forkoff = xfs_attr_shortform_bytesfit(args->dp, newsize); if (!forkoff) return -ENOSPC; xfs_attr_shortform_add(args, forkoff); return 0; } /*======================================================================== * External routines when attribute list is one block *========================================================================*/ /* * Return EEXIST if attr is found, or ENOATTR if not */ STATIC int xfs_attr_leaf_hasname( struct xfs_da_args *args, struct xfs_buf **bp) { int error = 0; error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, bp); if (error) return error; error = xfs_attr3_leaf_lookup_int(*bp, args); if (error != -ENOATTR && error != -EEXIST) xfs_trans_brelse(args->trans, *bp); return error; } /* * Remove a name from the leaf attribute list structure * * This leaf block cannot have a "remote" value, we only call this routine * if bmap_one_block() says there is only one block (ie: no remote blks). */ STATIC int xfs_attr_leaf_removename( struct xfs_da_args *args) { struct xfs_inode *dp; struct xfs_buf *bp; int error, forkoff; trace_xfs_attr_leaf_removename(args); /* * Remove the attribute. */ dp = args->dp; error = xfs_attr_leaf_hasname(args, &bp); if (error == -ENOATTR) { xfs_trans_brelse(args->trans, bp); if (args->op_flags & XFS_DA_OP_RECOVERY) return 0; return error; } else if (error != -EEXIST) return error; xfs_attr3_leaf_remove(bp, args); /* * If the result is small enough, shrink it all into the inode. */ forkoff = xfs_attr_shortform_allfit(bp, dp); if (forkoff) return xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ return 0; } /* * Look up a name in a leaf attribute list structure. * * This leaf block cannot have a "remote" value, we only call this routine * if bmap_one_block() says there is only one block (ie: no remote blks). * * Returns 0 on successful retrieval, otherwise an error. */ STATIC int xfs_attr_leaf_get(xfs_da_args_t *args) { struct xfs_buf *bp; int error; trace_xfs_attr_leaf_get(args); error = xfs_attr_leaf_hasname(args, &bp); if (error == -ENOATTR) { xfs_trans_brelse(args->trans, bp); return error; } else if (error != -EEXIST) return error; error = xfs_attr3_leaf_getvalue(bp, args); xfs_trans_brelse(args->trans, bp); return error; } /* Return EEXIST if attr is found, or ENOATTR if not. */ STATIC int xfs_attr_node_lookup( struct xfs_da_args *args, struct xfs_da_state *state) { int retval, error; /* * Search to see if name exists, and get back a pointer to it. */ error = xfs_da3_node_lookup_int(state, &retval); if (error) return error; return retval; } /*======================================================================== * External routines when attribute list size > geo->blksize *========================================================================*/ STATIC int xfs_attr_node_addname_find_attr( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; int error; /* * Search to see if name already exists, and get back a pointer * to where it should go. */ xfs_attr_item_init_da_state(attr); error = xfs_attr_node_lookup(args, attr->xattri_da_state); switch (error) { case -ENOATTR: if (args->op_flags & XFS_DA_OP_REPLACE) goto error; break; case -EEXIST: if (!(args->op_flags & XFS_DA_OP_REPLACE)) goto error; trace_xfs_attr_node_replace(args); /* * Save the existing remote attr state so that the current * values reflect the state of the new attribute we are about to * add, not the attribute we just found and will remove later. */ xfs_attr_save_rmt_blk(args); break; case 0: break; default: goto error; } return 0; error: if (attr->xattri_da_state) { xfs_da_state_free(attr->xattri_da_state); attr->xattri_da_state = NULL; } return error; } /* * Add a name to a Btree-format attribute list. * * This will involve walking down the Btree, and may involve splitting leaf * nodes and even splitting intermediate nodes up to and including the root * node (a special case of an intermediate node). * * If the tree was still in single leaf format and needs to converted to * real node format return 1 and let the caller handle that. */ static int xfs_attr_node_try_addname( struct xfs_attr_intent *attr) { struct xfs_da_state *state = attr->xattri_da_state; struct xfs_da_state_blk *blk; int error = 0; trace_xfs_attr_node_addname(state->args); blk = &state->path.blk[state->path.active-1]; ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC); if (!xfs_attr3_leaf_add(blk->bp, state->args)) { if (state->path.active == 1) { /* * Its really a single leaf node, but it had * out-of-line values so it looked like it *might* * have been a b-tree. Let the caller deal with this. */ error = 1; goto out; } /* * Split as many Btree elements as required. * This code tracks the new and old attr's location * in the index/blkno/rmtblkno/rmtblkcnt fields and * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields. */ error = xfs_da3_split(state); if (error) goto out; } else { /* * Addition succeeded, update Btree hashvals. */ xfs_da3_fixhashpath(state, &state->path); } out: xfs_da_state_free(state); attr->xattri_da_state = NULL; return error; } static int xfs_attr_node_removename( struct xfs_da_args *args, struct xfs_da_state *state) { struct xfs_da_state_blk *blk; int retval; /* * Remove the name and update the hashvals in the tree. */ blk = &state->path.blk[state->path.active-1]; ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC); retval = xfs_attr3_leaf_remove(blk->bp, args); xfs_da3_fixhashpath(state, &state->path); return retval; } static int xfs_attr_node_remove_attr( struct xfs_attr_intent *attr) { struct xfs_da_args *args = attr->xattri_da_args; struct xfs_da_state *state = xfs_da_state_alloc(args); int retval = 0; int error = 0; /* * The attr we are removing has already been marked incomplete, so * we need to set the filter appropriately to re-find the "old" * attribute entry after any split ops. */ args->attr_filter |= XFS_ATTR_INCOMPLETE; error = xfs_da3_node_lookup_int(state, &retval); if (error) goto out; error = xfs_attr_node_removename(args, state); /* * Check to see if the tree needs to be collapsed. */ if (retval && (state->path.active > 1)) { error = xfs_da3_join(state); if (error) goto out; } retval = error = 0; out: xfs_da_state_free(state); if (error) return error; return retval; } /* * Retrieve the attribute data from a node attribute list. * * This routine gets called for any attribute fork that has more than one * block, ie: both true Btree attr lists and for single-leaf-blocks with * "remote" values taking up more blocks. * * Returns 0 on successful retrieval, otherwise an error. */ STATIC int xfs_attr_node_get( struct xfs_da_args *args) { struct xfs_da_state *state; struct xfs_da_state_blk *blk; int i; int error; trace_xfs_attr_node_get(args); /* * Search to see if name exists, and get back a pointer to it. */ state = xfs_da_state_alloc(args); error = xfs_attr_node_lookup(args, state); if (error != -EEXIST) goto out_release; /* * Get the value, local or "remote" */ blk = &state->path.blk[state->path.active - 1]; error = xfs_attr3_leaf_getvalue(blk->bp, args); /* * If not in a transaction, we have to release all the buffers. */ out_release: for (i = 0; i < state->path.active; i++) { xfs_trans_brelse(args->trans, state->path.blk[i].bp); state->path.blk[i].bp = NULL; } xfs_da_state_free(state); return error; } /* Enforce that there is at most one namespace bit per attr. */ inline bool xfs_attr_check_namespace(unsigned int attr_flags) { return hweight32(attr_flags & XFS_ATTR_NSP_ONDISK_MASK) < 2; } /* Returns true if the attribute entry name is valid. */ bool xfs_attr_namecheck( unsigned int attr_flags, const void *name, size_t length) { /* Only one namespace bit allowed. */ if (!xfs_attr_check_namespace(attr_flags)) return false; /* * MAXNAMELEN includes the trailing null, but (name/length) leave it * out, so use >= for the length check. */ if (length >= MAXNAMELEN) return false; /* Parent pointers have their own validation. */ if (attr_flags & XFS_ATTR_PARENT) return xfs_parent_namecheck(attr_flags, name, length); /* There shouldn't be any nulls here */ return !memchr(name, 0, length); } int __init xfs_attr_intent_init_cache(void) { xfs_attr_intent_cache = kmem_cache_create("xfs_attr_intent", sizeof(struct xfs_attr_intent), 0, 0, NULL); return xfs_attr_intent_cache != NULL ? 0 : -ENOMEM; } void xfs_attr_intent_destroy_cache(void) { kmem_cache_destroy(xfs_attr_intent_cache); xfs_attr_intent_cache = NULL; } |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <net/net_namespace.h> #include <linux/if_arp.h> #include <net/rtnetlink.h> static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev) { dev_lstats_add(dev, skb->len); dev_kfree_skb(skb); return NETDEV_TX_OK; } struct nlmon { struct netlink_tap nt; }; static int nlmon_open(struct net_device *dev) { struct nlmon *nlmon = netdev_priv(dev); nlmon->nt.dev = dev; nlmon->nt.module = THIS_MODULE; return netlink_add_tap(&nlmon->nt); } static int nlmon_close(struct net_device *dev) { struct nlmon *nlmon = netdev_priv(dev); return netlink_remove_tap(&nlmon->nt); } static void nlmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { dev_lstats_read(dev, &stats->rx_packets, &stats->rx_bytes); } static u32 always_on(struct net_device *dev) { return 1; } static const struct ethtool_ops nlmon_ethtool_ops = { .get_link = always_on, }; static const struct net_device_ops nlmon_ops = { .ndo_open = nlmon_open, .ndo_stop = nlmon_close, .ndo_start_xmit = nlmon_xmit, .ndo_get_stats64 = nlmon_get_stats64, }; static void nlmon_setup(struct net_device *dev) { dev->type = ARPHRD_NETLINK; dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; dev->netdev_ops = &nlmon_ops; dev->ethtool_ops = &nlmon_ethtool_ops; dev->needs_free_netdev = true; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->flags = IFF_NOARP; dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS; /* That's rather a softlimit here, which, of course, * can be altered. Not a real MTU, but what is to be * expected in most cases. */ dev->mtu = NLMSG_GOODSIZE; dev->min_mtu = sizeof(struct nlmsghdr); } static int nlmon_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) return -EINVAL; return 0; } static struct rtnl_link_ops nlmon_link_ops __read_mostly = { .kind = "nlmon", .priv_size = sizeof(struct nlmon), .setup = nlmon_setup, .validate = nlmon_validate, }; static __init int nlmon_register(void) { return rtnl_link_register(&nlmon_link_ops); } static __exit void nlmon_unregister(void) { rtnl_link_unregister(&nlmon_link_ops); } module_init(nlmon_register); module_exit(nlmon_unregister); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_AUTHOR("Mathieu Geli <geli@enseirb.fr>"); MODULE_DESCRIPTION("Netlink monitoring device"); MODULE_ALIAS_RTNL_LINK("nlmon"); |
| 9 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 | // SPDX-License-Identifier: GPL-2.0-only /* * v4l2-event.c * * V4L2 events. * * Copyright (C) 2009--2010 Nokia Corporation. * * Contact: Sakari Ailus <sakari.ailus@iki.fi> */ #include <media/v4l2-dev.h> #include <media/v4l2-fh.h> #include <media/v4l2-event.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/export.h> static unsigned int sev_pos(const struct v4l2_subscribed_event *sev, unsigned int idx) { idx += sev->first; return idx >= sev->elems ? idx - sev->elems : idx; } static int __v4l2_event_dequeue(struct v4l2_fh *fh, struct v4l2_event *event) { struct v4l2_kevent *kev; struct timespec64 ts; unsigned long flags; spin_lock_irqsave(&fh->vdev->fh_lock, flags); if (list_empty(&fh->available)) { spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); return -ENOENT; } WARN_ON(fh->navailable == 0); kev = list_first_entry(&fh->available, struct v4l2_kevent, list); list_del(&kev->list); fh->navailable--; kev->event.pending = fh->navailable; *event = kev->event; ts = ns_to_timespec64(kev->ts); event->timestamp.tv_sec = ts.tv_sec; event->timestamp.tv_nsec = ts.tv_nsec; kev->sev->first = sev_pos(kev->sev, 1); kev->sev->in_use--; spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); return 0; } int v4l2_event_dequeue(struct v4l2_fh *fh, struct v4l2_event *event, int nonblocking) { int ret; if (nonblocking) return __v4l2_event_dequeue(fh, event); /* Release the vdev lock while waiting */ if (fh->vdev->lock) mutex_unlock(fh->vdev->lock); do { ret = wait_event_interruptible(fh->wait, fh->navailable != 0); if (ret < 0) break; ret = __v4l2_event_dequeue(fh, event); } while (ret == -ENOENT); if (fh->vdev->lock) mutex_lock(fh->vdev->lock); return ret; } EXPORT_SYMBOL_GPL(v4l2_event_dequeue); /* Caller must hold fh->vdev->fh_lock! */ static struct v4l2_subscribed_event *v4l2_event_subscribed( struct v4l2_fh *fh, u32 type, u32 id) { struct v4l2_subscribed_event *sev; assert_spin_locked(&fh->vdev->fh_lock); list_for_each_entry(sev, &fh->subscribed, list) if (sev->type == type && sev->id == id) return sev; return NULL; } static void __v4l2_event_queue_fh(struct v4l2_fh *fh, const struct v4l2_event *ev, u64 ts) { struct v4l2_subscribed_event *sev; struct v4l2_kevent *kev; bool copy_payload = true; /* Are we subscribed? */ sev = v4l2_event_subscribed(fh, ev->type, ev->id); if (sev == NULL) return; /* Increase event sequence number on fh. */ fh->sequence++; /* Do we have any free events? */ if (sev->in_use == sev->elems) { /* no, remove the oldest one */ kev = sev->events + sev_pos(sev, 0); list_del(&kev->list); sev->in_use--; sev->first = sev_pos(sev, 1); fh->navailable--; if (sev->elems == 1) { if (sev->ops && sev->ops->replace) { sev->ops->replace(&kev->event, ev); copy_payload = false; } } else if (sev->ops && sev->ops->merge) { struct v4l2_kevent *second_oldest = sev->events + sev_pos(sev, 0); sev->ops->merge(&kev->event, &second_oldest->event); } } /* Take one and fill it. */ kev = sev->events + sev_pos(sev, sev->in_use); kev->event.type = ev->type; if (copy_payload) kev->event.u = ev->u; kev->event.id = ev->id; kev->ts = ts; kev->event.sequence = fh->sequence; sev->in_use++; list_add_tail(&kev->list, &fh->available); fh->navailable++; wake_up_all(&fh->wait); } void v4l2_event_queue(struct video_device *vdev, const struct v4l2_event *ev) { struct v4l2_fh *fh; unsigned long flags; u64 ts; if (vdev == NULL) return; ts = ktime_get_ns(); spin_lock_irqsave(&vdev->fh_lock, flags); list_for_each_entry(fh, &vdev->fh_list, list) __v4l2_event_queue_fh(fh, ev, ts); spin_unlock_irqrestore(&vdev->fh_lock, flags); } EXPORT_SYMBOL_GPL(v4l2_event_queue); void v4l2_event_queue_fh(struct v4l2_fh *fh, const struct v4l2_event *ev) { unsigned long flags; u64 ts = ktime_get_ns(); spin_lock_irqsave(&fh->vdev->fh_lock, flags); __v4l2_event_queue_fh(fh, ev, ts); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); } EXPORT_SYMBOL_GPL(v4l2_event_queue_fh); int v4l2_event_pending(struct v4l2_fh *fh) { return fh->navailable; } EXPORT_SYMBOL_GPL(v4l2_event_pending); void v4l2_event_wake_all(struct video_device *vdev) { struct v4l2_fh *fh; unsigned long flags; if (!vdev) return; spin_lock_irqsave(&vdev->fh_lock, flags); list_for_each_entry(fh, &vdev->fh_list, list) wake_up_all(&fh->wait); spin_unlock_irqrestore(&vdev->fh_lock, flags); } EXPORT_SYMBOL_GPL(v4l2_event_wake_all); static void __v4l2_event_unsubscribe(struct v4l2_subscribed_event *sev) { struct v4l2_fh *fh = sev->fh; unsigned int i; lockdep_assert_held(&fh->subscribe_lock); assert_spin_locked(&fh->vdev->fh_lock); /* Remove any pending events for this subscription */ for (i = 0; i < sev->in_use; i++) { list_del(&sev->events[sev_pos(sev, i)].list); fh->navailable--; } list_del(&sev->list); } int v4l2_event_subscribe(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub, unsigned int elems, const struct v4l2_subscribed_event_ops *ops) { struct v4l2_subscribed_event *sev, *found_ev; unsigned long flags; unsigned int i; int ret = 0; if (sub->type == V4L2_EVENT_ALL) return -EINVAL; if (elems < 1) elems = 1; sev = kvzalloc(struct_size(sev, events, elems), GFP_KERNEL); if (!sev) return -ENOMEM; sev->elems = elems; for (i = 0; i < elems; i++) sev->events[i].sev = sev; sev->type = sub->type; sev->id = sub->id; sev->flags = sub->flags; sev->fh = fh; sev->ops = ops; mutex_lock(&fh->subscribe_lock); spin_lock_irqsave(&fh->vdev->fh_lock, flags); found_ev = v4l2_event_subscribed(fh, sub->type, sub->id); if (!found_ev) list_add(&sev->list, &fh->subscribed); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); if (found_ev) { /* Already listening */ kvfree(sev); } else if (sev->ops && sev->ops->add) { ret = sev->ops->add(sev, elems); if (ret) { spin_lock_irqsave(&fh->vdev->fh_lock, flags); __v4l2_event_unsubscribe(sev); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); kvfree(sev); } } mutex_unlock(&fh->subscribe_lock); return ret; } EXPORT_SYMBOL_GPL(v4l2_event_subscribe); void v4l2_event_unsubscribe_all(struct v4l2_fh *fh) { struct v4l2_event_subscription sub; struct v4l2_subscribed_event *sev; unsigned long flags; do { sev = NULL; spin_lock_irqsave(&fh->vdev->fh_lock, flags); if (!list_empty(&fh->subscribed)) { sev = list_first_entry(&fh->subscribed, struct v4l2_subscribed_event, list); sub.type = sev->type; sub.id = sev->id; } spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); if (sev) v4l2_event_unsubscribe(fh, &sub); } while (sev); } EXPORT_SYMBOL_GPL(v4l2_event_unsubscribe_all); int v4l2_event_unsubscribe(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub) { struct v4l2_subscribed_event *sev; unsigned long flags; if (sub->type == V4L2_EVENT_ALL) { v4l2_event_unsubscribe_all(fh); return 0; } mutex_lock(&fh->subscribe_lock); spin_lock_irqsave(&fh->vdev->fh_lock, flags); sev = v4l2_event_subscribed(fh, sub->type, sub->id); if (sev != NULL) __v4l2_event_unsubscribe(sev); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); if (sev && sev->ops && sev->ops->del) sev->ops->del(sev); mutex_unlock(&fh->subscribe_lock); kvfree(sev); return 0; } EXPORT_SYMBOL_GPL(v4l2_event_unsubscribe); int v4l2_event_subdev_unsubscribe(struct v4l2_subdev *sd, struct v4l2_fh *fh, struct v4l2_event_subscription *sub) { return v4l2_event_unsubscribe(fh, sub); } EXPORT_SYMBOL_GPL(v4l2_event_subdev_unsubscribe); static void v4l2_event_src_replace(struct v4l2_event *old, const struct v4l2_event *new) { u32 old_changes = old->u.src_change.changes; old->u.src_change = new->u.src_change; old->u.src_change.changes |= old_changes; } static void v4l2_event_src_merge(const struct v4l2_event *old, struct v4l2_event *new) { new->u.src_change.changes |= old->u.src_change.changes; } static const struct v4l2_subscribed_event_ops v4l2_event_src_ch_ops = { .replace = v4l2_event_src_replace, .merge = v4l2_event_src_merge, }; int v4l2_src_change_event_subscribe(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub) { if (sub->type == V4L2_EVENT_SOURCE_CHANGE) return v4l2_event_subscribe(fh, sub, 0, &v4l2_event_src_ch_ops); return -EINVAL; } EXPORT_SYMBOL_GPL(v4l2_src_change_event_subscribe); int v4l2_src_change_event_subdev_subscribe(struct v4l2_subdev *sd, struct v4l2_fh *fh, struct v4l2_event_subscription *sub) { return v4l2_src_change_event_subscribe(fh, sub); } EXPORT_SYMBOL_GPL(v4l2_src_change_event_subdev_subscribe); |
| 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "peerlookup.h" #include "peer.h" #include "noise.h" static struct hlist_head *pubkey_bucket(struct pubkey_hashtable *table, const u8 pubkey[NOISE_PUBLIC_KEY_LEN]) { /* siphash gives us a secure 64bit number based on a random key. Since * the bits are uniformly distributed, we can then mask off to get the * bits we need. */ const u64 hash = siphash(pubkey, NOISE_PUBLIC_KEY_LEN, &table->key); return &table->hashtable[hash & (HASH_SIZE(table->hashtable) - 1)]; } struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void) { struct pubkey_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL); if (!table) return NULL; get_random_bytes(&table->key, sizeof(table->key)); hash_init(table->hashtable); mutex_init(&table->lock); return table; } void wg_pubkey_hashtable_add(struct pubkey_hashtable *table, struct wg_peer *peer) { mutex_lock(&table->lock); hlist_add_head_rcu(&peer->pubkey_hash, pubkey_bucket(table, peer->handshake.remote_static)); mutex_unlock(&table->lock); } void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table, struct wg_peer *peer) { mutex_lock(&table->lock); hlist_del_init_rcu(&peer->pubkey_hash); mutex_unlock(&table->lock); } /* Returns a strong reference to a peer */ struct wg_peer * wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table, const u8 pubkey[NOISE_PUBLIC_KEY_LEN]) { struct wg_peer *iter_peer, *peer = NULL; rcu_read_lock_bh(); hlist_for_each_entry_rcu_bh(iter_peer, pubkey_bucket(table, pubkey), pubkey_hash) { if (!memcmp(pubkey, iter_peer->handshake.remote_static, NOISE_PUBLIC_KEY_LEN)) { peer = iter_peer; break; } } peer = wg_peer_get_maybe_zero(peer); rcu_read_unlock_bh(); return peer; } static struct hlist_head *index_bucket(struct index_hashtable *table, const __le32 index) { /* Since the indices are random and thus all bits are uniformly * distributed, we can find its bucket simply by masking. */ return &table->hashtable[(__force u32)index & (HASH_SIZE(table->hashtable) - 1)]; } struct index_hashtable *wg_index_hashtable_alloc(void) { struct index_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL); if (!table) return NULL; hash_init(table->hashtable); spin_lock_init(&table->lock); return table; } /* At the moment, we limit ourselves to 2^20 total peers, which generally might * amount to 2^20*3 items in this hashtable. The algorithm below works by * picking a random number and testing it. We can see that these limits mean we * usually succeed pretty quickly: * * >>> def calculation(tries, size): * ... return (size / 2**32)**(tries - 1) * (1 - (size / 2**32)) * ... * >>> calculation(1, 2**20 * 3) * 0.999267578125 * >>> calculation(2, 2**20 * 3) * 0.0007318854331970215 * >>> calculation(3, 2**20 * 3) * 5.360489012673497e-07 * >>> calculation(4, 2**20 * 3) * 3.9261394135792216e-10 * * At the moment, we don't do any masking, so this algorithm isn't exactly * constant time in either the random guessing or in the hash list lookup. We * could require a minimum of 3 tries, which would successfully mask the * guessing. this would not, however, help with the growing hash lengths, which * is another thing to consider moving forward. */ __le32 wg_index_hashtable_insert(struct index_hashtable *table, struct index_hashtable_entry *entry) { struct index_hashtable_entry *existing_entry; spin_lock_bh(&table->lock); hlist_del_init_rcu(&entry->index_hash); spin_unlock_bh(&table->lock); rcu_read_lock_bh(); search_unused_slot: /* First we try to find an unused slot, randomly, while unlocked. */ entry->index = (__force __le32)get_random_u32(); hlist_for_each_entry_rcu_bh(existing_entry, index_bucket(table, entry->index), index_hash) { if (existing_entry->index == entry->index) /* If it's already in use, we continue searching. */ goto search_unused_slot; } /* Once we've found an unused slot, we lock it, and then double-check * that nobody else stole it from us. */ spin_lock_bh(&table->lock); hlist_for_each_entry_rcu_bh(existing_entry, index_bucket(table, entry->index), index_hash) { if (existing_entry->index == entry->index) { spin_unlock_bh(&table->lock); /* If it was stolen, we start over. */ goto search_unused_slot; } } /* Otherwise, we know we have it exclusively (since we're locked), * so we insert. */ hlist_add_head_rcu(&entry->index_hash, index_bucket(table, entry->index)); spin_unlock_bh(&table->lock); rcu_read_unlock_bh(); return entry->index; } bool wg_index_hashtable_replace(struct index_hashtable *table, struct index_hashtable_entry *old, struct index_hashtable_entry *new) { bool ret; spin_lock_bh(&table->lock); ret = !hlist_unhashed(&old->index_hash); if (unlikely(!ret)) goto out; new->index = old->index; hlist_replace_rcu(&old->index_hash, &new->index_hash); /* Calling init here NULLs out index_hash, and in fact after this * function returns, it's theoretically possible for this to get * reinserted elsewhere. That means the RCU lookup below might either * terminate early or jump between buckets, in which case the packet * simply gets dropped, which isn't terrible. */ INIT_HLIST_NODE(&old->index_hash); out: spin_unlock_bh(&table->lock); return ret; } void wg_index_hashtable_remove(struct index_hashtable *table, struct index_hashtable_entry *entry) { spin_lock_bh(&table->lock); hlist_del_init_rcu(&entry->index_hash); spin_unlock_bh(&table->lock); } /* Returns a strong reference to a entry->peer */ struct index_hashtable_entry * wg_index_hashtable_lookup(struct index_hashtable *table, const enum index_hashtable_type type_mask, const __le32 index, struct wg_peer **peer) { struct index_hashtable_entry *iter_entry, *entry = NULL; rcu_read_lock_bh(); hlist_for_each_entry_rcu_bh(iter_entry, index_bucket(table, index), index_hash) { if (iter_entry->index == index) { if (likely(iter_entry->type & type_mask)) entry = iter_entry; break; } } if (likely(entry)) { entry->peer = wg_peer_get_maybe_zero(entry->peer); if (likely(entry->peer)) *peer = entry->peer; else entry = NULL; } rcu_read_unlock_bh(); return entry; } |
| 214 214 419 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_MOUNT_H__ #define __XFS_MOUNT_H__ struct xlog; struct xfs_inode; struct xfs_mru_cache; struct xfs_ail; struct xfs_quotainfo; struct xfs_da_geometry; struct xfs_perag; /* dynamic preallocation free space thresholds, 5% down to 1% */ enum { XFS_LOWSP_1_PCNT = 0, XFS_LOWSP_2_PCNT, XFS_LOWSP_3_PCNT, XFS_LOWSP_4_PCNT, XFS_LOWSP_5_PCNT, XFS_LOWSP_MAX, }; /* * Error Configuration * * Error classes define the subsystem the configuration belongs to. * Error numbers define the errors that are configurable. */ enum { XFS_ERR_METADATA, XFS_ERR_CLASS_MAX, }; enum { XFS_ERR_DEFAULT, XFS_ERR_EIO, XFS_ERR_ENOSPC, XFS_ERR_ENODEV, XFS_ERR_ERRNO_MAX, }; #define XFS_ERR_RETRY_FOREVER -1 /* * Although retry_timeout is in jiffies which is normally an unsigned long, * we limit the retry timeout to 86400 seconds, or one day. So even a * signed 32-bit long is sufficient for a HZ value up to 24855. Making it * signed lets us store the special "-1" value, meaning retry forever. */ struct xfs_error_cfg { struct xfs_kobj kobj; int max_retries; long retry_timeout; /* in jiffies, -1 = infinite */ }; /* * Per-cpu deferred inode inactivation GC lists. */ struct xfs_inodegc { struct xfs_mount *mp; struct llist_head list; struct delayed_work work; int error; /* approximate count of inodes in the list */ unsigned int items; unsigned int shrinker_hits; unsigned int cpu; }; /* * Container for each type of groups, used to look up individual groups and * describes the geometry. */ struct xfs_groups { struct xarray xa; /* * Maximum capacity of the group in FSBs. * * Each group is laid out densely in the daddr space. For the * degenerate case of a pre-rtgroups filesystem, the incore rtgroup * pretends to have a zero-block and zero-blklog rtgroup. */ uint32_t blocks; /* * Log(2) of the logical size of each group. * * Compared to the blocks field above this is rounded up to the next * power of two, and thus lays out the xfs_fsblock_t/xfs_rtblock_t * space sparsely with a hole from blocks to (1 << blklog) at the end * of each group. */ uint8_t blklog; /* * Mask to extract the group-relative block number from a FSB. * For a pre-rtgroups filesystem we pretend to have one very large * rtgroup, so this mask must be 64-bit. */ uint64_t blkmask; }; /* * The struct xfsmount layout is optimised to separate read-mostly variables * from variables that are frequently modified. We put the read-mostly variables * first, then place all the other variables at the end. * * Typically, read-mostly variables are those that are set at mount time and * never changed again, or only change rarely as a result of things like sysfs * knobs being tweaked. */ typedef struct xfs_mount { struct xfs_sb m_sb; /* copy of fs superblock */ struct super_block *m_super; struct xfs_ail *m_ail; /* fs active log item list */ struct xfs_buf *m_sb_bp; /* buffer for superblock */ struct xfs_buf *m_rtsb_bp; /* realtime superblock */ char *m_rtname; /* realtime device name */ char *m_logname; /* external log device name */ struct xfs_da_geometry *m_dir_geo; /* directory block geometry */ struct xfs_da_geometry *m_attr_geo; /* attribute block geometry */ struct xlog *m_log; /* log specific stuff */ struct xfs_inode *m_rootip; /* pointer to root directory */ struct xfs_inode *m_metadirip; /* ptr to metadata directory */ struct xfs_inode *m_rtdirip; /* ptr to realtime metadir */ struct xfs_quotainfo *m_quotainfo; /* disk quota information */ struct xfs_buftarg *m_ddev_targp; /* data device */ struct xfs_buftarg *m_logdev_targp;/* log device */ struct xfs_buftarg *m_rtdev_targp; /* rt device */ void __percpu *m_inodegc; /* percpu inodegc structures */ struct xfs_mru_cache *m_filestream; /* per-mount filestream data */ struct workqueue_struct *m_buf_workqueue; struct workqueue_struct *m_unwritten_workqueue; struct workqueue_struct *m_reclaim_workqueue; struct workqueue_struct *m_sync_workqueue; struct workqueue_struct *m_blockgc_wq; struct workqueue_struct *m_inodegc_wq; int m_bsize; /* fs logical block size */ uint8_t m_blkbit_log; /* blocklog + NBBY */ uint8_t m_blkbb_log; /* blocklog - BBSHIFT */ uint8_t m_agno_log; /* log #ag's */ uint8_t m_sectbb_log; /* sectlog - BBSHIFT */ int8_t m_rtxblklog; /* log2 of rextsize, if possible */ uint m_blockmask; /* sb_blocksize-1 */ uint m_blockwsize; /* sb_blocksize in words */ /* number of rt extents per rt bitmap block if rtgroups enabled */ unsigned int m_rtx_per_rbmblock; uint m_alloc_mxr[2]; /* max alloc btree records */ uint m_alloc_mnr[2]; /* min alloc btree records */ uint m_bmap_dmxr[2]; /* max bmap btree records */ uint m_bmap_dmnr[2]; /* min bmap btree records */ uint m_rmap_mxr[2]; /* max rmap btree records */ uint m_rmap_mnr[2]; /* min rmap btree records */ uint m_rtrmap_mxr[2]; /* max rtrmap btree records */ uint m_rtrmap_mnr[2]; /* min rtrmap btree records */ uint m_refc_mxr[2]; /* max refc btree records */ uint m_refc_mnr[2]; /* min refc btree records */ uint m_rtrefc_mxr[2]; /* max rtrefc btree records */ uint m_rtrefc_mnr[2]; /* min rtrefc btree records */ uint m_alloc_maxlevels; /* max alloc btree levels */ uint m_bm_maxlevels[2]; /* max bmap btree levels */ uint m_rmap_maxlevels; /* max rmap btree levels */ uint m_rtrmap_maxlevels; /* max rtrmap btree level */ uint m_refc_maxlevels; /* max refcount btree level */ uint m_rtrefc_maxlevels; /* max rtrefc btree level */ unsigned int m_agbtree_maxlevels; /* max level of all AG btrees */ unsigned int m_rtbtree_maxlevels; /* max level of all rt btrees */ xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */ uint m_alloc_set_aside; /* space we can't use */ uint m_ag_max_usable; /* max space per AG */ int m_dalign; /* stripe unit */ int m_swidth; /* stripe width */ xfs_agnumber_t m_maxagi; /* highest inode alloc group */ uint m_allocsize_log;/* min write size log bytes */ uint m_allocsize_blocks; /* min write size blocks */ int m_logbufs; /* number of log buffers */ int m_logbsize; /* size of each log buffer */ unsigned int m_rsumlevels; /* rt summary levels */ xfs_filblks_t m_rsumblocks; /* size of rt summary, FSBs */ int m_fixedfsid[2]; /* unchanged for life of FS */ uint m_qflags; /* quota status flags */ uint64_t m_features; /* active filesystem features */ uint64_t m_low_space[XFS_LOWSP_MAX]; uint64_t m_low_rtexts[XFS_LOWSP_MAX]; uint64_t m_rtxblkmask; /* rt extent block mask */ struct xfs_ino_geometry m_ino_geo; /* inode geometry */ struct xfs_trans_resv m_resv; /* precomputed res values */ /* low free space thresholds */ unsigned long m_opstate; /* dynamic state flags */ bool m_always_cow; bool m_fail_unmount; bool m_finobt_nores; /* no per-AG finobt resv. */ bool m_update_sb; /* sb needs update in mount */ /* * Bitsets of per-fs metadata that have been checked and/or are sick. * Callers must hold m_sb_lock to access these two fields. */ uint8_t m_fs_checked; uint8_t m_fs_sick; /* * Bitsets of rt metadata that have been checked and/or are sick. * Callers must hold m_sb_lock to access this field. */ uint8_t m_rt_checked; uint8_t m_rt_sick; /* * End of read-mostly variables. Frequently written variables and locks * should be placed below this comment from now on. The first variable * here is marked as cacheline aligned so they it is separated from * the read-mostly variables. */ spinlock_t ____cacheline_aligned m_sb_lock; /* sb counter lock */ struct percpu_counter m_icount; /* allocated inodes counter */ struct percpu_counter m_ifree; /* free inodes counter */ struct percpu_counter m_fdblocks; /* free block counter */ struct percpu_counter m_frextents; /* free rt extent counter */ /* * Count of data device blocks reserved for delayed allocations, * including indlen blocks. Does not include allocated CoW staging * extents or anything related to the rt device. */ struct percpu_counter m_delalloc_blks; /* * RT version of the above. */ struct percpu_counter m_delalloc_rtextents; /* * Global count of allocation btree blocks in use across all AGs. Only * used when perag reservation is enabled. Helps prevent block * reservation from attempting to reserve allocation btree blocks. */ atomic64_t m_allocbt_blks; struct xfs_groups m_groups[XG_TYPE_MAX]; uint64_t m_resblks; /* total reserved blocks */ uint64_t m_resblks_avail;/* available reserved blocks */ uint64_t m_resblks_save; /* reserved blks @ remount,ro */ struct delayed_work m_reclaim_work; /* background inode reclaim */ struct dentry *m_debugfs; /* debugfs parent */ struct xfs_kobj m_kobj; struct xfs_kobj m_error_kobj; struct xfs_kobj m_error_meta_kobj; struct xfs_error_cfg m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX]; struct xstats m_stats; /* per-fs stats */ #ifdef CONFIG_XFS_ONLINE_SCRUB_STATS struct xchk_stats *m_scrub_stats; #endif xfs_agnumber_t m_agfrotor; /* last ag where space found */ atomic_t m_agirotor; /* last ag dir inode alloced */ atomic_t m_rtgrotor; /* last rtgroup rtpicked */ /* Memory shrinker to throttle and reprioritize inodegc */ struct shrinker *m_inodegc_shrinker; /* * Workqueue item so that we can coalesce multiple inode flush attempts * into a single flush. */ struct work_struct m_flush_inodes_work; /* * Generation of the filesysyem layout. This is incremented by each * growfs, and used by the pNFS server to ensure the client updates * its view of the block device once it gets a layout that might * reference the newly added blocks. Does not need to be persistent * as long as we only allow file system size increments, but if we * ever support shrinks it would have to be persisted in addition * to various other kinds of pain inflicted on the pNFS server. */ uint32_t m_generation; struct mutex m_growlock; /* growfs mutex */ #ifdef DEBUG /* * Frequency with which errors are injected. Replaces xfs_etest; the * value stored in here is the inverse of the frequency with which the * error triggers. 1 = always, 2 = half the time, etc. */ unsigned int *m_errortag; struct xfs_kobj m_errortag_kobj; #endif /* cpus that have inodes queued for inactivation */ struct cpumask m_inodegc_cpumask; /* Hook to feed dirent updates to an active online repair. */ struct xfs_hooks m_dir_update_hooks; } xfs_mount_t; #define M_IGEO(mp) (&(mp)->m_ino_geo) /* * Flags for m_features. * * These are all the active features in the filesystem, regardless of how * they are configured. */ #define XFS_FEAT_ATTR (1ULL << 0) /* xattrs present in fs */ #define XFS_FEAT_NLINK (1ULL << 1) /* 32 bit link counts */ #define XFS_FEAT_QUOTA (1ULL << 2) /* quota active */ #define XFS_FEAT_ALIGN (1ULL << 3) /* inode alignment */ #define XFS_FEAT_DALIGN (1ULL << 4) /* data alignment */ #define XFS_FEAT_LOGV2 (1ULL << 5) /* version 2 logs */ #define XFS_FEAT_SECTOR (1ULL << 6) /* sector size > 512 bytes */ #define XFS_FEAT_EXTFLG (1ULL << 7) /* unwritten extents */ #define XFS_FEAT_ASCIICI (1ULL << 8) /* ASCII only case-insens. */ #define XFS_FEAT_LAZYSBCOUNT (1ULL << 9) /* Superblk counters */ #define XFS_FEAT_ATTR2 (1ULL << 10) /* dynamic attr fork */ #define XFS_FEAT_PARENT (1ULL << 11) /* parent pointers */ #define XFS_FEAT_PROJID32 (1ULL << 12) /* 32 bit project id */ #define XFS_FEAT_CRC (1ULL << 13) /* metadata CRCs */ #define XFS_FEAT_V3INODES (1ULL << 14) /* Version 3 inodes */ #define XFS_FEAT_PQUOTINO (1ULL << 15) /* non-shared proj/grp quotas */ #define XFS_FEAT_FTYPE (1ULL << 16) /* inode type in dir */ #define XFS_FEAT_FINOBT (1ULL << 17) /* free inode btree */ #define XFS_FEAT_RMAPBT (1ULL << 18) /* reverse map btree */ #define XFS_FEAT_REFLINK (1ULL << 19) /* reflinked files */ #define XFS_FEAT_SPINODES (1ULL << 20) /* sparse inode chunks */ #define XFS_FEAT_META_UUID (1ULL << 21) /* metadata UUID */ #define XFS_FEAT_REALTIME (1ULL << 22) /* realtime device present */ #define XFS_FEAT_INOBTCNT (1ULL << 23) /* inobt block counts */ #define XFS_FEAT_BIGTIME (1ULL << 24) /* large timestamps */ #define XFS_FEAT_NEEDSREPAIR (1ULL << 25) /* needs xfs_repair */ #define XFS_FEAT_NREXT64 (1ULL << 26) /* large extent counters */ #define XFS_FEAT_EXCHANGE_RANGE (1ULL << 27) /* exchange range */ #define XFS_FEAT_METADIR (1ULL << 28) /* metadata directory tree */ /* Mount features */ #define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */ #define XFS_FEAT_NOALIGN (1ULL << 49) /* ignore alignment */ #define XFS_FEAT_ALLOCSIZE (1ULL << 50) /* user specified allocation size */ #define XFS_FEAT_LARGE_IOSIZE (1ULL << 51) /* report large preferred * I/O size in stat() */ #define XFS_FEAT_WSYNC (1ULL << 52) /* synchronous metadata ops */ #define XFS_FEAT_DIRSYNC (1ULL << 53) /* synchronous directory ops */ #define XFS_FEAT_DISCARD (1ULL << 54) /* discard unused blocks */ #define XFS_FEAT_GRPID (1ULL << 55) /* group-ID assigned from directory */ #define XFS_FEAT_SMALL_INUMS (1ULL << 56) /* user wants 32bit inodes */ #define XFS_FEAT_IKEEP (1ULL << 57) /* keep empty inode clusters*/ #define XFS_FEAT_SWALLOC (1ULL << 58) /* stripe width allocation */ #define XFS_FEAT_FILESTREAMS (1ULL << 59) /* use filestreams allocator */ #define XFS_FEAT_DAX_ALWAYS (1ULL << 60) /* DAX always enabled */ #define XFS_FEAT_DAX_NEVER (1ULL << 61) /* DAX never enabled */ #define XFS_FEAT_NORECOVERY (1ULL << 62) /* no recovery - dirty fs */ #define XFS_FEAT_NOUUID (1ULL << 63) /* ignore uuid during mount */ #define __XFS_HAS_FEAT(name, NAME) \ static inline bool xfs_has_ ## name (const struct xfs_mount *mp) \ { \ return mp->m_features & XFS_FEAT_ ## NAME; \ } /* Some features can be added dynamically so they need a set wrapper, too. */ #define __XFS_ADD_FEAT(name, NAME) \ __XFS_HAS_FEAT(name, NAME); \ static inline void xfs_add_ ## name (struct xfs_mount *mp) \ { \ mp->m_features |= XFS_FEAT_ ## NAME; \ xfs_sb_version_add ## name(&mp->m_sb); \ } /* Superblock features */ __XFS_ADD_FEAT(attr, ATTR) __XFS_HAS_FEAT(nlink, NLINK) __XFS_ADD_FEAT(quota, QUOTA) __XFS_HAS_FEAT(dalign, DALIGN) __XFS_HAS_FEAT(sector, SECTOR) __XFS_HAS_FEAT(asciici, ASCIICI) __XFS_HAS_FEAT(parent, PARENT) __XFS_HAS_FEAT(ftype, FTYPE) __XFS_HAS_FEAT(finobt, FINOBT) __XFS_HAS_FEAT(rmapbt, RMAPBT) __XFS_HAS_FEAT(reflink, REFLINK) __XFS_HAS_FEAT(sparseinodes, SPINODES) __XFS_HAS_FEAT(metauuid, META_UUID) __XFS_HAS_FEAT(realtime, REALTIME) __XFS_HAS_FEAT(inobtcounts, INOBTCNT) __XFS_HAS_FEAT(bigtime, BIGTIME) __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR) __XFS_HAS_FEAT(large_extent_counts, NREXT64) __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE) __XFS_HAS_FEAT(metadir, METADIR) static inline bool xfs_has_rtgroups(const struct xfs_mount *mp) { /* all metadir file systems also allow rtgroups */ return xfs_has_metadir(mp); } static inline bool xfs_has_rtsb(const struct xfs_mount *mp) { /* all rtgroups filesystems with an rt section have an rtsb */ return xfs_has_rtgroups(mp) && xfs_has_realtime(mp); } static inline bool xfs_has_rtrmapbt(const struct xfs_mount *mp) { return xfs_has_rtgroups(mp) && xfs_has_realtime(mp) && xfs_has_rmapbt(mp); } static inline bool xfs_has_rtreflink(const struct xfs_mount *mp) { return xfs_has_metadir(mp) && xfs_has_realtime(mp) && xfs_has_reflink(mp); } /* * Some features are always on for v5 file systems, allow the compiler to * eliminiate dead code when building without v4 support. */ #define __XFS_HAS_V4_FEAT(name, NAME) \ static inline bool xfs_has_ ## name (struct xfs_mount *mp) \ { \ return !IS_ENABLED(CONFIG_XFS_SUPPORT_V4) || \ (mp->m_features & XFS_FEAT_ ## NAME); \ } #define __XFS_ADD_V4_FEAT(name, NAME) \ __XFS_HAS_V4_FEAT(name, NAME); \ static inline void xfs_add_ ## name (struct xfs_mount *mp) \ { \ if (IS_ENABLED(CONFIG_XFS_SUPPORT_V4)) { \ mp->m_features |= XFS_FEAT_ ## NAME; \ xfs_sb_version_add ## name(&mp->m_sb); \ } \ } __XFS_HAS_V4_FEAT(align, ALIGN) __XFS_HAS_V4_FEAT(logv2, LOGV2) __XFS_HAS_V4_FEAT(extflg, EXTFLG) __XFS_HAS_V4_FEAT(lazysbcount, LAZYSBCOUNT) __XFS_ADD_V4_FEAT(attr2, ATTR2) __XFS_ADD_V4_FEAT(projid32, PROJID32) __XFS_HAS_V4_FEAT(v3inodes, V3INODES) __XFS_HAS_V4_FEAT(crc, CRC) __XFS_HAS_V4_FEAT(pquotino, PQUOTINO) /* * Mount features * * These do not change dynamically - features that can come and go, such as 32 * bit inodes and read-only state, are kept as operational state rather than * features. */ __XFS_HAS_FEAT(noattr2, NOATTR2) __XFS_HAS_FEAT(noalign, NOALIGN) __XFS_HAS_FEAT(allocsize, ALLOCSIZE) __XFS_HAS_FEAT(large_iosize, LARGE_IOSIZE) __XFS_HAS_FEAT(wsync, WSYNC) __XFS_HAS_FEAT(dirsync, DIRSYNC) __XFS_HAS_FEAT(discard, DISCARD) __XFS_HAS_FEAT(grpid, GRPID) __XFS_HAS_FEAT(small_inums, SMALL_INUMS) __XFS_HAS_FEAT(ikeep, IKEEP) __XFS_HAS_FEAT(swalloc, SWALLOC) __XFS_HAS_FEAT(filestreams, FILESTREAMS) __XFS_HAS_FEAT(dax_always, DAX_ALWAYS) __XFS_HAS_FEAT(dax_never, DAX_NEVER) __XFS_HAS_FEAT(norecovery, NORECOVERY) __XFS_HAS_FEAT(nouuid, NOUUID) /* * Operational mount state flags * * Use these with atomic bit ops only! */ #define XFS_OPSTATE_UNMOUNTING 0 /* filesystem is unmounting */ #define XFS_OPSTATE_CLEAN 1 /* mount was clean */ #define XFS_OPSTATE_SHUTDOWN 2 /* stop all fs operations */ #define XFS_OPSTATE_INODE32 3 /* inode32 allocator active */ #define XFS_OPSTATE_READONLY 4 /* read-only fs */ /* * If set, inactivation worker threads will be scheduled to process queued * inodegc work. If not, queued inodes remain in memory waiting to be * processed. */ #define XFS_OPSTATE_INODEGC_ENABLED 5 /* * If set, background speculative prealloc gc worker threads will be scheduled * to process queued blockgc work. If not, inodes retain their preallocations * until explicitly deleted. */ #define XFS_OPSTATE_BLOCKGC_ENABLED 6 /* Kernel has logged a warning about pNFS being used on this fs. */ #define XFS_OPSTATE_WARNED_PNFS 7 /* Kernel has logged a warning about online fsck being used on this fs. */ #define XFS_OPSTATE_WARNED_SCRUB 8 /* Kernel has logged a warning about shrink being used on this fs. */ #define XFS_OPSTATE_WARNED_SHRINK 9 /* Kernel has logged a warning about logged xattr updates being used. */ #define XFS_OPSTATE_WARNED_LARP 10 /* Mount time quotacheck is running */ #define XFS_OPSTATE_QUOTACHECK_RUNNING 11 /* Do we want to clear log incompat flags? */ #define XFS_OPSTATE_UNSET_LOG_INCOMPAT 12 /* Filesystem can use logged extended attributes */ #define XFS_OPSTATE_USE_LARP 13 /* Kernel has logged a warning about blocksize > pagesize on this fs. */ #define XFS_OPSTATE_WARNED_LBS 14 /* Kernel has logged a warning about exchange-range being used on this fs. */ #define XFS_OPSTATE_WARNED_EXCHRANGE 15 /* Kernel has logged a warning about parent pointers being used on this fs. */ #define XFS_OPSTATE_WARNED_PPTR 16 /* Kernel has logged a warning about metadata dirs being used on this fs. */ #define XFS_OPSTATE_WARNED_METADIR 17 /* Filesystem should use qflags to determine quotaon status */ #define XFS_OPSTATE_RESUMING_QUOTAON 18 #define __XFS_IS_OPSTATE(name, NAME) \ static inline bool xfs_is_ ## name (struct xfs_mount *mp) \ { \ return test_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \ } \ static inline bool xfs_clear_ ## name (struct xfs_mount *mp) \ { \ return test_and_clear_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \ } \ static inline bool xfs_set_ ## name (struct xfs_mount *mp) \ { \ return test_and_set_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \ } __XFS_IS_OPSTATE(unmounting, UNMOUNTING) __XFS_IS_OPSTATE(clean, CLEAN) __XFS_IS_OPSTATE(shutdown, SHUTDOWN) __XFS_IS_OPSTATE(inode32, INODE32) __XFS_IS_OPSTATE(readonly, READONLY) __XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED) __XFS_IS_OPSTATE(blockgc_enabled, BLOCKGC_ENABLED) #ifdef CONFIG_XFS_QUOTA __XFS_IS_OPSTATE(quotacheck_running, QUOTACHECK_RUNNING) __XFS_IS_OPSTATE(resuming_quotaon, RESUMING_QUOTAON) #else static inline bool xfs_is_quotacheck_running(struct xfs_mount *mp) { return false; } static inline bool xfs_is_resuming_quotaon(struct xfs_mount *mp) { return false; } static inline void xfs_set_resuming_quotaon(struct xfs_mount *m) { } static inline bool xfs_clear_resuming_quotaon(struct xfs_mount *mp) { return false; } #endif /* CONFIG_XFS_QUOTA */ __XFS_IS_OPSTATE(done_with_log_incompat, UNSET_LOG_INCOMPAT) __XFS_IS_OPSTATE(using_logged_xattrs, USE_LARP) static inline bool xfs_should_warn(struct xfs_mount *mp, long nr) { return !test_and_set_bit(nr, &mp->m_opstate); } #define XFS_OPSTATE_STRINGS \ { (1UL << XFS_OPSTATE_UNMOUNTING), "unmounting" }, \ { (1UL << XFS_OPSTATE_CLEAN), "clean" }, \ { (1UL << XFS_OPSTATE_SHUTDOWN), "shutdown" }, \ { (1UL << XFS_OPSTATE_INODE32), "inode32" }, \ { (1UL << XFS_OPSTATE_READONLY), "read_only" }, \ { (1UL << XFS_OPSTATE_INODEGC_ENABLED), "inodegc" }, \ { (1UL << XFS_OPSTATE_BLOCKGC_ENABLED), "blockgc" }, \ { (1UL << XFS_OPSTATE_WARNED_SCRUB), "wscrub" }, \ { (1UL << XFS_OPSTATE_WARNED_SHRINK), "wshrink" }, \ { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" }, \ { (1UL << XFS_OPSTATE_QUOTACHECK_RUNNING), "quotacheck" }, \ { (1UL << XFS_OPSTATE_UNSET_LOG_INCOMPAT), "unset_log_incompat" }, \ { (1UL << XFS_OPSTATE_USE_LARP), "logged_xattrs" } /* * Max and min values for mount-option defined I/O * preallocation sizes. */ #define XFS_MAX_IO_LOG 30 /* 1G */ #define XFS_MIN_IO_LOG PAGE_SHIFT void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname, int lnnum); #define xfs_force_shutdown(m,f) \ xfs_do_force_shutdown(m, f, __FILE__, __LINE__) #define SHUTDOWN_META_IO_ERROR (1u << 0) /* write attempt to metadata failed */ #define SHUTDOWN_LOG_IO_ERROR (1u << 1) /* write attempt to the log failed */ #define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */ #define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */ #define SHUTDOWN_DEVICE_REMOVED (1u << 5) /* device removed underneath us */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ { SHUTDOWN_LOG_IO_ERROR, "log_io" }, \ { SHUTDOWN_FORCE_UMOUNT, "force_umount" }, \ { SHUTDOWN_CORRUPT_INCORE, "corruption" }, \ { SHUTDOWN_DEVICE_REMOVED, "device_removed" } /* * Flags for xfs_mountfs */ #define XFS_MFSI_QUIET 0x40 /* Be silent if mount errors found */ static inline xfs_agnumber_t xfs_daddr_to_agno(struct xfs_mount *mp, xfs_daddr_t d) { xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d); do_div(ld, mp->m_sb.sb_agblocks); return (xfs_agnumber_t) ld; } static inline xfs_agblock_t xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) { xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d); return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks); } extern void xfs_uuid_table_free(void); extern uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); extern void xfs_unmountfs(xfs_mount_t *); /* * Deltas for the block count can vary from 1 to very large, but lock contention * only occurs on frequent small block count updates such as in the delayed * allocation path for buffered writes (page a time updates). Hence we set * a large batch count (1024) to minimise global counter updates except when * we get near to ENOSPC and we have to be very accurate with our updates. */ #define XFS_FDBLOCKS_BATCH 1024 /* * Estimate the amount of free space that is not available to userspace and is * not explicitly reserved from the incore fdblocks. This includes: * * - The minimum number of blocks needed to support splitting a bmap btree * - The blocks currently in use by the freespace btrees because they record * the actual blocks that will fill per-AG metadata space reservations */ static inline uint64_t xfs_fdblocks_unavailable( struct xfs_mount *mp) { return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks); } int xfs_dec_freecounter(struct xfs_mount *mp, struct percpu_counter *counter, uint64_t delta, bool rsvd); void xfs_add_freecounter(struct xfs_mount *mp, struct percpu_counter *counter, uint64_t delta); static inline int xfs_dec_fdblocks(struct xfs_mount *mp, uint64_t delta, bool reserved) { return xfs_dec_freecounter(mp, &mp->m_fdblocks, delta, reserved); } static inline void xfs_add_fdblocks(struct xfs_mount *mp, uint64_t delta) { xfs_add_freecounter(mp, &mp->m_fdblocks, delta); } static inline int xfs_dec_frextents(struct xfs_mount *mp, uint64_t delta) { return xfs_dec_freecounter(mp, &mp->m_frextents, delta, false); } static inline void xfs_add_frextents(struct xfs_mount *mp, uint64_t delta) { xfs_add_freecounter(mp, &mp->m_frextents, delta); } extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); extern bool xfs_fs_writable(struct xfs_mount *mp, int level); extern int xfs_sb_validate_fsb_count(struct xfs_sb *, uint64_t); extern int xfs_dev_is_read_only(struct xfs_mount *, char *); extern void xfs_set_low_space_thresholds(struct xfs_mount *); int xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb, xfs_off_t count_fsb); struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp, int error_class, int error); void xfs_force_summary_recalc(struct xfs_mount *mp); int xfs_add_incompat_log_feature(struct xfs_mount *mp, uint32_t feature); bool xfs_clear_incompat_log_features(struct xfs_mount *mp); void xfs_mod_delalloc(struct xfs_inode *ip, int64_t data_delta, int64_t ind_delta); #endif /* __XFS_MOUNT_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 */ /* * Copyright (C) 2012 Fusion-io All rights reserved. * Copyright (C) 2012 Intel Corp. All rights reserved. */ #ifndef BTRFS_RAID56_H #define BTRFS_RAID56_H #include <linux/types.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/bio.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include "volumes.h" struct page; struct sector_ptr; struct btrfs_fs_info; enum btrfs_rbio_ops { BTRFS_RBIO_WRITE, BTRFS_RBIO_READ_REBUILD, BTRFS_RBIO_PARITY_SCRUB, }; struct btrfs_raid_bio { struct btrfs_io_context *bioc; /* * While we're doing RMW on a stripe we put it into a hash table so we * can lock the stripe and merge more rbios into it. */ struct list_head hash_list; /* LRU list for the stripe cache */ struct list_head stripe_cache; /* For scheduling work in the helper threads */ struct work_struct work; /* * bio_list and bio_list_lock are used to add more bios into the stripe * in hopes of avoiding the full RMW */ struct bio_list bio_list; spinlock_t bio_list_lock; /* * Also protected by the bio_list_lock, the plug list is used by the * plugging code to collect partial bios while plugged. The stripe * locking code also uses it to hand off the stripe lock to the next * pending IO. */ struct list_head plug_list; /* Flags that tell us if it is safe to merge with this bio. */ unsigned long flags; /* * Set if we're doing a parity rebuild for a read from higher up, which * is handled differently from a parity rebuild as part of RMW. */ enum btrfs_rbio_ops operation; /* How many pages there are for the full stripe including P/Q */ u16 nr_pages; /* How many sectors there are for the full stripe including P/Q */ u16 nr_sectors; /* Number of data stripes (no p/q) */ u8 nr_data; /* Number of all stripes (including P/Q) */ u8 real_stripes; /* How many pages there are for each stripe */ u8 stripe_npages; /* How many sectors there are for each stripe */ u8 stripe_nsectors; /* Stripe number that we're scrubbing */ u8 scrubp; /* * Size of all the bios in the bio_list. This helps us decide if the * rbio maps to a full stripe or not. */ int bio_list_bytes; refcount_t refs; atomic_t stripes_pending; wait_queue_head_t io_wait; /* Bitmap to record which horizontal stripe has data */ unsigned long dbitmap; /* Allocated with stripe_nsectors-many bits for finish_*() calls */ unsigned long finish_pbitmap; /* * These are two arrays of pointers. We allocate the rbio big enough * to hold them both and setup their locations when the rbio is * allocated. */ /* * Pointers to pages that we allocated for reading/writing stripes * directly from the disk (including P/Q). */ struct page **stripe_pages; /* Pointers to the sectors in the bio_list, for faster lookup */ struct sector_ptr *bio_sectors; /* * For subpage support, we need to map each sector to above * stripe_pages. */ struct sector_ptr *stripe_sectors; /* Allocated with real_stripes-many pointers for finish_*() calls */ void **finish_pointers; /* * The bitmap recording where IO errors happened. * Each bit is corresponding to one sector in either bio_sectors[] or * stripe_sectors[] array. * * The reason we don't use another bit in sector_ptr is, we have two * arrays of sectors, and a lot of IO can use sectors in both arrays. * Thus making it much harder to iterate. */ unsigned long *error_bitmap; /* * Checksum buffer if the rbio is for data. The buffer should cover * all data sectors (excluding P/Q sectors). */ u8 *csum_buf; /* * Each bit represents if the corresponding sector has data csum found. * Should only cover data sectors (excluding P/Q sectors). */ unsigned long *csum_bitmap; }; /* * For trace event usage only. Records useful debug info for each bio submitted * by RAID56 to each physical device. * * No matter signed or not, (-1) is always the one indicating we can not grab * the proper stripe number. */ struct raid56_bio_trace_info { u64 devid; /* The offset inside the stripe. (<= STRIPE_LEN) */ u32 offset; /* * Stripe number. * 0 is the first data stripe, and nr_data for P stripe, * nr_data + 1 for Q stripe. * >= real_stripes for */ u8 stripe_nr; }; static inline int nr_data_stripes(const struct btrfs_chunk_map *map) { return map->num_stripes - btrfs_nr_parity_stripes(map->type); } static inline int nr_bioc_data_stripes(const struct btrfs_io_context *bioc) { return bioc->num_stripes - btrfs_nr_parity_stripes(bioc->map_type); } #define RAID5_P_STRIPE ((u64)-2) #define RAID6_Q_STRIPE ((u64)-1) #define is_parity_stripe(x) (((x) == RAID5_P_STRIPE) || \ ((x) == RAID6_Q_STRIPE)) struct btrfs_device; void raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc, int mirror_num); void raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc); struct btrfs_raid_bio *raid56_parity_alloc_scrub_rbio(struct bio *bio, struct btrfs_io_context *bioc, struct btrfs_device *scrub_dev, unsigned long *dbitmap, int stripe_nsectors); void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio); void raid56_parity_cache_data_pages(struct btrfs_raid_bio *rbio, struct page **data_pages, u64 data_logical); int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info); void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info); #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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* user-type.h: User-defined key type * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _KEYS_USER_TYPE_H #define _KEYS_USER_TYPE_H #include <linux/key.h> #include <linux/rcupdate.h> #ifdef CONFIG_KEYS /*****************************************************************************/ /* * the payload for a key of type "user" or "logon" * - once filled in and attached to a key: * - the payload struct is invariant may not be changed, only replaced * - the payload must be read with RCU procedures or with the key semaphore * held * - the payload may only be replaced with the key semaphore write-locked * - the key's data length is the size of the actual data, not including the * payload wrapper */ struct user_key_payload { struct rcu_head rcu; /* RCU destructor */ unsigned short datalen; /* length of this data */ char data[] __aligned(__alignof__(u64)); /* actual data */ }; extern struct key_type key_type_user; extern struct key_type key_type_logon; struct key_preparsed_payload; extern int user_preparse(struct key_preparsed_payload *prep); extern void user_free_preparse(struct key_preparsed_payload *prep); extern int user_update(struct key *key, struct key_preparsed_payload *prep); extern void user_revoke(struct key *key); extern void user_destroy(struct key *key); extern void user_describe(const struct key *user, struct seq_file *m); extern long user_read(const struct key *key, char *buffer, size_t buflen); static inline const struct user_key_payload *user_key_payload_rcu(const struct key *key) { return (struct user_key_payload *)dereference_key_rcu(key); } static inline struct user_key_payload *user_key_payload_locked(const struct key *key) { return (struct user_key_payload *)dereference_key_locked((struct key *)key); } #endif /* CONFIG_KEYS */ #endif /* _KEYS_USER_TYPE_H */ |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 | // SPDX-License-Identifier: GPL-2.0-only /* * The "user cache". * * (C) Copyright 1991-2000 Linus Torvalds * * We have a per-user structure to keep track of how many * processes, files etc the user has claimed, in order to be * able to have per-user limits for system resources. */ #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/key.h> #include <linux/sched/user.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/proc_ns.h> #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc init_binfmt_misc = { .entries = LIST_HEAD_INIT(init_binfmt_misc.entries), .enabled = true, .entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock), }; EXPORT_SYMBOL_GPL(init_binfmt_misc); #endif /* * userns count is 1 for root user, 1 for init_uts_ns, * and 1 for... ? */ struct user_namespace init_user_ns = { .uid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .gid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .projid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .ns.count = REFCOUNT_INIT(3), .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .ns.inum = PROC_USER_INIT_INO, #ifdef CONFIG_USER_NS .ns.ops = &userns_operations, #endif .flags = USERNS_INIT_FLAGS, #ifdef CONFIG_KEYS .keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list), .keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem), #endif #if IS_ENABLED(CONFIG_BINFMT_MISC) .binfmt_misc = &init_binfmt_misc, #endif }; EXPORT_SYMBOL_GPL(init_user_ns); /* * UID task count cache, to get fast user lookup in "alloc_uid" * when changing user ID's (ie setuid() and friends). */ #define UIDHASH_BITS (IS_ENABLED(CONFIG_BASE_SMALL) ? 3 : 7) #define UIDHASH_SZ (1 << UIDHASH_BITS) #define UIDHASH_MASK (UIDHASH_SZ - 1) #define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) #define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid)))) static struct kmem_cache *uid_cachep; static struct hlist_head uidhash_table[UIDHASH_SZ]; /* * The uidhash_lock is mostly taken from process context, but it is * occasionally also taken from softirq/tasklet context, when * task-structs get RCU-freed. Hence all locking must be softirq-safe. * But free_uid() is also called with local interrupts disabled, and running * local_bh_enable() with local interrupts disabled is an error - we'll run * softirq callbacks, and they can unconditionally enable interrupts, and * the caller of free_uid() didn't expect that.. */ static DEFINE_SPINLOCK(uidhash_lock); /* root_user.__count is 1, for init task cred */ struct user_struct root_user = { .__count = REFCOUNT_INIT(1), .uid = GLOBAL_ROOT_UID, .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; /* * These routines must be called with the uidhash spinlock held! */ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) { hlist_add_head(&up->uidhash_node, hashent); } static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); } static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) { struct user_struct *user; hlist_for_each_entry(user, hashent, uidhash_node) { if (uid_eq(user->uid, uid)) { refcount_inc(&user->__count); return user; } } return NULL; } static int user_epoll_alloc(struct user_struct *up) { #ifdef CONFIG_EPOLL return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL); #else return 0; #endif } static void user_epoll_free(struct user_struct *up) { #ifdef CONFIG_EPOLL percpu_counter_destroy(&up->epoll_watches); #endif } /* IRQs are disabled and uidhash_lock is held upon function entry. * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); user_epoll_free(up); kmem_cache_free(uid_cachep, up); } /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). * * If the user_struct could not be found, return NULL. */ struct user_struct *find_user(kuid_t uid) { struct user_struct *ret; unsigned long flags; spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(uid)); spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } void free_uid(struct user_struct *up) { unsigned long flags; if (!up) return; if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags)) free_user(up, flags); } EXPORT_SYMBOL_GPL(free_uid); struct user_struct *alloc_uid(kuid_t uid) { struct hlist_head *hashent = uidhashentry(uid); struct user_struct *up, *new; spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); spin_unlock_irq(&uidhash_lock); if (!up) { new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL); if (!new) return NULL; new->uid = uid; refcount_set(&new->__count, 1); if (user_epoll_alloc(new)) { kmem_cache_free(uid_cachep, new); return NULL; } ratelimit_state_init(&new->ratelimit, HZ, 100); ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); /* * Before adding this, check whether we raced * on adding the same user already.. */ spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { user_epoll_free(new); kmem_cache_free(uid_cachep, new); } else { uid_hash_insert(new, hashent); up = new; } spin_unlock_irq(&uidhash_lock); } return up; } static int __init uid_cache_init(void) { int n; uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); for(n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(uidhash_table + n); if (user_epoll_alloc(&root_user)) panic("root_user epoll percpu counter alloc failed"); /* Insert the root user immediately (init already runs as root) */ spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); spin_unlock_irq(&uidhash_lock); return 0; } subsys_initcall(uid_cache_init); |
| 3 2 1 8 9 9 6 6 6 6 6 3 3 6 10 9 9 9 9 1 1 2 20 20 18 11 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/root.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc root directory handling functions */ #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/pid_namespace.h> #include <linux/fs_parser.h> #include <linux/cred.h> #include <linux/magic.h> #include <linux/slab.h> #include "internal.h" struct proc_fs_context { struct pid_namespace *pid_ns; unsigned int mask; enum proc_hidepid hidepid; int gid; enum proc_pidonly pidonly; }; enum proc_param { Opt_gid, Opt_hidepid, Opt_subset, }; static const struct fs_parameter_spec proc_fs_parameters[] = { fsparam_u32("gid", Opt_gid), fsparam_string("hidepid", Opt_hidepid), fsparam_string("subset", Opt_subset), {} }; static inline int valid_hidepid(unsigned int value) { return (value == HIDEPID_OFF || value == HIDEPID_NO_ACCESS || value == HIDEPID_INVISIBLE || value == HIDEPID_NOT_PTRACEABLE); } static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param) { struct proc_fs_context *ctx = fc->fs_private; struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid); struct fs_parse_result result; int base = (unsigned long)hidepid_u32_spec.data; if (param->type != fs_value_is_string) return invalf(fc, "proc: unexpected type of hidepid value\n"); if (!kstrtouint(param->string, base, &result.uint_32)) { if (!valid_hidepid(result.uint_32)) return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); ctx->hidepid = result.uint_32; return 0; } if (!strcmp(param->string, "off")) ctx->hidepid = HIDEPID_OFF; else if (!strcmp(param->string, "noaccess")) ctx->hidepid = HIDEPID_NO_ACCESS; else if (!strcmp(param->string, "invisible")) ctx->hidepid = HIDEPID_INVISIBLE; else if (!strcmp(param->string, "ptraceable")) ctx->hidepid = HIDEPID_NOT_PTRACEABLE; else return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); return 0; } static int proc_parse_subset_param(struct fs_context *fc, char *value) { struct proc_fs_context *ctx = fc->fs_private; while (value) { char *ptr = strchr(value, ','); if (ptr != NULL) *ptr++ = '\0'; if (*value != '\0') { if (!strcmp(value, "pid")) { ctx->pidonly = PROC_PIDONLY_ON; } else { return invalf(fc, "proc: unsupported subset option - %s\n", value); } } value = ptr; } return 0; } static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct proc_fs_context *ctx = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, proc_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_gid: ctx->gid = result.uint_32; break; case Opt_hidepid: if (proc_parse_hidepid_param(fc, param)) return -EINVAL; break; case Opt_subset: if (proc_parse_subset_param(fc, param->string) < 0) return -EINVAL; break; default: return -EINVAL; } ctx->mask |= 1 << opt; return 0; } static void proc_apply_options(struct proc_fs_info *fs_info, struct fs_context *fc, struct user_namespace *user_ns) { struct proc_fs_context *ctx = fc->fs_private; if (ctx->mask & (1 << Opt_gid)) fs_info->pid_gid = make_kgid(user_ns, ctx->gid); if (ctx->mask & (1 << Opt_hidepid)) fs_info->hide_pid = ctx->hidepid; if (ctx->mask & (1 << Opt_subset)) fs_info->pidonly = ctx->pidonly; } static int proc_fill_super(struct super_block *s, struct fs_context *fc) { struct proc_fs_context *ctx = fc->fs_private; struct inode *root_inode; struct proc_fs_info *fs_info; int ret; fs_info = kzalloc(sizeof(*fs_info), GFP_KERNEL); if (!fs_info) return -ENOMEM; fs_info->pid_ns = get_pid_ns(ctx->pid_ns); proc_apply_options(fs_info, fc, current_user_ns()); /* User space would break if executables or devices appear on proc */ s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV; s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = PROC_SUPER_MAGIC; s->s_op = &proc_sops; s->s_time_gran = 1; s->s_fs_info = fs_info; /* * procfs isn't actually a stacking filesystem; however, there is * too much magic going on inside it to permit stacking things on * top of it */ s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; /* procfs dentries and inodes don't require IO to create */ s->s_shrink->seeks = 0; pde_get(&proc_root); root_inode = proc_get_inode(s, &proc_root); if (!root_inode) { pr_err("proc_fill_super: get root inode failed\n"); return -ENOMEM; } s->s_root = d_make_root(root_inode); if (!s->s_root) { pr_err("proc_fill_super: allocate dentry failed\n"); return -ENOMEM; } ret = proc_setup_self(s); if (ret) { return ret; } return proc_setup_thread_self(s); } static int proc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct proc_fs_info *fs_info = proc_sb_info(sb); sync_filesystem(sb); proc_apply_options(fs_info, fc, current_user_ns()); return 0; } static int proc_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, proc_fill_super); } static void proc_fs_context_free(struct fs_context *fc) { struct proc_fs_context *ctx = fc->fs_private; put_pid_ns(ctx->pid_ns); kfree(ctx); } static const struct fs_context_operations proc_fs_context_ops = { .free = proc_fs_context_free, .parse_param = proc_parse_param, .get_tree = proc_get_tree, .reconfigure = proc_reconfigure, }; static int proc_init_fs_context(struct fs_context *fc) { struct proc_fs_context *ctx; ctx = kzalloc(sizeof(struct proc_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->pid_ns = get_pid_ns(task_active_pid_ns(current)); put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->pid_ns->user_ns); fc->fs_private = ctx; fc->ops = &proc_fs_context_ops; return 0; } static void proc_kill_sb(struct super_block *sb) { struct proc_fs_info *fs_info = proc_sb_info(sb); if (!fs_info) { kill_anon_super(sb); return; } dput(fs_info->proc_self); dput(fs_info->proc_thread_self); kill_anon_super(sb); put_pid_ns(fs_info->pid_ns); kfree_rcu(fs_info, rcu); } static struct file_system_type proc_fs_type = { .name = "proc", .init_fs_context = proc_init_fs_context, .parameters = proc_fs_parameters, .kill_sb = proc_kill_sb, .fs_flags = FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM, }; void __init proc_root_init(void) { proc_init_kmemcache(); set_proc_pid_nlink(); proc_self_init(); proc_thread_self_init(); proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); proc_mkdir("fs", NULL); proc_mkdir("driver", NULL); proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */ #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE) /* just give it a mountpoint */ proc_create_mount_point("openprom"); #endif proc_tty_init(); proc_mkdir("bus", NULL); proc_sys_init(); /* * Last things last. It is not like userspace processes eager * to open /proc files exist at this point but register last * anyway. */ register_filesystem(&proc_fs_type); } static int proc_root_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(path->dentry), stat); stat->nlink = proc_root.nlink + nr_processes(); return 0; } static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { if (!proc_pid_lookup(dentry, flags)) return NULL; return proc_lookup(dir, dentry, flags); } static int proc_root_readdir(struct file *file, struct dir_context *ctx) { if (ctx->pos < FIRST_PROCESS_ENTRY) { int error = proc_readdir(file, ctx); if (unlikely(error <= 0)) return error; ctx->pos = FIRST_PROCESS_ENTRY; } return proc_pid_readdir(file, ctx); } /* * The root /proc directory is special, as it has the * <pid> directories. Thus we don't use the generic * directory handling functions for that.. */ static const struct file_operations proc_root_operations = { .read = generic_read_dir, .iterate_shared = proc_root_readdir, .llseek = generic_file_llseek, }; /* * proc root can do almost nothing.. */ static const struct inode_operations proc_root_inode_operations = { .lookup = proc_root_lookup, .getattr = proc_root_getattr, }; /* * This is the root "inode" in the /proc tree.. */ struct proc_dir_entry proc_root = { .low_ino = PROC_ROOT_INO, .namelen = 5, .mode = S_IFDIR | S_IRUGO | S_IXUGO, .nlink = 2, .refcnt = REFCOUNT_INIT(1), .proc_iops = &proc_root_inode_operations, .proc_dir_ops = &proc_root_operations, .parent = &proc_root, .subdir = RB_ROOT, .name = "/proc", }; |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/xarray.h> #include <net/net_debug.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/page_pool/types.h> #include <net/sock.h> #include "devmem.h" #include "page_pool_priv.h" #include "netdev-genl-gen.h" static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); /* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user. * Ordering: inside rtnl_lock */ static DEFINE_MUTEX(page_pools_lock); /* Page pools are only reachable from user space (via netlink) if they are * linked to a netdev at creation time. Following page pool "visibility" * states are possible: * - normal * - user.list: linked to real netdev, netdev: real netdev * - orphaned - real netdev has disappeared * - user.list: linked to lo, netdev: lo * - invisible - either (a) created without netdev linking, (b) unlisted due * to error, or (c) the entire namespace which owned this pool disappeared * - user.list: unhashed, netdev: unknown */ typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info); static int netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill) { struct page_pool *pool; struct sk_buff *rsp; int err; mutex_lock(&page_pools_lock); pool = xa_load(&page_pools, id); if (!pool || hlist_unhashed(&pool->user.list) || !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) { err = -ENOENT; goto err_unlock; } rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) { err = -ENOMEM; goto err_unlock; } err = fill(rsp, pool, info); if (err) goto err_free_msg; mutex_unlock(&page_pools_lock); return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); err_unlock: mutex_unlock(&page_pools_lock); return err; } struct page_pool_dump_cb { unsigned long ifindex; u32 pp_id; }; static int netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, pp_nl_fill_cb fill) { struct page_pool_dump_cb *state = (void *)cb->ctx; const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; struct page_pool *pool; int err = 0; rtnl_lock(); mutex_lock(&page_pools_lock); for_each_netdev_dump(net, netdev, state->ifindex) { hlist_for_each_entry(pool, &netdev->page_pools, user.list) { if (state->pp_id && state->pp_id < pool->user.id) continue; state->pp_id = pool->user.id; err = fill(skb, pool, info); if (err) goto out; } state->pp_id = 0; } out: mutex_unlock(&page_pools_lock); rtnl_unlock(); return err; } static int page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { #ifdef CONFIG_PAGE_POOL_STATS struct page_pool_stats stats = {}; struct nlattr *nest; void *hdr; if (!page_pool_get_stats(pool, &stats)) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO); if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) || (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex))) goto err_cancel_nest; nla_nest_end(rsp, nest); if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST, stats.alloc_stats.fast) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, stats.alloc_stats.slow) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, stats.alloc_stats.slow_high_order) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, stats.alloc_stats.empty) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, stats.alloc_stats.refill) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, stats.alloc_stats.waive) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, stats.recycle_stats.cached) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, stats.recycle_stats.cache_full) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, stats.recycle_stats.ring) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, stats.recycle_stats.ring_full) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, stats.recycle_stats.released_refcnt)) goto err_cancel_msg; genlmsg_end(rsp, hdr); return 0; err_cancel_nest: nla_nest_cancel(rsp, nest); err_cancel_msg: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; #else GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS"); return -EOPNOTSUPP; #endif } int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)]; struct nlattr *nest; int err; u32 id; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO)) return -EINVAL; nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO]; err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest, netdev_page_pool_info_nl_policy, info->extack); if (err) return err; if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID)) return -EINVAL; if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NETDEV_A_PAGE_POOL_IFINDEX], "selecting by ifindex not supported"); return -EINVAL; } id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]); return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill); } int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill); } static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id)) goto err_cancel; if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex)) goto err_cancel; if (pool->user.napi_id && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) goto err_cancel; inflight = page_pool_inflight(pool, false); refsz = PAGE_SIZE << pool->p.order; if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, inflight * refsz)) goto err_cancel; if (pool->user.detach_time && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, pool->user.detach_time)) goto err_cancel; if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id)) goto err_cancel; genlmsg_end(rsp, hdr); return 0; err_cancel: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd) { struct genl_info info; struct sk_buff *ntf; struct net *net; lockdep_assert_held(&page_pools_lock); /* 'invisible' page pools don't matter */ if (hlist_unhashed(&pool->user.list)) return; net = dev_net(pool->slow.netdev); if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL)) return; genl_info_init_ntf(&info, &netdev_nl_family, cmd); ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ntf) return; if (page_pool_nl_fill(ntf, pool, &info)) { nlmsg_free(ntf); return; } genlmsg_multicast_netns(&netdev_nl_family, net, ntf, 0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL); } int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { u32 id; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID)) return -EINVAL; id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]); return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill); } int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill); } int page_pool_list(struct page_pool *pool) { static u32 id_alloc_next; int err; mutex_lock(&page_pools_lock); err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b, &id_alloc_next, GFP_KERNEL); if (err < 0) goto err_unlock; INIT_HLIST_NODE(&pool->user.list); if (pool->slow.netdev) { hlist_add_head(&pool->user.list, &pool->slow.netdev->page_pools); pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0; netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); } mutex_unlock(&page_pools_lock); return 0; err_unlock: mutex_unlock(&page_pools_lock); return err; } void page_pool_detached(struct page_pool *pool) { mutex_lock(&page_pools_lock); pool->user.detach_time = ktime_get_boottime_seconds(); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); mutex_unlock(&page_pools_lock); } void page_pool_unlist(struct page_pool *pool) { mutex_lock(&page_pools_lock); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF); xa_erase(&page_pools, pool->user.id); if (!hlist_unhashed(&pool->user.list)) hlist_del(&pool->user.list); mutex_unlock(&page_pools_lock); } int page_pool_check_memory_provider(struct net_device *dev, struct netdev_rx_queue *rxq) { struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv; struct page_pool *pool; struct hlist_node *n; if (!binding) return 0; mutex_lock(&page_pools_lock); hlist_for_each_entry_safe(pool, n, &dev->page_pools, user.list) { if (pool->mp_priv != binding) continue; if (pool->slow.queue_idx == get_netdev_rx_queue_index(rxq)) { mutex_unlock(&page_pools_lock); return 0; } } mutex_unlock(&page_pools_lock); return -ENODATA; } static void page_pool_unreg_netdev_wipe(struct net_device *netdev) { struct page_pool *pool; struct hlist_node *n; mutex_lock(&page_pools_lock); hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) { hlist_del_init(&pool->user.list); pool->slow.netdev = NET_PTR_POISON; } mutex_unlock(&page_pools_lock); } static void page_pool_unreg_netdev(struct net_device *netdev) { struct page_pool *pool, *last; struct net_device *lo; lo = dev_net(netdev)->loopback_dev; mutex_lock(&page_pools_lock); last = NULL; hlist_for_each_entry(pool, &netdev->page_pools, user.list) { pool->slow.netdev = lo; netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); last = pool; } if (last) hlist_splice_init(&netdev->page_pools, &last->user.list, &lo->page_pools); mutex_unlock(&page_pools_lock); } static int page_pool_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; if (hlist_empty(&netdev->page_pools)) return NOTIFY_OK; if (netdev->ifindex != LOOPBACK_IFINDEX) page_pool_unreg_netdev(netdev); else page_pool_unreg_netdev_wipe(netdev); return NOTIFY_OK; } static struct notifier_block page_pool_netdevice_nb = { .notifier_call = page_pool_netdevice_event, }; static int __init page_pool_user_init(void) { return register_netdevice_notifier(&page_pool_netdevice_nb); } subsys_initcall(page_pool_user_init); |
| 160 201 204 192 280 279 117 3 2 2 201 201 196 188 69 5 56 22 1 23 4 3 112 7 118 279 2 200 201 201 116 116 116 115 116 116 201 4 4 201 201 201 10 201 200 201 201 201 201 201 201 200 204 204 204 204 201 112 201 201 201 201 201 279 269 278 2 116 2 116 118 117 3 118 118 5 112 8 8 280 10 28 270 280 3 280 280 280 279 3 1 280 118 279 4 5 280 202 128 29 271 271 271 270 110 29 28 8 23 280 279 280 3 280 280 29 271 278 117 280 3 271 271 29 29 5 5 5 201 207 124 123 124 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2009 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/sort.h> #include "messages.h" #include "ctree.h" #include "delayed-ref.h" #include "extent-tree.h" #include "transaction.h" #include "qgroup.h" #include "space-info.h" #include "tree-mod-log.h" #include "fs.h" struct kmem_cache *btrfs_delayed_ref_head_cachep; struct kmem_cache *btrfs_delayed_ref_node_cachep; struct kmem_cache *btrfs_delayed_extent_op_cachep; /* * delayed back reference update tracking. For subvolume trees * we queue up extent allocations and backref maintenance for * delayed processing. This avoids deep call chains where we * add extents in the middle of btrfs_search_slot, and it allows * us to buffer up frequently modified backrefs in an rb tree instead * of hammering updates on the extent allocation tree. */ bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info) { struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; bool ret = false; u64 reserved; spin_lock(&global_rsv->lock); reserved = global_rsv->reserved; spin_unlock(&global_rsv->lock); /* * Since the global reserve is just kind of magic we don't really want * to rely on it to save our bacon, so if our size is more than the * delayed_refs_rsv and the global rsv then it's time to think about * bailing. */ spin_lock(&delayed_refs_rsv->lock); reserved += delayed_refs_rsv->reserved; if (delayed_refs_rsv->size >= reserved) ret = true; spin_unlock(&delayed_refs_rsv->lock); return ret; } /* * Release a ref head's reservation. * * @fs_info: the filesystem * @nr_refs: number of delayed refs to drop * @nr_csums: number of csum items to drop * * Drops the delayed ref head's count from the delayed refs rsv and free any * excess reservation we had. */ void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr_refs, int nr_csums) { struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv; u64 num_bytes; u64 released; num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, nr_refs); num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums); released = btrfs_block_rsv_release(fs_info, block_rsv, num_bytes, NULL); if (released) trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, released, 0); } /* * Adjust the size of the delayed refs rsv. * * This is to be called anytime we may have adjusted trans->delayed_ref_updates * or trans->delayed_ref_csum_deletions, it'll calculate the additional size and * add it to the delayed_refs_rsv. */ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv; struct btrfs_block_rsv *local_rsv = &trans->delayed_rsv; u64 num_bytes; u64 reserved_bytes; if (btrfs_is_testing(fs_info)) return; num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, trans->delayed_ref_updates); num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info, trans->delayed_ref_csum_deletions); if (num_bytes == 0) return; /* * Try to take num_bytes from the transaction's local delayed reserve. * If not possible, try to take as much as it's available. If the local * reserve doesn't have enough reserved space, the delayed refs reserve * will be refilled next time btrfs_delayed_refs_rsv_refill() is called * by someone or if a transaction commit is triggered before that, the * global block reserve will be used. We want to minimize using the * global block reserve for cases we can account for in advance, to * avoid exhausting it and reach -ENOSPC during a transaction commit. */ spin_lock(&local_rsv->lock); reserved_bytes = min(num_bytes, local_rsv->reserved); local_rsv->reserved -= reserved_bytes; local_rsv->full = (local_rsv->reserved >= local_rsv->size); spin_unlock(&local_rsv->lock); spin_lock(&delayed_rsv->lock); delayed_rsv->size += num_bytes; delayed_rsv->reserved += reserved_bytes; delayed_rsv->full = (delayed_rsv->reserved >= delayed_rsv->size); spin_unlock(&delayed_rsv->lock); trans->delayed_ref_updates = 0; trans->delayed_ref_csum_deletions = 0; } /* * Adjust the size of the delayed refs block reserve for 1 block group item * insertion, used after allocating a block group. */ void btrfs_inc_delayed_refs_rsv_bg_inserts(struct btrfs_fs_info *fs_info) { struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv; spin_lock(&delayed_rsv->lock); /* * Inserting a block group item does not require changing the free space * tree, only the extent tree or the block group tree, so this is all we * need. */ delayed_rsv->size += btrfs_calc_insert_metadata_size(fs_info, 1); delayed_rsv->full = false; spin_unlock(&delayed_rsv->lock); } /* * Adjust the size of the delayed refs block reserve to release space for 1 * block group item insertion. */ void btrfs_dec_delayed_refs_rsv_bg_inserts(struct btrfs_fs_info *fs_info) { struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv; const u64 num_bytes = btrfs_calc_insert_metadata_size(fs_info, 1); u64 released; released = btrfs_block_rsv_release(fs_info, delayed_rsv, num_bytes, NULL); if (released > 0) trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, released, 0); } /* * Adjust the size of the delayed refs block reserve for 1 block group item * update. */ void btrfs_inc_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info) { struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv; spin_lock(&delayed_rsv->lock); /* * Updating a block group item does not result in new nodes/leaves and * does not require changing the free space tree, only the extent tree * or the block group tree, so this is all we need. */ delayed_rsv->size += btrfs_calc_metadata_size(fs_info, 1); delayed_rsv->full = false; spin_unlock(&delayed_rsv->lock); } /* * Adjust the size of the delayed refs block reserve to release space for 1 * block group item update. */ void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info) { struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv; const u64 num_bytes = btrfs_calc_metadata_size(fs_info, 1); u64 released; released = btrfs_block_rsv_release(fs_info, delayed_rsv, num_bytes, NULL); if (released > 0) trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, released, 0); } /* * Refill based on our delayed refs usage. * * @fs_info: the filesystem * @flush: control how we can flush for this reservation. * * This will refill the delayed block_rsv up to 1 items size worth of space and * will return -ENOSPC if we can't make the reservation. */ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush) { struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv; struct btrfs_space_info *space_info = block_rsv->space_info; u64 limit = btrfs_calc_delayed_ref_bytes(fs_info, 1); u64 num_bytes = 0; u64 refilled_bytes; u64 to_free; int ret = -ENOSPC; spin_lock(&block_rsv->lock); if (block_rsv->reserved < block_rsv->size) { num_bytes = block_rsv->size - block_rsv->reserved; num_bytes = min(num_bytes, limit); } spin_unlock(&block_rsv->lock); if (!num_bytes) return 0; ret = btrfs_reserve_metadata_bytes(fs_info, space_info, num_bytes, flush); if (ret) return ret; /* * We may have raced with someone else, so check again if we the block * reserve is still not full and release any excess space. */ spin_lock(&block_rsv->lock); if (block_rsv->reserved < block_rsv->size) { u64 needed = block_rsv->size - block_rsv->reserved; if (num_bytes >= needed) { block_rsv->reserved += needed; block_rsv->full = true; to_free = num_bytes - needed; refilled_bytes = needed; } else { block_rsv->reserved += num_bytes; to_free = 0; refilled_bytes = num_bytes; } } else { to_free = num_bytes; refilled_bytes = 0; } spin_unlock(&block_rsv->lock); if (to_free > 0) btrfs_space_info_free_bytes_may_use(space_info, to_free); if (refilled_bytes > 0) trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, refilled_bytes, 1); return 0; } /* * compare two delayed data backrefs with same bytenr and type */ static int comp_data_refs(const struct btrfs_delayed_ref_node *ref1, const struct btrfs_delayed_ref_node *ref2) { if (ref1->data_ref.objectid < ref2->data_ref.objectid) return -1; if (ref1->data_ref.objectid > ref2->data_ref.objectid) return 1; if (ref1->data_ref.offset < ref2->data_ref.offset) return -1; if (ref1->data_ref.offset > ref2->data_ref.offset) return 1; return 0; } static int comp_refs(const struct btrfs_delayed_ref_node *ref1, const struct btrfs_delayed_ref_node *ref2, bool check_seq) { int ret = 0; if (ref1->type < ref2->type) return -1; if (ref1->type > ref2->type) return 1; if (ref1->type == BTRFS_SHARED_BLOCK_REF_KEY || ref1->type == BTRFS_SHARED_DATA_REF_KEY) { if (ref1->parent < ref2->parent) return -1; if (ref1->parent > ref2->parent) return 1; } else { if (ref1->ref_root < ref2->ref_root) return -1; if (ref1->ref_root > ref2->ref_root) return 1; if (ref1->type == BTRFS_EXTENT_DATA_REF_KEY) ret = comp_data_refs(ref1, ref2); } if (ret) return ret; if (check_seq) { if (ref1->seq < ref2->seq) return -1; if (ref1->seq > ref2->seq) return 1; } return 0; } static int cmp_refs_node(const struct rb_node *new, const struct rb_node *exist) { const struct btrfs_delayed_ref_node *new_node = rb_entry(new, struct btrfs_delayed_ref_node, ref_node); const struct btrfs_delayed_ref_node *exist_node = rb_entry(exist, struct btrfs_delayed_ref_node, ref_node); return comp_refs(new_node, exist_node, true); } static struct btrfs_delayed_ref_node* tree_insert(struct rb_root_cached *root, struct btrfs_delayed_ref_node *ins) { struct rb_node *node = &ins->ref_node; struct rb_node *exist; exist = rb_find_add_cached(node, root, cmp_refs_node); if (exist) return rb_entry(exist, struct btrfs_delayed_ref_node, ref_node); return NULL; } static struct btrfs_delayed_ref_head *find_first_ref_head( struct btrfs_delayed_ref_root *dr) { unsigned long from = 0; lockdep_assert_held(&dr->lock); return xa_find(&dr->head_refs, &from, ULONG_MAX, XA_PRESENT); } static bool btrfs_delayed_ref_lock(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { lockdep_assert_held(&delayed_refs->lock); if (mutex_trylock(&head->mutex)) return true; refcount_inc(&head->refs); spin_unlock(&delayed_refs->lock); mutex_lock(&head->mutex); spin_lock(&delayed_refs->lock); if (!head->tracked) { mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); return false; } btrfs_put_delayed_ref_head(head); return true; } static inline void drop_delayed_ref(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head, struct btrfs_delayed_ref_node *ref) { lockdep_assert_held(&head->lock); rb_erase_cached(&ref->ref_node, &head->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) list_del(&ref->add_list); btrfs_put_delayed_ref(ref); btrfs_delayed_refs_rsv_release(fs_info, 1, 0); } static bool merge_ref(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head, struct btrfs_delayed_ref_node *ref, u64 seq) { struct btrfs_delayed_ref_node *next; struct rb_node *node = rb_next(&ref->ref_node); bool done = false; while (!done && node) { int mod; next = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); node = rb_next(node); if (seq && next->seq >= seq) break; if (comp_refs(ref, next, false)) break; if (ref->action == next->action) { mod = next->ref_mod; } else { if (ref->ref_mod < next->ref_mod) { swap(ref, next); done = true; } mod = -next->ref_mod; } drop_delayed_ref(fs_info, delayed_refs, head, next); ref->ref_mod += mod; if (ref->ref_mod == 0) { drop_delayed_ref(fs_info, delayed_refs, head, ref); done = true; } else { /* * Can't have multiples of the same ref on a tree block. */ WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY || ref->type == BTRFS_SHARED_BLOCK_REF_KEY); } } return done; } void btrfs_merge_delayed_refs(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { struct btrfs_delayed_ref_node *ref; struct rb_node *node; u64 seq = 0; lockdep_assert_held(&head->lock); if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) return; /* We don't have too many refs to merge for data. */ if (head->is_data) return; seq = btrfs_tree_mod_log_lowest_seq(fs_info); again: for (node = rb_first_cached(&head->ref_tree); node; node = rb_next(node)) { ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); if (seq && ref->seq >= seq) continue; if (merge_ref(fs_info, delayed_refs, head, ref, seq)) goto again; } } int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq) { int ret = 0; u64 min_seq = btrfs_tree_mod_log_lowest_seq(fs_info); if (min_seq != 0 && seq >= min_seq) { btrfs_debug(fs_info, "holding back delayed_ref %llu, lowest is %llu", seq, min_seq); ret = 1; } return ret; } struct btrfs_delayed_ref_head *btrfs_select_ref_head( const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs) { struct btrfs_delayed_ref_head *head; unsigned long start_index; unsigned long found_index; bool found_head = false; bool locked; spin_lock(&delayed_refs->lock); again: start_index = (delayed_refs->run_delayed_start >> fs_info->sectorsize_bits); xa_for_each_start(&delayed_refs->head_refs, found_index, head, start_index) { if (!head->processing) { found_head = true; break; } } if (!found_head) { if (delayed_refs->run_delayed_start == 0) { spin_unlock(&delayed_refs->lock); return NULL; } delayed_refs->run_delayed_start = 0; goto again; } head->processing = true; WARN_ON(delayed_refs->num_heads_ready == 0); delayed_refs->num_heads_ready--; delayed_refs->run_delayed_start = head->bytenr + head->num_bytes; locked = btrfs_delayed_ref_lock(delayed_refs, head); spin_unlock(&delayed_refs->lock); /* * We may have dropped the spin lock to get the head mutex lock, and * that might have given someone else time to free the head. If that's * true, it has been removed from our list and we can move on. */ if (!locked) return ERR_PTR(-EAGAIN); return head; } void btrfs_unselect_ref_head(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { spin_lock(&delayed_refs->lock); head->processing = false; delayed_refs->num_heads_ready++; spin_unlock(&delayed_refs->lock); btrfs_delayed_ref_unlock(head); } void btrfs_delete_ref_head(const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { const unsigned long index = (head->bytenr >> fs_info->sectorsize_bits); lockdep_assert_held(&delayed_refs->lock); lockdep_assert_held(&head->lock); xa_erase(&delayed_refs->head_refs, index); head->tracked = false; delayed_refs->num_heads--; if (!head->processing) delayed_refs->num_heads_ready--; } struct btrfs_delayed_ref_node *btrfs_select_delayed_ref(struct btrfs_delayed_ref_head *head) { struct btrfs_delayed_ref_node *ref; lockdep_assert_held(&head->mutex); lockdep_assert_held(&head->lock); if (RB_EMPTY_ROOT(&head->ref_tree.rb_root)) return NULL; /* * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first. * This is to prevent a ref count from going down to zero, which deletes * the extent item from the extent tree, when there still are references * to add, which would fail because they would not find the extent item. */ if (!list_empty(&head->ref_add_list)) return list_first_entry(&head->ref_add_list, struct btrfs_delayed_ref_node, add_list); ref = rb_entry(rb_first_cached(&head->ref_tree), struct btrfs_delayed_ref_node, ref_node); ASSERT(list_empty(&ref->add_list)); return ref; } /* * Helper to insert the ref_node to the tail or merge with tail. * * Return false if the ref was inserted. * Return true if the ref was merged into an existing one (and therefore can be * freed by the caller). */ static bool insert_delayed_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, struct btrfs_delayed_ref_node *ref) { struct btrfs_delayed_ref_root *root = &trans->transaction->delayed_refs; struct btrfs_delayed_ref_node *exist; int mod; spin_lock(&href->lock); exist = tree_insert(&href->ref_tree, ref); if (!exist) { if (ref->action == BTRFS_ADD_DELAYED_REF) list_add_tail(&ref->add_list, &href->ref_add_list); spin_unlock(&href->lock); trans->delayed_ref_updates++; return false; } /* Now we are sure we can merge */ if (exist->action == ref->action) { mod = ref->ref_mod; } else { /* Need to change action */ if (exist->ref_mod < ref->ref_mod) { exist->action = ref->action; mod = -exist->ref_mod; exist->ref_mod = ref->ref_mod; if (ref->action == BTRFS_ADD_DELAYED_REF) list_add_tail(&exist->add_list, &href->ref_add_list); else if (ref->action == BTRFS_DROP_DELAYED_REF) { ASSERT(!list_empty(&exist->add_list)); list_del_init(&exist->add_list); } else { ASSERT(0); } } else mod = -ref->ref_mod; } exist->ref_mod += mod; /* remove existing tail if its ref_mod is zero */ if (exist->ref_mod == 0) drop_delayed_ref(trans->fs_info, root, href, exist); spin_unlock(&href->lock); return true; } /* * helper function to update the accounting in the head ref * existing and update must have the same bytenr */ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *existing, struct btrfs_delayed_ref_head *update) { struct btrfs_delayed_ref_root *delayed_refs = &trans->transaction->delayed_refs; struct btrfs_fs_info *fs_info = trans->fs_info; int old_ref_mod; BUG_ON(existing->is_data != update->is_data); spin_lock(&existing->lock); /* * When freeing an extent, we may not know the owning root when we * first create the head_ref. However, some deref before the last deref * will know it, so we just need to update the head_ref accordingly. */ if (!existing->owning_root) existing->owning_root = update->owning_root; if (update->must_insert_reserved) { /* if the extent was freed and then * reallocated before the delayed ref * entries were processed, we can end up * with an existing head ref without * the must_insert_reserved flag set. * Set it again here */ existing->must_insert_reserved = update->must_insert_reserved; existing->owning_root = update->owning_root; /* * update the num_bytes so we make sure the accounting * is done correctly */ existing->num_bytes = update->num_bytes; } if (update->extent_op) { if (!existing->extent_op) { existing->extent_op = update->extent_op; } else { if (update->extent_op->update_key) { memcpy(&existing->extent_op->key, &update->extent_op->key, sizeof(update->extent_op->key)); existing->extent_op->update_key = true; } if (update->extent_op->update_flags) { existing->extent_op->flags_to_set |= update->extent_op->flags_to_set; existing->extent_op->update_flags = true; } btrfs_free_delayed_extent_op(update->extent_op); } } /* * update the reference mod on the head to reflect this new operation, * only need the lock for this case cause we could be processing it * currently, for refs we just added we know we're a-ok. */ old_ref_mod = existing->total_ref_mod; existing->ref_mod += update->ref_mod; existing->total_ref_mod += update->ref_mod; /* * If we are going to from a positive ref mod to a negative or vice * versa we need to make sure to adjust pending_csums accordingly. * We reserve bytes for csum deletion when adding or updating a ref head * see add_delayed_ref_head() for more details. */ if (existing->is_data) { u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, existing->num_bytes); if (existing->total_ref_mod >= 0 && old_ref_mod < 0) { delayed_refs->pending_csums -= existing->num_bytes; btrfs_delayed_refs_rsv_release(fs_info, 0, csum_leaves); } if (existing->total_ref_mod < 0 && old_ref_mod >= 0) { delayed_refs->pending_csums += existing->num_bytes; trans->delayed_ref_csum_deletions += csum_leaves; } } spin_unlock(&existing->lock); } static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref, struct btrfs_ref *generic_ref, struct btrfs_qgroup_extent_record *qrecord, u64 reserved) { int count_mod = 1; bool must_insert_reserved = false; /* If reserved is provided, it must be a data extent. */ BUG_ON(generic_ref->type != BTRFS_REF_DATA && reserved); switch (generic_ref->action) { case BTRFS_ADD_DELAYED_REF: /* count_mod is already set to 1. */ break; case BTRFS_UPDATE_DELAYED_HEAD: count_mod = 0; break; case BTRFS_DROP_DELAYED_REF: /* * The head node stores the sum of all the mods, so dropping a ref * should drop the sum in the head node by one. */ count_mod = -1; break; case BTRFS_ADD_DELAYED_EXTENT: /* * BTRFS_ADD_DELAYED_EXTENT means that we need to update the * reserved accounting when the extent is finally added, or if a * later modification deletes the delayed ref without ever * inserting the extent into the extent allocation tree. * ref->must_insert_reserved is the flag used to record that * accounting mods are required. * * Once we record must_insert_reserved, switch the action to * BTRFS_ADD_DELAYED_REF because other special casing is not * required. */ must_insert_reserved = true; break; } refcount_set(&head_ref->refs, 1); head_ref->bytenr = generic_ref->bytenr; head_ref->num_bytes = generic_ref->num_bytes; head_ref->ref_mod = count_mod; head_ref->reserved_bytes = reserved; head_ref->must_insert_reserved = must_insert_reserved; head_ref->owning_root = generic_ref->owning_root; head_ref->is_data = (generic_ref->type == BTRFS_REF_DATA); head_ref->is_system = (generic_ref->ref_root == BTRFS_CHUNK_TREE_OBJECTID); head_ref->ref_tree = RB_ROOT_CACHED; INIT_LIST_HEAD(&head_ref->ref_add_list); head_ref->tracked = false; head_ref->processing = false; head_ref->total_ref_mod = count_mod; spin_lock_init(&head_ref->lock); mutex_init(&head_ref->mutex); /* If not metadata set an impossible level to help debugging. */ if (generic_ref->type == BTRFS_REF_METADATA) head_ref->level = generic_ref->tree_ref.level; else head_ref->level = U8_MAX; if (qrecord) { if (generic_ref->ref_root && reserved) { qrecord->data_rsv = reserved; qrecord->data_rsv_refroot = generic_ref->ref_root; } qrecord->num_bytes = generic_ref->num_bytes; qrecord->old_roots = NULL; } } /* * helper function to actually insert a head node into the rbtree. * this does all the dirty work in terms of maintaining the correct * overall modification count. * * Returns an error pointer in case of an error. */ static noinline struct btrfs_delayed_ref_head * add_delayed_ref_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head_ref, struct btrfs_qgroup_extent_record *qrecord, int action, bool *qrecord_inserted_ret) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_root *delayed_refs; const unsigned long index = (head_ref->bytenr >> fs_info->sectorsize_bits); bool qrecord_inserted = false; delayed_refs = &trans->transaction->delayed_refs; lockdep_assert_held(&delayed_refs->lock); #if BITS_PER_LONG == 32 if (head_ref->bytenr >= MAX_LFS_FILESIZE) { if (qrecord) xa_release(&delayed_refs->dirty_extents, index); btrfs_err_rl(fs_info, "delayed ref head %llu is beyond 32bit page cache and xarray index limit", head_ref->bytenr); btrfs_err_32bit_limit(fs_info); return ERR_PTR(-EOVERFLOW); } #endif /* Record qgroup extent info if provided */ if (qrecord) { int ret; ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, qrecord, head_ref->bytenr); if (ret) { /* Clean up if insertion fails or item exists. */ xa_release(&delayed_refs->dirty_extents, index); /* Caller responsible for freeing qrecord on error. */ if (ret < 0) return ERR_PTR(ret); kfree(qrecord); } else { qrecord_inserted = true; } } trace_add_delayed_ref_head(fs_info, head_ref, action); existing = xa_load(&delayed_refs->head_refs, index); if (existing) { update_existing_head_ref(trans, existing, head_ref); /* * we've updated the existing ref, free the newly * allocated ref */ kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); head_ref = existing; } else { existing = xa_store(&delayed_refs->head_refs, index, head_ref, GFP_ATOMIC); if (xa_is_err(existing)) { /* Memory was preallocated by the caller. */ ASSERT(xa_err(existing) != -ENOMEM); return ERR_PTR(xa_err(existing)); } else if (WARN_ON(existing)) { /* * Shouldn't happen we just did a lookup before under * delayed_refs->lock. */ return ERR_PTR(-EEXIST); } head_ref->tracked = true; /* * We reserve the amount of bytes needed to delete csums when * adding the ref head and not when adding individual drop refs * since the csum items are deleted only after running the last * delayed drop ref (the data extent's ref count drops to 0). */ if (head_ref->is_data && head_ref->ref_mod < 0) { delayed_refs->pending_csums += head_ref->num_bytes; trans->delayed_ref_csum_deletions += btrfs_csum_bytes_to_leaves(fs_info, head_ref->num_bytes); } delayed_refs->num_heads++; delayed_refs->num_heads_ready++; } if (qrecord_inserted_ret) *qrecord_inserted_ret = qrecord_inserted; return head_ref; } /* * Initialize the structure which represents a modification to a an extent. * * @fs_info: Internal to the mounted filesystem mount structure. * * @ref: The structure which is going to be initialized. * * @bytenr: The logical address of the extent for which a modification is * going to be recorded. * * @num_bytes: Size of the extent whose modification is being recorded. * * @ref_root: The id of the root where this modification has originated, this * can be either one of the well-known metadata trees or the * subvolume id which references this extent. * * @action: Can be one of BTRFS_ADD_DELAYED_REF/BTRFS_DROP_DELAYED_REF or * BTRFS_ADD_DELAYED_EXTENT * * @ref_type: Holds the type of the extent which is being recorded, can be * one of BTRFS_SHARED_BLOCK_REF_KEY/BTRFS_TREE_BLOCK_REF_KEY * when recording a metadata extent or BTRFS_SHARED_DATA_REF_KEY/ * BTRFS_EXTENT_DATA_REF_KEY when recording data extent */ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_node *ref, struct btrfs_ref *generic_ref) { int action = generic_ref->action; u64 seq = 0; if (action == BTRFS_ADD_DELAYED_EXTENT) action = BTRFS_ADD_DELAYED_REF; if (is_fstree(generic_ref->ref_root)) seq = atomic64_read(&fs_info->tree_mod_seq); refcount_set(&ref->refs, 1); ref->bytenr = generic_ref->bytenr; ref->num_bytes = generic_ref->num_bytes; ref->ref_mod = 1; ref->action = action; ref->seq = seq; ref->type = btrfs_ref_type(generic_ref); ref->ref_root = generic_ref->ref_root; ref->parent = generic_ref->parent; RB_CLEAR_NODE(&ref->ref_node); INIT_LIST_HEAD(&ref->add_list); if (generic_ref->type == BTRFS_REF_DATA) ref->data_ref = generic_ref->data_ref; else ref->tree_ref = generic_ref->tree_ref; } void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 mod_root, bool skip_qgroup) { #ifdef CONFIG_BTRFS_FS_REF_VERIFY /* If @real_root not set, use @root as fallback */ generic_ref->real_root = mod_root ?: generic_ref->ref_root; #endif generic_ref->tree_ref.level = level; generic_ref->type = BTRFS_REF_METADATA; if (skip_qgroup || !(is_fstree(generic_ref->ref_root) && (!mod_root || is_fstree(mod_root)))) generic_ref->skip_qgroup = true; else generic_ref->skip_qgroup = false; } void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ino, u64 offset, u64 mod_root, bool skip_qgroup) { #ifdef CONFIG_BTRFS_FS_REF_VERIFY /* If @real_root not set, use @root as fallback */ generic_ref->real_root = mod_root ?: generic_ref->ref_root; #endif generic_ref->data_ref.objectid = ino; generic_ref->data_ref.offset = offset; generic_ref->type = BTRFS_REF_DATA; if (skip_qgroup || !(is_fstree(generic_ref->ref_root) && (!mod_root || is_fstree(mod_root)))) generic_ref->skip_qgroup = true; else generic_ref->skip_qgroup = false; } static int add_delayed_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, struct btrfs_delayed_extent_op *extent_op, u64 reserved) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_node *node; struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_head *new_head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; const unsigned long index = (generic_ref->bytenr >> fs_info->sectorsize_bits); bool qrecord_reserved = false; bool qrecord_inserted; int action = generic_ref->action; bool merged; int ret; node = kmem_cache_alloc(btrfs_delayed_ref_node_cachep, GFP_NOFS); if (!node) return -ENOMEM; head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS); if (!head_ref) { ret = -ENOMEM; goto free_node; } delayed_refs = &trans->transaction->delayed_refs; if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) { record = kzalloc(sizeof(*record), GFP_NOFS); if (!record) { ret = -ENOMEM; goto free_head_ref; } if (xa_reserve(&delayed_refs->dirty_extents, index, GFP_NOFS)) { ret = -ENOMEM; goto free_record; } qrecord_reserved = true; } ret = xa_reserve(&delayed_refs->head_refs, index, GFP_NOFS); if (ret) { if (qrecord_reserved) xa_release(&delayed_refs->dirty_extents, index); goto free_record; } init_delayed_ref_common(fs_info, node, generic_ref); init_delayed_ref_head(head_ref, generic_ref, record, reserved); head_ref->extent_op = extent_op; spin_lock(&delayed_refs->lock); /* * insert both the head node and the new ref without dropping * the spin lock */ new_head_ref = add_delayed_ref_head(trans, head_ref, record, action, &qrecord_inserted); if (IS_ERR(new_head_ref)) { xa_release(&delayed_refs->head_refs, index); spin_unlock(&delayed_refs->lock); ret = PTR_ERR(new_head_ref); goto free_record; } head_ref = new_head_ref; merged = insert_delayed_ref(trans, head_ref, node); spin_unlock(&delayed_refs->lock); /* * Need to update the delayed_refs_rsv with any changes we may have * made. */ btrfs_update_delayed_refs_rsv(trans); if (generic_ref->type == BTRFS_REF_DATA) trace_add_delayed_data_ref(trans->fs_info, node); else trace_add_delayed_tree_ref(trans->fs_info, node); if (merged) kmem_cache_free(btrfs_delayed_ref_node_cachep, node); if (qrecord_inserted) return btrfs_qgroup_trace_extent_post(trans, record, generic_ref->bytenr); return 0; free_record: kfree(record); free_head_ref: kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); free_node: kmem_cache_free(btrfs_delayed_ref_node_cachep, node); return ret; } /* * Add a delayed tree ref. This does all of the accounting required to make sure * the delayed ref is eventually processed before this transaction commits. */ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, struct btrfs_delayed_extent_op *extent_op) { ASSERT(generic_ref->type == BTRFS_REF_METADATA && generic_ref->action); return add_delayed_ref(trans, generic_ref, extent_op, 0); } /* * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref. */ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, u64 reserved) { ASSERT(generic_ref->type == BTRFS_REF_DATA && generic_ref->action); return add_delayed_ref(trans, generic_ref, NULL, reserved); } int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u8 level, struct btrfs_delayed_extent_op *extent_op) { const unsigned long index = (bytenr >> trans->fs_info->sectorsize_bits); struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_head *head_ref_ret; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_ref generic_ref = { .type = BTRFS_REF_METADATA, .action = BTRFS_UPDATE_DELAYED_HEAD, .bytenr = bytenr, .num_bytes = num_bytes, .tree_ref.level = level, }; int ret; head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS); if (!head_ref) return -ENOMEM; init_delayed_ref_head(head_ref, &generic_ref, NULL, 0); head_ref->extent_op = extent_op; delayed_refs = &trans->transaction->delayed_refs; ret = xa_reserve(&delayed_refs->head_refs, index, GFP_NOFS); if (ret) { kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); return ret; } spin_lock(&delayed_refs->lock); head_ref_ret = add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD, NULL); if (IS_ERR(head_ref_ret)) { xa_release(&delayed_refs->head_refs, index); spin_unlock(&delayed_refs->lock); kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); return PTR_ERR(head_ref_ret); } spin_unlock(&delayed_refs->lock); /* * Need to update the delayed_refs_rsv with any changes we may have * made. */ btrfs_update_delayed_refs_rsv(trans); return 0; } void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref) { if (refcount_dec_and_test(&ref->refs)) { WARN_ON(!RB_EMPTY_NODE(&ref->ref_node)); kmem_cache_free(btrfs_delayed_ref_node_cachep, ref); } } /* * This does a simple search for the head node for a given extent. Returns the * head node if found, or NULL if not. */ struct btrfs_delayed_ref_head * btrfs_find_delayed_ref_head(const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, u64 bytenr) { const unsigned long index = (bytenr >> fs_info->sectorsize_bits); lockdep_assert_held(&delayed_refs->lock); return xa_load(&delayed_refs->head_refs, index); } static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent) { int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY; if (type < entry->type) return -1; if (type > entry->type) return 1; if (type == BTRFS_TREE_BLOCK_REF_KEY) { if (root < entry->ref_root) return -1; if (root > entry->ref_root) return 1; } else { if (parent < entry->parent) return -1; if (parent > entry->parent) return 1; } return 0; } /* * Check to see if a given root/parent reference is attached to the head. This * only checks for BTRFS_ADD_DELAYED_REF references that match, as that * indicates the reference exists for the given root or parent. This is for * tree blocks only. * * @head: the head of the bytenr we're searching. * @root: the root objectid of the reference if it is a normal reference. * @parent: the parent if this is a shared backref. */ bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, u64 root, u64 parent) { struct rb_node *node; bool found = false; lockdep_assert_held(&head->mutex); spin_lock(&head->lock); node = head->ref_tree.rb_root.rb_node; while (node) { struct btrfs_delayed_ref_node *entry; int ret; entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); ret = find_comp(entry, root, parent); if (ret < 0) { node = node->rb_left; } else if (ret > 0) { node = node->rb_right; } else { /* * We only want to count ADD actions, as drops mean the * ref doesn't exist. */ if (entry->action == BTRFS_ADD_DELAYED_REF) found = true; break; } } spin_unlock(&head->lock); return found; } void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans) { struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs; struct btrfs_fs_info *fs_info = trans->fs_info; bool testing = btrfs_is_testing(fs_info); spin_lock(&delayed_refs->lock); while (true) { struct btrfs_delayed_ref_head *head; struct rb_node *n; bool pin_bytes = false; head = find_first_ref_head(delayed_refs); if (!head) break; if (!btrfs_delayed_ref_lock(delayed_refs, head)) continue; spin_lock(&head->lock); while ((n = rb_first_cached(&head->ref_tree)) != NULL) { struct btrfs_delayed_ref_node *ref; ref = rb_entry(n, struct btrfs_delayed_ref_node, ref_node); drop_delayed_ref(fs_info, delayed_refs, head, ref); } if (head->must_insert_reserved) pin_bytes = true; btrfs_free_delayed_extent_op(head->extent_op); btrfs_delete_ref_head(fs_info, delayed_refs, head); spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); mutex_unlock(&head->mutex); if (!testing && pin_bytes) { struct btrfs_block_group *bg; bg = btrfs_lookup_block_group(fs_info, head->bytenr); if (WARN_ON_ONCE(bg == NULL)) { /* * Unexpected and there's nothing we can do here * because we are in a transaction abort path, * so any errors can only be ignored or reported * while attempting to cleanup all resources. */ btrfs_err(fs_info, "block group for delayed ref at %llu was not found while destroying ref head", head->bytenr); } else { spin_lock(&bg->space_info->lock); spin_lock(&bg->lock); bg->pinned += head->num_bytes; btrfs_space_info_update_bytes_pinned(bg->space_info, head->num_bytes); bg->reserved -= head->num_bytes; bg->space_info->bytes_reserved -= head->num_bytes; spin_unlock(&bg->lock); spin_unlock(&bg->space_info->lock); btrfs_put_block_group(bg); } btrfs_error_unpin_extent_range(fs_info, head->bytenr, head->bytenr + head->num_bytes - 1); } if (!testing) btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); btrfs_put_delayed_ref_head(head); cond_resched(); spin_lock(&delayed_refs->lock); } if (!testing) btrfs_qgroup_destroy_extent_records(trans); spin_unlock(&delayed_refs->lock); } void __cold btrfs_delayed_ref_exit(void) { kmem_cache_destroy(btrfs_delayed_ref_head_cachep); kmem_cache_destroy(btrfs_delayed_ref_node_cachep); kmem_cache_destroy(btrfs_delayed_extent_op_cachep); } int __init btrfs_delayed_ref_init(void) { btrfs_delayed_ref_head_cachep = KMEM_CACHE(btrfs_delayed_ref_head, 0); if (!btrfs_delayed_ref_head_cachep) goto fail; btrfs_delayed_ref_node_cachep = KMEM_CACHE(btrfs_delayed_ref_node, 0); if (!btrfs_delayed_ref_node_cachep) goto fail; btrfs_delayed_extent_op_cachep = KMEM_CACHE(btrfs_delayed_extent_op, 0); if (!btrfs_delayed_extent_op_cachep) goto fail; return 0; fail: btrfs_delayed_ref_exit(); return -ENOMEM; } |
| 2 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. * * This file contains power management functions related to interrupts. */ #include <linux/irq.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> #include "internals.h" bool irq_pm_check_wakeup(struct irq_desc *desc) { if (irqd_is_wakeup_armed(&desc->irq_data)) { irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED); desc->istate |= IRQS_SUSPENDED | IRQS_PENDING; desc->depth++; irq_disable(desc); pm_system_irq_wakeup(irq_desc_get_irq(desc)); return true; } return false; } /* * Called from __setup_irq() with desc->lock held after @action has * been installed in the action chain. */ void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { desc->nr_actions++; if (action->flags & IRQF_FORCE_RESUME) desc->force_resume_depth++; WARN_ON_ONCE(desc->force_resume_depth && desc->force_resume_depth != desc->nr_actions); if (action->flags & IRQF_NO_SUSPEND) desc->no_suspend_depth++; else if (action->flags & IRQF_COND_SUSPEND) desc->cond_suspend_depth++; WARN_ON_ONCE(desc->no_suspend_depth && (desc->no_suspend_depth + desc->cond_suspend_depth) != desc->nr_actions); } /* * Called from __free_irq() with desc->lock held after @action has * been removed from the action chain. */ void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { desc->nr_actions--; if (action->flags & IRQF_FORCE_RESUME) desc->force_resume_depth--; if (action->flags & IRQF_NO_SUSPEND) desc->no_suspend_depth--; else if (action->flags & IRQF_COND_SUSPEND) desc->cond_suspend_depth--; } static bool suspend_device_irq(struct irq_desc *desc) { unsigned long chipflags = irq_desc_get_chip(desc)->flags; struct irq_data *irqd = &desc->irq_data; if (!desc->action || irq_desc_is_chained(desc) || desc->no_suspend_depth) return false; if (irqd_is_wakeup_set(irqd)) { irqd_set(irqd, IRQD_WAKEUP_ARMED); if ((chipflags & IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND) && irqd_irq_disabled(irqd)) { /* * Interrupt marked for wakeup is in disabled state. * Enable interrupt here to unmask/enable in irqchip * to be able to resume with such interrupts. */ __enable_irq(desc); irqd_set(irqd, IRQD_IRQ_ENABLED_ON_SUSPEND); } /* * We return true here to force the caller to issue * synchronize_irq(). We need to make sure that the * IRQD_WAKEUP_ARMED is visible before we return from * suspend_device_irqs(). */ return true; } desc->istate |= IRQS_SUSPENDED; __disable_irq(desc); /* * Hardware which has no wakeup source configuration facility * requires that the non wakeup interrupts are masked at the * chip level. The chip implementation indicates that with * IRQCHIP_MASK_ON_SUSPEND. */ if (chipflags & IRQCHIP_MASK_ON_SUSPEND) mask_irq(desc); return true; } /** * suspend_device_irqs - disable all currently enabled interrupt lines * * During system-wide suspend or hibernation device drivers need to be * prevented from receiving interrupts and this function is provided * for this purpose. * * So we disable all interrupts and mark them IRQS_SUSPENDED except * for those which are unused, those which are marked as not * suspendable via an interrupt request with the flag IRQF_NO_SUSPEND * set and those which are marked as active wakeup sources. * * The active wakeup sources are handled by the flow handler entry * code which checks for the IRQD_WAKEUP_ARMED flag, suspends the * interrupt and notifies the pm core about the wakeup. */ void suspend_device_irqs(void) { struct irq_desc *desc; int irq; for_each_irq_desc(irq, desc) { unsigned long flags; bool sync; if (irq_settings_is_nested_thread(desc)) continue; raw_spin_lock_irqsave(&desc->lock, flags); sync = suspend_device_irq(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); if (sync) synchronize_irq(irq); } } static void resume_irq(struct irq_desc *desc) { struct irq_data *irqd = &desc->irq_data; irqd_clear(irqd, IRQD_WAKEUP_ARMED); if (irqd_is_enabled_on_suspend(irqd)) { /* * Interrupt marked for wakeup was enabled during suspend * entry. Disable such interrupts to restore them back to * original state. */ __disable_irq(desc); irqd_clear(irqd, IRQD_IRQ_ENABLED_ON_SUSPEND); } if (desc->istate & IRQS_SUSPENDED) goto resume; /* Force resume the interrupt? */ if (!desc->force_resume_depth) return; /* Pretend that it got disabled ! */ desc->depth++; irq_state_set_disabled(desc); irq_state_set_masked(desc); resume: desc->istate &= ~IRQS_SUSPENDED; __enable_irq(desc); } static void resume_irqs(bool want_early) { struct irq_desc *desc; int irq; for_each_irq_desc(irq, desc) { unsigned long flags; bool is_early = desc->action && desc->action->flags & IRQF_EARLY_RESUME; if (!is_early && want_early) continue; if (irq_settings_is_nested_thread(desc)) continue; raw_spin_lock_irqsave(&desc->lock, flags); resume_irq(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); } } /** * rearm_wake_irq - rearm a wakeup interrupt line after signaling wakeup * @irq: Interrupt to rearm */ void rearm_wake_irq(unsigned int irq) { unsigned long flags; struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); if (!desc) return; if (!(desc->istate & IRQS_SUSPENDED) || !irqd_is_wakeup_set(&desc->irq_data)) goto unlock; desc->istate &= ~IRQS_SUSPENDED; irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED); __enable_irq(desc); unlock: irq_put_desc_busunlock(desc, flags); } /** * irq_pm_syscore_resume - enable interrupt lines early * * Enable all interrupt lines with %IRQF_EARLY_RESUME set. */ static void irq_pm_syscore_resume(void) { resume_irqs(true); } static struct syscore_ops irq_pm_syscore_ops = { .resume = irq_pm_syscore_resume, }; static int __init irq_pm_init_ops(void) { register_syscore_ops(&irq_pm_syscore_ops); return 0; } device_initcall(irq_pm_init_ops); /** * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs() * * Enable all non-%IRQF_EARLY_RESUME interrupt lines previously * disabled by suspend_device_irqs() that have the IRQS_SUSPENDED flag * set as well as those with %IRQF_FORCE_RESUME. */ void resume_device_irqs(void) { resume_irqs(false); } |
| 24 7 1 1 6 1 6 3 3 6 5 3 3 3 3 6 3 3 3 3 3 3 3 2 6 6 3 3 6 6 6 1 1 1 6 1 4 4 4 4 4 6 6 6 6 16 17 17 17 1 15 1 1 2 13 2 1 3 2 4 3 5 3 17 17 1 10 4 1 6 6 6 2 4 13 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 | // SPDX-License-Identifier: LGPL-2.1 /* * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd. * Written by Takashi Sato <t-sato@yk.jp.nec.com> * Akira Fujita <a-fujita@rs.jp.nec.com> */ #include <linux/fs.h> #include <linux/quotaops.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4.h" #include "ext4_extents.h" /** * get_ext_path() - Find an extent path for designated logical block number. * @inode: inode to be searched * @lblock: logical block number to find an extent path * @path: pointer to an extent path * * ext4_find_extent wrapper. Return an extent path pointer on success, * or an error pointer on failure. */ static inline struct ext4_ext_path * get_ext_path(struct inode *inode, ext4_lblk_t lblock, struct ext4_ext_path *path) { path = ext4_find_extent(inode, lblock, path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return path; if (path[ext_depth(inode)].p_ext == NULL) { ext4_free_ext_path(path); return ERR_PTR(-ENODATA); } return path; } /** * ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem * @first: inode to be locked * @second: inode to be locked * * Acquire write lock of i_data_sem of the two inodes */ void ext4_double_down_write_data_sem(struct inode *first, struct inode *second) { if (first < second) { down_write(&EXT4_I(first)->i_data_sem); down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER); } else { down_write(&EXT4_I(second)->i_data_sem); down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER); } } /** * ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem * * @orig_inode: original inode structure to be released its lock first * @donor_inode: donor inode structure to be released its lock second * Release write lock of i_data_sem of two inodes (orig and donor). */ void ext4_double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) { up_write(&EXT4_I(orig_inode)->i_data_sem); up_write(&EXT4_I(donor_inode)->i_data_sem); } /** * mext_check_coverage - Check that all extents in range has the same type * * @inode: inode in question * @from: block offset of inode * @count: block count to be checked * @unwritten: extents expected to be unwritten * @err: pointer to save error value * * Return 1 if all extents in range has expected type, and zero otherwise. */ static int mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count, int unwritten, int *err) { struct ext4_ext_path *path = NULL; struct ext4_extent *ext; int ret = 0; ext4_lblk_t last = from + count; while (from < last) { path = get_ext_path(inode, from, path); if (IS_ERR(path)) { *err = PTR_ERR(path); return ret; } ext = path[ext_depth(inode)].p_ext; if (unwritten != ext4_ext_is_unwritten(ext)) goto out; from += ext4_ext_get_actual_len(ext); } ret = 1; out: ext4_free_ext_path(path); return ret; } /** * mext_folio_double_lock - Grab and lock folio on both @inode1 and @inode2 * * @inode1: the inode structure * @inode2: the inode structure * @index1: folio index * @index2: folio index * @folio: result folio vector * * Grab two locked folio for inode's by inode order */ static int mext_folio_double_lock(struct inode *inode1, struct inode *inode2, pgoff_t index1, pgoff_t index2, struct folio *folio[2]) { struct address_space *mapping[2]; unsigned int flags; BUG_ON(!inode1 || !inode2); if (inode1 < inode2) { mapping[0] = inode1->i_mapping; mapping[1] = inode2->i_mapping; } else { swap(index1, index2); mapping[0] = inode2->i_mapping; mapping[1] = inode1->i_mapping; } flags = memalloc_nofs_save(); folio[0] = __filemap_get_folio(mapping[0], index1, FGP_WRITEBEGIN, mapping_gfp_mask(mapping[0])); if (IS_ERR(folio[0])) { memalloc_nofs_restore(flags); return PTR_ERR(folio[0]); } folio[1] = __filemap_get_folio(mapping[1], index2, FGP_WRITEBEGIN, mapping_gfp_mask(mapping[1])); memalloc_nofs_restore(flags); if (IS_ERR(folio[1])) { folio_unlock(folio[0]); folio_put(folio[0]); return PTR_ERR(folio[1]); } /* * __filemap_get_folio() may not wait on folio's writeback if * BDI not demand that. But it is reasonable to be very conservative * here and explicitly wait on folio's writeback */ folio_wait_writeback(folio[0]); folio_wait_writeback(folio[1]); if (inode1 > inode2) swap(folio[0], folio[1]); return 0; } /* Force folio buffers uptodate w/o dropping folio's lock */ static int mext_page_mkuptodate(struct folio *folio, size_t from, size_t to) { struct inode *inode = folio->mapping->host; sector_t block; struct buffer_head *bh, *head; unsigned int blocksize, block_start, block_end; int nr = 0; bool partial = false; BUG_ON(!folio_test_locked(folio)); BUG_ON(folio_test_writeback(folio)); if (folio_test_uptodate(folio)) return 0; blocksize = i_blocksize(inode); head = folio_buffers(folio); if (!head) head = create_empty_buffers(folio, blocksize, 0); block = folio_pos(folio) >> inode->i_blkbits; block_end = 0; bh = head; do { block_start = block_end; block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = true; continue; } if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = ext4_get_block(inode, block, bh, 0); if (err) return err; if (!buffer_mapped(bh)) { folio_zero_range(folio, block_start, blocksize); set_buffer_uptodate(bh); continue; } } lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } ext4_read_bh_nowait(bh, 0, NULL, false); nr++; } while (block++, (bh = bh->b_this_page) != head); /* No io required */ if (!nr) goto out; bh = head; do { if (bh_offset(bh) + blocksize <= from) continue; if (bh_offset(bh) > to) break; wait_on_buffer(bh); if (buffer_uptodate(bh)) continue; return -EIO; } while ((bh = bh->b_this_page) != head); out: if (!partial) folio_mark_uptodate(folio); return 0; } /** * move_extent_per_page - Move extent data per page * * @o_filp: file structure of original file * @donor_inode: donor inode * @orig_page_offset: page index on original file * @donor_page_offset: page index on donor file * @data_offset_in_page: block index where data swapping starts * @block_len_in_page: the number of blocks to be swapped * @unwritten: orig extent is unwritten or not * @err: pointer to save return value * * Save the data in original inode blocks and replace original inode extents * with donor inode extents by calling ext4_swap_extents(). * Finally, write out the saved data in new original inode blocks. Return * replaced block count. */ static int move_extent_per_page(struct file *o_filp, struct inode *donor_inode, pgoff_t orig_page_offset, pgoff_t donor_page_offset, int data_offset_in_page, int block_len_in_page, int unwritten, int *err) { struct inode *orig_inode = file_inode(o_filp); struct folio *folio[2] = {NULL, NULL}; handle_t *handle; ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because * inode and donor_inode may change each different metadata blocks. */ again: *err = 0; jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, jblocks); if (IS_ERR(handle)) { *err = PTR_ERR(handle); return 0; } orig_blk_offset = orig_page_offset * blocks_per_page + data_offset_in_page; donor_blk_offset = donor_page_offset * blocks_per_page + data_offset_in_page; /* Calculate data_size */ if ((orig_blk_offset + block_len_in_page - 1) == ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) { /* Replace the last block */ tmp_data_size = orig_inode->i_size & (blocksize - 1); /* * If data_size equal zero, it shows data_size is multiples of * blocksize. So we set appropriate value. */ if (tmp_data_size == 0) tmp_data_size = blocksize; data_size = tmp_data_size + ((block_len_in_page - 1) << orig_inode->i_blkbits); } else data_size = block_len_in_page << orig_inode->i_blkbits; replaced_size = data_size; *err = mext_folio_double_lock(orig_inode, donor_inode, orig_page_offset, donor_page_offset, folio); if (unlikely(*err < 0)) goto stop_journal; /* * If orig extent was unwritten it can become initialized * at any time after i_data_sem was dropped, in order to * serialize with delalloc we have recheck extent while we * hold page's lock, if it is still the case data copy is not * necessary, just swap data blocks between orig and donor. */ VM_BUG_ON_FOLIO(folio_test_large(folio[0]), folio[0]); VM_BUG_ON_FOLIO(folio_test_large(folio[1]), folio[1]); VM_BUG_ON_FOLIO(folio_nr_pages(folio[0]) != folio_nr_pages(folio[1]), folio[1]); if (unwritten) { ext4_double_down_write_data_sem(orig_inode, donor_inode); /* If any of extents in range became initialized we have to * fallback to data copying */ unwritten = mext_check_coverage(orig_inode, orig_blk_offset, block_len_in_page, 1, err); if (*err) goto drop_data_sem; unwritten &= mext_check_coverage(donor_inode, donor_blk_offset, block_len_in_page, 1, err); if (*err) goto drop_data_sem; if (!unwritten) { ext4_double_up_write_data_sem(orig_inode, donor_inode); goto data_copy; } if (!filemap_release_folio(folio[0], 0) || !filemap_release_folio(folio[1], 0)) { *err = -EBUSY; goto drop_data_sem; } replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode, orig_blk_offset, donor_blk_offset, block_len_in_page, 1, err); drop_data_sem: ext4_double_up_write_data_sem(orig_inode, donor_inode); goto unlock_folios; } data_copy: *err = mext_page_mkuptodate(folio[0], from, from + replaced_size); if (*err) goto unlock_folios; /* At this point all buffers in range are uptodate, old mapping layout * is no longer required, try to drop it now. */ if (!filemap_release_folio(folio[0], 0) || !filemap_release_folio(folio[1], 0)) { *err = -EBUSY; goto unlock_folios; } ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode, orig_blk_offset, donor_blk_offset, block_len_in_page, 1, err); ext4_double_up_write_data_sem(orig_inode, donor_inode); if (*err) { if (replaced_count) { block_len_in_page = replaced_count; replaced_size = block_len_in_page << orig_inode->i_blkbits; } else goto unlock_folios; } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ bh = folio_buffers(folio[0]); if (!bh) bh = create_empty_buffers(folio[0], 1 << orig_inode->i_blkbits, 0); for (i = 0; i < data_offset_in_page; i++) bh = bh->b_this_page; for (i = 0; i < block_len_in_page; i++) { *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); if (*err < 0) goto repair_branches; bh = bh->b_this_page; } block_commit_write(&folio[0]->page, from, from + replaced_size); /* Even in case of data=writeback it is reasonable to pin * inode to transaction, to prevent unexpected data loss */ *err = ext4_jbd2_inode_add_write(handle, orig_inode, (loff_t)orig_page_offset << PAGE_SHIFT, replaced_size); unlock_folios: folio_unlock(folio[0]); folio_put(folio[0]); folio_unlock(folio[1]); folio_put(folio[1]); stop_journal: ext4_journal_stop(handle); if (*err == -ENOSPC && ext4_should_retry_alloc(sb, &retries)) goto again; /* Buffer was busy because probably is pinned to journal transaction, * force transaction commit may help to free it. */ if (*err == -EBUSY && retries++ < 4 && EXT4_SB(sb)->s_journal && jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal)) goto again; return replaced_count; repair_branches: /* * This should never ever happen! * Extents are swapped already, but we are not able to copy data. * Try to swap extents to it's original places */ ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = ext4_swap_extents(handle, donor_inode, orig_inode, orig_blk_offset, donor_blk_offset, block_len_in_page, 0, &err2); ext4_double_up_write_data_sem(orig_inode, donor_inode); if (replaced_count != block_len_in_page) { ext4_error_inode_block(orig_inode, (sector_t)(orig_blk_offset), EIO, "Unable to copy data block," " data will be lost."); *err = -EIO; } replaced_count = 0; goto unlock_folios; } /** * mext_check_arguments - Check whether move extent can be done * * @orig_inode: original inode * @donor_inode: donor inode * @orig_start: logical start offset in block for orig * @donor_start: logical start offset in block for donor * @len: the number of blocks to be moved * * Check the arguments of ext4_move_extents() whether the files can be * exchanged with each other. * Return 0 on success, or a negative error value on failure. */ static int mext_check_arguments(struct inode *orig_inode, struct inode *donor_inode, __u64 orig_start, __u64 donor_start, __u64 *len) { __u64 orig_eof, donor_eof; unsigned int blkbits = orig_inode->i_blkbits; unsigned int blocksize = 1 << blkbits; orig_eof = (i_size_read(orig_inode) + blocksize - 1) >> blkbits; donor_eof = (i_size_read(donor_inode) + blocksize - 1) >> blkbits; if (donor_inode->i_mode & (S_ISUID|S_ISGID)) { ext4_debug("ext4 move extent: suid or sgid is set" " to donor file [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode)) return -EPERM; /* Ext4 move extent does not support swap files */ if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) { ext4_debug("ext4 move extent: The argument files should not be swap files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -ETXTBSY; } if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) { ext4_debug("ext4 move extent: The argument files should not be quota files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EOPNOTSUPP; } /* Ext4 move extent supports only extent based file */ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: orig file is not extents " "based file [ino:orig %lu]\n", orig_inode->i_ino); return -EOPNOTSUPP; } else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: donor file is not extents " "based file [ino:donor %lu]\n", donor_inode->i_ino); return -EOPNOTSUPP; } if ((!orig_inode->i_size) || (!donor_inode->i_size)) { ext4_debug("ext4 move extent: File size is 0 byte\n"); return -EINVAL; } /* Start offset should be same */ if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) != (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) { ext4_debug("ext4 move extent: orig and donor's start " "offsets are not aligned [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } if ((orig_start >= EXT_MAX_BLOCKS) || (donor_start >= EXT_MAX_BLOCKS) || (*len > EXT_MAX_BLOCKS) || (donor_start + *len >= EXT_MAX_BLOCKS) || (orig_start + *len >= EXT_MAX_BLOCKS)) { ext4_debug("ext4 move extent: Can't handle over [%u] blocks " "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } if (orig_eof <= orig_start) *len = 0; else if (orig_eof < orig_start + *len - 1) *len = orig_eof - orig_start; if (donor_eof <= donor_start) *len = 0; else if (donor_eof < donor_start + *len - 1) *len = donor_eof - donor_start; if (!*len) { ext4_debug("ext4 move extent: len should not be 0 " "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } return 0; } /** * ext4_move_extents - Exchange the specified range of a file * * @o_filp: file structure of the original file * @d_filp: file structure of the donor file * @orig_blk: start offset in block for orig * @donor_blk: start offset in block for donor * @len: the number of blocks to be moved * @moved_len: moved block length * * This function returns 0 and moved block length is set in moved_len * if succeed, otherwise returns error value. * */ int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, __u64 donor_blk, __u64 len, __u64 *moved_len) { struct inode *orig_inode = file_inode(o_filp); struct inode *donor_inode = file_inode(d_filp); struct ext4_ext_path *path = NULL; int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits; ext4_lblk_t o_end, o_start = orig_blk; ext4_lblk_t d_start = donor_blk; int ret; if (orig_inode->i_sb != donor_inode->i_sb) { ext4_debug("ext4 move extent: The argument files " "should be in same FS [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } /* orig and donor should be different inodes */ if (orig_inode == donor_inode) { ext4_debug("ext4 move extent: The argument files should not " "be same inode [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } /* Regular file check */ if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) { ext4_debug("ext4 move extent: The argument files should be " "regular file [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } /* TODO: it's not obvious how to swap blocks for inodes with full journaling enabled */ if (ext4_should_journal_data(orig_inode) || ext4_should_journal_data(donor_inode)) { ext4_msg(orig_inode->i_sb, KERN_ERR, "Online defrag not supported with data journaling"); return -EOPNOTSUPP; } if (IS_ENCRYPTED(orig_inode) || IS_ENCRYPTED(donor_inode)) { ext4_msg(orig_inode->i_sb, KERN_ERR, "Online defrag not supported for encrypted files"); return -EOPNOTSUPP; } /* Protect orig and donor inodes against a truncate */ lock_two_nondirectories(orig_inode, donor_inode); /* Wait for all existing dio workers */ inode_dio_wait(orig_inode); inode_dio_wait(donor_inode); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ ret = mext_check_arguments(orig_inode, donor_inode, orig_blk, donor_blk, &len); if (ret) goto out; o_end = o_start + len; *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; pgoff_t orig_page_index, donor_page_index; int offset_in_page; int unwritten, cur_len; path = get_ext_path(orig_inode, o_start, path); if (IS_ERR(path)) { ret = PTR_ERR(path); goto out; } ex = path[path->p_depth].p_ext; cur_blk = le32_to_cpu(ex->ee_block); cur_len = ext4_ext_get_actual_len(ex); /* Check hole before the start pos */ if (cur_blk + cur_len - 1 < o_start) { next_blk = ext4_ext_next_allocated_block(path); if (next_blk == EXT_MAX_BLOCKS) { ret = -ENODATA; goto out; } d_start += next_blk - o_start; o_start = next_blk; continue; /* Check hole after the start pos */ } else if (cur_blk > o_start) { /* Skip hole */ d_start += cur_blk - o_start; o_start = cur_blk; /* Extent inside requested range ?*/ if (cur_blk >= o_end) goto out; } else { /* in_range(o_start, o_blk, o_len) */ cur_len += cur_blk - o_start; } unwritten = ext4_ext_is_unwritten(ex); if (o_end - o_start < cur_len) cur_len = o_end - o_start; orig_page_index = o_start >> (PAGE_SHIFT - orig_inode->i_blkbits); donor_page_index = d_start >> (PAGE_SHIFT - donor_inode->i_blkbits); offset_in_page = o_start % blocks_per_page; if (cur_len > blocks_per_page - offset_in_page) cur_len = blocks_per_page - offset_in_page; /* * Up semaphore to avoid following problems: * a. transaction deadlock among ext4_journal_start, * ->write_begin via pagefault, and jbd2_journal_commit * b. racing with ->read_folio, ->write_begin, and * ext4_get_block in move_extent_per_page */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); ext4_double_down_write_data_sem(orig_inode, donor_inode); if (ret < 0) break; o_start += cur_len; d_start += cur_len; } out: if (*moved_len) { ext4_discard_preallocations(orig_inode); ext4_discard_preallocations(donor_inode); } ext4_free_ext_path(path); ext4_double_up_write_data_sem(orig_inode, donor_inode); unlock_two_nondirectories(orig_inode, donor_inode); return ret; } |
| 290 292 88 51 162 51 155 8 5 8 8 8 8 8 7 8 5 2 4 431 5 483 28 34 31 109 8 79 82 45 45 38 38 11 1 1 9 3 5 2 4 3 1 11 12 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 | // SPDX-License-Identifier: GPL-2.0 /* * High-level sync()-related operations */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/namei.h> #include <linux/sched.h> #include <linux/writeback.h> #include <linux/syscalls.h> #include <linux/linkage.h> #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/backing-dev.h> #include "internal.h" #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ SYNC_FILE_RANGE_WAIT_AFTER) /* * Write out and wait upon all dirty data associated with this * superblock. Filesystem data as well as the underlying block * device. Takes the superblock lock. */ int sync_filesystem(struct super_block *sb) { int ret = 0; /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* * No point in syncing out anything if the filesystem is read-only. */ if (sb_rdonly(sb)) return 0; /* * Do the filesystem syncing work. For simple filesystems * writeback_inodes_sb(sb) just dirties buffers with inodes so we have * to submit I/O for these buffers via sync_blockdev(). This also * speeds up the wait == 1 case since in that case write_inode() * methods call sync_dirty_buffer() and thus effectively write one block * at a time. */ writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 0); if (ret) return ret; } ret = sync_blockdev_nowait(sb->s_bdev); if (ret) return ret; sync_inodes_sb(sb); if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 1); if (ret) return ret; } return sync_blockdev(sb->s_bdev); } EXPORT_SYMBOL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!sb_rdonly(sb)) sync_inodes_sb(sb); } static void sync_fs_one_sb(struct super_block *sb, void *arg) { if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_SKIP_SYNC) && sb->s_op->sync_fs) sb->s_op->sync_fs(sb, *(int *)arg); } /* * Sync everything. We start by waking flusher threads so that most of * writeback runs on all devices in parallel. Then we sync all inodes reliably * which effectively also waits for all flusher threads to finish doing * writeback. At this point all data is on disk so metadata should be stable * and we tell filesystems to sync their metadata via ->sync_fs() calls. * Finally, we writeout all block devices because some filesystems (e.g. ext2) * just write metadata (such as inodes or bitmaps) to block device page cache * and do not sync it on their own in ->sync_fs(). */ void ksys_sync(void) { int nowait = 0, wait = 1; wakeup_flusher_threads(WB_REASON_SYNC); iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); sync_bdevs(false); sync_bdevs(true); if (unlikely(laptop_mode)) laptop_sync_completion(); } SYSCALL_DEFINE0(sync) { ksys_sync(); return 0; } static void do_sync_work(struct work_struct *work) { int nowait = 0; /* * Sync twice to reduce the possibility we skipped some inodes / pages * because they were temporarily locked */ iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); sync_bdevs(false); iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); sync_bdevs(false); printk("Emergency Sync complete\n"); kfree(work); } void emergency_sync(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_sync_work); schedule_work(work); } } /* * sync a single super */ SYSCALL_DEFINE1(syncfs, int, fd) { CLASS(fd, f)(fd); struct super_block *sb; int ret, ret2; if (fd_empty(f)) return -EBADF; sb = fd_file(f)->f_path.dentry->d_sb; down_read(&sb->s_umount); ret = sync_filesystem(sb); up_read(&sb->s_umount); ret2 = errseq_check_and_advance(&sb->s_wb_err, &fd_file(f)->f_sb_err); return ret ? ret : ret2; } /** * vfs_fsync_range - helper to sync a range of data & metadata to disk * @file: file to sync * @start: offset in bytes of the beginning of data range to sync * @end: offset in bytes of the end of data range (inclusive) * @datasync: perform only datasync * * Write back data in range @start..@end and metadata for @file to disk. If * @datasync is set only metadata needed to access modified file data is * written. */ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; if (!file->f_op->fsync) return -EINVAL; if (!datasync && (inode->i_state & I_DIRTY_TIME)) mark_inode_dirty_sync(inode); return file->f_op->fsync(file, start, end, datasync); } EXPORT_SYMBOL(vfs_fsync_range); /** * vfs_fsync - perform a fsync or fdatasync on a file * @file: file to sync * @datasync: only perform a fdatasync operation * * Write back data and metadata for @file to disk. If @datasync is * set only metadata needed to access modified file data is written. */ int vfs_fsync(struct file *file, int datasync) { return vfs_fsync_range(file, 0, LLONG_MAX, datasync); } EXPORT_SYMBOL(vfs_fsync); static int do_fsync(unsigned int fd, int datasync) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fsync(fd_file(f), datasync); } SYSCALL_DEFINE1(fsync, unsigned int, fd) { return do_fsync(fd, 0); } SYSCALL_DEFINE1(fdatasync, unsigned int, fd) { return do_fsync(fd, 1); } int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags) { int ret; struct address_space *mapping; loff_t endbyte; /* inclusive */ umode_t i_mode; ret = -EINVAL; if (flags & ~VALID_FLAGS) goto out; endbyte = offset + nbytes; if ((s64)offset < 0) goto out; if ((s64)endbyte < 0) goto out; if (endbyte < offset) goto out; if (sizeof(pgoff_t) == 4) { if (offset >= (0x100000000ULL << PAGE_SHIFT)) { /* * The range starts outside a 32 bit machine's * pagecache addressing capabilities. Let it "succeed" */ ret = 0; goto out; } if (endbyte >= (0x100000000ULL << PAGE_SHIFT)) { /* * Out to EOF */ nbytes = 0; } } if (nbytes == 0) endbyte = LLONG_MAX; else endbyte--; /* inclusive */ i_mode = file_inode(file)->i_mode; ret = -ESPIPE; if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) && !S_ISLNK(i_mode)) goto out; mapping = file->f_mapping; ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { ret = file_fdatawait_range(file, offset, endbyte); if (ret < 0) goto out; } if (flags & SYNC_FILE_RANGE_WRITE) { int sync_mode = WB_SYNC_NONE; if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) == SYNC_FILE_RANGE_WRITE_AND_WAIT) sync_mode = WB_SYNC_ALL; ret = __filemap_fdatawrite_range(mapping, offset, endbyte, sync_mode); if (ret < 0) goto out; } if (flags & SYNC_FILE_RANGE_WAIT_AFTER) ret = file_fdatawait_range(file, offset, endbyte); out: return ret; } /* * ksys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is * zero then ksys_sync_file_range() will operate from offset out to EOF. * * The flag bits are: * * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range * before performing the write. * * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the * range which are not presently under writeback. Note that this may block for * significant periods due to exhaustion of disk request structures. * * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range * after performing the write. * * Useful combinations of the flag bits are: * * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages * in the range which were dirty on entry to ksys_sync_file_range() are placed * under writeout. This is a start-write-for-data-integrity operation. * * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which * are not presently under writeout. This is an asynchronous flush-to-disk * operation. Not suitable for data integrity operations. * * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for * completion of writeout of all pages in the range. This will be used after an * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait * for that operation to complete and to return the result. * * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER * (a.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT): * a traditional sync() operation. This is a write-for-data-integrity operation * which will ensure that all pages in the range which were dirty on entry to * ksys_sync_file_range() are written to disk. It should be noted that disk * caches are not flushed by this call, so there are no guarantees here that the * data will be available on disk after a crash. * * * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any * I/O errors or ENOSPC conditions and will return those to the caller, after * clearing the EIO and ENOSPC flags in the address_space. * * It should be noted that none of these operations write out the file's * metadata. So unless the application is strictly performing overwrites of * already-instantiated disk blocks, there are no guarantees here that the data * will be available after a crash. */ int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, unsigned int flags) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return sync_file_range(fd_file(f), offset, nbytes, flags); } SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, unsigned int, flags) { return ksys_sync_file_range(fd, offset, nbytes, flags); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_SYNC_FILE_RANGE) COMPAT_SYSCALL_DEFINE6(sync_file_range, int, fd, compat_arg_u64_dual(offset), compat_arg_u64_dual(nbytes), unsigned int, flags) { return ksys_sync_file_range(fd, compat_arg_u64_glue(offset), compat_arg_u64_glue(nbytes), flags); } #endif /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags, loff_t, offset, loff_t, nbytes) { return ksys_sync_file_range(fd, offset, nbytes, flags); } |
| 13 4 3 1 13 12 14 14 5 3 7 9 1 5 3 14 27 13 14 2 11 10 11 12 13 13 23 1 1 1 1 27 27 27 2 24 2 26 26 23 22 1 18 18 25 1 23 2 1 24 2 23 1 23 23 4 3 9 13 17 2 1 22 1 18 28 28 2 1 25 23 2 21 30 30 13 30 28 23 2 25 30 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2018-2019 HUAWEI, Inc. * https://www.huawei.com/ */ #include "internal.h" #include <linux/unaligned.h> #include <trace/events/erofs.h> struct z_erofs_maprecorder { struct inode *inode; struct erofs_map_blocks *map; unsigned long lcn; /* compression extent information gathered */ u8 type, headtype; u16 clusterofs; u16 delta[2]; erofs_blk_t pblk, compressedblks; erofs_off_t nextpackoff; bool partialref; }; static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m, unsigned long lcn) { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); const erofs_off_t pos = Z_EROFS_FULL_INDEX_ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize) + lcn * sizeof(struct z_erofs_lcluster_index); struct z_erofs_lcluster_index *di; unsigned int advise; di = erofs_read_metabuf(&m->map->buf, inode->i_sb, pos, EROFS_KMAP); if (IS_ERR(di)) return PTR_ERR(di); m->lcn = lcn; m->nextpackoff = pos + sizeof(struct z_erofs_lcluster_index); advise = le16_to_cpu(di->di_advise); m->type = advise & Z_EROFS_LI_LCLUSTER_TYPE_MASK; if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { m->clusterofs = 1 << vi->z_logical_clusterbits; m->delta[0] = le16_to_cpu(di->di_u.delta[0]); if (m->delta[0] & Z_EROFS_LI_D0_CBLKCNT) { if (!(vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { DBG_BUGON(1); return -EFSCORRUPTED; } m->compressedblks = m->delta[0] & ~Z_EROFS_LI_D0_CBLKCNT; m->delta[0] = 1; } m->delta[1] = le16_to_cpu(di->di_u.delta[1]); } else { m->partialref = !!(advise & Z_EROFS_LI_PARTIAL_REF); m->clusterofs = le16_to_cpu(di->di_clusterofs); if (m->clusterofs >= 1 << vi->z_logical_clusterbits) { DBG_BUGON(1); return -EFSCORRUPTED; } m->pblk = le32_to_cpu(di->di_u.blkaddr); } return 0; } static unsigned int decode_compactedbits(unsigned int lobits, u8 *in, unsigned int pos, u8 *type) { const unsigned int v = get_unaligned_le32(in + pos / 8) >> (pos & 7); const unsigned int lo = v & ((1 << lobits) - 1); *type = (v >> lobits) & 3; return lo; } static int get_compacted_la_distance(unsigned int lobits, unsigned int encodebits, unsigned int vcnt, u8 *in, int i) { unsigned int lo, d1 = 0; u8 type; DBG_BUGON(i >= vcnt); do { lo = decode_compactedbits(lobits, in, encodebits * i, &type); if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) return d1; ++d1; } while (++i < vcnt); /* vcnt - 1 (Z_EROFS_LCLUSTER_TYPE_NONHEAD) item */ if (!(lo & Z_EROFS_LI_D0_CBLKCNT)) d1 += lo - 1; return d1; } static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, unsigned long lcn, bool lookahead) { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); const erofs_off_t ebase = sizeof(struct z_erofs_map_header) + ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); const unsigned int lclusterbits = vi->z_logical_clusterbits; const unsigned int totalidx = erofs_iblks(inode); unsigned int compacted_4b_initial, compacted_2b, amortizedshift; unsigned int vcnt, lo, lobits, encodebits, nblk, bytes; bool big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; erofs_off_t pos; u8 *in, type; int i; if (lcn >= totalidx || lclusterbits > 14) return -EINVAL; m->lcn = lcn; /* used to align to 32-byte (compacted_2b) alignment */ compacted_4b_initial = ((32 - ebase % 32) / 4) & 7; compacted_2b = 0; if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) && compacted_4b_initial < totalidx) compacted_2b = rounddown(totalidx - compacted_4b_initial, 16); pos = ebase; amortizedshift = 2; /* compact_4b */ if (lcn >= compacted_4b_initial) { pos += compacted_4b_initial * 4; lcn -= compacted_4b_initial; if (lcn < compacted_2b) { amortizedshift = 1; } else { pos += compacted_2b * 2; lcn -= compacted_2b; } } pos += lcn * (1 << amortizedshift); /* figure out the lcluster count in this pack */ if (1 << amortizedshift == 4 && lclusterbits <= 14) vcnt = 2; else if (1 << amortizedshift == 2 && lclusterbits <= 12) vcnt = 16; else return -EOPNOTSUPP; in = erofs_read_metabuf(&m->map->buf, m->inode->i_sb, pos, EROFS_KMAP); if (IS_ERR(in)) return PTR_ERR(in); /* it doesn't equal to round_up(..) */ m->nextpackoff = round_down(pos, vcnt << amortizedshift) + (vcnt << amortizedshift); lobits = max(lclusterbits, ilog2(Z_EROFS_LI_D0_CBLKCNT) + 1U); encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt; bytes = pos & ((vcnt << amortizedshift) - 1); in -= bytes; i = bytes >> amortizedshift; lo = decode_compactedbits(lobits, in, encodebits * i, &type); m->type = type; if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { m->clusterofs = 1 << lclusterbits; /* figure out lookahead_distance: delta[1] if needed */ if (lookahead) m->delta[1] = get_compacted_la_distance(lobits, encodebits, vcnt, in, i); if (lo & Z_EROFS_LI_D0_CBLKCNT) { if (!big_pcluster) { DBG_BUGON(1); return -EFSCORRUPTED; } m->compressedblks = lo & ~Z_EROFS_LI_D0_CBLKCNT; m->delta[0] = 1; return 0; } else if (i + 1 != (int)vcnt) { m->delta[0] = lo; return 0; } /* * since the last lcluster in the pack is special, * of which lo saves delta[1] rather than delta[0]. * Hence, get delta[0] by the previous lcluster indirectly. */ lo = decode_compactedbits(lobits, in, encodebits * (i - 1), &type); if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) lo = 0; else if (lo & Z_EROFS_LI_D0_CBLKCNT) lo = 1; m->delta[0] = lo + 1; return 0; } m->clusterofs = lo; m->delta[0] = 0; /* figout out blkaddr (pblk) for HEAD lclusters */ if (!big_pcluster) { nblk = 1; while (i > 0) { --i; lo = decode_compactedbits(lobits, in, encodebits * i, &type); if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) i -= lo; if (i >= 0) ++nblk; } } else { nblk = 0; while (i > 0) { --i; lo = decode_compactedbits(lobits, in, encodebits * i, &type); if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { if (lo & Z_EROFS_LI_D0_CBLKCNT) { --i; nblk += lo & ~Z_EROFS_LI_D0_CBLKCNT; continue; } /* bigpcluster shouldn't have plain d0 == 1 */ if (lo <= 1) { DBG_BUGON(1); return -EFSCORRUPTED; } i -= lo - 2; continue; } ++nblk; } } in += (vcnt << amortizedshift) - sizeof(__le32); m->pblk = le32_to_cpu(*(__le32 *)in) + nblk; return 0; } static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m, unsigned int lcn, bool lookahead) { switch (EROFS_I(m->inode)->datalayout) { case EROFS_INODE_COMPRESSED_FULL: return z_erofs_load_full_lcluster(m, lcn); case EROFS_INODE_COMPRESSED_COMPACT: return z_erofs_load_compact_lcluster(m, lcn, lookahead); default: return -EINVAL; } } static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, unsigned int lookback_distance) { struct super_block *sb = m->inode->i_sb; struct erofs_inode *const vi = EROFS_I(m->inode); const unsigned int lclusterbits = vi->z_logical_clusterbits; while (m->lcn >= lookback_distance) { unsigned long lcn = m->lcn - lookback_distance; int err; err = z_erofs_load_lcluster_from_disk(m, lcn, false); if (err) return err; switch (m->type) { case Z_EROFS_LCLUSTER_TYPE_NONHEAD: lookback_distance = m->delta[0]; if (!lookback_distance) goto err_bogus; continue; case Z_EROFS_LCLUSTER_TYPE_PLAIN: case Z_EROFS_LCLUSTER_TYPE_HEAD1: case Z_EROFS_LCLUSTER_TYPE_HEAD2: m->headtype = m->type; m->map->m_la = (lcn << lclusterbits) | m->clusterofs; return 0; default: erofs_err(sb, "unknown type %u @ lcn %lu of nid %llu", m->type, lcn, vi->nid); DBG_BUGON(1); return -EOPNOTSUPP; } } err_bogus: erofs_err(sb, "bogus lookback distance %u @ lcn %lu of nid %llu", lookback_distance, m->lcn, vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, unsigned int initial_lcn) { struct inode *inode = m->inode; struct super_block *sb = inode->i_sb; struct erofs_inode *vi = EROFS_I(inode); bool bigpcl1 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; bool bigpcl2 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2; unsigned long lcn = m->lcn + 1; int err; DBG_BUGON(m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD); DBG_BUGON(m->type != m->headtype); if ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1 && !bigpcl1) || ((m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN || m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) && !bigpcl2) || (lcn << vi->z_logical_clusterbits) >= inode->i_size) m->compressedblks = 1; if (m->compressedblks) goto out; err = z_erofs_load_lcluster_from_disk(m, lcn, false); if (err) return err; /* * If the 1st NONHEAD lcluster has already been handled initially w/o * valid compressedblks, which means at least it mustn't be CBLKCNT, or * an internal implemenatation error is detected. * * The following code can also handle it properly anyway, but let's * BUG_ON in the debugging mode only for developers to notice that. */ DBG_BUGON(lcn == initial_lcn && m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD); switch (m->type) { case Z_EROFS_LCLUSTER_TYPE_PLAIN: case Z_EROFS_LCLUSTER_TYPE_HEAD1: case Z_EROFS_LCLUSTER_TYPE_HEAD2: /* * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type * rather than CBLKCNT, it's a 1 block-sized pcluster. */ m->compressedblks = 1; break; case Z_EROFS_LCLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; if (m->compressedblks) break; fallthrough; default: erofs_err(sb, "cannot found CBLKCNT @ lcn %lu of nid %llu", lcn, vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } out: m->map->m_plen = erofs_pos(sb, m->compressedblks); return 0; err_bonus_cblkcnt: erofs_err(sb, "bogus CBLKCNT @ lcn %lu of nid %llu", lcn, vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m) { struct inode *inode = m->inode; struct erofs_inode *vi = EROFS_I(inode); struct erofs_map_blocks *map = m->map; unsigned int lclusterbits = vi->z_logical_clusterbits; u64 lcn = m->lcn, headlcn = map->m_la >> lclusterbits; int err; while (1) { /* handle the last EOF pcluster (no next HEAD lcluster) */ if ((lcn << lclusterbits) >= inode->i_size) { map->m_llen = inode->i_size - map->m_la; return 0; } err = z_erofs_load_lcluster_from_disk(m, lcn, true); if (err) return err; if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { /* work around invalid d1 generated by pre-1.0 mkfs */ if (unlikely(!m->delta[1])) { m->delta[1] = 1; DBG_BUGON(1); } } else if (m->type == Z_EROFS_LCLUSTER_TYPE_PLAIN || m->type == Z_EROFS_LCLUSTER_TYPE_HEAD1 || m->type == Z_EROFS_LCLUSTER_TYPE_HEAD2) { if (lcn != headlcn) break; /* ends at the next HEAD lcluster */ m->delta[1] = 1; } else { erofs_err(inode->i_sb, "unknown type %u @ lcn %llu of nid %llu", m->type, lcn, vi->nid); DBG_BUGON(1); return -EOPNOTSUPP; } lcn += m->delta[1]; } map->m_llen = (lcn << lclusterbits) + m->clusterofs - map->m_la; return 0; } static int z_erofs_do_map_blocks(struct inode *inode, struct erofs_map_blocks *map, int flags) { struct erofs_inode *const vi = EROFS_I(inode); bool ztailpacking = vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER; bool fragment = vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; struct z_erofs_maprecorder m = { .inode = inode, .map = map, }; int err = 0; unsigned int lclusterbits, endoff, afmt; unsigned long initial_lcn; unsigned long long ofs, end; lclusterbits = vi->z_logical_clusterbits; ofs = flags & EROFS_GET_BLOCKS_FINDTAIL ? inode->i_size - 1 : map->m_la; initial_lcn = ofs >> lclusterbits; endoff = ofs & ((1 << lclusterbits) - 1); err = z_erofs_load_lcluster_from_disk(&m, initial_lcn, false); if (err) goto unmap_out; if (ztailpacking && (flags & EROFS_GET_BLOCKS_FINDTAIL)) vi->z_idataoff = m.nextpackoff; map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_ENCODED; end = (m.lcn + 1ULL) << lclusterbits; switch (m.type) { case Z_EROFS_LCLUSTER_TYPE_PLAIN: case Z_EROFS_LCLUSTER_TYPE_HEAD1: case Z_EROFS_LCLUSTER_TYPE_HEAD2: if (endoff >= m.clusterofs) { m.headtype = m.type; map->m_la = (m.lcn << lclusterbits) | m.clusterofs; /* * For ztailpacking files, in order to inline data more * effectively, special EOF lclusters are now supported * which can have three parts at most. */ if (ztailpacking && end > inode->i_size) end = inode->i_size; break; } /* m.lcn should be >= 1 if endoff < m.clusterofs */ if (!m.lcn) { erofs_err(inode->i_sb, "invalid logical cluster 0 at nid %llu", vi->nid); err = -EFSCORRUPTED; goto unmap_out; } end = (m.lcn << lclusterbits) | m.clusterofs; map->m_flags |= EROFS_MAP_FULL_MAPPED; m.delta[0] = 1; fallthrough; case Z_EROFS_LCLUSTER_TYPE_NONHEAD: /* get the corresponding first chunk */ err = z_erofs_extent_lookback(&m, m.delta[0]); if (err) goto unmap_out; break; default: erofs_err(inode->i_sb, "unknown type %u @ offset %llu of nid %llu", m.type, ofs, vi->nid); err = -EOPNOTSUPP; goto unmap_out; } if (m.partialref) map->m_flags |= EROFS_MAP_PARTIAL_REF; map->m_llen = end - map->m_la; if (flags & EROFS_GET_BLOCKS_FINDTAIL) { vi->z_tailextent_headlcn = m.lcn; /* for non-compact indexes, fragmentoff is 64 bits */ if (fragment && vi->datalayout == EROFS_INODE_COMPRESSED_FULL) vi->z_fragmentoff |= (u64)m.pblk << 32; } if (ztailpacking && m.lcn == vi->z_tailextent_headlcn) { map->m_flags |= EROFS_MAP_META; map->m_pa = vi->z_idataoff; map->m_plen = vi->z_idata_size; } else if (fragment && m.lcn == vi->z_tailextent_headlcn) { map->m_flags |= EROFS_MAP_FRAGMENT; } else { map->m_pa = erofs_pos(inode->i_sb, m.pblk); err = z_erofs_get_extent_compressedlen(&m, initial_lcn); if (err) goto unmap_out; } if (m.headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN) { if (map->m_llen > map->m_plen) { DBG_BUGON(1); err = -EFSCORRUPTED; goto unmap_out; } afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? Z_EROFS_COMPRESSION_INTERLACED : Z_EROFS_COMPRESSION_SHIFTED; } else { afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ? vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", afmt, vi->nid); err = -EFSCORRUPTED; goto unmap_out; } } map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && (map->m_algorithmformat == Z_EROFS_COMPRESSION_LZMA || map->m_algorithmformat == Z_EROFS_COMPRESSION_DEFLATE || map->m_algorithmformat == Z_EROFS_COMPRESSION_ZSTD) && map->m_llen >= i_blocksize(inode))) { err = z_erofs_get_extent_decompressedlen(&m); if (!err) map->m_flags |= EROFS_MAP_FULL_MAPPED; } unmap_out: erofs_unmap_metabuf(&m.map->buf); return err; } static int z_erofs_fill_inode_lazy(struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); struct super_block *const sb = inode->i_sb; int err, headnr; erofs_off_t pos; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct z_erofs_map_header *h; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { /* * paired with smp_mb() at the end of the function to ensure * fields will only be observed after the bit is set. */ smp_mb(); return 0; } if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) return -ERESTARTSYS; err = 0; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) goto out_unlock; pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); h = erofs_read_metabuf(&buf, sb, pos, EROFS_KMAP); if (IS_ERR(h)) { err = PTR_ERR(h); goto out_unlock; } /* * if the highest bit of the 8-byte map header is set, the whole file * is stored in the packed inode. The rest bits keeps z_fragmentoff. */ if (h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT) { vi->z_advise = Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; vi->z_fragmentoff = le64_to_cpu(*(__le64 *)h) ^ (1ULL << 63); vi->z_tailextent_headlcn = 0; goto done; } vi->z_advise = le16_to_cpu(h->h_advise); vi->z_algorithmtype[0] = h->h_algorithmtype & 15; vi->z_algorithmtype[1] = h->h_algorithmtype >> 4; headnr = 0; if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX || vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) { erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", headnr + 1, vi->z_algorithmtype[headnr], vi->nid); err = -EOPNOTSUPP; goto out_put_metabuf; } vi->z_logical_clusterbits = sb->s_blocksize_bits + (h->h_clusterbits & 7); if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu", vi->nid); err = -EFSCORRUPTED; goto out_put_metabuf; } if (vi->datalayout == EROFS_INODE_COMPRESSED_COMPACT && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", vi->nid); err = -EFSCORRUPTED; goto out_put_metabuf; } if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) { struct erofs_map_blocks map = { .buf = __EROFS_BUF_INITIALIZER }; vi->z_idata_size = le16_to_cpu(h->h_idata_size); err = z_erofs_do_map_blocks(inode, &map, EROFS_GET_BLOCKS_FINDTAIL); erofs_put_metabuf(&map.buf); if (!map.m_plen || erofs_blkoff(sb, map.m_pa) + map.m_plen > sb->s_blocksize) { erofs_err(sb, "invalid tail-packing pclustersize %llu", map.m_plen); err = -EFSCORRUPTED; } if (err < 0) goto out_put_metabuf; } if (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER && !(h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT)) { struct erofs_map_blocks map = { .buf = __EROFS_BUF_INITIALIZER }; vi->z_fragmentoff = le32_to_cpu(h->h_fragmentoff); err = z_erofs_do_map_blocks(inode, &map, EROFS_GET_BLOCKS_FINDTAIL); erofs_put_metabuf(&map.buf); if (err < 0) goto out_put_metabuf; } done: /* paired with smp_mb() at the beginning of the function */ smp_mb(); set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); out_put_metabuf: erofs_put_metabuf(&buf); out_unlock: clear_and_wake_up_bit(EROFS_I_BL_Z_BIT, &vi->flags); return err; } int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags) { struct erofs_inode *const vi = EROFS_I(inode); int err = 0; trace_erofs_map_blocks_enter(inode, map, flags); if (map->m_la >= inode->i_size) { /* post-EOF unmapped extent */ map->m_llen = map->m_la + 1 - inode->i_size; map->m_la = inode->i_size; map->m_flags = 0; } else { err = z_erofs_fill_inode_lazy(inode); if (!err) { if ((vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER) && !vi->z_tailextent_headlcn) { map->m_la = 0; map->m_llen = inode->i_size; map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_FULL_MAPPED | EROFS_MAP_FRAGMENT; } else { err = z_erofs_do_map_blocks(inode, map, flags); } } if (!err && (map->m_flags & EROFS_MAP_ENCODED) && unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) err = -EOPNOTSUPP; if (err) map->m_llen = 0; } trace_erofs_map_blocks_exit(inode, map, flags, err); return err; } static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { int ret; struct erofs_map_blocks map = { .m_la = offset }; ret = z_erofs_map_blocks_iter(inode, &map, EROFS_GET_BLOCKS_FIEMAP); erofs_put_metabuf(&map.buf); if (ret < 0) return ret; iomap->bdev = inode->i_sb->s_bdev; iomap->offset = map.m_la; iomap->length = map.m_llen; if (map.m_flags & EROFS_MAP_MAPPED) { iomap->type = IOMAP_MAPPED; iomap->addr = map.m_flags & EROFS_MAP_FRAGMENT ? IOMAP_NULL_ADDR : map.m_pa; } else { iomap->type = IOMAP_HOLE; iomap->addr = IOMAP_NULL_ADDR; /* * No strict rule on how to describe extents for post EOF, yet * we need to do like below. Otherwise, iomap itself will get * into an endless loop on post EOF. * * Calculate the effective offset by subtracting extent start * (map.m_la) from the requested offset, and add it to length. * (NB: offset >= map.m_la always) */ if (iomap->offset >= inode->i_size) iomap->length = length + offset - map.m_la; } iomap->flags = 0; return 0; } const struct iomap_ops z_erofs_iomap_report_ops = { .iomap_begin = z_erofs_iomap_begin_report, }; |
| 1856 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* 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_DCCP) \ 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> |
| 72 94 13 13 11 78 93 89 89 2 6 36 12 12 13 11 4 7 1 7 18 18 18 16 16 16 2 2 93 235 234 53 118 63 163 212 49 1 163 163 163 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2014 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_trans.h" #include "xfs_alloc.h" #include "xfs_btree.h" #include "xfs_btree_staging.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" #include "xfs_health.h" #include "xfs_trace.h" #include "xfs_error.h" #include "xfs_extent_busy.h" #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_buf_mem.h" #include "xfs_btree_mem.h" static struct kmem_cache *xfs_rmapbt_cur_cache; /* * Reverse map btree. * * This is a per-ag tree used to track the owner(s) of a given extent. With * reflink it is possible for there to be multiple owners, which is a departure * from classic XFS. Owner records for data extents are inserted when the * extent is mapped and removed when an extent is unmapped. Owner records for * all other block types (i.e. metadata) are inserted when an extent is * allocated and removed when an extent is freed. There can only be one owner * of a metadata extent, usually an inode or some other metadata structure like * an AG btree. * * The rmap btree is part of the free space management, so blocks for the tree * are sourced from the agfl. Hence we need transaction reservation support for * this tree so that the freelist is always large enough. This also impacts on * the minimum space we need to leave free in the AG. * * The tree is ordered by [ag block, owner, offset]. This is a large key size, * but it is the only way to enforce unique keys when a block can be owned by * multiple files at any offset. There's no need to order/search by extent * size for online updating/management of the tree. It is intended that most * reverse lookups will be to find the owner(s) of a particular block, or to * try to recover tree and file data from corrupt primary metadata. */ static struct xfs_btree_cur * xfs_rmapbt_dup_cursor( struct xfs_btree_cur *cur) { return xfs_rmapbt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp, to_perag(cur->bc_group)); } STATIC void xfs_rmapbt_set_root( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, int inc) { struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; struct xfs_perag *pag = to_perag(cur->bc_group); ASSERT(ptr->s != 0); agf->agf_rmap_root = ptr->s; be32_add_cpu(&agf->agf_rmap_level, inc); pag->pagf_rmap_level += inc; xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS); } STATIC int xfs_rmapbt_alloc_block( struct xfs_btree_cur *cur, const union xfs_btree_ptr *start, union xfs_btree_ptr *new, int *stat) { struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; struct xfs_perag *pag = to_perag(cur->bc_group); struct xfs_alloc_arg args = { .len = 1 }; int error; xfs_agblock_t bno; /* Allocate the new block from the freelist. If we can't, give up. */ error = xfs_alloc_get_freelist(pag, cur->bc_tp, cur->bc_ag.agbp, &bno, 1); if (error) return error; if (bno == NULLAGBLOCK) { *stat = 0; return 0; } xfs_extent_busy_reuse(pag_group(pag), bno, 1, false); new->s = cpu_to_be32(bno); be32_add_cpu(&agf->agf_rmap_blocks, 1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); /* * Since rmapbt blocks are sourced from the AGFL, they are allocated one * at a time and the reservation updates don't require a transaction. */ xfs_ag_resv_alloc_extent(pag, XFS_AG_RESV_RMAPBT, &args); *stat = 1; return 0; } STATIC int xfs_rmapbt_free_block( struct xfs_btree_cur *cur, struct xfs_buf *bp) { struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; struct xfs_perag *pag = to_perag(cur->bc_group); xfs_agblock_t bno; int error; bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp)); be32_add_cpu(&agf->agf_rmap_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); error = xfs_alloc_put_freelist(pag, cur->bc_tp, agbp, NULL, bno, 1); if (error) return error; xfs_extent_busy_insert(cur->bc_tp, pag_group(pag), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1); return 0; } STATIC int xfs_rmapbt_get_minrecs( struct xfs_btree_cur *cur, int level) { return cur->bc_mp->m_rmap_mnr[level != 0]; } STATIC int xfs_rmapbt_get_maxrecs( struct xfs_btree_cur *cur, int level) { return cur->bc_mp->m_rmap_mxr[level != 0]; } /* * Convert the ondisk record's offset field into the ondisk key's offset field. * Fork and bmbt are significant parts of the rmap record key, but written * status is merely a record attribute. */ static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) { return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); } STATIC void xfs_rmapbt_init_key_from_rec( union xfs_btree_key *key, const union xfs_btree_rec *rec) { key->rmap.rm_startblock = rec->rmap.rm_startblock; key->rmap.rm_owner = rec->rmap.rm_owner; key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); } /* * The high key for a reverse mapping record can be computed by shifting * the startblock and offset to the highest value that would still map * to that record. In practice this means that we add blockcount-1 to * the startblock for all records, and if the record is for a data/attr * fork mapping, we add blockcount-1 to the offset too. */ STATIC void xfs_rmapbt_init_high_key_from_rec( union xfs_btree_key *key, const union xfs_btree_rec *rec) { uint64_t off; int adj; adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1; key->rmap.rm_startblock = rec->rmap.rm_startblock; be32_add_cpu(&key->rmap.rm_startblock, adj); key->rmap.rm_owner = rec->rmap.rm_owner; key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) return; off = be64_to_cpu(key->rmap.rm_offset); off = (XFS_RMAP_OFF(off) + adj) | (off & ~XFS_RMAP_OFF_MASK); key->rmap.rm_offset = cpu_to_be64(off); } STATIC void xfs_rmapbt_init_rec_from_cur( struct xfs_btree_cur *cur, union xfs_btree_rec *rec) { rec->rmap.rm_startblock = cpu_to_be32(cur->bc_rec.r.rm_startblock); rec->rmap.rm_blockcount = cpu_to_be32(cur->bc_rec.r.rm_blockcount); rec->rmap.rm_owner = cpu_to_be64(cur->bc_rec.r.rm_owner); rec->rmap.rm_offset = cpu_to_be64( xfs_rmap_irec_offset_pack(&cur->bc_rec.r)); } STATIC void xfs_rmapbt_init_ptr_from_cur( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr) { struct xfs_agf *agf = cur->bc_ag.agbp->b_addr; ASSERT(cur->bc_group->xg_gno == be32_to_cpu(agf->agf_seqno)); ptr->s = agf->agf_rmap_root; } /* * Mask the appropriate parts of the ondisk key field for a key comparison. * Fork and bmbt are significant parts of the rmap record key, but written * status is merely a record attribute. */ static inline uint64_t offset_keymask(uint64_t offset) { return offset & ~XFS_RMAP_OFF_UNWRITTEN; } STATIC int64_t xfs_rmapbt_key_diff( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { struct xfs_rmap_irec *rec = &cur->bc_rec.r; const struct xfs_rmap_key *kp = &key->rmap; __u64 x, y; int64_t d; d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; if (d) return d; x = be64_to_cpu(kp->rm_owner); y = rec->rm_owner; if (x > y) return 1; else if (y > x) return -1; x = offset_keymask(be64_to_cpu(kp->rm_offset)); y = offset_keymask(xfs_rmap_irec_offset_pack(rec)); if (x > y) return 1; else if (y > x) return -1; return 0; } STATIC int64_t xfs_rmapbt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, const union xfs_btree_key *k2, const union xfs_btree_key *mask) { const struct xfs_rmap_key *kp1 = &k1->rmap; const struct xfs_rmap_key *kp2 = &k2->rmap; int64_t d; __u64 x, y; /* Doesn't make sense to mask off the physical space part */ ASSERT(!mask || mask->rmap.rm_startblock); d = (int64_t)be32_to_cpu(kp1->rm_startblock) - be32_to_cpu(kp2->rm_startblock); if (d) return d; if (!mask || mask->rmap.rm_owner) { x = be64_to_cpu(kp1->rm_owner); y = be64_to_cpu(kp2->rm_owner); if (x > y) return 1; else if (y > x) return -1; } if (!mask || mask->rmap.rm_offset) { /* Doesn't make sense to allow offset but not owner */ ASSERT(!mask || mask->rmap.rm_owner); x = offset_keymask(be64_to_cpu(kp1->rm_offset)); y = offset_keymask(be64_to_cpu(kp2->rm_offset)); if (x > y) return 1; else if (y > x) return -1; } return 0; } static xfs_failaddr_t xfs_rmapbt_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_perag *pag = bp->b_pag; xfs_failaddr_t fa; unsigned int level; /* * magic number and level verification * * During growfs operations, we can't verify the exact level or owner as * the perag is not fully initialised and hence not attached to the * buffer. In this case, check against the maximum tree depth. * * Similarly, during log recovery we will have a perag structure * attached, but the agf information will not yet have been initialised * from the on disk AGF. Again, we can only check against maximum limits * in this case. */ if (!xfs_verify_magic(bp, block->bb_magic)) return __this_address; if (!xfs_has_rmapbt(mp)) return __this_address; fa = xfs_btree_agblock_v5hdr_verify(bp); if (fa) return fa; level = be16_to_cpu(block->bb_level); if (pag && xfs_perag_initialised_agf(pag)) { unsigned int maxlevel = pag->pagf_rmap_level; #ifdef CONFIG_XFS_ONLINE_REPAIR /* * Online repair could be rewriting the free space btrees, so * we'll validate against the larger of either tree while this * is going on. */ maxlevel = max_t(unsigned int, maxlevel, pag->pagf_repair_rmap_level); #endif if (level >= maxlevel) return __this_address; } else if (level >= mp->m_rmap_maxlevels) return __this_address; return xfs_btree_agblock_verify(bp, mp->m_rmap_mxr[level != 0]); } static void xfs_rmapbt_read_verify( struct xfs_buf *bp) { xfs_failaddr_t fa; if (!xfs_btree_agblock_verify_crc(bp)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_rmapbt_verify(bp); if (fa) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } if (bp->b_error) trace_xfs_btree_corrupt(bp, _RET_IP_); } static void xfs_rmapbt_write_verify( struct xfs_buf *bp) { xfs_failaddr_t fa; fa = xfs_rmapbt_verify(bp); if (fa) { trace_xfs_btree_corrupt(bp, _RET_IP_); xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } xfs_btree_agblock_calc_crc(bp); } const struct xfs_buf_ops xfs_rmapbt_buf_ops = { .name = "xfs_rmapbt", .magic = { 0, cpu_to_be32(XFS_RMAP_CRC_MAGIC) }, .verify_read = xfs_rmapbt_read_verify, .verify_write = xfs_rmapbt_write_verify, .verify_struct = xfs_rmapbt_verify, }; STATIC int xfs_rmapbt_keys_inorder( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, const union xfs_btree_key *k2) { uint32_t x; uint32_t y; uint64_t a; uint64_t b; x = be32_to_cpu(k1->rmap.rm_startblock); y = be32_to_cpu(k2->rmap.rm_startblock); if (x < y) return 1; else if (x > y) return 0; a = be64_to_cpu(k1->rmap.rm_owner); b = be64_to_cpu(k2->rmap.rm_owner); if (a < b) return 1; else if (a > b) return 0; a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); if (a <= b) return 1; return 0; } STATIC int xfs_rmapbt_recs_inorder( struct xfs_btree_cur *cur, const union xfs_btree_rec *r1, const union xfs_btree_rec *r2) { uint32_t x; uint32_t y; uint64_t a; uint64_t b; x = be32_to_cpu(r1->rmap.rm_startblock); y = be32_to_cpu(r2->rmap.rm_startblock); if (x < y) return 1; else if (x > y) return 0; a = be64_to_cpu(r1->rmap.rm_owner); b = be64_to_cpu(r2->rmap.rm_owner); if (a < b) return 1; else if (a > b) return 0; a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); if (a <= b) return 1; return 0; } STATIC enum xbtree_key_contig xfs_rmapbt_keys_contiguous( struct xfs_btree_cur *cur, const union xfs_btree_key *key1, const union xfs_btree_key *key2, const union xfs_btree_key *mask) { ASSERT(!mask || mask->rmap.rm_startblock); /* * We only support checking contiguity of the physical space component. * If any callers ever need more specificity than that, they'll have to * implement it here. */ ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), be32_to_cpu(key2->rmap.rm_startblock)); } const struct xfs_btree_ops xfs_rmapbt_ops = { .name = "rmap", .type = XFS_BTREE_TYPE_AG, .geom_flags = XFS_BTGEO_OVERLAPPING, .rec_len = sizeof(struct xfs_rmap_rec), /* Overlapping btree; 2 keys per pointer. */ .key_len = 2 * sizeof(struct xfs_rmap_key), .ptr_len = XFS_BTREE_SHORT_PTR_LEN, .lru_refs = XFS_RMAP_BTREE_REF, .statoff = XFS_STATS_CALC_INDEX(xs_rmap_2), .sick_mask = XFS_SICK_AG_RMAPBT, .dup_cursor = xfs_rmapbt_dup_cursor, .set_root = xfs_rmapbt_set_root, .alloc_block = xfs_rmapbt_alloc_block, .free_block = xfs_rmapbt_free_block, .get_minrecs = xfs_rmapbt_get_minrecs, .get_maxrecs = xfs_rmapbt_get_maxrecs, .init_key_from_rec = xfs_rmapbt_init_key_from_rec, .init_high_key_from_rec = xfs_rmapbt_init_high_key_from_rec, .init_rec_from_cur = xfs_rmapbt_init_rec_from_cur, .init_ptr_from_cur = xfs_rmapbt_init_ptr_from_cur, .key_diff = xfs_rmapbt_key_diff, .buf_ops = &xfs_rmapbt_buf_ops, .diff_two_keys = xfs_rmapbt_diff_two_keys, .keys_inorder = xfs_rmapbt_keys_inorder, .recs_inorder = xfs_rmapbt_recs_inorder, .keys_contiguous = xfs_rmapbt_keys_contiguous, }; /* * Create a new reverse mapping btree cursor. * * For staging cursors tp and agbp are NULL. */ struct xfs_btree_cur * xfs_rmapbt_init_cursor( struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_buf *agbp, struct xfs_perag *pag) { struct xfs_btree_cur *cur; cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_ops, mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache); cur->bc_group = xfs_group_hold(pag_group(pag)); cur->bc_ag.agbp = agbp; if (agbp) { struct xfs_agf *agf = agbp->b_addr; cur->bc_nlevels = be32_to_cpu(agf->agf_rmap_level); } return cur; } #ifdef CONFIG_XFS_BTREE_IN_MEM static inline unsigned int xfs_rmapbt_mem_block_maxrecs( unsigned int blocklen, bool leaf) { if (leaf) return blocklen / sizeof(struct xfs_rmap_rec); return blocklen / (2 * sizeof(struct xfs_rmap_key) + sizeof(__be64)); } /* * Validate an in-memory rmap btree block. Callers are allowed to generate an * in-memory btree even if the ondisk feature is not enabled. */ static xfs_failaddr_t xfs_rmapbt_mem_verify( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_failaddr_t fa; unsigned int level; unsigned int maxrecs; if (!xfs_verify_magic(bp, block->bb_magic)) return __this_address; fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); if (fa) return fa; level = be16_to_cpu(block->bb_level); if (level >= xfs_rmapbt_maxlevels_ondisk()) return __this_address; maxrecs = xfs_rmapbt_mem_block_maxrecs( XFBNO_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN, level == 0); return xfs_btree_memblock_verify(bp, maxrecs); } static void xfs_rmapbt_mem_rw_verify( struct xfs_buf *bp) { xfs_failaddr_t fa = xfs_rmapbt_mem_verify(bp); if (fa) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } /* skip crc checks on in-memory btrees to save time */ static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = { .name = "xfs_rmapbt_mem", .magic = { 0, cpu_to_be32(XFS_RMAP_CRC_MAGIC) }, .verify_read = xfs_rmapbt_mem_rw_verify, .verify_write = xfs_rmapbt_mem_rw_verify, .verify_struct = xfs_rmapbt_mem_verify, }; const struct xfs_btree_ops xfs_rmapbt_mem_ops = { .name = "mem_rmap", .type = XFS_BTREE_TYPE_MEM, .geom_flags = XFS_BTGEO_OVERLAPPING, .rec_len = sizeof(struct xfs_rmap_rec), /* Overlapping btree; 2 keys per pointer. */ .key_len = 2 * sizeof(struct xfs_rmap_key), .ptr_len = XFS_BTREE_LONG_PTR_LEN, .lru_refs = XFS_RMAP_BTREE_REF, .statoff = XFS_STATS_CALC_INDEX(xs_rmap_mem_2), .dup_cursor = xfbtree_dup_cursor, .set_root = xfbtree_set_root, .alloc_block = xfbtree_alloc_block, .free_block = xfbtree_free_block, .get_minrecs = xfbtree_get_minrecs, .get_maxrecs = xfbtree_get_maxrecs, .init_key_from_rec = xfs_rmapbt_init_key_from_rec, .init_high_key_from_rec = xfs_rmapbt_init_high_key_from_rec, .init_rec_from_cur = xfs_rmapbt_init_rec_from_cur, .init_ptr_from_cur = xfbtree_init_ptr_from_cur, .key_diff = xfs_rmapbt_key_diff, .buf_ops = &xfs_rmapbt_mem_buf_ops, .diff_two_keys = xfs_rmapbt_diff_two_keys, .keys_inorder = xfs_rmapbt_keys_inorder, .recs_inorder = xfs_rmapbt_recs_inorder, .keys_contiguous = xfs_rmapbt_keys_contiguous, }; /* Create a cursor for an in-memory btree. */ struct xfs_btree_cur * xfs_rmapbt_mem_cursor( struct xfs_perag *pag, struct xfs_trans *tp, struct xfbtree *xfbt) { struct xfs_btree_cur *cur; cur = xfs_btree_alloc_cursor(pag_mount(pag), tp, &xfs_rmapbt_mem_ops, xfs_rmapbt_maxlevels_ondisk(), xfs_rmapbt_cur_cache); cur->bc_mem.xfbtree = xfbt; cur->bc_nlevels = xfbt->nlevels; cur->bc_group = xfs_group_hold(pag_group(pag)); return cur; } /* Create an in-memory rmap btree. */ int xfs_rmapbt_mem_init( struct xfs_mount *mp, struct xfbtree *xfbt, struct xfs_buftarg *btp, xfs_agnumber_t agno) { xfbt->owner = agno; return xfbtree_init(mp, xfbt, btp, &xfs_rmapbt_mem_ops); } /* Compute the max possible height for reverse mapping btrees in memory. */ static unsigned int xfs_rmapbt_mem_maxlevels(void) { unsigned int minrecs[2]; unsigned int blocklen; blocklen = XFBNO_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; minrecs[0] = xfs_rmapbt_mem_block_maxrecs(blocklen, true) / 2; minrecs[1] = xfs_rmapbt_mem_block_maxrecs(blocklen, false) / 2; /* * How tall can an in-memory rmap btree become if we filled the entire * AG with rmap records? */ return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_AG_BYTES / sizeof(struct xfs_rmap_rec)); } #else # define xfs_rmapbt_mem_maxlevels() (0) #endif /* CONFIG_XFS_BTREE_IN_MEM */ /* * Install a new reverse mapping btree root. Caller is responsible for * invalidating and freeing the old btree blocks. */ void xfs_rmapbt_commit_staged_btree( struct xfs_btree_cur *cur, struct xfs_trans *tp, struct xfs_buf *agbp) { struct xfs_agf *agf = agbp->b_addr; struct xbtree_afakeroot *afake = cur->bc_ag.afake; ASSERT(cur->bc_flags & XFS_BTREE_STAGING); agf->agf_rmap_root = cpu_to_be32(afake->af_root); agf->agf_rmap_level = cpu_to_be32(afake->af_levels); agf->agf_rmap_blocks = cpu_to_be32(afake->af_blocks); xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS | XFS_AGF_RMAP_BLOCKS); xfs_btree_commit_afakeroot(cur, tp, agbp); } /* Calculate number of records in a reverse mapping btree block. */ static inline unsigned int xfs_rmapbt_block_maxrecs( unsigned int blocklen, bool leaf) { if (leaf) return blocklen / sizeof(struct xfs_rmap_rec); return blocklen / (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rmap_ptr_t)); } /* * Calculate number of records in an rmap btree block. */ unsigned int xfs_rmapbt_maxrecs( struct xfs_mount *mp, unsigned int blocklen, bool leaf) { blocklen -= XFS_RMAP_BLOCK_LEN; return xfs_rmapbt_block_maxrecs(blocklen, leaf); } /* Compute the max possible height for reverse mapping btrees. */ unsigned int xfs_rmapbt_maxlevels_ondisk(void) { unsigned int minrecs[2]; unsigned int blocklen; blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN; minrecs[0] = xfs_rmapbt_block_maxrecs(blocklen, true) / 2; minrecs[1] = xfs_rmapbt_block_maxrecs(blocklen, false) / 2; /* * Compute the asymptotic maxlevels for an rmapbt on any reflink fs. * * On a reflink filesystem, each AG block can have up to 2^32 (per the * refcount record format) owners, which means that theoretically we * could face up to 2^64 rmap records. However, we're likely to run * out of blocks in the AG long before that happens, which means that * we must compute the max height based on what the btree will look * like if it consumes almost all the blocks in the AG due to maximal * sharing factor. */ return max(xfs_btree_space_to_height(minrecs, XFS_MAX_CRC_AG_BLOCKS), xfs_rmapbt_mem_maxlevels()); } /* Compute the maximum height of an rmap btree. */ void xfs_rmapbt_compute_maxlevels( struct xfs_mount *mp) { if (!xfs_has_rmapbt(mp)) { mp->m_rmap_maxlevels = 0; return; } if (xfs_has_reflink(mp)) { /* * Compute the asymptotic maxlevels for an rmap btree on a * filesystem that supports reflink. * * On a reflink filesystem, each AG block can have up to 2^32 * (per the refcount record format) owners, which means that * theoretically we could face up to 2^64 rmap records. * However, we're likely to run out of blocks in the AG long * before that happens, which means that we must compute the * max height based on what the btree will look like if it * consumes almost all the blocks in the AG due to maximal * sharing factor. */ mp->m_rmap_maxlevels = xfs_btree_space_to_height(mp->m_rmap_mnr, mp->m_sb.sb_agblocks); } else { /* * If there's no block sharing, compute the maximum rmapbt * height assuming one rmap record per AG block. */ mp->m_rmap_maxlevels = xfs_btree_compute_maxlevels( mp->m_rmap_mnr, mp->m_sb.sb_agblocks); } ASSERT(mp->m_rmap_maxlevels <= xfs_rmapbt_maxlevels_ondisk()); } /* Calculate the refcount btree size for some records. */ xfs_extlen_t xfs_rmapbt_calc_size( struct xfs_mount *mp, unsigned long long len) { return xfs_btree_calc_size(mp->m_rmap_mnr, len); } /* * Calculate the maximum refcount btree size. */ xfs_extlen_t xfs_rmapbt_max_size( struct xfs_mount *mp, xfs_agblock_t agblocks) { /* Bail out if we're uninitialized, which can happen in mkfs. */ if (mp->m_rmap_mxr[0] == 0) return 0; return xfs_rmapbt_calc_size(mp, agblocks); } /* * Figure out how many blocks to reserve and how many are used by this btree. */ int xfs_rmapbt_calc_reserves( struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_perag *pag, xfs_extlen_t *ask, xfs_extlen_t *used) { struct xfs_buf *agbp; struct xfs_agf *agf; xfs_agblock_t agblocks; xfs_extlen_t tree_len; int error; if (!xfs_has_rmapbt(mp)) return 0; error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) return error; agf = agbp->b_addr; agblocks = be32_to_cpu(agf->agf_length); tree_len = be32_to_cpu(agf->agf_rmap_blocks); xfs_trans_brelse(tp, agbp); /* * The log is permanently allocated, so the space it occupies will * never be available for the kinds of things that would require btree * expansion. We therefore can pretend the space isn't there. */ if (xfs_ag_contains_log(mp, pag_agno(pag))) agblocks -= mp->m_sb.sb_logblocks; /* Reserve 1% of the AG or enough for 1 block per record. */ *ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks)); *used += tree_len; return error; } int __init xfs_rmapbt_init_cur_cache(void) { xfs_rmapbt_cur_cache = kmem_cache_create("xfs_rmapbt_cur", xfs_btree_cur_sizeof(xfs_rmapbt_maxlevels_ondisk()), 0, 0, NULL); if (!xfs_rmapbt_cur_cache) return -ENOMEM; return 0; } void xfs_rmapbt_destroy_cur_cache(void) { kmem_cache_destroy(xfs_rmapbt_cur_cache); xfs_rmapbt_cur_cache = NULL; } |
| 4 2 4 4 4 4 4 2 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 | // SPDX-License-Identifier: GPL-2.0 #include <linux/in.h> #include <linux/inet.h> #include <linux/list.h> #include <linux/module.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/rculist.h> #include <linux/seq_file.h> #include <linux/socket.h> #include <net/inet_sock.h> #include <net/kcm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/tcp.h> #ifdef CONFIG_PROC_FS static struct kcm_mux *kcm_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); return list_first_or_null_rcu(&knet->mux_list, struct kcm_mux, kcm_mux_list); } static struct kcm_mux *kcm_get_next(struct kcm_mux *mux) { struct kcm_net *knet = mux->knet; return list_next_or_null_rcu(&knet->mux_list, &mux->kcm_mux_list, struct kcm_mux, kcm_mux_list); } static struct kcm_mux *kcm_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); struct kcm_mux *m; list_for_each_entry_rcu(m, &knet->mux_list, kcm_mux_list) { if (!pos) return m; --pos; } return NULL; } static void *kcm_seq_next(struct seq_file *seq, void *v, loff_t *pos) { void *p; if (v == SEQ_START_TOKEN) p = kcm_get_first(seq); else p = kcm_get_next(v); ++*pos; return p; } static void *kcm_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; else return kcm_get_idx(seq, *pos - 1); } static void kcm_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { rcu_read_unlock(); } struct kcm_proc_mux_state { struct seq_net_private p; int idx; }; static void kcm_format_mux_header(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); seq_printf(seq, "*** KCM statistics (%d MUX) ****\n", knet->count); seq_printf(seq, "%-14s %-10s %-16s %-10s %-16s %-8s %-8s %-8s %-8s %s", "Object", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "Recv-Q", "Rmem", "Send-Q", "Smem", "Status"); /* XXX: pdsts header stuff here */ seq_puts(seq, "\n"); } static void kcm_format_sock(struct kcm_sock *kcm, struct seq_file *seq, int i, int *len) { seq_printf(seq, " kcm-%-7u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8s ", kcm->index, kcm->stats.rx_msgs, kcm->stats.rx_bytes, kcm->stats.tx_msgs, kcm->stats.tx_bytes, kcm->sk.sk_receive_queue.qlen, sk_rmem_alloc_get(&kcm->sk), kcm->sk.sk_write_queue.qlen, "-"); if (kcm->tx_psock) seq_printf(seq, "Psck-%u ", kcm->tx_psock->index); if (kcm->tx_wait) seq_puts(seq, "TxWait "); if (kcm->tx_wait_more) seq_puts(seq, "WMore "); if (kcm->rx_wait) seq_puts(seq, "RxWait "); seq_puts(seq, "\n"); } static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, int i, int *len) { seq_printf(seq, " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ", psock->index, psock->strp.stats.msgs, psock->strp.stats.bytes, psock->stats.tx_msgs, psock->stats.tx_bytes, psock->sk->sk_receive_queue.qlen, atomic_read(&psock->sk->sk_rmem_alloc), psock->sk->sk_write_queue.qlen, refcount_read(&psock->sk->sk_wmem_alloc)); if (psock->done) seq_puts(seq, "Done "); if (psock->tx_stopped) seq_puts(seq, "TxStop "); if (psock->strp.stopped) seq_puts(seq, "RxStop "); if (psock->tx_kcm) seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index); if (!psock->strp.paused && !psock->ready_rx_msg) { if (psock->sk->sk_receive_queue.qlen) { if (psock->strp.need_bytes) seq_printf(seq, "RxWait=%u ", psock->strp.need_bytes); else seq_printf(seq, "RxWait "); } } else { if (psock->strp.paused) seq_puts(seq, "RxPause "); if (psock->ready_rx_msg) seq_puts(seq, "RdyRx "); } seq_puts(seq, "\n"); } static void kcm_format_mux(struct kcm_mux *mux, loff_t idx, struct seq_file *seq) { int i, len; struct kcm_sock *kcm; struct kcm_psock *psock; /* mux information */ seq_printf(seq, "%-6s%-8s %-10llu %-16llu %-10llu %-16llu %-8s %-8s %-8s %-8s ", "mux", "", mux->stats.rx_msgs, mux->stats.rx_bytes, mux->stats.tx_msgs, mux->stats.tx_bytes, "-", "-", "-", "-"); seq_printf(seq, "KCMs: %d, Psocks %d\n", mux->kcm_socks_cnt, mux->psocks_cnt); /* kcm sock information */ i = 0; spin_lock_bh(&mux->lock); list_for_each_entry(kcm, &mux->kcm_socks, kcm_sock_list) { kcm_format_sock(kcm, seq, i, &len); i++; } i = 0; list_for_each_entry(psock, &mux->psocks, psock_list) { kcm_format_psock(psock, seq, i, &len); i++; } spin_unlock_bh(&mux->lock); } static int kcm_seq_show(struct seq_file *seq, void *v) { struct kcm_proc_mux_state *mux_state; mux_state = seq->private; if (v == SEQ_START_TOKEN) { mux_state->idx = 0; kcm_format_mux_header(seq); } else { kcm_format_mux(v, mux_state->idx, seq); mux_state->idx++; } return 0; } static const struct seq_operations kcm_seq_ops = { .show = kcm_seq_show, .start = kcm_seq_start, .next = kcm_seq_next, .stop = kcm_seq_stop, }; static int kcm_stats_seq_show(struct seq_file *seq, void *v) { struct kcm_psock_stats psock_stats; struct kcm_mux_stats mux_stats; struct strp_aggr_stats strp_stats; struct kcm_mux *mux; struct kcm_psock *psock; struct net *net = seq->private; struct kcm_net *knet = net_generic(net, kcm_net_id); memset(&mux_stats, 0, sizeof(mux_stats)); memset(&psock_stats, 0, sizeof(psock_stats)); memset(&strp_stats, 0, sizeof(strp_stats)); mutex_lock(&knet->mutex); aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats); aggregate_psock_stats(&knet->aggregate_psock_stats, &psock_stats); aggregate_strp_stats(&knet->aggregate_strp_stats, &strp_stats); list_for_each_entry(mux, &knet->mux_list, kcm_mux_list) { spin_lock_bh(&mux->lock); aggregate_mux_stats(&mux->stats, &mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &psock_stats); aggregate_strp_stats(&mux->aggregate_strp_stats, &strp_stats); list_for_each_entry(psock, &mux->psocks, psock_list) { aggregate_psock_stats(&psock->stats, &psock_stats); save_strp_stats(&psock->strp, &strp_stats); } spin_unlock_bh(&mux->lock); } mutex_unlock(&knet->mutex); seq_printf(seq, "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s\n", "MUX", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "TX-Retries", "Attach", "Unattach", "UnattchRsvd", "RX-RdyDrops"); seq_printf(seq, "%-8s %-10llu %-16llu %-10llu %-16llu %-10u %-10u %-10u %-10u %-10u\n", "", mux_stats.rx_msgs, mux_stats.rx_bytes, mux_stats.tx_msgs, mux_stats.tx_bytes, mux_stats.tx_retries, mux_stats.psock_attach, mux_stats.psock_unattach_rsvd, mux_stats.psock_unattach, mux_stats.rx_ready_drops); seq_printf(seq, "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", "Psock", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "Reserved", "Unreserved", "RX-Aborts", "RX-Intr", "RX-Unrecov", "RX-MemFail", "RX-NeedMor", "RX-BadLen", "RX-TooBig", "RX-Timeout", "TX-Aborts"); seq_printf(seq, "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n", "", strp_stats.msgs, strp_stats.bytes, psock_stats.tx_msgs, psock_stats.tx_bytes, psock_stats.reserved, psock_stats.unreserved, strp_stats.aborts, strp_stats.interrupted, strp_stats.unrecov_intr, strp_stats.mem_fail, strp_stats.need_more_hdr, strp_stats.bad_hdr_len, strp_stats.msg_too_big, strp_stats.msg_timeouts, psock_stats.tx_aborts); return 0; } static int kcm_proc_init_net(struct net *net) { if (!proc_create_net_single("kcm_stats", 0444, net->proc_net, kcm_stats_seq_show, NULL)) goto out_kcm_stats; if (!proc_create_net("kcm", 0444, net->proc_net, &kcm_seq_ops, sizeof(struct kcm_proc_mux_state))) goto out_kcm; return 0; out_kcm: remove_proc_entry("kcm_stats", net->proc_net); out_kcm_stats: return -ENOMEM; } static void kcm_proc_exit_net(struct net *net) { remove_proc_entry("kcm", net->proc_net); remove_proc_entry("kcm_stats", net->proc_net); } static struct pernet_operations kcm_net_ops = { .init = kcm_proc_init_net, .exit = kcm_proc_exit_net, }; int __init kcm_proc_init(void) { return register_pernet_subsys(&kcm_net_ops); } void __exit kcm_proc_exit(void) { unregister_pernet_subsys(&kcm_net_ops); } #endif /* CONFIG_PROC_FS */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * seq_oss_writeq.c - write queue and sync * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_writeq.h" #include "seq_oss_event.h" #include "seq_oss_timer.h" #include <sound/seq_oss_legacy.h> #include "../seq_lock.h" #include "../seq_clientmgr.h" #include <linux/wait.h> #include <linux/slab.h> #include <linux/sched/signal.h> /* * create a write queue record */ struct seq_oss_writeq * snd_seq_oss_writeq_new(struct seq_oss_devinfo *dp, int maxlen) { struct seq_oss_writeq *q; struct snd_seq_client_pool pool; q = kzalloc(sizeof(*q), GFP_KERNEL); if (!q) return NULL; q->dp = dp; q->maxlen = maxlen; spin_lock_init(&q->sync_lock); q->sync_event_put = 0; q->sync_time = 0; init_waitqueue_head(&q->sync_sleep); memset(&pool, 0, sizeof(pool)); pool.client = dp->cseq; pool.output_pool = maxlen; pool.output_room = maxlen / 2; snd_seq_oss_control(dp, SNDRV_SEQ_IOCTL_SET_CLIENT_POOL, &pool); return q; } /* * delete the write queue */ void snd_seq_oss_writeq_delete(struct seq_oss_writeq *q) { if (q) { snd_seq_oss_writeq_clear(q); /* to be sure */ kfree(q); } } /* * reset the write queue */ void snd_seq_oss_writeq_clear(struct seq_oss_writeq *q) { struct snd_seq_remove_events reset; memset(&reset, 0, sizeof(reset)); reset.remove_mode = SNDRV_SEQ_REMOVE_OUTPUT; /* remove all */ snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_REMOVE_EVENTS, &reset); /* wake up sleepers if any */ snd_seq_oss_writeq_wakeup(q, 0); } /* * wait until the write buffer has enough room */ int snd_seq_oss_writeq_sync(struct seq_oss_writeq *q) { struct seq_oss_devinfo *dp = q->dp; abstime_t time; time = snd_seq_oss_timer_cur_tick(dp->timer); if (q->sync_time >= time) return 0; /* already finished */ if (! q->sync_event_put) { struct snd_seq_event ev; union evrec *rec; /* put echoback event */ memset(&ev, 0, sizeof(ev)); ev.flags = 0; ev.type = SNDRV_SEQ_EVENT_ECHO; ev.time.tick = time; /* echo back to itself */ snd_seq_oss_fill_addr(dp, &ev, dp->addr.client, dp->addr.port); rec = (union evrec *)&ev.data; rec->t.code = SEQ_SYNCTIMER; rec->t.time = time; q->sync_event_put = 1; snd_seq_kernel_client_enqueue(dp->cseq, &ev, NULL, true); } wait_event_interruptible_timeout(q->sync_sleep, ! q->sync_event_put, HZ); if (signal_pending(current)) /* interrupted - return 0 to finish sync */ q->sync_event_put = 0; if (! q->sync_event_put || q->sync_time >= time) return 0; return 1; } /* * wake up sync - echo event was catched */ void snd_seq_oss_writeq_wakeup(struct seq_oss_writeq *q, abstime_t time) { unsigned long flags; spin_lock_irqsave(&q->sync_lock, flags); q->sync_time = time; q->sync_event_put = 0; wake_up(&q->sync_sleep); spin_unlock_irqrestore(&q->sync_lock, flags); } /* * return the unused pool size */ int snd_seq_oss_writeq_get_free_size(struct seq_oss_writeq *q) { struct snd_seq_client_pool pool; pool.client = q->dp->cseq; snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_GET_CLIENT_POOL, &pool); return pool.output_free; } /* * set output threshold size from ioctl */ void snd_seq_oss_writeq_set_output(struct seq_oss_writeq *q, int val) { struct snd_seq_client_pool pool; pool.client = q->dp->cseq; snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_GET_CLIENT_POOL, &pool); pool.output_room = val; snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_SET_CLIENT_POOL, &pool); } |
| 2 1 416 15 844 5 4 271 271 271 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { struct ns_common ns; struct mount * root; struct { struct rb_root mounts; /* Protected by namespace_sem */ struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ }; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ union { wait_queue_head_t poll; struct rcu_head mnt_ns_rcu; }; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ struct list_head mnt_ns_list; /* entry in the sequential list of mounts namespace */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { refcount_inc(&ns->ns.count); } extern seqlock_t mount_lock; struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } static inline bool mnt_ns_attached(const struct mount *mnt) { return !RB_EMPTY_NODE(&mnt->mnt_node); } static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { struct mnt_namespace *ns = mnt->mnt_ns; WARN_ON(!mnt_ns_attached(mnt)); if (ns->mnt_last_node == &mnt->mnt_node) ns->mnt_last_node = rb_prev(&mnt->mnt_node); if (ns->mnt_first_node == &mnt->mnt_node) ns->mnt_first_node = rb_next(&mnt->mnt_node); rb_erase(&mnt->mnt_node, &ns->mounts); RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } |
| 3 3 5 5 4 1 14 14 1 1 1 1 2 3 2 1 2 2 2 10 1 2 1 2 7 1 1 4 1 4 4 1 3 1 1 2 10 10 10 10 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/hpfs/super.c * * Mikulas Patocka (mikulas@artax.karlin.mff.cuni.cz), 1998-1999 * * mounting, unmounting, error handling */ #include "hpfs_fn.h" #include <linux/module.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/init.h> #include <linux/statfs.h> #include <linux/magic.h> #include <linux/sched.h> #include <linux/bitmap.h> #include <linux/slab.h> #include <linux/seq_file.h> /* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */ static void mark_dirty(struct super_block *s, int remount) { if (hpfs_sb(s)->sb_chkdsk && (remount || !sb_rdonly(s))) { struct buffer_head *bh; struct hpfs_spare_block *sb; if ((sb = hpfs_map_sector(s, 17, &bh, 0))) { sb->dirty = 1; sb->old_wrote = 0; mark_buffer_dirty(bh); sync_dirty_buffer(bh); brelse(bh); } } } /* Mark the filesystem clean (mark it dirty for chkdsk if chkdsk==2 or if there were errors) */ static void unmark_dirty(struct super_block *s) { struct buffer_head *bh; struct hpfs_spare_block *sb; if (sb_rdonly(s)) return; sync_blockdev(s->s_bdev); if ((sb = hpfs_map_sector(s, 17, &bh, 0))) { sb->dirty = hpfs_sb(s)->sb_chkdsk > 1 - hpfs_sb(s)->sb_was_error; sb->old_wrote = hpfs_sb(s)->sb_chkdsk >= 2 && !hpfs_sb(s)->sb_was_error; mark_buffer_dirty(bh); sync_dirty_buffer(bh); brelse(bh); } } /* Filesystem error... */ void hpfs_error(struct super_block *s, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_err("filesystem error: %pV", &vaf); va_end(args); if (!hpfs_sb(s)->sb_was_error) { if (hpfs_sb(s)->sb_err == 2) { pr_cont("; crashing the system because you wanted it\n"); mark_dirty(s, 0); panic("HPFS panic"); } else if (hpfs_sb(s)->sb_err == 1) { if (sb_rdonly(s)) pr_cont("; already mounted read-only\n"); else { pr_cont("; remounting read-only\n"); mark_dirty(s, 0); s->s_flags |= SB_RDONLY; } } else if (sb_rdonly(s)) pr_cont("; going on - but anything won't be destroyed because it's read-only\n"); else pr_cont("; corrupted filesystem mounted read/write - your computer will explode within 20 seconds ... but you wanted it so!\n"); } else pr_cont("\n"); hpfs_sb(s)->sb_was_error = 1; } /* * A little trick to detect cycles in many hpfs structures and don't let the * kernel crash on corrupted filesystem. When first called, set c2 to 0. * * BTW. chkdsk doesn't detect cycles correctly. When I had 2 lost directories * nested each in other, chkdsk locked up happilly. */ int hpfs_stop_cycles(struct super_block *s, int key, int *c1, int *c2, char *msg) { if (*c2 && *c1 == key) { hpfs_error(s, "cycle detected on key %08x in %s", key, msg); return 1; } (*c2)++; if (!((*c2 - 1) & *c2)) *c1 = key; return 0; } static void free_sbi(struct hpfs_sb_info *sbi) { kfree(sbi->sb_cp_table); kfree(sbi->sb_bmp_dir); kfree(sbi); } static void lazy_free_sbi(struct rcu_head *rcu) { free_sbi(container_of(rcu, struct hpfs_sb_info, rcu)); } static void hpfs_put_super(struct super_block *s) { hpfs_lock(s); unmark_dirty(s); hpfs_unlock(s); call_rcu(&hpfs_sb(s)->rcu, lazy_free_sbi); } static unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno) { struct quad_buffer_head qbh; unsigned long *bits; unsigned count; bits = hpfs_map_4sectors(s, secno, &qbh, 0); if (!bits) return (unsigned)-1; count = bitmap_weight(bits, 2048 * BITS_PER_BYTE); hpfs_brelse4(&qbh); return count; } static unsigned count_bitmaps(struct super_block *s) { unsigned n, count, n_bands; n_bands = (hpfs_sb(s)->sb_fs_size + 0x3fff) >> 14; count = 0; for (n = 0; n < COUNT_RD_AHEAD; n++) { hpfs_prefetch_bitmap(s, n); } for (n = 0; n < n_bands; n++) { unsigned c; hpfs_prefetch_bitmap(s, n + COUNT_RD_AHEAD); c = hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n])); if (c != (unsigned)-1) count += c; } return count; } unsigned hpfs_get_free_dnodes(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); if (sbi->sb_n_free_dnodes == (unsigned)-1) { unsigned c = hpfs_count_one_bitmap(s, sbi->sb_dmap); if (c == (unsigned)-1) return 0; sbi->sb_n_free_dnodes = c; } return sbi->sb_n_free_dnodes; } static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(s); u64 id = huge_encode_dev(s->s_bdev->bd_dev); hpfs_lock(s); if (sbi->sb_n_free == (unsigned)-1) sbi->sb_n_free = count_bitmaps(s); buf->f_type = s->s_magic; buf->f_bsize = 512; buf->f_blocks = sbi->sb_fs_size; buf->f_bfree = sbi->sb_n_free; buf->f_bavail = sbi->sb_n_free; buf->f_files = sbi->sb_dirband_size / 4; buf->f_ffree = hpfs_get_free_dnodes(s); buf->f_fsid = u64_to_fsid(id); buf->f_namelen = 254; hpfs_unlock(s); return 0; } long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg) { switch (cmd) { case FITRIM: { struct fstrim_range range; secno n_trimmed; int r; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; r = hpfs_trim_fs(file_inode(file)->i_sb, range.start >> 9, (range.start + range.len) >> 9, (range.minlen + 511) >> 9, &n_trimmed); if (r) return r; range.len = (u64)n_trimmed << 9; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; return 0; } default: { return -ENOIOCTLCMD; } } } static struct kmem_cache * hpfs_inode_cachep; static struct inode *hpfs_alloc_inode(struct super_block *sb) { struct hpfs_inode_info *ei; ei = alloc_inode_sb(sb, hpfs_inode_cachep, GFP_NOFS); if (!ei) return NULL; return &ei->vfs_inode; } static void hpfs_free_inode(struct inode *inode) { kmem_cache_free(hpfs_inode_cachep, hpfs_i(inode)); } static void init_once(void *foo) { struct hpfs_inode_info *ei = (struct hpfs_inode_info *) foo; inode_init_once(&ei->vfs_inode); } static int init_inodecache(void) { hpfs_inode_cachep = kmem_cache_create("hpfs_inode_cache", sizeof(struct hpfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (hpfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(hpfs_inode_cachep); } enum { Opt_help, Opt_uid, Opt_gid, Opt_umask, Opt_case, Opt_check, Opt_err, Opt_eas, Opt_chkdsk, Opt_timeshift, }; static const struct constant_table hpfs_param_case[] = { {"asis", 0}, {"lower", 1}, {} }; static const struct constant_table hpfs_param_check[] = { {"none", 0}, {"normal", 1}, {"strict", 2}, {} }; static const struct constant_table hpfs_param_err[] = { {"continue", 0}, {"remount-ro", 1}, {"panic", 2}, {} }; static const struct constant_table hpfs_param_eas[] = { {"no", 0}, {"ro", 1}, {"rw", 2}, {} }; static const struct constant_table hpfs_param_chkdsk[] = { {"no", 0}, {"errors", 1}, {"always", 2}, {} }; static const struct fs_parameter_spec hpfs_param_spec[] = { fsparam_flag ("help", Opt_help), fsparam_uid ("uid", Opt_uid), fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("umask", Opt_umask), fsparam_enum ("case", Opt_case, hpfs_param_case), fsparam_enum ("check", Opt_check, hpfs_param_check), fsparam_enum ("errors", Opt_err, hpfs_param_err), fsparam_enum ("eas", Opt_eas, hpfs_param_eas), fsparam_enum ("chkdsk", Opt_chkdsk, hpfs_param_chkdsk), fsparam_s32 ("timeshift", Opt_timeshift), {} }; struct hpfs_fc_context { kuid_t uid; kgid_t gid; umode_t umask; int lowercase; int eas; int chk; int errs; int chkdsk; int timeshift; }; static inline void hpfs_help(void) { pr_info("\n\ HPFS filesystem options:\n\ help do not mount and display this text\n\ uid=xxx set uid of files that don't have uid specified in eas\n\ gid=xxx set gid of files that don't have gid specified in eas\n\ umask=xxx set mode of files that don't have mode specified in eas\n\ case=lower lowercase all files\n\ case=asis do not lowercase files (default)\n\ check=none no fs checks - kernel may crash on corrupted filesystem\n\ check=normal do some checks - it should not crash (default)\n\ check=strict do extra time-consuming checks, used for debugging\n\ errors=continue continue on errors\n\ errors=remount-ro remount read-only if errors found (default)\n\ errors=panic panic on errors\n\ chkdsk=no do not mark fs for chkdsking even if there were errors\n\ chkdsk=errors mark fs dirty if errors found (default)\n\ chkdsk=always always mark fs dirty - used for debugging\n\ eas=no ignore extended attributes\n\ eas=ro read but do not write extended attributes\n\ eas=rw r/w eas => enables chmod, chown, mknod, ln -s (default)\n\ timeshift=nnn add nnn seconds to file times\n\ \n"); } static int hpfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hpfs_fc_context *ctx = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, hpfs_param_spec, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_help: hpfs_help(); return -EINVAL; case Opt_uid: ctx->uid = result.uid; break; case Opt_gid: ctx->gid = result.gid; break; case Opt_umask: ctx->umask = result.uint_32; break; case Opt_case: ctx->lowercase = result.uint_32; break; case Opt_check: ctx->chk = result.uint_32; break; case Opt_err: ctx->errs = result.uint_32; break; case Opt_eas: ctx->eas = result.uint_32; break; case Opt_chkdsk: ctx->chkdsk = result.uint_32; break; case Opt_timeshift: { int m = 1; char *rhs = param->string; int timeshift; if (*rhs == '-') m = -1; if (*rhs == '+' || *rhs == '-') rhs++; timeshift = simple_strtoul(rhs, &rhs, 0) * m; if (*rhs) return -EINVAL; ctx->timeshift = timeshift; break; } default: return -EINVAL; } return 0; } static int hpfs_reconfigure(struct fs_context *fc) { struct hpfs_fc_context *ctx = fc->fs_private; struct super_block *s = fc->root->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(s); sync_filesystem(s); fc->sb_flags |= SB_NOATIME; hpfs_lock(s); if (ctx->timeshift != sbi->sb_timeshift) { pr_err("timeshift can't be changed using remount.\n"); goto out_err; } unmark_dirty(s); sbi->sb_uid = ctx->uid; sbi->sb_gid = ctx->gid; sbi->sb_mode = 0777 & ~ctx->umask; sbi->sb_lowercase = ctx->lowercase; sbi->sb_eas = ctx->eas; sbi->sb_chk = ctx->chk; sbi->sb_chkdsk = ctx->chkdsk; sbi->sb_err = ctx->errs; sbi->sb_timeshift = ctx->timeshift; if (!(fc->sb_flags & SB_RDONLY)) mark_dirty(s, 1); hpfs_unlock(s); return 0; out_err: hpfs_unlock(s); return -EINVAL; } static int hpfs_show_options(struct seq_file *seq, struct dentry *root) { struct hpfs_sb_info *sbi = hpfs_sb(root->d_sb); seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, sbi->sb_uid)); seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbi->sb_gid)); seq_printf(seq, ",umask=%03o", (~sbi->sb_mode & 0777)); if (sbi->sb_lowercase) seq_printf(seq, ",case=lower"); if (!sbi->sb_chk) seq_printf(seq, ",check=none"); if (sbi->sb_chk == 2) seq_printf(seq, ",check=strict"); if (!sbi->sb_err) seq_printf(seq, ",errors=continue"); if (sbi->sb_err == 2) seq_printf(seq, ",errors=panic"); if (!sbi->sb_chkdsk) seq_printf(seq, ",chkdsk=no"); if (sbi->sb_chkdsk == 2) seq_printf(seq, ",chkdsk=always"); if (!sbi->sb_eas) seq_printf(seq, ",eas=no"); if (sbi->sb_eas == 1) seq_printf(seq, ",eas=ro"); if (sbi->sb_timeshift) seq_printf(seq, ",timeshift=%d", sbi->sb_timeshift); return 0; } /* Super operations */ static const struct super_operations hpfs_sops = { .alloc_inode = hpfs_alloc_inode, .free_inode = hpfs_free_inode, .evict_inode = hpfs_evict_inode, .put_super = hpfs_put_super, .statfs = hpfs_statfs, .show_options = hpfs_show_options, }; static int hpfs_fill_super(struct super_block *s, struct fs_context *fc) { struct hpfs_fc_context *ctx = fc->fs_private; struct buffer_head *bh0, *bh1, *bh2; struct hpfs_boot_block *bootblock; struct hpfs_super_block *superblock; struct hpfs_spare_block *spareblock; struct hpfs_sb_info *sbi; struct inode *root; int silent = fc->sb_flags & SB_SILENT; dnode_secno root_dno; struct hpfs_dirent *de = NULL; struct quad_buffer_head qbh; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) { return -ENOMEM; } s->s_fs_info = sbi; mutex_init(&sbi->hpfs_mutex); hpfs_lock(s); /*sbi->sb_mounting = 1;*/ sb_set_blocksize(s, 512); sbi->sb_fs_size = -1; if (!(bootblock = hpfs_map_sector(s, 0, &bh0, 0))) goto bail1; if (!(superblock = hpfs_map_sector(s, 16, &bh1, 1))) goto bail2; if (!(spareblock = hpfs_map_sector(s, 17, &bh2, 0))) goto bail3; /* Check magics */ if (/*le16_to_cpu(bootblock->magic) != BB_MAGIC ||*/ le32_to_cpu(superblock->magic) != SB_MAGIC || le32_to_cpu(spareblock->magic) != SP_MAGIC) { if (!silent) pr_err("Bad magic ... probably not HPFS\n"); goto bail4; } /* Check version */ if (!sb_rdonly(s) && superblock->funcversion != 2 && superblock->funcversion != 3) { pr_err("Bad version %d,%d. Mount readonly to go around\n", (int)superblock->version, (int)superblock->funcversion); pr_err("please try recent version of HPFS driver at http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi and if it still can't understand this format, contact author - mikulas@artax.karlin.mff.cuni.cz\n"); goto bail4; } s->s_flags |= SB_NOATIME; /* Fill superblock stuff */ s->s_magic = HPFS_SUPER_MAGIC; s->s_op = &hpfs_sops; s->s_d_op = &hpfs_dentry_operations; s->s_time_min = local_to_gmt(s, 0); s->s_time_max = local_to_gmt(s, U32_MAX); sbi->sb_root = le32_to_cpu(superblock->root); sbi->sb_fs_size = le32_to_cpu(superblock->n_sectors); sbi->sb_bitmaps = le32_to_cpu(superblock->bitmaps); sbi->sb_dirband_start = le32_to_cpu(superblock->dir_band_start); sbi->sb_dirband_size = le32_to_cpu(superblock->n_dir_band); sbi->sb_dmap = le32_to_cpu(superblock->dir_band_bitmap); sbi->sb_uid = ctx->uid; sbi->sb_gid = ctx->gid; sbi->sb_mode = 0777 & ~ctx->umask; sbi->sb_n_free = -1; sbi->sb_n_free_dnodes = -1; sbi->sb_lowercase = ctx->lowercase; sbi->sb_eas = ctx->eas; sbi->sb_chk = ctx->chk; sbi->sb_chkdsk = ctx->chkdsk; sbi->sb_err = ctx->errs; sbi->sb_timeshift = ctx->timeshift; sbi->sb_was_error = 0; sbi->sb_cp_table = NULL; sbi->sb_c_bitmap = -1; sbi->sb_max_fwd_alloc = 0xffffff; if (sbi->sb_fs_size >= 0x80000000) { hpfs_error(s, "invalid size in superblock: %08x", (unsigned)sbi->sb_fs_size); goto bail4; } if (spareblock->n_spares_used) hpfs_load_hotfix_map(s, spareblock); /* Load bitmap directory */ if (!(sbi->sb_bmp_dir = hpfs_load_bitmap_directory(s, le32_to_cpu(superblock->bitmaps)))) goto bail4; /* Check for general fs errors*/ if (spareblock->dirty && !spareblock->old_wrote) { if (sbi->sb_err == 2) { pr_err("Improperly stopped, not mounted\n"); goto bail4; } hpfs_error(s, "improperly stopped"); } if (!sb_rdonly(s)) { spareblock->dirty = 1; spareblock->old_wrote = 0; mark_buffer_dirty(bh2); } if (le32_to_cpu(spareblock->n_dnode_spares) != le32_to_cpu(spareblock->n_dnode_spares_free)) { if (sbi->sb_err >= 2) { pr_err("Spare dnodes used, try chkdsk\n"); mark_dirty(s, 0); goto bail4; } hpfs_error(s, "warning: spare dnodes used, try chkdsk"); if (sbi->sb_err == 0) pr_err("Proceeding, but your filesystem could be corrupted if you delete files or directories\n"); } if (sbi->sb_chk) { unsigned a; if (le32_to_cpu(superblock->dir_band_end) - le32_to_cpu(superblock->dir_band_start) + 1 != le32_to_cpu(superblock->n_dir_band) || le32_to_cpu(superblock->dir_band_end) < le32_to_cpu(superblock->dir_band_start) || le32_to_cpu(superblock->n_dir_band) > 0x4000) { hpfs_error(s, "dir band size mismatch: dir_band_start==%08x, dir_band_end==%08x, n_dir_band==%08x", le32_to_cpu(superblock->dir_band_start), le32_to_cpu(superblock->dir_band_end), le32_to_cpu(superblock->n_dir_band)); goto bail4; } a = sbi->sb_dirband_size; sbi->sb_dirband_size = 0; if (hpfs_chk_sectors(s, le32_to_cpu(superblock->dir_band_start), le32_to_cpu(superblock->n_dir_band), "dir_band") || hpfs_chk_sectors(s, le32_to_cpu(superblock->dir_band_bitmap), 4, "dir_band_bitmap") || hpfs_chk_sectors(s, le32_to_cpu(superblock->bitmaps), 4, "bitmaps")) { mark_dirty(s, 0); goto bail4; } sbi->sb_dirband_size = a; } else pr_err("You really don't want any checks? You are crazy...\n"); /* Load code page table */ if (le32_to_cpu(spareblock->n_code_pages)) if (!(sbi->sb_cp_table = hpfs_load_code_page(s, le32_to_cpu(spareblock->code_page_dir)))) pr_err("code page support is disabled\n"); brelse(bh2); brelse(bh1); brelse(bh0); root = iget_locked(s, sbi->sb_root); if (!root) goto bail0; hpfs_init_inode(root); hpfs_read_inode(root); unlock_new_inode(root); s->s_root = d_make_root(root); if (!s->s_root) goto bail0; /* * find the root directory's . pointer & finish filling in the inode */ root_dno = hpfs_fnode_dno(s, sbi->sb_root); if (root_dno) de = map_dirent(root, root_dno, "\001\001", 2, NULL, &qbh); if (!de) hpfs_error(s, "unable to find root dir"); else { inode_set_atime(root, local_to_gmt(s, le32_to_cpu(de->read_date)), 0); inode_set_mtime(root, local_to_gmt(s, le32_to_cpu(de->write_date)), 0); inode_set_ctime(root, local_to_gmt(s, le32_to_cpu(de->creation_date)), 0); hpfs_i(root)->i_ea_size = le32_to_cpu(de->ea_size); hpfs_i(root)->i_parent_dir = root->i_ino; if (root->i_size == -1) root->i_size = 2048; if (root->i_blocks == -1) root->i_blocks = 5; hpfs_brelse4(&qbh); } hpfs_unlock(s); return 0; bail4: brelse(bh2); bail3: brelse(bh1); bail2: brelse(bh0); bail1: bail0: hpfs_unlock(s); free_sbi(sbi); return -EINVAL; } static int hpfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, hpfs_fill_super); } static void hpfs_free_fc(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations hpfs_fc_context_ops = { .parse_param = hpfs_parse_param, .get_tree = hpfs_get_tree, .reconfigure = hpfs_reconfigure, .free = hpfs_free_fc, }; static int hpfs_init_fs_context(struct fs_context *fc) { struct hpfs_fc_context *ctx; ctx = kzalloc(sizeof(struct hpfs_fc_context), GFP_KERNEL); if (!ctx) return -ENOMEM; if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { struct super_block *sb = fc->root->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(sb); ctx->uid = sbi->sb_uid; ctx->gid = sbi->sb_gid; ctx->umask = 0777 & ~sbi->sb_mode; ctx->lowercase = sbi->sb_lowercase; ctx->eas = sbi->sb_eas; ctx->chk = sbi->sb_chk; ctx->chkdsk = sbi->sb_chkdsk; ctx->errs = sbi->sb_err; ctx->timeshift = sbi->sb_timeshift; } else { ctx->uid = current_uid(); ctx->gid = current_gid(); ctx->umask = current_umask(); ctx->lowercase = 0; ctx->eas = 2; ctx->chk = 1; ctx->errs = 1; ctx->chkdsk = 1; ctx->timeshift = 0; } fc->fs_private = ctx; fc->ops = &hpfs_fc_context_ops; return 0; }; static struct file_system_type hpfs_fs_type = { .owner = THIS_MODULE, .name = "hpfs", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = hpfs_init_fs_context, .parameters = hpfs_param_spec, }; MODULE_ALIAS_FS("hpfs"); static int __init init_hpfs_fs(void) { int err = init_inodecache(); if (err) goto out1; err = register_filesystem(&hpfs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_hpfs_fs(void) { unregister_filesystem(&hpfs_fs_type); destroy_inodecache(); } module_init(init_hpfs_fs) module_exit(exit_hpfs_fs) MODULE_DESCRIPTION("OS/2 HPFS file system support"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * Copyright (c) 2013 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_da_format.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_bmap.h" #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_attr_sf.h" #include "xfs_attr_leaf.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_dir2.h" #include "xfs_health.h" STATIC int xfs_attr_shortform_compare(const void *a, const void *b) { xfs_attr_sf_sort_t *sa, *sb; sa = (xfs_attr_sf_sort_t *)a; sb = (xfs_attr_sf_sort_t *)b; if (sa->hash < sb->hash) { return -1; } else if (sa->hash > sb->hash) { return 1; } else { return sa->entno - sb->entno; } } #define XFS_ISRESET_CURSOR(cursor) \ (!((cursor)->initted) && !((cursor)->hashval) && \ !((cursor)->blkno) && !((cursor)->offset)) /* * Copy out entries of shortform attribute lists for attr_list(). * Shortform attribute lists are not stored in hashval sorted order. * If the output buffer is not large enough to hold them all, then * we have to calculate each entries' hashvalue and sort them before * we can begin returning them to the user. */ static int xfs_attr_shortform_list( struct xfs_attr_list_context *context) { struct xfs_attrlist_cursor_kern *cursor = &context->cursor; struct xfs_inode *dp = context->dp; struct xfs_attr_sf_sort *sbuf, *sbp; struct xfs_attr_sf_hdr *sf = dp->i_af.if_data; struct xfs_attr_sf_entry *sfe; int sbsize, nsbuf, count, i; int error = 0; ASSERT(sf != NULL); if (!sf->count) return 0; trace_xfs_attr_list_sf(context); /* * If the buffer is large enough and the cursor is at the start, * do not bother with sorting since we will return everything in * one buffer and another call using the cursor won't need to be * made. * Note the generous fudge factor of 16 overhead bytes per entry. * If bufsize is zero then put_listent must be a search function * and can just scan through what we have. */ if (context->bufsize == 0 || (XFS_ISRESET_CURSOR(cursor) && (dp->i_af.if_bytes + sf->count * 16) < context->bufsize)) { for (i = 0, sfe = xfs_attr_sf_firstentry(sf); i < sf->count; i++) { if (XFS_IS_CORRUPT(context->dp->i_mount, !xfs_attr_namecheck(sfe->flags, sfe->nameval, sfe->namelen))) { xfs_dirattr_mark_sick(context->dp, XFS_ATTR_FORK); return -EFSCORRUPTED; } context->put_listent(context, sfe->flags, sfe->nameval, (int)sfe->namelen, &sfe->nameval[sfe->namelen], (int)sfe->valuelen); /* * Either search callback finished early or * didn't fit it all in the buffer after all. */ if (context->seen_enough) break; sfe = xfs_attr_sf_nextentry(sfe); } trace_xfs_attr_list_sf_all(context); return 0; } /* do no more for a search callback */ if (context->bufsize == 0) return 0; /* * It didn't all fit, so we have to sort everything on hashval. */ sbsize = sf->count * sizeof(*sbuf); sbp = sbuf = kmalloc(sbsize, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); /* * Scan the attribute list for the rest of the entries, storing * the relevant info from only those that match into a buffer. */ nsbuf = 0; for (i = 0, sfe = xfs_attr_sf_firstentry(sf); i < sf->count; i++) { if (unlikely( ((char *)sfe < (char *)sf) || ((char *)sfe >= ((char *)sf + dp->i_af.if_bytes)) || !xfs_attr_check_namespace(sfe->flags))) { XFS_CORRUPTION_ERROR("xfs_attr_shortform_list", XFS_ERRLEVEL_LOW, context->dp->i_mount, sfe, sizeof(*sfe)); kfree(sbuf); xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); return -EFSCORRUPTED; } sbp->entno = i; sbp->name = sfe->nameval; sbp->namelen = sfe->namelen; /* These are bytes, and both on-disk, don't endian-flip */ sbp->value = &sfe->nameval[sfe->namelen]; sbp->valuelen = sfe->valuelen; sbp->flags = sfe->flags; sbp->hash = xfs_attr_hashval(dp->i_mount, sfe->flags, sfe->nameval, sfe->namelen, sfe->nameval + sfe->namelen, sfe->valuelen); sfe = xfs_attr_sf_nextentry(sfe); sbp++; nsbuf++; } /* * Sort the entries on hash then entno. */ xfs_sort(sbuf, nsbuf, sizeof(*sbuf), xfs_attr_shortform_compare); /* * Re-find our place IN THE SORTED LIST. */ count = 0; cursor->initted = 1; cursor->blkno = 0; for (sbp = sbuf, i = 0; i < nsbuf; i++, sbp++) { if (sbp->hash == cursor->hashval) { if (cursor->offset == count) { break; } count++; } else if (sbp->hash > cursor->hashval) { break; } } if (i == nsbuf) goto out; /* * Loop putting entries into the user buffer. */ for ( ; i < nsbuf; i++, sbp++) { if (cursor->hashval != sbp->hash) { cursor->hashval = sbp->hash; cursor->offset = 0; } if (XFS_IS_CORRUPT(context->dp->i_mount, !xfs_attr_namecheck(sbp->flags, sbp->name, sbp->namelen))) { xfs_dirattr_mark_sick(context->dp, XFS_ATTR_FORK); error = -EFSCORRUPTED; goto out; } context->put_listent(context, sbp->flags, sbp->name, sbp->namelen, sbp->value, sbp->valuelen); if (context->seen_enough) break; cursor->offset++; } out: kfree(sbuf); return error; } /* * We didn't find the block & hash mentioned in the cursor state, so * walk down the attr btree looking for the hash. */ STATIC int xfs_attr_node_list_lookup( struct xfs_attr_list_context *context, struct xfs_attrlist_cursor_kern *cursor, struct xfs_buf **pbp) { struct xfs_da3_icnode_hdr nodehdr; struct xfs_da_intnode *node; struct xfs_da_node_entry *btree; struct xfs_inode *dp = context->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_trans *tp = context->tp; struct xfs_buf *bp; xfs_failaddr_t fa; int i; int error = 0; unsigned int expected_level = 0; uint16_t magic; ASSERT(*pbp == NULL); cursor->blkno = 0; for (;;) { error = xfs_da3_node_read(tp, dp, cursor->blkno, &bp, XFS_ATTR_FORK); if (error) return error; node = bp->b_addr; magic = be16_to_cpu(node->hdr.info.magic); if (magic == XFS_ATTR_LEAF_MAGIC || magic == XFS_ATTR3_LEAF_MAGIC) break; if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, node, sizeof(*node)); goto out_corruptbuf; } fa = xfs_da3_node_header_check(bp, dp->i_ino); if (fa) goto out_corruptbuf; xfs_da3_node_hdr_from_disk(mp, &nodehdr, node); /* Tree taller than we can handle; bail out! */ if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) goto out_corruptbuf; /* Check the level from the root node. */ if (cursor->blkno == 0) expected_level = nodehdr.level - 1; else if (expected_level != nodehdr.level) goto out_corruptbuf; else expected_level--; btree = nodehdr.btree; for (i = 0; i < nodehdr.count; btree++, i++) { if (cursor->hashval <= be32_to_cpu(btree->hashval)) { cursor->blkno = be32_to_cpu(btree->before); trace_xfs_attr_list_node_descend(context, btree); break; } } xfs_trans_brelse(tp, bp); if (i == nodehdr.count) return 0; /* We can't point back to the root. */ if (XFS_IS_CORRUPT(mp, cursor->blkno == 0)) { xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); return -EFSCORRUPTED; } } fa = xfs_attr3_leaf_header_check(bp, dp->i_ino); if (fa) { __xfs_buf_mark_corrupt(bp, fa); goto out_releasebuf; } if (expected_level != 0) goto out_corruptbuf; *pbp = bp; return 0; out_corruptbuf: xfs_buf_mark_corrupt(bp); out_releasebuf: xfs_trans_brelse(tp, bp); xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); return -EFSCORRUPTED; } STATIC int xfs_attr_node_list( struct xfs_attr_list_context *context) { struct xfs_attrlist_cursor_kern *cursor = &context->cursor; struct xfs_attr3_icleaf_hdr leafhdr; struct xfs_attr_leafblock *leaf; struct xfs_da_intnode *node; struct xfs_buf *bp; struct xfs_inode *dp = context->dp; struct xfs_mount *mp = dp->i_mount; xfs_failaddr_t fa; int error = 0; trace_xfs_attr_node_list(context); cursor->initted = 1; /* * Do all sorts of validation on the passed-in cursor structure. * If anything is amiss, ignore the cursor and look up the hashval * starting from the btree root. */ bp = NULL; if (cursor->blkno > 0) { struct xfs_attr_leaf_entry *entries; error = xfs_da3_node_read(context->tp, dp, cursor->blkno, &bp, XFS_ATTR_FORK); if (xfs_metadata_is_sick(error)) xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); if (error != 0 && error != -EFSCORRUPTED) return error; if (!bp) goto need_lookup; node = bp->b_addr; switch (be16_to_cpu(node->hdr.info.magic)) { case XFS_DA_NODE_MAGIC: case XFS_DA3_NODE_MAGIC: trace_xfs_attr_list_wrong_blk(context); fa = xfs_da3_node_header_check(bp, dp->i_ino); if (fa) { __xfs_buf_mark_corrupt(bp, fa); xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); } xfs_trans_brelse(context->tp, bp); bp = NULL; break; case XFS_ATTR_LEAF_MAGIC: case XFS_ATTR3_LEAF_MAGIC: leaf = bp->b_addr; fa = xfs_attr3_leaf_header_check(bp, dp->i_ino); if (fa) { __xfs_buf_mark_corrupt(bp, fa); xfs_trans_brelse(context->tp, bp); xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); bp = NULL; break; } xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); if (cursor->hashval > be32_to_cpu( entries[leafhdr.count - 1].hashval)) { trace_xfs_attr_list_wrong_blk(context); xfs_trans_brelse(context->tp, bp); bp = NULL; } else if (cursor->hashval <= be32_to_cpu( entries[0].hashval)) { trace_xfs_attr_list_wrong_blk(context); xfs_trans_brelse(context->tp, bp); bp = NULL; } break; default: trace_xfs_attr_list_wrong_blk(context); xfs_trans_brelse(context->tp, bp); bp = NULL; } } /* * We did not find what we expected given the cursor's contents, * so we start from the top and work down based on the hash value. * Note that start of node block is same as start of leaf block. */ if (bp == NULL) { need_lookup: error = xfs_attr_node_list_lookup(context, cursor, &bp); if (error || !bp) return error; } ASSERT(bp != NULL); /* * Roll upward through the blocks, processing each leaf block in * order. As long as there is space in the result buffer, keep * adding the information. */ for (;;) { leaf = bp->b_addr; error = xfs_attr3_leaf_list_int(bp, context); if (error) break; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf); if (context->seen_enough || leafhdr.forw == 0) break; cursor->blkno = leafhdr.forw; xfs_trans_brelse(context->tp, bp); error = xfs_attr3_leaf_read(context->tp, dp, dp->i_ino, cursor->blkno, &bp); if (error) return error; } xfs_trans_brelse(context->tp, bp); return error; } /* * Copy out attribute list entries for attr_list(), for leaf attribute lists. */ int xfs_attr3_leaf_list_int( struct xfs_buf *bp, struct xfs_attr_list_context *context) { struct xfs_attrlist_cursor_kern *cursor = &context->cursor; struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entries; struct xfs_attr_leaf_entry *entry; int i; struct xfs_mount *mp = context->dp->i_mount; trace_xfs_attr_list_leaf(context); leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); cursor->initted = 1; /* * Re-find our place in the leaf block if this is a new syscall. */ if (context->resynch) { entry = &entries[0]; for (i = 0; i < ichdr.count; entry++, i++) { if (be32_to_cpu(entry->hashval) == cursor->hashval) { if (cursor->offset == context->dupcnt) { context->dupcnt = 0; break; } context->dupcnt++; } else if (be32_to_cpu(entry->hashval) > cursor->hashval) { context->dupcnt = 0; break; } } if (i == ichdr.count) { trace_xfs_attr_list_notfound(context); return 0; } } else { entry = &entries[0]; i = 0; } context->resynch = 0; /* * We have found our place, start copying out the new attributes. */ for (; i < ichdr.count; entry++, i++) { char *name; void *value; int namelen, valuelen; if (be32_to_cpu(entry->hashval) != cursor->hashval) { cursor->hashval = be32_to_cpu(entry->hashval); cursor->offset = 0; } if ((entry->flags & XFS_ATTR_INCOMPLETE) && !context->allow_incomplete) continue; if (entry->flags & XFS_ATTR_LOCAL) { xfs_attr_leaf_name_local_t *name_loc; name_loc = xfs_attr3_leaf_name_local(leaf, i); name = name_loc->nameval; namelen = name_loc->namelen; value = &name_loc->nameval[name_loc->namelen]; valuelen = be16_to_cpu(name_loc->valuelen); } else { xfs_attr_leaf_name_remote_t *name_rmt; name_rmt = xfs_attr3_leaf_name_remote(leaf, i); name = name_rmt->name; namelen = name_rmt->namelen; value = NULL; valuelen = be32_to_cpu(name_rmt->valuelen); } if (XFS_IS_CORRUPT(context->dp->i_mount, !xfs_attr_namecheck(entry->flags, name, namelen))) { xfs_dirattr_mark_sick(context->dp, XFS_ATTR_FORK); return -EFSCORRUPTED; } context->put_listent(context, entry->flags, name, namelen, value, valuelen); if (context->seen_enough) break; cursor->offset++; } trace_xfs_attr_list_leaf_end(context); return 0; } /* * Copy out attribute entries for attr_list(), for leaf attribute lists. */ STATIC int xfs_attr_leaf_list( struct xfs_attr_list_context *context) { struct xfs_buf *bp; int error; trace_xfs_attr_leaf_list(context); context->cursor.blkno = 0; error = xfs_attr3_leaf_read(context->tp, context->dp, context->dp->i_ino, 0, &bp); if (error) return error; error = xfs_attr3_leaf_list_int(bp, context); xfs_trans_brelse(context->tp, bp); return error; } int xfs_attr_list_ilocked( struct xfs_attr_list_context *context) { struct xfs_inode *dp = context->dp; int error; xfs_assert_ilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); /* * Decide on what work routines to call based on the inode size. */ if (!xfs_inode_hasattr(dp)) return 0; if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) return xfs_attr_shortform_list(context); /* Prerequisite for xfs_attr_is_leaf */ error = xfs_iread_extents(NULL, dp, XFS_ATTR_FORK); if (error) return error; if (xfs_attr_is_leaf(dp)) return xfs_attr_leaf_list(context); return xfs_attr_node_list(context); } int xfs_attr_list( struct xfs_attr_list_context *context) { struct xfs_inode *dp = context->dp; uint lock_mode; int error; XFS_STATS_INC(dp->i_mount, xs_attr_list); if (xfs_is_shutdown(dp->i_mount)) return -EIO; lock_mode = xfs_ilock_attr_map_shared(dp); error = xfs_attr_list_ilocked(context); xfs_iunlock(dp, lock_mode); return error; } |
| 5 5 5 5 5 5 1 1 1 1 1 3 1 1 1 5 5 5 5 5 5 5 5 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 | // SPDX-License-Identifier: GPL-2.0-or-later /* AFS dynamic root handling * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/fs.h> #include <linux/namei.h> #include <linux/dns_resolver.h> #include "internal.h" static atomic_t afs_autocell_ino; /* * iget5() comparator for inode created by autocell operations * * These pseudo inodes don't match anything. */ static int afs_iget5_pseudo_test(struct inode *inode, void *opaque) { return 0; } /* * iget5() inode initialiser */ static int afs_iget5_pseudo_set(struct inode *inode, void *opaque) { struct afs_super_info *as = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_fid *fid = opaque; vnode->volume = as->volume; vnode->fid = *fid; inode->i_ino = fid->vnode; inode->i_generation = fid->unique; return 0; } /* * Create an inode for a dynamic root directory or an autocell dynamic * automount dir. */ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) { struct afs_super_info *as = AFS_FS_S(sb); struct afs_vnode *vnode; struct inode *inode; struct afs_fid fid = {}; _enter(""); if (as->volume) fid.vid = as->volume->vid; if (root) { fid.vnode = 1; fid.unique = 1; } else { fid.vnode = atomic_inc_return(&afs_autocell_ino); fid.unique = 0; } inode = iget5_locked(sb, fid.vnode, afs_iget5_pseudo_test, afs_iget5_pseudo_set, &fid); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } _debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }", inode, inode->i_ino, fid.vid, fid.vnode, fid.unique); vnode = AFS_FS_I(inode); /* there shouldn't be an existing inode */ BUG_ON(!(inode->i_state & I_NEW)); netfs_inode_init(&vnode->netfs, NULL, false); inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; if (root) { inode->i_op = &afs_dynroot_inode_operations; inode->i_fop = &simple_dir_operations; } else { inode->i_op = &afs_autocell_inode_operations; } set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; simple_inode_init_ts(inode); inode->i_blocks = 0; inode->i_generation = 0; set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags); if (!root) { set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); inode->i_flags |= S_AUTOMOUNT; } inode->i_flags |= S_NOATIME; unlock_new_inode(inode); _leave(" = %p", inode); return inode; } /* * Probe to see if a cell may exist. This prevents positive dentries from * being created unnecessarily. */ static int afs_probe_cell_name(struct dentry *dentry) { struct afs_cell *cell; struct afs_net *net = afs_d2net(dentry); const char *name = dentry->d_name.name; size_t len = dentry->d_name.len; char *result = NULL; int ret; /* Names prefixed with a dot are R/W mounts. */ if (name[0] == '.') { if (len == 1) return -EINVAL; name++; len--; } cell = afs_find_cell(net, name, len, afs_cell_trace_use_probe); if (!IS_ERR(cell)) { afs_unuse_cell(net, cell, afs_cell_trace_unuse_probe); return 0; } ret = dns_query(net->net, "afsdb", name, len, "srv=1", &result, NULL, false); if (ret == -ENODATA || ret == -ENOKEY || ret == 0) ret = -ENOENT; if (ret > 0 && ret >= sizeof(struct dns_server_list_v1_header)) { struct dns_server_list_v1_header *v1 = (void *)result; if (v1->hdr.zero == 0 && v1->hdr.content == DNS_PAYLOAD_IS_SERVER_LIST && v1->hdr.version == 1 && (v1->status != DNS_LOOKUP_GOOD && v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) return -ENOENT; } kfree(result); return ret; } /* * Try to auto mount the mountpoint with pseudo directory, if the autocell * operation is setted. */ struct inode *afs_try_auto_mntpt(struct dentry *dentry, struct inode *dir) { struct afs_vnode *vnode = AFS_FS_I(dir); struct inode *inode; int ret = -ENOENT; _enter("%p{%pd}, {%llx:%llu}", dentry, dentry, vnode->fid.vid, vnode->fid.vnode); if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags)) goto out; ret = afs_probe_cell_name(dentry); if (ret < 0) goto out; inode = afs_iget_pseudo_dir(dir->i_sb, false); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto out; } _leave("= %p", inode); return inode; out: _leave("= %d", ret); return ret == -ENOENT ? NULL : ERR_PTR(ret); } /* * Look up an entry in a dynroot directory. */ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { _enter("%pd", dentry); ASSERTCMP(d_inode(dentry), ==, NULL); if (flags & LOOKUP_CREATE) return ERR_PTR(-EOPNOTSUPP); if (dentry->d_name.len >= AFSNAMEMAX) { _leave(" = -ENAMETOOLONG"); return ERR_PTR(-ENAMETOOLONG); } return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry); } const struct inode_operations afs_dynroot_inode_operations = { .lookup = afs_dynroot_lookup, }; const struct dentry_operations afs_dynroot_dentry_operations = { .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, }; /* * Create a manually added cell mount directory. * - The caller must hold net->proc_cells_lock */ int afs_dynroot_mkdir(struct afs_net *net, struct afs_cell *cell) { struct super_block *sb = net->dynroot_sb; struct dentry *root, *subdir, *dsubdir; char *dotname = cell->name - 1; int ret; if (!sb || atomic_read(&sb->s_active) == 0) return 0; /* Let the ->lookup op do the creation */ root = sb->s_root; inode_lock(root->d_inode); subdir = lookup_one_len(cell->name, root, cell->name_len); if (IS_ERR(subdir)) { ret = PTR_ERR(subdir); goto unlock; } dsubdir = lookup_one_len(dotname, root, cell->name_len + 1); if (IS_ERR(dsubdir)) { ret = PTR_ERR(dsubdir); dput(subdir); goto unlock; } /* Note that we're retaining extra refs on the dentries. */ subdir->d_fsdata = (void *)1UL; dsubdir->d_fsdata = (void *)1UL; ret = 0; unlock: inode_unlock(root->d_inode); return ret; } static void afs_dynroot_rm_one_dir(struct dentry *root, const char *name, size_t name_len) { struct dentry *subdir; /* Don't want to trigger a lookup call, which will re-add the cell */ subdir = try_lookup_one_len(name, root, name_len); if (IS_ERR_OR_NULL(subdir)) { _debug("lookup %ld", PTR_ERR(subdir)); return; } _debug("rmdir %pd %u", subdir, d_count(subdir)); if (subdir->d_fsdata) { _debug("unpin %u", d_count(subdir)); subdir->d_fsdata = NULL; dput(subdir); } dput(subdir); } /* * Remove a manually added cell mount directory. * - The caller must hold net->proc_cells_lock */ void afs_dynroot_rmdir(struct afs_net *net, struct afs_cell *cell) { struct super_block *sb = net->dynroot_sb; char *dotname = cell->name - 1; if (!sb || atomic_read(&sb->s_active) == 0) return; inode_lock(sb->s_root->d_inode); afs_dynroot_rm_one_dir(sb->s_root, cell->name, cell->name_len); afs_dynroot_rm_one_dir(sb->s_root, dotname, cell->name_len + 1); inode_unlock(sb->s_root->d_inode); _leave(""); } static void afs_atcell_delayed_put_cell(void *arg) { struct afs_cell *cell = arg; afs_put_cell(cell, afs_cell_trace_put_atcell); } /* * Read @cell or .@cell symlinks. */ static const char *afs_atcell_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_cell *cell; struct afs_net *net = afs_i2net(inode); const char *name; bool dotted = vnode->fid.vnode == 3; if (!net->ws_cell) return ERR_PTR(-ENOENT); down_read(&net->cells_lock); cell = net->ws_cell; if (dotted) name = cell->name - 1; else name = cell->name; afs_get_cell(cell, afs_cell_trace_get_atcell); set_delayed_call(done, afs_atcell_delayed_put_cell, cell); up_read(&net->cells_lock); return name; } static const struct inode_operations afs_atcell_inode_operations = { .get_link = afs_atcell_get_link, }; /* * Look up @cell or .@cell in a dynroot directory. This is a substitution for * the local cell name for the net namespace. */ static struct dentry *afs_dynroot_create_symlink(struct dentry *root, const char *name) { struct afs_vnode *vnode; struct afs_fid fid = { .vnode = 2, .unique = 1, }; struct dentry *dentry; struct inode *inode; if (name[0] == '.') fid.vnode = 3; dentry = d_alloc_name(root, name); if (!dentry) return ERR_PTR(-ENOMEM); inode = iget5_locked(dentry->d_sb, fid.vnode, afs_iget5_pseudo_test, afs_iget5_pseudo_set, &fid); if (!inode) { dput(dentry); return ERR_PTR(-ENOMEM); } vnode = AFS_FS_I(inode); /* there shouldn't be an existing inode */ if (WARN_ON_ONCE(!(inode->i_state & I_NEW))) { iput(inode); dput(dentry); return ERR_PTR(-EIO); } netfs_inode_init(&vnode->netfs, NULL, false); simple_inode_init_ts(inode); set_nlink(inode, 1); inode->i_size = 0; inode->i_mode = S_IFLNK | 0555; inode->i_op = &afs_atcell_inode_operations; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_blocks = 0; inode->i_generation = 0; inode->i_flags |= S_NOATIME; unlock_new_inode(inode); d_splice_alias(inode, dentry); return dentry; } /* * Create @cell and .@cell symlinks. */ static int afs_dynroot_symlink(struct afs_net *net) { struct super_block *sb = net->dynroot_sb; struct dentry *root, *symlink, *dsymlink; int ret; /* Let the ->lookup op do the creation */ root = sb->s_root; inode_lock(root->d_inode); symlink = afs_dynroot_create_symlink(root, "@cell"); if (IS_ERR(symlink)) { ret = PTR_ERR(symlink); goto unlock; } dsymlink = afs_dynroot_create_symlink(root, ".@cell"); if (IS_ERR(dsymlink)) { ret = PTR_ERR(dsymlink); dput(symlink); goto unlock; } /* Note that we're retaining extra refs on the dentries. */ symlink->d_fsdata = (void *)1UL; dsymlink->d_fsdata = (void *)1UL; ret = 0; unlock: inode_unlock(root->d_inode); return ret; } /* * Populate a newly created dynamic root with cell names. */ int afs_dynroot_populate(struct super_block *sb) { struct afs_cell *cell; struct afs_net *net = afs_sb2net(sb); int ret; mutex_lock(&net->proc_cells_lock); net->dynroot_sb = sb; ret = afs_dynroot_symlink(net); if (ret < 0) goto error; hlist_for_each_entry(cell, &net->proc_cells, proc_link) { ret = afs_dynroot_mkdir(net, cell); if (ret < 0) goto error; } ret = 0; out: mutex_unlock(&net->proc_cells_lock); return ret; error: net->dynroot_sb = NULL; goto out; } /* * When a dynamic root that's in the process of being destroyed, depopulate it * of pinned directories. */ void afs_dynroot_depopulate(struct super_block *sb) { struct afs_net *net = afs_sb2net(sb); struct dentry *root = sb->s_root, *subdir; /* Prevent more subdirs from being created */ mutex_lock(&net->proc_cells_lock); if (net->dynroot_sb == sb) net->dynroot_sb = NULL; mutex_unlock(&net->proc_cells_lock); if (root) { struct hlist_node *n; inode_lock(root->d_inode); /* Remove all the pins for dirs created for manually added cells */ hlist_for_each_entry_safe(subdir, n, &root->d_children, d_sib) { if (subdir->d_fsdata) { subdir->d_fsdata = NULL; dput(subdir); } } inode_unlock(root->d_inode); } } |
| 22 12 22 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* * linux/fs/nls/nls_cp775.c * * Charset cp775 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0106, 0x00fc, 0x00e9, 0x0101, 0x00e4, 0x0123, 0x00e5, 0x0107, 0x0142, 0x0113, 0x0156, 0x0157, 0x012b, 0x0179, 0x00c4, 0x00c5, /* 0x90*/ 0x00c9, 0x00e6, 0x00c6, 0x014d, 0x00f6, 0x0122, 0x00a2, 0x015a, 0x015b, 0x00d6, 0x00dc, 0x00f8, 0x00a3, 0x00d8, 0x00d7, 0x00a4, /* 0xa0*/ 0x0100, 0x012a, 0x00f3, 0x017b, 0x017c, 0x017a, 0x201d, 0x00a6, 0x00a9, 0x00ae, 0x00ac, 0x00bd, 0x00bc, 0x0141, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x0104, 0x010c, 0x0118, 0x0116, 0x2563, 0x2551, 0x2557, 0x255d, 0x012e, 0x0160, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x0172, 0x016a, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x017d, /* 0xd0*/ 0x0105, 0x010d, 0x0119, 0x0117, 0x012f, 0x0161, 0x0173, 0x016b, 0x017e, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x00d3, 0x00df, 0x014c, 0x0143, 0x00f5, 0x00d5, 0x00b5, 0x0144, 0x0136, 0x0137, 0x013b, 0x013c, 0x0146, 0x0112, 0x0145, 0x2019, /* 0xf0*/ 0x00ad, 0x00b1, 0x201c, 0x00be, 0x00b6, 0x00a7, 0x00f7, 0x201e, 0x00b0, 0x2219, 0x00b7, 0x00b9, 0x00b3, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x96, 0x9c, 0x9f, 0x00, 0xa7, 0xf5, /* 0xa0-0xa7 */ 0x00, 0xa8, 0x00, 0xae, 0xaa, 0xf0, 0xa9, 0x00, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0xfc, 0x00, 0xe6, 0xf4, 0xfa, /* 0xb0-0xb7 */ 0x00, 0xfb, 0x00, 0xaf, 0xac, 0xab, 0xf3, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x8e, 0x8f, 0x92, 0x00, /* 0xc0-0xc7 */ 0x00, 0x90, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0xe0, 0x00, 0xe5, 0x99, 0x9e, /* 0xd0-0xd7 */ 0x9d, 0x00, 0x00, 0x00, 0x9a, 0x00, 0x00, 0xe1, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x84, 0x86, 0x91, 0x00, /* 0xe0-0xe7 */ 0x00, 0x82, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0xa2, 0x00, 0xe4, 0x94, 0xf6, /* 0xf0-0xf7 */ 0x9b, 0x00, 0x00, 0x00, 0x81, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0xa0, 0x83, 0x00, 0x00, 0xb5, 0xd0, 0x80, 0x87, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xb6, 0xd1, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0xed, 0x89, 0x00, 0x00, 0xb8, 0xd3, /* 0x10-0x17 */ 0xb7, 0xd2, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x95, 0x85, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0xa1, 0x8c, 0x00, 0x00, 0xbd, 0xd4, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe8, 0xe9, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0xea, 0xeb, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0xad, 0x88, 0xe3, 0xe7, 0xee, 0xec, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0xe2, 0x93, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8a, 0x8b, /* 0x50-0x57 */ 0x00, 0x00, 0x97, 0x98, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0xbe, 0xd5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0xc7, 0xd7, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0xc6, 0xd6, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x8d, 0xa5, 0xa3, 0xa4, 0xcf, 0xd8, 0x00, /* 0x78-0x7f */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xef, 0x00, 0x00, 0xf2, 0xa6, 0xf7, 0x00, /* 0x18-0x1f */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0x00, 0x00, 0xc9, 0x00, 0x00, 0xbb, /* 0x50-0x57 */ 0x00, 0x00, 0xc8, 0x00, 0x00, 0xbc, 0x00, 0x00, /* 0x58-0x5f */ 0xcc, 0x00, 0x00, 0xb9, 0x00, 0x00, 0xcb, 0x00, /* 0x60-0x67 */ 0x00, 0xca, 0x00, 0x00, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, NULL, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8b, 0x8b, 0x8c, 0xa5, 0x84, 0x86, /* 0x88-0x8f */ 0x82, 0x91, 0x91, 0x93, 0x94, 0x85, 0x96, 0x98, /* 0x90-0x97 */ 0x98, 0x94, 0x81, 0x9b, 0x9c, 0x9b, 0x9e, 0x9f, /* 0x98-0x9f */ 0x83, 0x8c, 0xa2, 0xa4, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0x88, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xd0, 0xd1, 0xd2, /* 0xb0-0xb7 */ 0xd3, 0xb9, 0xba, 0xbb, 0xbc, 0xd4, 0xd5, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xd6, 0xd7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xd8, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xa2, 0xe1, 0x93, 0xe7, 0xe4, 0xe4, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe9, 0xe9, 0xeb, 0xeb, 0xec, 0x89, 0xec, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0xa0, 0x8e, 0x95, 0x8f, 0x80, /* 0x80-0x87 */ 0xad, 0xed, 0x8a, 0x8a, 0xa1, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x92, 0x92, 0xe2, 0x99, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x97, 0x99, 0x9a, 0x9d, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xe0, 0xa3, 0xa3, 0x8d, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xb5, 0xb6, 0xb7, 0xb8, 0xbd, 0xbe, 0xc6, 0xc7, /* 0xd0-0xd7 */ 0xcf, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe5, 0xe5, 0x00, 0xe3, /* 0xe0-0xe7 */ 0xe8, 0xe8, 0xea, 0xea, 0xee, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp775", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp775(void) { return register_nls(&table); } static void __exit exit_nls_cp775(void) { unregister_nls(&table); } module_init(init_nls_cp775) module_exit(exit_nls_cp775) MODULE_DESCRIPTION("NLS Codepage 775 (Baltic Rim)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 8109 8109 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_H #define _ASM_X86_PAGE_H #include <linux/types.h> #ifdef __KERNEL__ #include <asm/page_types.h> #ifdef CONFIG_X86_64 #include <asm/page_64.h> #else #include <asm/page_32.h> #endif /* CONFIG_X86_64 */ #ifndef __ASSEMBLY__ struct page; #include <linux/range.h> extern struct range pfn_mapped[]; extern int nr_pfn_mapped; static inline void clear_user_page(void *page, unsigned long vaddr, struct page *pg) { clear_page(page); } static inline void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage) { copy_page(to, from); } #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) #ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) #endif #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ /* * We need __phys_reloc_hide() here because gcc may assume that there is no * overflow during __pa() calculation and can optimize it unexpectedly. * Newer versions of gcc provide -fno-strict-overflow switch to handle this * case properly. Once all supported versions of gcc understand it, we can * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) */ #define __pa_symbol(x) \ __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) #ifndef __va #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) #endif #define __boot_va(x) __va(x) #define __boot_pa(x) __pa(x) /* * virt_to_page(kaddr) returns a valid pointer if and only if * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) static __always_inline void *pfn_to_kaddr(unsigned long pfn) { return __va(pfn << PAGE_SHIFT); } static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits) { return __canonical_address(vaddr, vaddr_bits) == vaddr; } #endif /* __ASSEMBLY__ */ #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #endif /* __KERNEL__ */ #endif /* _ASM_X86_PAGE_H */ |
| 231 133 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_MISC_H #define BTRFS_MISC_H #include <linux/types.h> #include <linux/bitmap.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/math64.h> #include <linux/rbtree.h> /* * Enumerate bits using enum autoincrement. Define the @name as the n-th bit. */ #define ENUM_BIT(name) \ __ ## name ## _BIT, \ name = (1U << __ ## name ## _BIT), \ __ ## name ## _SEQ = __ ## name ## _BIT static inline void cond_wake_up(struct wait_queue_head *wq) { /* * This implies a full smp_mb barrier, see comments for * waitqueue_active why. */ if (wq_has_sleeper(wq)) wake_up(wq); } static inline void cond_wake_up_nomb(struct wait_queue_head *wq) { /* * Special case for conditional wakeup where the barrier required for * waitqueue_active is implied by some of the preceding code. Eg. one * of such atomic operations (atomic_dec_and_return, ...), or a * unlock/lock sequence, etc. */ if (waitqueue_active(wq)) wake_up(wq); } static inline u64 mult_perc(u64 num, u32 percent) { return div_u64(num * percent, 100); } /* Copy of is_power_of_two that is 64bit safe */ static inline bool is_power_of_two_u64(u64 n) { return n != 0 && (n & (n - 1)) == 0; } static inline bool has_single_bit_set(u64 n) { return is_power_of_two_u64(n); } /* * Simple bytenr based rb_tree relate structures * * Any structure wants to use bytenr as single search index should have their * structure start with these members. */ struct rb_simple_node { struct rb_node rb_node; u64 bytenr; }; static inline struct rb_node *rb_simple_search(const struct rb_root *root, u64 bytenr) { struct rb_node *node = root->rb_node; struct rb_simple_node *entry; while (node) { entry = rb_entry(node, struct rb_simple_node, rb_node); if (bytenr < entry->bytenr) node = node->rb_left; else if (bytenr > entry->bytenr) node = node->rb_right; else return node; } return NULL; } /* * Search @root from an entry that starts or comes after @bytenr. * * @root: the root to search. * @bytenr: bytenr to search from. * * Return the rb_node that start at or after @bytenr. If there is no entry at * or after @bytner return NULL. */ static inline struct rb_node *rb_simple_search_first(const struct rb_root *root, u64 bytenr) { struct rb_node *node = root->rb_node, *ret = NULL; struct rb_simple_node *entry, *ret_entry = NULL; while (node) { entry = rb_entry(node, struct rb_simple_node, rb_node); if (bytenr < entry->bytenr) { if (!ret || entry->bytenr < ret_entry->bytenr) { ret = node; ret_entry = entry; } node = node->rb_left; } else if (bytenr > entry->bytenr) { node = node->rb_right; } else { return node; } } return ret; } static inline struct rb_node *rb_simple_insert(struct rb_root *root, u64 bytenr, struct rb_node *node) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct rb_simple_node *entry; while (*p) { parent = *p; entry = rb_entry(parent, struct rb_simple_node, rb_node); if (bytenr < entry->bytenr) p = &(*p)->rb_left; else if (bytenr > entry->bytenr) p = &(*p)->rb_right; else return parent; } rb_link_node(node, parent, p); rb_insert_color(node, root); return NULL; } static inline bool bitmap_test_range_all_set(const unsigned long *addr, unsigned long start, unsigned long nbits) { unsigned long found_zero; found_zero = find_next_zero_bit(addr, start + nbits, start); return (found_zero == start + nbits); } static inline bool bitmap_test_range_all_zero(const unsigned long *addr, unsigned long start, unsigned long nbits) { unsigned long found_set; found_set = find_next_bit(addr, start + nbits, start); return (found_set == start + nbits); } #endif |
| 12 12 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/jump_label.h> #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern bool cpuset_cpu_is_isolated(int cpu); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); #else static inline void cpuset_memory_pressure_bump(void) { } #endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { return false; } static inline bool cpuset_cpu_is_isolated(int cpu) { return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 3 3 1 1 2 2 1 1 2 2 2 3 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * Simple file system for zoned block devices exposing zones as files. * * Copyright (C) 2019 Western Digital Corporation or its affiliates. */ #include <linux/module.h> #include <linux/pagemap.h> #include <linux/magic.h> #include <linux/iomap.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/statfs.h> #include <linux/writeback.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/mman.h> #include <linux/sched/mm.h> #include <linux/crc32.h> #include <linux/task_io_accounting_ops.h> #include <linux/fs_parser.h> #include <linux/fs_context.h> #include "zonefs.h" #define CREATE_TRACE_POINTS #include "trace.h" /* * Get the name of a zone group directory. */ static const char *zonefs_zgroup_name(enum zonefs_ztype ztype) { switch (ztype) { case ZONEFS_ZTYPE_CNV: return "cnv"; case ZONEFS_ZTYPE_SEQ: return "seq"; default: WARN_ON_ONCE(1); return "???"; } } /* * Manage the active zone count. */ static void zonefs_account_active(struct super_block *sb, struct zonefs_zone *z) { struct zonefs_sb_info *sbi = ZONEFS_SB(sb); if (zonefs_zone_is_cnv(z)) return; /* * For zones that transitioned to the offline or readonly condition, * we only need to clear the active state. */ if (z->z_flags & (ZONEFS_ZONE_OFFLINE | ZONEFS_ZONE_READONLY)) goto out; /* * If the zone is active, that is, if it is explicitly open or * partially written, check if it was already accounted as active. */ if ((z->z_flags & ZONEFS_ZONE_OPEN) || (z->z_wpoffset > 0 && z->z_wpoffset < z->z_capacity)) { if (!(z->z_flags & ZONEFS_ZONE_ACTIVE)) { z->z_flags |= ZONEFS_ZONE_ACTIVE; atomic_inc(&sbi->s_active_seq_files); } return; } out: /* The zone is not active. If it was, update the active count */ if (z->z_flags & ZONEFS_ZONE_ACTIVE) { z->z_flags &= ~ZONEFS_ZONE_ACTIVE; atomic_dec(&sbi->s_active_seq_files); } } /* * Manage the active zone count. Called with zi->i_truncate_mutex held. */ void zonefs_inode_account_active(struct inode *inode) { lockdep_assert_held(&ZONEFS_I(inode)->i_truncate_mutex); return zonefs_account_active(inode->i_sb, zonefs_inode_zone(inode)); } /* * Execute a zone management operation. */ static int zonefs_zone_mgmt(struct super_block *sb, struct zonefs_zone *z, enum req_op op) { int ret; /* * With ZNS drives, closing an explicitly open zone that has not been * written will change the zone state to "closed", that is, the zone * will remain active. Since this can then cause failure of explicit * open operation on other zones if the drive active zone resources * are exceeded, make sure that the zone does not remain active by * resetting it. */ if (op == REQ_OP_ZONE_CLOSE && !z->z_wpoffset) op = REQ_OP_ZONE_RESET; trace_zonefs_zone_mgmt(sb, z, op); ret = blkdev_zone_mgmt(sb->s_bdev, op, z->z_sector, z->z_size >> SECTOR_SHIFT); if (ret) { zonefs_err(sb, "Zone management operation %s at %llu failed %d\n", blk_op_str(op), z->z_sector, ret); return ret; } return 0; } int zonefs_inode_zone_mgmt(struct inode *inode, enum req_op op) { lockdep_assert_held(&ZONEFS_I(inode)->i_truncate_mutex); return zonefs_zone_mgmt(inode->i_sb, zonefs_inode_zone(inode), op); } void zonefs_i_size_write(struct inode *inode, loff_t isize) { struct zonefs_zone *z = zonefs_inode_zone(inode); i_size_write(inode, isize); /* * A full zone is no longer open/active and does not need * explicit closing. */ if (isize >= z->z_capacity) { struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); if (z->z_flags & ZONEFS_ZONE_ACTIVE) atomic_dec(&sbi->s_active_seq_files); z->z_flags &= ~(ZONEFS_ZONE_OPEN | ZONEFS_ZONE_ACTIVE); } } void zonefs_update_stats(struct inode *inode, loff_t new_isize) { struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); loff_t old_isize = i_size_read(inode); loff_t nr_blocks; if (new_isize == old_isize) return; spin_lock(&sbi->s_lock); /* * This may be called for an update after an IO error. * So beware of the values seen. */ if (new_isize < old_isize) { nr_blocks = (old_isize - new_isize) >> sb->s_blocksize_bits; if (sbi->s_used_blocks > nr_blocks) sbi->s_used_blocks -= nr_blocks; else sbi->s_used_blocks = 0; } else { sbi->s_used_blocks += (new_isize - old_isize) >> sb->s_blocksize_bits; if (sbi->s_used_blocks > sbi->s_blocks) sbi->s_used_blocks = sbi->s_blocks; } spin_unlock(&sbi->s_lock); } /* * Check a zone condition. Return the amount of written (and still readable) * data in the zone. */ static loff_t zonefs_check_zone_condition(struct super_block *sb, struct zonefs_zone *z, struct blk_zone *zone) { switch (zone->cond) { case BLK_ZONE_COND_OFFLINE: zonefs_warn(sb, "Zone %llu: offline zone\n", z->z_sector); z->z_flags |= ZONEFS_ZONE_OFFLINE; return 0; case BLK_ZONE_COND_READONLY: /* * The write pointer of read-only zones is invalid, so we cannot * determine the zone wpoffset (inode size). We thus keep the * zone wpoffset as is, which leads to an empty file * (wpoffset == 0) on mount. For a runtime error, this keeps * the inode size as it was when last updated so that the user * can recover data. */ zonefs_warn(sb, "Zone %llu: read-only zone\n", z->z_sector); z->z_flags |= ZONEFS_ZONE_READONLY; if (zonefs_zone_is_cnv(z)) return z->z_capacity; return z->z_wpoffset; case BLK_ZONE_COND_FULL: /* The write pointer of full zones is invalid. */ return z->z_capacity; default: if (zonefs_zone_is_cnv(z)) return z->z_capacity; return (zone->wp - zone->start) << SECTOR_SHIFT; } } /* * Check a zone condition and adjust its inode access permissions for * offline and readonly zones. */ static void zonefs_inode_update_mode(struct inode *inode) { struct zonefs_zone *z = zonefs_inode_zone(inode); if (z->z_flags & ZONEFS_ZONE_OFFLINE) { /* Offline zones cannot be read nor written */ inode->i_flags |= S_IMMUTABLE; inode->i_mode &= ~0777; } else if (z->z_flags & ZONEFS_ZONE_READONLY) { /* Readonly zones cannot be written */ inode->i_flags |= S_IMMUTABLE; if (z->z_flags & ZONEFS_ZONE_INIT_MODE) inode->i_mode &= ~0777; else inode->i_mode &= ~0222; } z->z_flags &= ~ZONEFS_ZONE_INIT_MODE; z->z_mode = inode->i_mode; } static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct blk_zone *z = data; *z = *zone; return 0; } static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, bool write) { struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); loff_t isize, data_size; /* * Check the zone condition: if the zone is not "bad" (offline or * read-only), read errors are simply signaled to the IO issuer as long * as there is no inconsistency between the inode size and the amount of * data writen in the zone (data_size). */ data_size = zonefs_check_zone_condition(sb, z, zone); isize = i_size_read(inode); if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) && !write && isize == data_size) return; /* * At this point, we detected either a bad zone or an inconsistency * between the inode size and the amount of data written in the zone. * For the latter case, the cause may be a write IO error or an external * action on the device. Two error patterns exist: * 1) The inode size is lower than the amount of data in the zone: * a write operation partially failed and data was writen at the end * of the file. This can happen in the case of a large direct IO * needing several BIOs and/or write requests to be processed. * 2) The inode size is larger than the amount of data in the zone: * this can happen with a deferred write error with the use of the * device side write cache after getting successful write IO * completions. Other possibilities are (a) an external corruption, * e.g. an application reset the zone directly, or (b) the device * has a serious problem (e.g. firmware bug). * * In all cases, warn about inode size inconsistency and handle the * IO error according to the zone condition and to the mount options. */ if (isize != data_size) zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", inode->i_ino, isize, data_size); /* * First handle bad zones signaled by hardware. The mount options * errors=zone-ro and errors=zone-offline result in changing the * zone condition to read-only and offline respectively, as if the * condition was signaled by the hardware. */ if ((z->z_flags & ZONEFS_ZONE_OFFLINE) || (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL)) { zonefs_warn(sb, "inode %lu: read/write access disabled\n", inode->i_ino); if (!(z->z_flags & ZONEFS_ZONE_OFFLINE)) z->z_flags |= ZONEFS_ZONE_OFFLINE; zonefs_inode_update_mode(inode); data_size = 0; } else if ((z->z_flags & ZONEFS_ZONE_READONLY) || (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO)) { zonefs_warn(sb, "inode %lu: write access disabled\n", inode->i_ino); if (!(z->z_flags & ZONEFS_ZONE_READONLY)) z->z_flags |= ZONEFS_ZONE_READONLY; zonefs_inode_update_mode(inode); data_size = isize; } else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO && data_size > isize) { /* Do not expose garbage data */ data_size = isize; } /* * If the filesystem is mounted with the explicit-open mount option, we * need to clear the ZONEFS_ZONE_OPEN flag if the zone transitioned to * the read-only or offline condition, to avoid attempting an explicit * close of the zone when the inode file is closed. */ if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) && (z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE))) z->z_flags &= ~ZONEFS_ZONE_OPEN; /* * If error=remount-ro was specified, any error result in remounting * the volume as read-only. */ if ((sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO) && !sb_rdonly(sb)) { zonefs_warn(sb, "remounting filesystem read-only\n"); sb->s_flags |= SB_RDONLY; } /* * Update block usage stats and the inode size to prevent access to * invalid data. */ zonefs_update_stats(inode, data_size); zonefs_i_size_write(inode, data_size); z->z_wpoffset = data_size; zonefs_inode_account_active(inode); } /* * When an file IO error occurs, check the file zone to see if there is a change * in the zone condition (e.g. offline or read-only). For a failed write to a * sequential zone, the zone write pointer position must also be checked to * eventually correct the file size and zonefs inode write pointer offset * (which can be out of sync with the drive due to partial write failures). */ void __zonefs_io_error(struct inode *inode, bool write) { struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; unsigned int noio_flag; struct blk_zone zone; int ret; /* * Conventional zone have no write pointer and cannot become read-only * or offline. So simply fake a report for a single or aggregated zone * and let zonefs_handle_io_error() correct the zone inode information * according to the mount options. */ if (!zonefs_zone_is_seq(z)) { zone.start = z->z_sector; zone.len = z->z_size >> SECTOR_SHIFT; zone.wp = zone.start + zone.len; zone.type = BLK_ZONE_TYPE_CONVENTIONAL; zone.cond = BLK_ZONE_COND_NOT_WP; zone.capacity = zone.len; goto handle_io_error; } /* * Memory allocations in blkdev_report_zones() can trigger a memory * reclaim which may in turn cause a recursion into zonefs as well as * struct request allocations for the same device. The former case may * end up in a deadlock on the inode truncate mutex, while the latter * may prevent IO forward progress. Executing the report zones under * the GFP_NOIO context avoids both problems. */ noio_flag = memalloc_noio_save(); ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1, zonefs_io_error_cb, &zone); memalloc_noio_restore(noio_flag); if (ret != 1) { zonefs_err(sb, "Get inode %lu zone information failed %d\n", inode->i_ino, ret); zonefs_warn(sb, "remounting filesystem read-only\n"); sb->s_flags |= SB_RDONLY; return; } handle_io_error: zonefs_handle_io_error(inode, &zone, write); } static struct kmem_cache *zonefs_inode_cachep; static struct inode *zonefs_alloc_inode(struct super_block *sb) { struct zonefs_inode_info *zi; zi = alloc_inode_sb(sb, zonefs_inode_cachep, GFP_KERNEL); if (!zi) return NULL; inode_init_once(&zi->i_vnode); mutex_init(&zi->i_truncate_mutex); zi->i_wr_refcnt = 0; return &zi->i_vnode; } static void zonefs_free_inode(struct inode *inode) { kmem_cache_free(zonefs_inode_cachep, ZONEFS_I(inode)); } /* * File system stat. */ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); enum zonefs_ztype t; buf->f_type = ZONEFS_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_namelen = ZONEFS_NAME_MAX; spin_lock(&sbi->s_lock); buf->f_blocks = sbi->s_blocks; if (WARN_ON(sbi->s_used_blocks > sbi->s_blocks)) buf->f_bfree = 0; else buf->f_bfree = buf->f_blocks - sbi->s_used_blocks; buf->f_bavail = buf->f_bfree; for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) { if (sbi->s_zgroup[t].g_nr_zones) buf->f_files += sbi->s_zgroup[t].g_nr_zones + 1; } buf->f_ffree = 0; spin_unlock(&sbi->s_lock); buf->f_fsid = uuid_to_fsid(sbi->s_uuid.b); return 0; } enum { Opt_errors, Opt_explicit_open, }; struct zonefs_context { unsigned long s_mount_opts; }; static const struct constant_table zonefs_param_errors[] = { {"remount-ro", ZONEFS_MNTOPT_ERRORS_RO}, {"zone-ro", ZONEFS_MNTOPT_ERRORS_ZRO}, {"zone-offline", ZONEFS_MNTOPT_ERRORS_ZOL}, {"repair", ZONEFS_MNTOPT_ERRORS_REPAIR}, {} }; static const struct fs_parameter_spec zonefs_param_spec[] = { fsparam_enum ("errors", Opt_errors, zonefs_param_errors), fsparam_flag ("explicit-open", Opt_explicit_open), {} }; static int zonefs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct zonefs_context *ctx = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, zonefs_param_spec, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_errors: ctx->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK; ctx->s_mount_opts |= result.uint_32; break; case Opt_explicit_open: ctx->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN; break; default: return -EINVAL; } return 0; } static int zonefs_show_options(struct seq_file *seq, struct dentry *root) { struct zonefs_sb_info *sbi = ZONEFS_SB(root->d_sb); if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO) seq_puts(seq, ",errors=remount-ro"); if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO) seq_puts(seq, ",errors=zone-ro"); if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL) seq_puts(seq, ",errors=zone-offline"); if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_REPAIR) seq_puts(seq, ",errors=repair"); return 0; } static int zonefs_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int ret; if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; ret = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (ret) return ret; /* * Since files and directories cannot be created nor deleted, do not * allow setting any write attributes on the sub-directories grouping * files by zone type. */ if ((iattr->ia_valid & ATTR_MODE) && S_ISDIR(inode->i_mode) && (iattr->ia_mode & 0222)) return -EPERM; if (((iattr->ia_valid & ATTR_UID) && !uid_eq(iattr->ia_uid, inode->i_uid)) || ((iattr->ia_valid & ATTR_GID) && !gid_eq(iattr->ia_gid, inode->i_gid))) { ret = dquot_transfer(&nop_mnt_idmap, inode, iattr); if (ret) return ret; } if (iattr->ia_valid & ATTR_SIZE) { ret = zonefs_file_truncate(inode, iattr->ia_size); if (ret) return ret; } setattr_copy(&nop_mnt_idmap, inode, iattr); if (S_ISREG(inode->i_mode)) { struct zonefs_zone *z = zonefs_inode_zone(inode); z->z_mode = inode->i_mode; z->z_uid = inode->i_uid; z->z_gid = inode->i_gid; } return 0; } static const struct inode_operations zonefs_file_inode_operations = { .setattr = zonefs_inode_setattr, }; static long zonefs_fname_to_fno(const struct qstr *fname) { const char *name = fname->name; unsigned int len = fname->len; long fno = 0, shift = 1; const char *rname; char c = *name; unsigned int i; /* * File names are always a base-10 number string without any * leading 0s. */ if (!isdigit(c)) return -ENOENT; if (len > 1 && c == '0') return -ENOENT; if (len == 1) return c - '0'; for (i = 0, rname = name + len - 1; i < len; i++, rname--) { c = *rname; if (!isdigit(c)) return -ENOENT; fno += (c - '0') * shift; shift *= 10; } return fno; } static struct inode *zonefs_get_file_inode(struct inode *dir, struct dentry *dentry) { struct zonefs_zone_group *zgroup = dir->i_private; struct super_block *sb = dir->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_zone *z; struct inode *inode; ino_t ino; long fno; /* Get the file number from the file name */ fno = zonefs_fname_to_fno(&dentry->d_name); if (fno < 0) return ERR_PTR(fno); if (!zgroup->g_nr_zones || fno >= zgroup->g_nr_zones) return ERR_PTR(-ENOENT); z = &zgroup->g_zones[fno]; ino = z->z_sector >> sbi->s_zone_sectors_shift; inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) { WARN_ON_ONCE(inode->i_private != z); return inode; } inode->i_ino = ino; inode->i_mode = z->z_mode; inode_set_mtime_to_ts(inode, inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, inode_get_ctime(dir)))); inode->i_uid = z->z_uid; inode->i_gid = z->z_gid; inode->i_size = z->z_wpoffset; inode->i_blocks = z->z_capacity >> SECTOR_SHIFT; inode->i_private = z; inode->i_op = &zonefs_file_inode_operations; inode->i_fop = &zonefs_file_operations; inode->i_mapping->a_ops = &zonefs_file_aops; mapping_set_large_folios(inode->i_mapping); /* Update the inode access rights depending on the zone condition */ zonefs_inode_update_mode(inode); unlock_new_inode(inode); return inode; } static struct inode *zonefs_get_zgroup_inode(struct super_block *sb, enum zonefs_ztype ztype) { struct inode *root = d_inode(sb->s_root); struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct inode *inode; ino_t ino = bdev_nr_zones(sb->s_bdev) + ztype + 1; inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; inode->i_ino = ino; inode_init_owner(&nop_mnt_idmap, inode, root, S_IFDIR | 0555); inode->i_size = sbi->s_zgroup[ztype].g_nr_zones; inode_set_mtime_to_ts(inode, inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, inode_get_ctime(root)))); inode->i_private = &sbi->s_zgroup[ztype]; set_nlink(inode, 2); inode->i_op = &zonefs_dir_inode_operations; inode->i_fop = &zonefs_dir_operations; unlock_new_inode(inode); return inode; } static struct inode *zonefs_get_dir_inode(struct inode *dir, struct dentry *dentry) { struct super_block *sb = dir->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); const char *name = dentry->d_name.name; enum zonefs_ztype ztype; /* * We only need to check for the "seq" directory and * the "cnv" directory if we have conventional zones. */ if (dentry->d_name.len != 3) return ERR_PTR(-ENOENT); for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) { if (sbi->s_zgroup[ztype].g_nr_zones && memcmp(name, zonefs_zgroup_name(ztype), 3) == 0) break; } if (ztype == ZONEFS_ZTYPE_MAX) return ERR_PTR(-ENOENT); return zonefs_get_zgroup_inode(sb, ztype); } static struct dentry *zonefs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; if (dentry->d_name.len > ZONEFS_NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (dir == d_inode(dir->i_sb->s_root)) inode = zonefs_get_dir_inode(dir, dentry); else inode = zonefs_get_file_inode(dir, dentry); return d_splice_alias(inode, dentry); } static int zonefs_readdir_root(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); enum zonefs_ztype ztype = ZONEFS_ZTYPE_CNV; ino_t base_ino = bdev_nr_zones(sb->s_bdev) + 1; if (ctx->pos >= inode->i_size) return 0; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) { if (!sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones) ztype = ZONEFS_ZTYPE_SEQ; if (!dir_emit(ctx, zonefs_zgroup_name(ztype), 3, base_ino + ztype, DT_DIR)) return 0; ctx->pos++; } if (ctx->pos == 3 && ztype != ZONEFS_ZTYPE_SEQ) { ztype = ZONEFS_ZTYPE_SEQ; if (!dir_emit(ctx, zonefs_zgroup_name(ztype), 3, base_ino + ztype, DT_DIR)) return 0; ctx->pos++; } return 0; } static int zonefs_readdir_zgroup(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct zonefs_zone_group *zgroup = inode->i_private; struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_zone *z; int fname_len; char *fname; ino_t ino; int f; /* * The size of zone group directories is equal to the number * of zone files in the group and does note include the "." and * ".." entries. Hence the "+ 2" here. */ if (ctx->pos >= inode->i_size + 2) return 0; if (!dir_emit_dots(file, ctx)) return 0; fname = kmalloc(ZONEFS_NAME_MAX, GFP_KERNEL); if (!fname) return -ENOMEM; for (f = ctx->pos - 2; f < zgroup->g_nr_zones; f++) { z = &zgroup->g_zones[f]; ino = z->z_sector >> sbi->s_zone_sectors_shift; fname_len = snprintf(fname, ZONEFS_NAME_MAX - 1, "%u", f); if (!dir_emit(ctx, fname, fname_len, ino, DT_REG)) break; ctx->pos++; } kfree(fname); return 0; } static int zonefs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); if (inode == d_inode(inode->i_sb->s_root)) return zonefs_readdir_root(file, ctx); return zonefs_readdir_zgroup(file, ctx); } const struct inode_operations zonefs_dir_inode_operations = { .lookup = zonefs_lookup, .setattr = zonefs_inode_setattr, }; const struct file_operations zonefs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = zonefs_readdir, }; struct zonefs_zone_data { struct super_block *sb; unsigned int nr_zones[ZONEFS_ZTYPE_MAX]; sector_t cnv_zone_start; struct blk_zone *zones; }; static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct zonefs_zone_data *zd = data; struct super_block *sb = zd->sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); /* * We do not care about the first zone: it contains the super block * and not exposed as a file. */ if (!idx) return 0; /* * Count the number of zones that will be exposed as files. * For sequential zones, we always have as many files as zones. * FOr conventional zones, the number of files depends on if we have * conventional zones aggregation enabled. */ switch (zone->type) { case BLK_ZONE_TYPE_CONVENTIONAL: if (sbi->s_features & ZONEFS_F_AGGRCNV) { /* One file per set of contiguous conventional zones */ if (!(sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones) || zone->start != zd->cnv_zone_start) sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones++; zd->cnv_zone_start = zone->start + zone->len; } else { /* One file per zone */ sbi->s_zgroup[ZONEFS_ZTYPE_CNV].g_nr_zones++; } break; case BLK_ZONE_TYPE_SEQWRITE_REQ: case BLK_ZONE_TYPE_SEQWRITE_PREF: sbi->s_zgroup[ZONEFS_ZTYPE_SEQ].g_nr_zones++; break; default: zonefs_err(zd->sb, "Unsupported zone type 0x%x\n", zone->type); return -EIO; } memcpy(&zd->zones[idx], zone, sizeof(struct blk_zone)); return 0; } static int zonefs_get_zone_info(struct zonefs_zone_data *zd) { struct block_device *bdev = zd->sb->s_bdev; int ret; zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone), GFP_KERNEL); if (!zd->zones) return -ENOMEM; /* Get zones information from the device */ ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, zonefs_get_zone_info_cb, zd); if (ret < 0) { zonefs_err(zd->sb, "Zone report failed %d\n", ret); return ret; } if (ret != bdev_nr_zones(bdev)) { zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n", ret, bdev_nr_zones(bdev)); return -EIO; } return 0; } static inline void zonefs_free_zone_info(struct zonefs_zone_data *zd) { kvfree(zd->zones); } /* * Create a zone group and populate it with zone files. */ static int zonefs_init_zgroup(struct super_block *sb, struct zonefs_zone_data *zd, enum zonefs_ztype ztype) { struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_zone_group *zgroup = &sbi->s_zgroup[ztype]; struct blk_zone *zone, *next, *end; struct zonefs_zone *z; unsigned int n = 0; int ret; /* Allocate the zone group. If it is empty, we have nothing to do. */ if (!zgroup->g_nr_zones) return 0; zgroup->g_zones = kvcalloc(zgroup->g_nr_zones, sizeof(struct zonefs_zone), GFP_KERNEL); if (!zgroup->g_zones) return -ENOMEM; /* * Initialize the zone groups using the device zone information. * We always skip the first zone as it contains the super block * and is not use to back a file. */ end = zd->zones + bdev_nr_zones(sb->s_bdev); for (zone = &zd->zones[1]; zone < end; zone = next) { next = zone + 1; if (zonefs_zone_type(zone) != ztype) continue; if (WARN_ON_ONCE(n >= zgroup->g_nr_zones)) return -EINVAL; /* * For conventional zones, contiguous zones can be aggregated * together to form larger files. Note that this overwrites the * length of the first zone of the set of contiguous zones * aggregated together. If one offline or read-only zone is * found, assume that all zones aggregated have the same * condition. */ if (ztype == ZONEFS_ZTYPE_CNV && (sbi->s_features & ZONEFS_F_AGGRCNV)) { for (; next < end; next++) { if (zonefs_zone_type(next) != ztype) break; zone->len += next->len; zone->capacity += next->capacity; if (next->cond == BLK_ZONE_COND_READONLY && zone->cond != BLK_ZONE_COND_OFFLINE) zone->cond = BLK_ZONE_COND_READONLY; else if (next->cond == BLK_ZONE_COND_OFFLINE) zone->cond = BLK_ZONE_COND_OFFLINE; } } z = &zgroup->g_zones[n]; if (ztype == ZONEFS_ZTYPE_CNV) z->z_flags |= ZONEFS_ZONE_CNV; z->z_sector = zone->start; z->z_size = zone->len << SECTOR_SHIFT; if (z->z_size > bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT && !(sbi->s_features & ZONEFS_F_AGGRCNV)) { zonefs_err(sb, "Invalid zone size %llu (device zone sectors %llu)\n", z->z_size, bdev_zone_sectors(sb->s_bdev) << SECTOR_SHIFT); return -EINVAL; } z->z_capacity = min_t(loff_t, MAX_LFS_FILESIZE, zone->capacity << SECTOR_SHIFT); z->z_wpoffset = zonefs_check_zone_condition(sb, z, zone); z->z_mode = S_IFREG | sbi->s_perm; z->z_uid = sbi->s_uid; z->z_gid = sbi->s_gid; /* * Let zonefs_inode_update_mode() know that we will need * special initialization of the inode mode the first time * it is accessed. */ z->z_flags |= ZONEFS_ZONE_INIT_MODE; sb->s_maxbytes = max(z->z_capacity, sb->s_maxbytes); sbi->s_blocks += z->z_capacity >> sb->s_blocksize_bits; sbi->s_used_blocks += z->z_wpoffset >> sb->s_blocksize_bits; /* * For sequential zones, make sure that any open zone is closed * first to ensure that the initial number of open zones is 0, * in sync with the open zone accounting done when the mount * option ZONEFS_MNTOPT_EXPLICIT_OPEN is used. */ if (ztype == ZONEFS_ZTYPE_SEQ && (zone->cond == BLK_ZONE_COND_IMP_OPEN || zone->cond == BLK_ZONE_COND_EXP_OPEN)) { ret = zonefs_zone_mgmt(sb, z, REQ_OP_ZONE_CLOSE); if (ret) return ret; } zonefs_account_active(sb, z); n++; } if (WARN_ON_ONCE(n != zgroup->g_nr_zones)) return -EINVAL; zonefs_info(sb, "Zone group \"%s\" has %u file%s\n", zonefs_zgroup_name(ztype), zgroup->g_nr_zones, str_plural(zgroup->g_nr_zones)); return 0; } static void zonefs_free_zgroups(struct super_block *sb) { struct zonefs_sb_info *sbi = ZONEFS_SB(sb); enum zonefs_ztype ztype; if (!sbi) return; for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) { kvfree(sbi->s_zgroup[ztype].g_zones); sbi->s_zgroup[ztype].g_zones = NULL; } } /* * Create a zone group and populate it with zone files. */ static int zonefs_init_zgroups(struct super_block *sb) { struct zonefs_zone_data zd; enum zonefs_ztype ztype; int ret; /* First get the device zone information */ memset(&zd, 0, sizeof(struct zonefs_zone_data)); zd.sb = sb; ret = zonefs_get_zone_info(&zd); if (ret) goto cleanup; /* Allocate and initialize the zone groups */ for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) { ret = zonefs_init_zgroup(sb, &zd, ztype); if (ret) { zonefs_info(sb, "Zone group \"%s\" initialization failed\n", zonefs_zgroup_name(ztype)); break; } } cleanup: zonefs_free_zone_info(&zd); if (ret) zonefs_free_zgroups(sb); return ret; } /* * Read super block information from the device. */ static int zonefs_read_super(struct super_block *sb) { struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_super *super; u32 crc, stored_crc; struct page *page; struct bio_vec bio_vec; struct bio bio; int ret; page = alloc_page(GFP_KERNEL); if (!page) return -ENOMEM; bio_init(&bio, sb->s_bdev, &bio_vec, 1, REQ_OP_READ); bio.bi_iter.bi_sector = 0; __bio_add_page(&bio, page, PAGE_SIZE, 0); ret = submit_bio_wait(&bio); if (ret) goto free_page; super = page_address(page); ret = -EINVAL; if (le32_to_cpu(super->s_magic) != ZONEFS_MAGIC) goto free_page; stored_crc = le32_to_cpu(super->s_crc); super->s_crc = 0; crc = crc32(~0U, (unsigned char *)super, sizeof(struct zonefs_super)); if (crc != stored_crc) { zonefs_err(sb, "Invalid checksum (Expected 0x%08x, got 0x%08x)", crc, stored_crc); goto free_page; } sbi->s_features = le64_to_cpu(super->s_features); if (sbi->s_features & ~ZONEFS_F_DEFINED_FEATURES) { zonefs_err(sb, "Unknown features set 0x%llx\n", sbi->s_features); goto free_page; } if (sbi->s_features & ZONEFS_F_UID) { sbi->s_uid = make_kuid(current_user_ns(), le32_to_cpu(super->s_uid)); if (!uid_valid(sbi->s_uid)) { zonefs_err(sb, "Invalid UID feature\n"); goto free_page; } } if (sbi->s_features & ZONEFS_F_GID) { sbi->s_gid = make_kgid(current_user_ns(), le32_to_cpu(super->s_gid)); if (!gid_valid(sbi->s_gid)) { zonefs_err(sb, "Invalid GID feature\n"); goto free_page; } } if (sbi->s_features & ZONEFS_F_PERM) sbi->s_perm = le32_to_cpu(super->s_perm); if (memchr_inv(super->s_reserved, 0, sizeof(super->s_reserved))) { zonefs_err(sb, "Reserved area is being used\n"); goto free_page; } import_uuid(&sbi->s_uuid, super->s_uuid); ret = 0; free_page: __free_page(page); return ret; } static const struct super_operations zonefs_sops = { .alloc_inode = zonefs_alloc_inode, .free_inode = zonefs_free_inode, .statfs = zonefs_statfs, .show_options = zonefs_show_options, }; static int zonefs_get_zgroup_inodes(struct super_block *sb) { struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct inode *dir_inode; enum zonefs_ztype ztype; for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) { if (!sbi->s_zgroup[ztype].g_nr_zones) continue; dir_inode = zonefs_get_zgroup_inode(sb, ztype); if (IS_ERR(dir_inode)) return PTR_ERR(dir_inode); sbi->s_zgroup[ztype].g_inode = dir_inode; } return 0; } static void zonefs_release_zgroup_inodes(struct super_block *sb) { struct zonefs_sb_info *sbi = ZONEFS_SB(sb); enum zonefs_ztype ztype; if (!sbi) return; for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) { if (sbi->s_zgroup[ztype].g_inode) { iput(sbi->s_zgroup[ztype].g_inode); sbi->s_zgroup[ztype].g_inode = NULL; } } } /* * Check that the device is zoned. If it is, get the list of zones and create * sub-directories and files according to the device zone configuration and * format options. */ static int zonefs_fill_super(struct super_block *sb, struct fs_context *fc) { struct zonefs_sb_info *sbi; struct zonefs_context *ctx = fc->fs_private; struct inode *inode; enum zonefs_ztype ztype; int ret; if (!bdev_is_zoned(sb->s_bdev)) { zonefs_err(sb, "Not a zoned block device\n"); return -EINVAL; } /* * Initialize super block information: the maximum file size is updated * when the zone files are created so that the format option * ZONEFS_F_AGGRCNV which increases the maximum file size of a file * beyond the zone size is taken into account. */ sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; spin_lock_init(&sbi->s_lock); sb->s_fs_info = sbi; sb->s_magic = ZONEFS_MAGIC; sb->s_maxbytes = 0; sb->s_op = &zonefs_sops; sb->s_time_gran = 1; /* * The block size is set to the device zone write granularity to ensure * that write operations are always aligned according to the device * interface constraints. */ sb_set_blocksize(sb, bdev_zone_write_granularity(sb->s_bdev)); sbi->s_zone_sectors_shift = ilog2(bdev_zone_sectors(sb->s_bdev)); sbi->s_uid = GLOBAL_ROOT_UID; sbi->s_gid = GLOBAL_ROOT_GID; sbi->s_perm = 0640; sbi->s_mount_opts = ctx->s_mount_opts; atomic_set(&sbi->s_wro_seq_files, 0); sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev); atomic_set(&sbi->s_active_seq_files, 0); sbi->s_max_active_seq_files = bdev_max_active_zones(sb->s_bdev); ret = zonefs_read_super(sb); if (ret) return ret; zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev)); if (!sbi->s_max_wro_seq_files && !sbi->s_max_active_seq_files && sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) { zonefs_info(sb, "No open and active zone limits. Ignoring explicit_open mount option\n"); sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN; } /* Initialize the zone groups */ ret = zonefs_init_zgroups(sb); if (ret) goto cleanup; /* Create the root directory inode */ ret = -ENOMEM; inode = new_inode(sb); if (!inode) goto cleanup; inode->i_ino = bdev_nr_zones(sb->s_bdev); inode->i_mode = S_IFDIR | 0555; simple_inode_init_ts(inode); inode->i_op = &zonefs_dir_inode_operations; inode->i_fop = &zonefs_dir_operations; inode->i_size = 2; set_nlink(inode, 2); for (ztype = 0; ztype < ZONEFS_ZTYPE_MAX; ztype++) { if (sbi->s_zgroup[ztype].g_nr_zones) { inc_nlink(inode); inode->i_size++; } } sb->s_root = d_make_root(inode); if (!sb->s_root) goto cleanup; /* * Take a reference on the zone groups directory inodes * to keep them in the inode cache. */ ret = zonefs_get_zgroup_inodes(sb); if (ret) goto cleanup; ret = zonefs_sysfs_register(sb); if (ret) goto cleanup; return 0; cleanup: zonefs_release_zgroup_inodes(sb); zonefs_free_zgroups(sb); return ret; } static void zonefs_kill_super(struct super_block *sb) { struct zonefs_sb_info *sbi = ZONEFS_SB(sb); /* Release the reference on the zone group directory inodes */ zonefs_release_zgroup_inodes(sb); kill_block_super(sb); zonefs_sysfs_unregister(sb); zonefs_free_zgroups(sb); kfree(sbi); } static void zonefs_free_fc(struct fs_context *fc) { struct zonefs_context *ctx = fc->fs_private; kfree(ctx); } static int zonefs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, zonefs_fill_super); } static int zonefs_reconfigure(struct fs_context *fc) { struct zonefs_context *ctx = fc->fs_private; struct super_block *sb = fc->root->d_sb; struct zonefs_sb_info *sbi = sb->s_fs_info; sync_filesystem(fc->root->d_sb); /* Copy new options from ctx into sbi. */ sbi->s_mount_opts = ctx->s_mount_opts; return 0; } static const struct fs_context_operations zonefs_context_ops = { .parse_param = zonefs_parse_param, .get_tree = zonefs_get_tree, .reconfigure = zonefs_reconfigure, .free = zonefs_free_fc, }; /* * Set up the filesystem mount context. */ static int zonefs_init_fs_context(struct fs_context *fc) { struct zonefs_context *ctx; ctx = kzalloc(sizeof(struct zonefs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO; fc->ops = &zonefs_context_ops; fc->fs_private = ctx; return 0; } /* * File system definition and registration. */ static struct file_system_type zonefs_type = { .owner = THIS_MODULE, .name = "zonefs", .kill_sb = zonefs_kill_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = zonefs_init_fs_context, .parameters = zonefs_param_spec, }; static int __init zonefs_init_inodecache(void) { zonefs_inode_cachep = kmem_cache_create("zonefs_inode_cache", sizeof(struct zonefs_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, NULL); if (zonefs_inode_cachep == NULL) return -ENOMEM; return 0; } static void zonefs_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy the inode cache. */ rcu_barrier(); kmem_cache_destroy(zonefs_inode_cachep); } static int __init zonefs_init(void) { int ret; BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE); ret = zonefs_init_inodecache(); if (ret) return ret; ret = zonefs_sysfs_init(); if (ret) goto destroy_inodecache; ret = register_filesystem(&zonefs_type); if (ret) goto sysfs_exit; return 0; sysfs_exit: zonefs_sysfs_exit(); destroy_inodecache: zonefs_destroy_inodecache(); return ret; } static void __exit zonefs_exit(void) { unregister_filesystem(&zonefs_type); zonefs_sysfs_exit(); zonefs_destroy_inodecache(); } MODULE_AUTHOR("Damien Le Moal"); MODULE_DESCRIPTION("Zone file system for zoned block devices"); MODULE_LICENSE("GPL"); MODULE_ALIAS_FS("zonefs"); module_init(zonefs_init); module_exit(zonefs_exit); |
| 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Authentication token and access key management internal defs * * Copyright (C) 2003-5, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _INTERNAL_H #define _INTERNAL_H #include <linux/sched.h> #include <linux/wait_bit.h> #include <linux/cred.h> #include <linux/key-type.h> #include <linux/task_work.h> #include <linux/keyctl.h> #include <linux/refcount.h> #include <linux/watch_queue.h> #include <linux/compat.h> #include <linux/mm.h> #include <linux/vmalloc.h> struct iovec; #ifdef __KDEBUG #define kenter(FMT, ...) \ printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) #define kleave(FMT, ...) \ printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) #define kdebug(FMT, ...) \ printk(KERN_DEBUG " "FMT"\n", ##__VA_ARGS__) #else #define kenter(FMT, ...) \ no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) #define kleave(FMT, ...) \ no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) #define kdebug(FMT, ...) \ no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__) #endif extern struct key_type key_type_dead; extern struct key_type key_type_user; extern struct key_type key_type_logon; /*****************************************************************************/ /* * Keep track of keys for a user. * * This needs to be separate to user_struct to avoid a refcount-loop * (user_struct pins some keyrings which pin this struct). * * We also keep track of keys under request from userspace for this UID here. */ struct key_user { struct rb_node node; struct mutex cons_lock; /* construction initiation lock */ spinlock_t lock; refcount_t usage; /* for accessing qnkeys & qnbytes */ atomic_t nkeys; /* number of keys */ atomic_t nikeys; /* number of instantiated keys */ kuid_t uid; int qnkeys; /* number of keys allocated to this user */ int qnbytes; /* number of bytes allocated to this user */ }; extern struct rb_root key_user_tree; extern spinlock_t key_user_lock; extern struct key_user root_key_user; extern struct key_user *key_user_lookup(kuid_t uid); extern void key_user_put(struct key_user *user); /* * Key quota limits. * - root has its own separate limits to everyone else */ extern unsigned key_quota_root_maxkeys; extern unsigned key_quota_root_maxbytes; extern unsigned key_quota_maxkeys; extern unsigned key_quota_maxbytes; #define KEYQUOTA_LINK_BYTES 4 /* a link in a keyring is worth 4 bytes */ extern struct kmem_cache *key_jar; extern struct rb_root key_serial_tree; extern spinlock_t key_serial_lock; extern struct mutex key_construction_mutex; extern wait_queue_head_t request_key_conswq; extern void key_set_index_key(struct keyring_index_key *index_key); extern struct key_type *key_type_lookup(const char *type); extern void key_type_put(struct key_type *ktype); extern int __key_link_lock(struct key *keyring, const struct keyring_index_key *index_key); extern int __key_move_lock(struct key *l_keyring, struct key *u_keyring, const struct keyring_index_key *index_key); extern int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit **_edit); extern int __key_link_check_live_key(struct key *keyring, struct key *key); extern void __key_link(struct key *keyring, struct key *key, struct assoc_array_edit **_edit); extern void __key_link_end(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit *edit); extern key_ref_t find_key_to_update(key_ref_t keyring_ref, const struct keyring_index_key *index_key); struct keyring_search_context { struct keyring_index_key index_key; const struct cred *cred; struct key_match_data match_data; unsigned flags; #define KEYRING_SEARCH_NO_STATE_CHECK 0x0001 /* Skip state checks */ #define KEYRING_SEARCH_DO_STATE_CHECK 0x0002 /* Override NO_STATE_CHECK */ #define KEYRING_SEARCH_NO_UPDATE_TIME 0x0004 /* Don't update times */ #define KEYRING_SEARCH_NO_CHECK_PERM 0x0008 /* Don't check permissions */ #define KEYRING_SEARCH_DETECT_TOO_DEEP 0x0010 /* Give an error on excessive depth */ #define KEYRING_SEARCH_SKIP_EXPIRED 0x0020 /* Ignore expired keys (intention to replace) */ #define KEYRING_SEARCH_RECURSE 0x0040 /* Search child keyrings also */ int (*iterator)(const void *object, void *iterator_data); /* Internal stuff */ int skipped_ret; bool possessed; key_ref_t result; time64_t now; }; extern bool key_default_cmp(const struct key *key, const struct key_match_data *match_data); extern key_ref_t keyring_search_rcu(key_ref_t keyring_ref, struct keyring_search_context *ctx); extern key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx); extern key_ref_t search_process_keyrings_rcu(struct keyring_search_context *ctx); extern struct key *find_keyring_by_name(const char *name, bool uid_keyring); extern int look_up_user_keyrings(struct key **, struct key **); extern struct key *get_user_session_keyring_rcu(const struct cred *); extern int install_thread_keyring_to_cred(struct cred *); extern int install_process_keyring_to_cred(struct cred *); extern int install_session_keyring_to_cred(struct cred *, struct key *); extern struct key *request_key_and_link(struct key_type *type, const char *description, struct key_tag *domain_tag, const void *callout_info, size_t callout_len, void *aux, struct key *dest_keyring, unsigned long flags); extern bool lookup_user_key_possessed(const struct key *key, const struct key_match_data *match_data); extern long join_session_keyring(const char *name); extern void key_change_session_keyring(struct callback_head *twork); extern struct work_struct key_gc_work; extern unsigned key_gc_delay; extern void keyring_gc(struct key *keyring, time64_t limit); extern void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type); void key_set_expiry(struct key *key, time64_t expiry); extern void key_schedule_gc(time64_t gc_at); extern void key_schedule_gc_links(void); extern void key_gc_keytype(struct key_type *ktype); extern int key_task_permission(const key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm); static inline void notify_key(struct key *key, enum key_notification_subtype subtype, u32 aux) { #ifdef CONFIG_KEY_NOTIFICATIONS struct key_notification n = { .watch.type = WATCH_TYPE_KEY_NOTIFY, .watch.subtype = subtype, .watch.info = watch_sizeof(n), .key_id = key_serial(key), .aux = aux, }; post_watch_notification(key->watchers, &n.watch, current_cred(), n.key_id); #endif } /* * Check to see whether permission is granted to use a key in the desired way. */ static inline int key_permission(const key_ref_t key_ref, enum key_need_perm need_perm) { return key_task_permission(key_ref, current_cred(), need_perm); } extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, const char *op, const void *callout_info, size_t callout_len, struct key *dest_keyring); extern struct key *key_get_instantiation_authkey(key_serial_t target_id); /* * Determine whether a key is dead. */ static inline bool key_is_dead(const struct key *key, time64_t limit) { time64_t expiry = key->expiry; if (expiry != TIME64_MAX) { if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) expiry += key_gc_delay; if (expiry <= limit) return true; } return key->flags & ((1 << KEY_FLAG_DEAD) | (1 << KEY_FLAG_INVALIDATED)) || key->domain_tag->removed; } /* * keyctl() functions */ extern long keyctl_get_keyring_ID(key_serial_t, int); extern long keyctl_join_session_keyring(const char __user *); extern long keyctl_update_key(key_serial_t, const void __user *, size_t); extern long keyctl_revoke_key(key_serial_t); extern long keyctl_keyring_clear(key_serial_t); extern long keyctl_keyring_link(key_serial_t, key_serial_t); extern long keyctl_keyring_move(key_serial_t, key_serial_t, key_serial_t, unsigned int); extern long keyctl_keyring_unlink(key_serial_t, key_serial_t); extern long keyctl_describe_key(key_serial_t, char __user *, size_t); extern long keyctl_keyring_search(key_serial_t, const char __user *, const char __user *, key_serial_t); extern long keyctl_read_key(key_serial_t, char __user *, size_t); extern long keyctl_chown_key(key_serial_t, uid_t, gid_t); extern long keyctl_setperm_key(key_serial_t, key_perm_t); extern long keyctl_instantiate_key(key_serial_t, const void __user *, size_t, key_serial_t); extern long keyctl_negate_key(key_serial_t, unsigned, key_serial_t); extern long keyctl_set_reqkey_keyring(int); extern long keyctl_set_timeout(key_serial_t, unsigned); extern long keyctl_assume_authority(key_serial_t); extern long keyctl_get_security(key_serial_t keyid, char __user *buffer, size_t buflen); extern long keyctl_session_to_parent(void); extern long keyctl_reject_key(key_serial_t, unsigned, unsigned, key_serial_t); extern long keyctl_instantiate_key_iov(key_serial_t, const struct iovec __user *, unsigned, key_serial_t); extern long keyctl_invalidate_key(key_serial_t); extern long keyctl_restrict_keyring(key_serial_t id, const char __user *_type, const char __user *_restriction); #ifdef CONFIG_PERSISTENT_KEYRINGS extern long keyctl_get_persistent(uid_t, key_serial_t); extern unsigned persistent_keyring_expiry; #else static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_KEY_DH_OPERATIONS extern long keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *, size_t, struct keyctl_kdf_params __user *); extern long __keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *, size_t, struct keyctl_kdf_params *); #ifdef CONFIG_COMPAT extern long compat_keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct compat_keyctl_kdf_params __user *kdf); #endif #define KEYCTL_KDF_MAX_OUTPUT_LEN 1024 /* max length of KDF output */ #define KEYCTL_KDF_MAX_OI_LEN 64 /* max length of otherinfo */ #else static inline long keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct keyctl_kdf_params __user *kdf) { return -EOPNOTSUPP; } #ifdef CONFIG_COMPAT static inline long compat_keyctl_dh_compute( struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct keyctl_kdf_params __user *kdf) { return -EOPNOTSUPP; } #endif #endif #ifdef CONFIG_ASYMMETRIC_KEY_TYPE extern long keyctl_pkey_query(key_serial_t, const char __user *, struct keyctl_pkey_query __user *); extern long keyctl_pkey_verify(const struct keyctl_pkey_params __user *, const char __user *, const void __user *, const void __user *); extern long keyctl_pkey_e_d_s(int, const struct keyctl_pkey_params __user *, const char __user *, const void __user *, void __user *); #else static inline long keyctl_pkey_query(key_serial_t id, const char __user *_info, struct keyctl_pkey_query __user *_res) { return -EOPNOTSUPP; } static inline long keyctl_pkey_verify(const struct keyctl_pkey_params __user *params, const char __user *_info, const void __user *_in, const void __user *_in2) { return -EOPNOTSUPP; } static inline long keyctl_pkey_e_d_s(int op, const struct keyctl_pkey_params __user *params, const char __user *_info, const void __user *_in, void __user *_out) { return -EOPNOTSUPP; } #endif extern long keyctl_capabilities(unsigned char __user *_buffer, size_t buflen); #ifdef CONFIG_KEY_NOTIFICATIONS extern long keyctl_watch_key(key_serial_t, int, int); #else static inline long keyctl_watch_key(key_serial_t key_id, int watch_fd, int watch_id) { return -EOPNOTSUPP; } #endif /* * Debugging key validation */ #ifdef KEY_DEBUGGING extern void __key_check(const struct key *); static inline void key_check(const struct key *key) { if (key && (IS_ERR(key) || key->magic != KEY_DEBUG_MAGIC)) __key_check(key); } #else #define key_check(key) do {} while(0) #endif #endif /* _INTERNAL_H */ |
| 13 13 17 13 3 4 4 1 2 4 4 4 13 13 13 13 1 12 1 11 12 1 11 19 6 19 2 17 7 6 13 2 2 6 2 4 2 1 1 1 4 1 1 2 19 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/sysv/inode.c * * minix/inode.c * Copyright (C) 1991, 1992 Linus Torvalds * * xenix/inode.c * Copyright (C) 1992 Doug Evans * * coh/inode.c * Copyright (C) 1993 Pascal Haible, Bruno Haible * * sysv/inode.c * Copyright (C) 1993 Paul B. Monday * * sysv/inode.c * Copyright (C) 1993 Bruno Haible * Copyright (C) 1997, 1998 Krzysztof G. Baranowski * * This file contains code for read/parsing the superblock. */ #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/buffer_head.h> #include "sysv.h" /* * The following functions try to recognize specific filesystems. * * We recognize: * - Xenix FS by its magic number. * - SystemV FS by its magic number. * - Coherent FS by its funny fname/fpack field. * - SCO AFS by s_nfree == 0xffff * - V7 FS has no distinguishing features. * * We discriminate among SystemV4 and SystemV2 FS by the assumption that * the time stamp is not < 01-01-1980. */ enum { JAN_1_1980 = (10*365 + 2) * 24 * 60 * 60 }; static void detected_xenix(struct sysv_sb_info *sbi, unsigned *max_links) { struct buffer_head *bh1 = sbi->s_bh1; struct buffer_head *bh2 = sbi->s_bh2; struct xenix_super_block * sbd1; struct xenix_super_block * sbd2; if (bh1 != bh2) sbd1 = sbd2 = (struct xenix_super_block *) bh1->b_data; else { /* block size = 512, so bh1 != bh2 */ sbd1 = (struct xenix_super_block *) bh1->b_data; sbd2 = (struct xenix_super_block *) (bh2->b_data - 512); } *max_links = XENIX_LINK_MAX; sbi->s_fic_size = XENIX_NICINOD; sbi->s_flc_size = XENIX_NICFREE; sbi->s_sbd1 = (char *)sbd1; sbi->s_sbd2 = (char *)sbd2; sbi->s_sb_fic_count = &sbd1->s_ninode; sbi->s_sb_fic_inodes = &sbd1->s_inode[0]; sbi->s_sb_total_free_inodes = &sbd2->s_tinode; sbi->s_bcache_count = &sbd1->s_nfree; sbi->s_bcache = &sbd1->s_free[0]; sbi->s_free_blocks = &sbd2->s_tfree; sbi->s_sb_time = &sbd2->s_time; sbi->s_firstdatazone = fs16_to_cpu(sbi, sbd1->s_isize); sbi->s_nzones = fs32_to_cpu(sbi, sbd1->s_fsize); } static void detected_sysv4(struct sysv_sb_info *sbi, unsigned *max_links) { struct sysv4_super_block * sbd; struct buffer_head *bh1 = sbi->s_bh1; struct buffer_head *bh2 = sbi->s_bh2; if (bh1 == bh2) sbd = (struct sysv4_super_block *) (bh1->b_data + BLOCK_SIZE/2); else sbd = (struct sysv4_super_block *) bh2->b_data; *max_links = SYSV_LINK_MAX; sbi->s_fic_size = SYSV_NICINOD; sbi->s_flc_size = SYSV_NICFREE; sbi->s_sbd1 = (char *)sbd; sbi->s_sbd2 = (char *)sbd; sbi->s_sb_fic_count = &sbd->s_ninode; sbi->s_sb_fic_inodes = &sbd->s_inode[0]; sbi->s_sb_total_free_inodes = &sbd->s_tinode; sbi->s_bcache_count = &sbd->s_nfree; sbi->s_bcache = &sbd->s_free[0]; sbi->s_free_blocks = &sbd->s_tfree; sbi->s_sb_time = &sbd->s_time; sbi->s_sb_state = &sbd->s_state; sbi->s_firstdatazone = fs16_to_cpu(sbi, sbd->s_isize); sbi->s_nzones = fs32_to_cpu(sbi, sbd->s_fsize); } static void detected_sysv2(struct sysv_sb_info *sbi, unsigned *max_links) { struct sysv2_super_block *sbd; struct buffer_head *bh1 = sbi->s_bh1; struct buffer_head *bh2 = sbi->s_bh2; if (bh1 == bh2) sbd = (struct sysv2_super_block *) (bh1->b_data + BLOCK_SIZE/2); else sbd = (struct sysv2_super_block *) bh2->b_data; *max_links = SYSV_LINK_MAX; sbi->s_fic_size = SYSV_NICINOD; sbi->s_flc_size = SYSV_NICFREE; sbi->s_sbd1 = (char *)sbd; sbi->s_sbd2 = (char *)sbd; sbi->s_sb_fic_count = &sbd->s_ninode; sbi->s_sb_fic_inodes = &sbd->s_inode[0]; sbi->s_sb_total_free_inodes = &sbd->s_tinode; sbi->s_bcache_count = &sbd->s_nfree; sbi->s_bcache = &sbd->s_free[0]; sbi->s_free_blocks = &sbd->s_tfree; sbi->s_sb_time = &sbd->s_time; sbi->s_sb_state = &sbd->s_state; sbi->s_firstdatazone = fs16_to_cpu(sbi, sbd->s_isize); sbi->s_nzones = fs32_to_cpu(sbi, sbd->s_fsize); } static void detected_coherent(struct sysv_sb_info *sbi, unsigned *max_links) { struct coh_super_block * sbd; struct buffer_head *bh1 = sbi->s_bh1; sbd = (struct coh_super_block *) bh1->b_data; *max_links = COH_LINK_MAX; sbi->s_fic_size = COH_NICINOD; sbi->s_flc_size = COH_NICFREE; sbi->s_sbd1 = (char *)sbd; sbi->s_sbd2 = (char *)sbd; sbi->s_sb_fic_count = &sbd->s_ninode; sbi->s_sb_fic_inodes = &sbd->s_inode[0]; sbi->s_sb_total_free_inodes = &sbd->s_tinode; sbi->s_bcache_count = &sbd->s_nfree; sbi->s_bcache = &sbd->s_free[0]; sbi->s_free_blocks = &sbd->s_tfree; sbi->s_sb_time = &sbd->s_time; sbi->s_firstdatazone = fs16_to_cpu(sbi, sbd->s_isize); sbi->s_nzones = fs32_to_cpu(sbi, sbd->s_fsize); } static void detected_v7(struct sysv_sb_info *sbi, unsigned *max_links) { struct buffer_head *bh2 = sbi->s_bh2; struct v7_super_block *sbd = (struct v7_super_block *)bh2->b_data; *max_links = V7_LINK_MAX; sbi->s_fic_size = V7_NICINOD; sbi->s_flc_size = V7_NICFREE; sbi->s_sbd1 = (char *)sbd; sbi->s_sbd2 = (char *)sbd; sbi->s_sb_fic_count = &sbd->s_ninode; sbi->s_sb_fic_inodes = &sbd->s_inode[0]; sbi->s_sb_total_free_inodes = &sbd->s_tinode; sbi->s_bcache_count = &sbd->s_nfree; sbi->s_bcache = &sbd->s_free[0]; sbi->s_free_blocks = &sbd->s_tfree; sbi->s_sb_time = &sbd->s_time; sbi->s_firstdatazone = fs16_to_cpu(sbi, sbd->s_isize); sbi->s_nzones = fs32_to_cpu(sbi, sbd->s_fsize); } static int detect_xenix(struct sysv_sb_info *sbi, struct buffer_head *bh) { struct xenix_super_block *sbd = (struct xenix_super_block *)bh->b_data; if (*(__le32 *)&sbd->s_magic == cpu_to_le32(0x2b5544)) sbi->s_bytesex = BYTESEX_LE; else if (*(__be32 *)&sbd->s_magic == cpu_to_be32(0x2b5544)) sbi->s_bytesex = BYTESEX_BE; else return 0; switch (fs32_to_cpu(sbi, sbd->s_type)) { case 1: sbi->s_type = FSTYPE_XENIX; return 1; case 2: sbi->s_type = FSTYPE_XENIX; return 2; default: return 0; } } static int detect_sysv(struct sysv_sb_info *sbi, struct buffer_head *bh) { struct super_block *sb = sbi->s_sb; /* All relevant fields are at the same offsets in R2 and R4 */ struct sysv4_super_block * sbd; u32 type; sbd = (struct sysv4_super_block *) (bh->b_data + BLOCK_SIZE/2); if (*(__le32 *)&sbd->s_magic == cpu_to_le32(0xfd187e20)) sbi->s_bytesex = BYTESEX_LE; else if (*(__be32 *)&sbd->s_magic == cpu_to_be32(0xfd187e20)) sbi->s_bytesex = BYTESEX_BE; else return 0; type = fs32_to_cpu(sbi, sbd->s_type); if (fs16_to_cpu(sbi, sbd->s_nfree) == 0xffff) { sbi->s_type = FSTYPE_AFS; sbi->s_forced_ro = 1; if (!sb_rdonly(sb)) { printk("SysV FS: SCO EAFS on %s detected, " "forcing read-only mode.\n", sb->s_id); } return type; } if (fs32_to_cpu(sbi, sbd->s_time) < JAN_1_1980) { /* this is likely to happen on SystemV2 FS */ if (type > 3 || type < 1) return 0; sbi->s_type = FSTYPE_SYSV2; return type; } if ((type > 3 || type < 1) && (type > 0x30 || type < 0x10)) return 0; /* On Interactive Unix (ISC) Version 4.0/3.x s_type field = 0x10, 0x20 or 0x30 indicates that symbolic links and the 14-character filename limit is gone. Due to lack of information about this feature read-only mode seems to be a reasonable approach... -KGB */ if (type >= 0x10) { printk("SysV FS: can't handle long file names on %s, " "forcing read-only mode.\n", sb->s_id); sbi->s_forced_ro = 1; } sbi->s_type = FSTYPE_SYSV4; return type >= 0x10 ? type >> 4 : type; } static int detect_coherent(struct sysv_sb_info *sbi, struct buffer_head *bh) { struct coh_super_block * sbd; sbd = (struct coh_super_block *) (bh->b_data + BLOCK_SIZE/2); if ((memcmp(sbd->s_fname,"noname",6) && memcmp(sbd->s_fname,"xxxxx ",6)) || (memcmp(sbd->s_fpack,"nopack",6) && memcmp(sbd->s_fpack,"xxxxx\n",6))) return 0; sbi->s_bytesex = BYTESEX_PDP; sbi->s_type = FSTYPE_COH; return 1; } static int detect_sysv_odd(struct sysv_sb_info *sbi, struct buffer_head *bh) { int size = detect_sysv(sbi, bh); return size>2 ? 0 : size; } static struct { int block; int (*test)(struct sysv_sb_info *, struct buffer_head *); } flavours[] = { {1, detect_xenix}, {0, detect_sysv}, {0, detect_coherent}, {9, detect_sysv_odd}, {15,detect_sysv_odd}, {18,detect_sysv}, }; static char *flavour_names[] = { [FSTYPE_XENIX] = "Xenix", [FSTYPE_SYSV4] = "SystemV", [FSTYPE_SYSV2] = "SystemV Release 2", [FSTYPE_COH] = "Coherent", [FSTYPE_V7] = "V7", [FSTYPE_AFS] = "AFS", }; static void (*flavour_setup[])(struct sysv_sb_info *, unsigned *) = { [FSTYPE_XENIX] = detected_xenix, [FSTYPE_SYSV4] = detected_sysv4, [FSTYPE_SYSV2] = detected_sysv2, [FSTYPE_COH] = detected_coherent, [FSTYPE_V7] = detected_v7, [FSTYPE_AFS] = detected_sysv4, }; static int complete_read_super(struct super_block *sb, int silent, int size) { struct sysv_sb_info *sbi = SYSV_SB(sb); struct inode *root_inode; char *found = flavour_names[sbi->s_type]; u_char n_bits = size+8; int bsize = 1 << n_bits; int bsize_4 = bsize >> 2; sbi->s_firstinodezone = 2; flavour_setup[sbi->s_type](sbi, &sb->s_max_links); if (sbi->s_firstdatazone < sbi->s_firstinodezone) return 0; sbi->s_ndatazones = sbi->s_nzones - sbi->s_firstdatazone; sbi->s_inodes_per_block = bsize >> 6; sbi->s_inodes_per_block_1 = (bsize >> 6)-1; sbi->s_inodes_per_block_bits = n_bits-6; sbi->s_ind_per_block = bsize_4; sbi->s_ind_per_block_2 = bsize_4*bsize_4; sbi->s_toobig_block = 10 + bsize_4 * (1 + bsize_4 * (1 + bsize_4)); sbi->s_ind_per_block_bits = n_bits-2; sbi->s_ninodes = (sbi->s_firstdatazone - sbi->s_firstinodezone) << sbi->s_inodes_per_block_bits; if (!silent) printk("VFS: Found a %s FS (block size = %ld) on device %s\n", found, sb->s_blocksize, sb->s_id); sb->s_magic = SYSV_MAGIC_BASE + sbi->s_type; /* set up enough so that it can read an inode */ sb->s_op = &sysv_sops; if (sbi->s_forced_ro) sb->s_flags |= SB_RDONLY; root_inode = sysv_iget(sb, SYSV_ROOT_INO); if (IS_ERR(root_inode)) { printk("SysV FS: get root inode failed\n"); return 0; } sb->s_root = d_make_root(root_inode); if (!sb->s_root) { printk("SysV FS: get root dentry failed\n"); return 0; } return 1; } static int sysv_fill_super(struct super_block *sb, void *data, int silent) { struct buffer_head *bh1, *bh = NULL; struct sysv_sb_info *sbi; unsigned long blocknr; int size = 0, i; BUILD_BUG_ON(1024 != sizeof (struct xenix_super_block)); BUILD_BUG_ON(512 != sizeof (struct sysv4_super_block)); BUILD_BUG_ON(512 != sizeof (struct sysv2_super_block)); BUILD_BUG_ON(500 != sizeof (struct coh_super_block)); BUILD_BUG_ON(64 != sizeof (struct sysv_inode)); sbi = kzalloc(sizeof(struct sysv_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sbi->s_sb = sb; sbi->s_block_base = 0; mutex_init(&sbi->s_lock); sb->s_fs_info = sbi; sb->s_time_min = 0; sb->s_time_max = U32_MAX; sb_set_blocksize(sb, BLOCK_SIZE); for (i = 0; i < ARRAY_SIZE(flavours) && !size; i++) { brelse(bh); bh = sb_bread(sb, flavours[i].block); if (!bh) continue; size = flavours[i].test(SYSV_SB(sb), bh); } if (!size) goto Eunknown; switch (size) { case 1: blocknr = bh->b_blocknr << 1; brelse(bh); sb_set_blocksize(sb, 512); bh1 = sb_bread(sb, blocknr); bh = sb_bread(sb, blocknr + 1); break; case 2: bh1 = bh; break; case 3: blocknr = bh->b_blocknr >> 1; brelse(bh); sb_set_blocksize(sb, 2048); bh1 = bh = sb_bread(sb, blocknr); break; default: goto Ebadsize; } if (bh && bh1) { sbi->s_bh1 = bh1; sbi->s_bh2 = bh; if (complete_read_super(sb, silent, size)) return 0; } brelse(bh1); brelse(bh); sb_set_blocksize(sb, BLOCK_SIZE); printk("oldfs: cannot read superblock\n"); failed: kfree(sbi); return -EINVAL; Eunknown: brelse(bh); if (!silent) printk("VFS: unable to find oldfs superblock on device %s\n", sb->s_id); goto failed; Ebadsize: brelse(bh); if (!silent) printk("VFS: oldfs: unsupported block size (%dKb)\n", 1<<(size-2)); goto failed; } static int v7_sanity_check(struct super_block *sb, struct buffer_head *bh) { struct v7_super_block *v7sb; struct sysv_inode *v7i; struct buffer_head *bh2; struct sysv_sb_info *sbi; sbi = sb->s_fs_info; /* plausibility check on superblock */ v7sb = (struct v7_super_block *) bh->b_data; if (fs16_to_cpu(sbi, v7sb->s_nfree) > V7_NICFREE || fs16_to_cpu(sbi, v7sb->s_ninode) > V7_NICINOD || fs32_to_cpu(sbi, v7sb->s_fsize) > V7_MAXSIZE) return 0; /* plausibility check on root inode: it is a directory, with a nonzero size that is a multiple of 16 */ bh2 = sb_bread(sb, 2); if (bh2 == NULL) return 0; v7i = (struct sysv_inode *)(bh2->b_data + 64); if ((fs16_to_cpu(sbi, v7i->i_mode) & ~0777) != S_IFDIR || (fs32_to_cpu(sbi, v7i->i_size) == 0) || (fs32_to_cpu(sbi, v7i->i_size) & 017) || (fs32_to_cpu(sbi, v7i->i_size) > V7_NFILES * sizeof(struct sysv_dir_entry))) { brelse(bh2); return 0; } brelse(bh2); return 1; } static int v7_fill_super(struct super_block *sb, void *data, int silent) { struct sysv_sb_info *sbi; struct buffer_head *bh; BUILD_BUG_ON(sizeof(struct v7_super_block) != 440); BUILD_BUG_ON(sizeof(struct sysv_inode) != 64); sbi = kzalloc(sizeof(struct sysv_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sbi->s_sb = sb; sbi->s_block_base = 0; sbi->s_type = FSTYPE_V7; mutex_init(&sbi->s_lock); sb->s_fs_info = sbi; sb->s_time_min = 0; sb->s_time_max = U32_MAX; sb_set_blocksize(sb, 512); if ((bh = sb_bread(sb, 1)) == NULL) { if (!silent) printk("VFS: unable to read V7 FS superblock on " "device %s.\n", sb->s_id); goto failed; } /* Try PDP-11 UNIX */ sbi->s_bytesex = BYTESEX_PDP; if (v7_sanity_check(sb, bh)) goto detected; /* Try PC/IX, v7/x86 */ sbi->s_bytesex = BYTESEX_LE; if (v7_sanity_check(sb, bh)) goto detected; goto failed; detected: sbi->s_bh1 = bh; sbi->s_bh2 = bh; if (complete_read_super(sb, silent, 1)) return 0; failed: printk(KERN_ERR "VFS: could not find a valid V7 on %s.\n", sb->s_id); brelse(bh); kfree(sbi); return -EINVAL; } /* Every kernel module contains stuff like this. */ static struct dentry *sysv_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_bdev(fs_type, flags, dev_name, data, sysv_fill_super); } static struct dentry *v7_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_bdev(fs_type, flags, dev_name, data, v7_fill_super); } static struct file_system_type sysv_fs_type = { .owner = THIS_MODULE, .name = "sysv", .mount = sysv_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("sysv"); static struct file_system_type v7_fs_type = { .owner = THIS_MODULE, .name = "v7", .mount = v7_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("v7"); MODULE_ALIAS("v7"); static int __init init_sysv_fs(void) { int error; error = sysv_init_icache(); if (error) goto out; error = register_filesystem(&sysv_fs_type); if (error) goto destroy_icache; error = register_filesystem(&v7_fs_type); if (error) goto unregister; return 0; unregister: unregister_filesystem(&sysv_fs_type); destroy_icache: sysv_destroy_icache(); out: return error; } static void __exit exit_sysv_fs(void) { unregister_filesystem(&sysv_fs_type); unregister_filesystem(&v7_fs_type); sysv_destroy_icache(); } module_init(init_sysv_fs) module_exit(exit_sysv_fs) MODULE_DESCRIPTION("SystemV Filesystem"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 1 1 4 11 11 11 11 1 4 10 2 6 6 10 8 2 10 10 6 4 1 10 10 10 10 10 3 3 2 2 2 1 2 20 11 11 5 1 11 118 118 118 1 118 1 10 10 18 16 9 11 7 14 1 24 24 11 20 24 4 6 15 17 10 20 12 2 16 2 2 24 2 2 29 30 4 27 24 23 1 1 4 4 3 3 1 24 24 18 6 10 16 16 19 18 18 10 10 11 19 10 1 1 15 3 18 18 18 19 1 19 18 11 19 19 3 18 19 19 19 19 19 18 11 1 15 3 3 3 19 19 19 2 19 19 1 19 2 6 1 6 1 20 3 1 13 15 15 7 4 1 4 4 14 6 24 24 4 20 3 13 10 19 19 19 1 11 19 11 18 11 15 15 11 15 19 3 1 1 1 1 1 1 20 1 19 1 7 7 7 23 23 7 19 1 19 19 3 16 10 1 2 6 19 20 20 3 23 19 1 3 4 4 4 4 4 1 2 2 3 3 3 1 1 3 3 3 3 3 3 3 3 3 3 2 1 2 1 3 3 3 2 1 6 5 1 5 3 12 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <asm/byteorder.h> #include <linux/swap.h> #include <linux/mpage.h> #include <linux/quotaops.h> #include <linux/blkdev.h> #include <linux/uio.h> #include <linux/mm.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "aops.h" #include "dlmglue.h" #include "extent_map.h" #include "file.h" #include "inode.h" #include "journal.h" #include "suballoc.h" #include "super.h" #include "symlink.h" #include "refcounttree.h" #include "ocfs2_trace.h" #include "buffer_head_io.h" #include "dir.h" #include "namei.h" #include "sysfile.h" static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int err = -EIO; int status; struct ocfs2_dinode *fe = NULL; struct buffer_head *bh = NULL; struct buffer_head *buffer_cache_bh = NULL; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); void *kaddr; trace_ocfs2_symlink_get_block( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)iblock, bh_result, create); BUG_ON(ocfs2_inode_is_fast_symlink(inode)); if ((iblock << inode->i_sb->s_blocksize_bits) > PATH_MAX + 1) { mlog(ML_ERROR, "block offset > PATH_MAX: %llu", (unsigned long long)iblock); goto bail; } status = ocfs2_read_inode_block(inode, &bh); if (status < 0) { mlog_errno(status); goto bail; } fe = (struct ocfs2_dinode *) bh->b_data; if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb, le32_to_cpu(fe->i_clusters))) { err = -ENOMEM; mlog(ML_ERROR, "block offset is outside the allocated size: " "%llu\n", (unsigned long long)iblock); goto bail; } /* We don't use the page cache to create symlink data, so if * need be, copy it over from the buffer cache. */ if (!buffer_uptodate(bh_result) && ocfs2_inode_is_new(inode)) { u64 blkno = le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) + iblock; buffer_cache_bh = sb_getblk(osb->sb, blkno); if (!buffer_cache_bh) { err = -ENOMEM; mlog(ML_ERROR, "couldn't getblock for symlink!\n"); goto bail; } /* we haven't locked out transactions, so a commit * could've happened. Since we've got a reference on * the bh, even if it commits while we're doing the * copy, the data is still good. */ if (buffer_jbd(buffer_cache_bh) && ocfs2_inode_is_new(inode)) { kaddr = kmap_atomic(bh_result->b_page); if (!kaddr) { mlog(ML_ERROR, "couldn't kmap!\n"); goto bail; } memcpy(kaddr + (bh_result->b_size * iblock), buffer_cache_bh->b_data, bh_result->b_size); kunmap_atomic(kaddr); set_buffer_uptodate(bh_result); } brelse(buffer_cache_bh); } map_bh(bh_result, inode->i_sb, le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) + iblock); err = 0; bail: brelse(bh); return err; } static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret = 0; struct ocfs2_inode_info *oi = OCFS2_I(inode); down_read(&oi->ip_alloc_sem); ret = ocfs2_get_block(inode, iblock, bh_result, create); up_read(&oi->ip_alloc_sem); return ret; } int ocfs2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int err = 0; unsigned int ext_flags; u64 max_blocks = bh_result->b_size >> inode->i_blkbits; u64 p_blkno, count, past_eof; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); trace_ocfs2_get_block((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)iblock, bh_result, create); if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) mlog(ML_NOTICE, "get_block on system inode 0x%p (%lu)\n", inode, inode->i_ino); if (S_ISLNK(inode->i_mode)) { /* this always does I/O for some reason. */ err = ocfs2_symlink_get_block(inode, iblock, bh_result, create); goto bail; } err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count, &ext_flags); if (err) { mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, " "block: %llu\n", inode, (unsigned long long)iblock); goto bail; } if (max_blocks < count) count = max_blocks; /* * ocfs2 never allocates in this function - the only time we * need to use BH_New is when we're extending i_size on a file * system which doesn't support holes, in which case BH_New * allows __block_write_begin() to zero. * * If we see this on a sparse file system, then a truncate has * raced us and removed the cluster. In this case, we clear * the buffers dirty and uptodate bits and let the buffer code * ignore it as a hole. */ if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) { clear_buffer_dirty(bh_result); clear_buffer_uptodate(bh_result); goto bail; } /* Treat the unwritten extent as a hole for zeroing purposes. */ if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN)) map_bh(bh_result, inode->i_sb, p_blkno); bh_result->b_size = count << inode->i_blkbits; if (!ocfs2_sparse_alloc(osb)) { if (p_blkno == 0) { err = -EIO; mlog(ML_ERROR, "iblock = %llu p_blkno = %llu blkno=(%llu)\n", (unsigned long long)iblock, (unsigned long long)p_blkno, (unsigned long long)OCFS2_I(inode)->ip_blkno); mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters); dump_stack(); goto bail; } } past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); trace_ocfs2_get_block_end((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)past_eof); if (create && (iblock >= past_eof)) set_buffer_new(bh_result); bail: if (err < 0) err = -EIO; return err; } int ocfs2_read_inline_data(struct inode *inode, struct folio *folio, struct buffer_head *di_bh) { loff_t size; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) { ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); return -EROFS; } size = i_size_read(inode); if (size > folio_size(folio) || size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) { ocfs2_error(inode->i_sb, "Inode %llu has with inline data has bad size: %Lu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)size); return -EROFS; } folio_fill_tail(folio, 0, di->id2.i_data.id_data, size); folio_mark_uptodate(folio); return 0; } static int ocfs2_readpage_inline(struct inode *inode, struct folio *folio) { int ret; struct buffer_head *di_bh = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)); ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_read_inline_data(inode, folio, di_bh); out: folio_unlock(folio); brelse(di_bh); return ret; } static int ocfs2_read_folio(struct file *file, struct folio *folio) { struct inode *inode = folio->mapping->host; struct ocfs2_inode_info *oi = OCFS2_I(inode); loff_t start = folio_pos(folio); int ret, unlock = 1; trace_ocfs2_readpage((unsigned long long)oi->ip_blkno, folio->index); ret = ocfs2_inode_lock_with_folio(inode, NULL, 0, folio); if (ret != 0) { if (ret == AOP_TRUNCATED_PAGE) unlock = 0; mlog_errno(ret); goto out; } if (down_read_trylock(&oi->ip_alloc_sem) == 0) { /* * Unlock the folio and cycle ip_alloc_sem so that we don't * busyloop waiting for ip_alloc_sem to unlock */ ret = AOP_TRUNCATED_PAGE; folio_unlock(folio); unlock = 0; down_read(&oi->ip_alloc_sem); up_read(&oi->ip_alloc_sem); goto out_inode_unlock; } /* * i_size might have just been updated as we grabbed the meta lock. We * might now be discovering a truncate that hit on another node. * block_read_full_folio->get_block freaks out if it is asked to read * beyond the end of a file, so we check here. Callers * (generic_file_read, vm_ops->fault) are clever enough to check i_size * and notice that the folio they just read isn't needed. * * XXX sys_readahead() seems to get that wrong? */ if (start >= i_size_read(inode)) { folio_zero_segment(folio, 0, folio_size(folio)); folio_mark_uptodate(folio); ret = 0; goto out_alloc; } if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) ret = ocfs2_readpage_inline(inode, folio); else ret = block_read_full_folio(folio, ocfs2_get_block); unlock = 0; out_alloc: up_read(&oi->ip_alloc_sem); out_inode_unlock: ocfs2_inode_unlock(inode, 0); out: if (unlock) folio_unlock(folio); return ret; } /* * This is used only for read-ahead. Failures or difficult to handle * situations are safe to ignore. * * Right now, we don't bother with BH_Boundary - in-inode extent lists * are quite large (243 extents on 4k blocks), so most inodes don't * grow out to a tree. If need be, detecting boundary extents could * trivially be added in a future version of ocfs2_get_block(). */ static void ocfs2_readahead(struct readahead_control *rac) { int ret; struct inode *inode = rac->mapping->host; struct ocfs2_inode_info *oi = OCFS2_I(inode); /* * Use the nonblocking flag for the dlm code to avoid page * lock inversion, but don't bother with retrying. */ ret = ocfs2_inode_lock_full(inode, NULL, 0, OCFS2_LOCK_NONBLOCK); if (ret) return; if (down_read_trylock(&oi->ip_alloc_sem) == 0) goto out_unlock; /* * Don't bother with inline-data. There isn't anything * to read-ahead in that case anyway... */ if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) goto out_up; /* * Check whether a remote node truncated this file - we just * drop out in that case as it's not worth handling here. */ if (readahead_pos(rac) >= i_size_read(inode)) goto out_up; mpage_readahead(rac, ocfs2_get_block); out_up: up_read(&oi->ip_alloc_sem); out_unlock: ocfs2_inode_unlock(inode, 0); } /* Note: Because we don't support holes, our allocation has * already happened (allocation writes zeros to the file data) * so we don't have to worry about ordered writes in * ocfs2_writepages. * * ->writepages is called during the process of invalidating the page cache * during blocked lock processing. It can't block on any cluster locks * to during block mapping. It's relying on the fact that the block * mapping can't have disappeared under the dirty pages that it is * being asked to write back. */ static int ocfs2_writepages(struct address_space *mapping, struct writeback_control *wbc) { return mpage_writepages(mapping, wbc, ocfs2_get_block); } /* Taken from ext3. We don't necessarily need the full blown * functionality yet, but IMHO it's better to cut and paste the whole * thing so we can avoid introducing our own bugs (and easily pick up * their fixes when they happen) --Mark */ int walk_page_buffers( handle_t *handle, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)( handle_t *handle, struct buffer_head *bh)) { struct buffer_head *bh; unsigned block_start, block_end; unsigned blocksize = head->b_size; int err, ret = 0; struct buffer_head *next; for ( bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (partial && !buffer_uptodate(bh)) *partial = 1; continue; } err = (*fn)(handle, bh); if (!ret) ret = err; } return ret; } static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block) { sector_t status; u64 p_blkno = 0; int err = 0; struct inode *inode = mapping->host; trace_ocfs2_bmap((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)block); /* * The swap code (ab-)uses ->bmap to get a block mapping and then * bypasseѕ the file system for actual I/O. We really can't allow * that on refcounted inodes, so we have to skip out here. And yes, * 0 is the magic code for a bmap error.. */ if (ocfs2_is_refcount_inode(inode)) return 0; /* We don't need to lock journal system files, since they aren't * accessed concurrently from multiple nodes. */ if (!INODE_JOURNAL(inode)) { err = ocfs2_inode_lock(inode, NULL, 0); if (err) { if (err != -ENOENT) mlog_errno(err); goto bail; } down_read(&OCFS2_I(inode)->ip_alloc_sem); } if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL, NULL); if (!INODE_JOURNAL(inode)) { up_read(&OCFS2_I(inode)->ip_alloc_sem); ocfs2_inode_unlock(inode, 0); } if (err) { mlog(ML_ERROR, "get_blocks() failed, block = %llu\n", (unsigned long long)block); mlog_errno(err); goto bail; } bail: status = err ? 0 : p_blkno; return status; } static bool ocfs2_release_folio(struct folio *folio, gfp_t wait) { if (!folio_buffers(folio)) return false; return try_to_free_buffers(folio); } static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb, u32 cpos, unsigned int *start, unsigned int *end) { unsigned int cluster_start = 0, cluster_end = PAGE_SIZE; if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) { unsigned int cpp; cpp = 1 << (PAGE_SHIFT - osb->s_clustersize_bits); cluster_start = cpos % cpp; cluster_start = cluster_start << osb->s_clustersize_bits; cluster_end = cluster_start + osb->s_clustersize; } BUG_ON(cluster_start > PAGE_SIZE); BUG_ON(cluster_end > PAGE_SIZE); if (start) *start = cluster_start; if (end) *end = cluster_end; } /* * 'from' and 'to' are the region in the page to avoid zeroing. * * If pagesize > clustersize, this function will avoid zeroing outside * of the cluster boundary. * * from == to == 0 is code for "zero the entire cluster region" */ static void ocfs2_clear_folio_regions(struct folio *folio, struct ocfs2_super *osb, u32 cpos, unsigned from, unsigned to) { void *kaddr; unsigned int cluster_start, cluster_end; ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end); kaddr = kmap_local_folio(folio, 0); if (from || to) { if (from > cluster_start) memset(kaddr + cluster_start, 0, from - cluster_start); if (to < cluster_end) memset(kaddr + to, 0, cluster_end - to); } else { memset(kaddr + cluster_start, 0, cluster_end - cluster_start); } kunmap_local(kaddr); } /* * Nonsparse file systems fully allocate before we get to the write * code. This prevents ocfs2_write() from tagging the write as an * allocating one, which means ocfs2_map_folio_blocks() might try to * read-in the blocks at the tail of our file. Avoid reading them by * testing i_size against each block offset. */ static int ocfs2_should_read_blk(struct inode *inode, struct folio *folio, unsigned int block_start) { u64 offset = folio_pos(folio) + block_start; if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) return 1; if (i_size_read(inode) > offset) return 1; return 0; } /* * Some of this taken from __block_write_begin(). We already have our * mapping by now though, and the entire write will be allocating or * it won't, so not much need to use BH_New. * * This will also skip zeroing, which is handled externally. */ int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno, struct inode *inode, unsigned int from, unsigned int to, int new) { int ret = 0; struct buffer_head *head, *bh, *wait[2], **wait_bh = wait; unsigned int block_end, block_start; unsigned int bsize = i_blocksize(inode); head = folio_buffers(folio); if (!head) head = create_empty_buffers(folio, bsize, 0); for (bh = head, block_start = 0; bh != head || !block_start; bh = bh->b_this_page, block_start += bsize) { block_end = block_start + bsize; clear_buffer_new(bh); /* * Ignore blocks outside of our i/o range - * they may belong to unallocated clusters. */ if (block_start >= to || block_end <= from) { if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); continue; } /* * For an allocating write with cluster size >= page * size, we always write the entire page. */ if (new) set_buffer_new(bh); if (!buffer_mapped(bh)) { map_bh(bh, inode->i_sb, *p_blkno); clean_bdev_bh_alias(bh); } if (folio_test_uptodate(folio)) { set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_new(bh) && ocfs2_should_read_blk(inode, folio, block_start) && (block_start < from || block_end > to)) { bh_read_nowait(bh, 0); *wait_bh++=bh; } *p_blkno = *p_blkno + 1; } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) ret = -EIO; } if (ret == 0 || !new) return ret; /* * If we get -EIO above, zero out any newly allocated blocks * to avoid exposing stale data. */ bh = head; block_start = 0; do { block_end = block_start + bsize; if (block_end <= from) goto next_bh; if (block_start >= to) break; folio_zero_range(folio, block_start, bh->b_size); set_buffer_uptodate(bh); mark_buffer_dirty(bh); next_bh: block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } #if (PAGE_SIZE >= OCFS2_MAX_CLUSTERSIZE) #define OCFS2_MAX_CTXT_PAGES 1 #else #define OCFS2_MAX_CTXT_PAGES (OCFS2_MAX_CLUSTERSIZE / PAGE_SIZE) #endif #define OCFS2_MAX_CLUSTERS_PER_PAGE (PAGE_SIZE / OCFS2_MIN_CLUSTERSIZE) struct ocfs2_unwritten_extent { struct list_head ue_node; struct list_head ue_ip_node; u32 ue_cpos; u32 ue_phys; }; /* * Describe the state of a single cluster to be written to. */ struct ocfs2_write_cluster_desc { u32 c_cpos; u32 c_phys; /* * Give this a unique field because c_phys eventually gets * filled. */ unsigned c_new; unsigned c_clear_unwritten; unsigned c_needs_zero; }; struct ocfs2_write_ctxt { /* Logical cluster position / len of write */ u32 w_cpos; u32 w_clen; /* First cluster allocated in a nonsparse extend */ u32 w_first_new_cpos; /* Type of caller. Must be one of buffer, mmap, direct. */ ocfs2_write_type_t w_type; struct ocfs2_write_cluster_desc w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE]; /* * This is true if page_size > cluster_size. * * It triggers a set of special cases during write which might * have to deal with allocating writes to partial pages. */ unsigned int w_large_pages; /* * Folios involved in this write. * * w_target_folio is the folio being written to by the user. * * w_folios is an array of folios which always contains * w_target_folio, and in the case of an allocating write with * page_size < cluster size, it will contain zero'd and mapped * pages adjacent to w_target_folio which need to be written * out in so that future reads from that region will get * zero's. */ unsigned int w_num_folios; struct folio *w_folios[OCFS2_MAX_CTXT_PAGES]; struct folio *w_target_folio; /* * w_target_locked is used for page_mkwrite path indicating no unlocking * against w_target_folio in ocfs2_write_end_nolock. */ unsigned int w_target_locked:1; /* * ocfs2_write_end() uses this to know what the real range to * write in the target should be. */ unsigned int w_target_from; unsigned int w_target_to; /* * We could use journal_current_handle() but this is cleaner, * IMHO -Mark */ handle_t *w_handle; struct buffer_head *w_di_bh; struct ocfs2_cached_dealloc_ctxt w_dealloc; struct list_head w_unwritten_list; unsigned int w_unwritten_count; }; void ocfs2_unlock_and_free_folios(struct folio **folios, int num_folios) { int i; for(i = 0; i < num_folios; i++) { if (!folios[i]) continue; folio_unlock(folios[i]); folio_mark_accessed(folios[i]); folio_put(folios[i]); } } static void ocfs2_unlock_folios(struct ocfs2_write_ctxt *wc) { int i; /* * w_target_locked is only set to true in the page_mkwrite() case. * The intent is to allow us to lock the target page from write_begin() * to write_end(). The caller must hold a ref on w_target_folio. */ if (wc->w_target_locked) { BUG_ON(!wc->w_target_folio); for (i = 0; i < wc->w_num_folios; i++) { if (wc->w_target_folio == wc->w_folios[i]) { wc->w_folios[i] = NULL; break; } } folio_mark_accessed(wc->w_target_folio); folio_put(wc->w_target_folio); } ocfs2_unlock_and_free_folios(wc->w_folios, wc->w_num_folios); } static void ocfs2_free_unwritten_list(struct inode *inode, struct list_head *head) { struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL; list_for_each_entry_safe(ue, tmp, head, ue_node) { list_del(&ue->ue_node); spin_lock(&oi->ip_lock); list_del(&ue->ue_ip_node); spin_unlock(&oi->ip_lock); kfree(ue); } } static void ocfs2_free_write_ctxt(struct inode *inode, struct ocfs2_write_ctxt *wc) { ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list); ocfs2_unlock_folios(wc); brelse(wc->w_di_bh); kfree(wc); } static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, struct ocfs2_super *osb, loff_t pos, unsigned len, ocfs2_write_type_t type, struct buffer_head *di_bh) { u32 cend; struct ocfs2_write_ctxt *wc; wc = kzalloc(sizeof(struct ocfs2_write_ctxt), GFP_NOFS); if (!wc) return -ENOMEM; wc->w_cpos = pos >> osb->s_clustersize_bits; wc->w_first_new_cpos = UINT_MAX; cend = (pos + len - 1) >> osb->s_clustersize_bits; wc->w_clen = cend - wc->w_cpos + 1; get_bh(di_bh); wc->w_di_bh = di_bh; wc->w_type = type; if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) wc->w_large_pages = 1; else wc->w_large_pages = 0; ocfs2_init_dealloc_ctxt(&wc->w_dealloc); INIT_LIST_HEAD(&wc->w_unwritten_list); *wcp = wc; return 0; } /* * If a page has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ static void ocfs2_zero_new_buffers(struct folio *folio, size_t from, size_t to) { unsigned int block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!folio_test_uptodate(folio)) { unsigned start, end; start = max(from, block_start); end = min(to, block_end); folio_zero_segment(folio, start, end); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } /* * Only called when we have a failure during allocating write to write * zero's to the newly allocated region. */ static void ocfs2_write_failure(struct inode *inode, struct ocfs2_write_ctxt *wc, loff_t user_pos, unsigned user_len) { int i; unsigned from = user_pos & (PAGE_SIZE - 1), to = user_pos + user_len; if (wc->w_target_folio) ocfs2_zero_new_buffers(wc->w_target_folio, from, to); for (i = 0; i < wc->w_num_folios; i++) { struct folio *folio = wc->w_folios[i]; if (folio && folio_buffers(folio)) { if (ocfs2_should_order_data(inode)) ocfs2_jbd2_inode_add_write(wc->w_handle, inode, user_pos, user_len); block_commit_write(&folio->page, from, to); } } } static int ocfs2_prepare_folio_for_write(struct inode *inode, u64 *p_blkno, struct ocfs2_write_ctxt *wc, struct folio *folio, u32 cpos, loff_t user_pos, unsigned user_len, int new) { int ret; unsigned int map_from = 0, map_to = 0; unsigned int cluster_start, cluster_end; unsigned int user_data_from = 0, user_data_to = 0; ocfs2_figure_cluster_boundaries(OCFS2_SB(inode->i_sb), cpos, &cluster_start, &cluster_end); /* treat the write as new if the a hole/lseek spanned across * the page boundary. */ new = new | ((i_size_read(inode) <= folio_pos(folio)) && (folio_pos(folio) <= user_pos)); if (folio == wc->w_target_folio) { map_from = user_pos & (PAGE_SIZE - 1); map_to = map_from + user_len; if (new) ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, cluster_start, cluster_end, new); else ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, map_from, map_to, new); if (ret) { mlog_errno(ret); goto out; } user_data_from = map_from; user_data_to = map_to; if (new) { map_from = cluster_start; map_to = cluster_end; } } else { /* * If we haven't allocated the new folio yet, we * shouldn't be writing it out without copying user * data. This is likely a math error from the caller. */ BUG_ON(!new); map_from = cluster_start; map_to = cluster_end; ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, cluster_start, cluster_end, new); if (ret) { mlog_errno(ret); goto out; } } /* * Parts of newly allocated folios need to be zero'd. * * Above, we have also rewritten 'to' and 'from' - as far as * the rest of the function is concerned, the entire cluster * range inside of a folio needs to be written. * * We can skip this if the folio is uptodate - it's already * been zero'd from being read in as a hole. */ if (new && !folio_test_uptodate(folio)) ocfs2_clear_folio_regions(folio, OCFS2_SB(inode->i_sb), cpos, user_data_from, user_data_to); flush_dcache_folio(folio); out: return ret; } /* * This function will only grab one clusters worth of pages. */ static int ocfs2_grab_folios_for_write(struct address_space *mapping, struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos, unsigned user_len, int new, struct folio *mmap_folio) { int ret = 0, i; unsigned long start, target_index, end_index, index; struct inode *inode = mapping->host; loff_t last_byte; target_index = user_pos >> PAGE_SHIFT; /* * Figure out how many pages we'll be manipulating here. For * non allocating write, we just change the one * page. Otherwise, we'll need a whole clusters worth. If we're * writing past i_size, we only need enough pages to cover the * last page of the write. */ if (new) { wc->w_num_folios = ocfs2_pages_per_cluster(inode->i_sb); start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos); /* * We need the index *past* the last page we could possibly * touch. This is the page past the end of the write or * i_size, whichever is greater. */ last_byte = max(user_pos + user_len, i_size_read(inode)); BUG_ON(last_byte < 1); end_index = ((last_byte - 1) >> PAGE_SHIFT) + 1; if ((start + wc->w_num_folios) > end_index) wc->w_num_folios = end_index - start; } else { wc->w_num_folios = 1; start = target_index; } end_index = (user_pos + user_len - 1) >> PAGE_SHIFT; for(i = 0; i < wc->w_num_folios; i++) { index = start + i; if (index >= target_index && index <= end_index && wc->w_type == OCFS2_WRITE_MMAP) { /* * ocfs2_pagemkwrite() is a little different * and wants us to directly use the page * passed in. */ folio_lock(mmap_folio); /* Exit and let the caller retry */ if (mmap_folio->mapping != mapping) { WARN_ON(mmap_folio->mapping); folio_unlock(mmap_folio); ret = -EAGAIN; goto out; } folio_get(mmap_folio); wc->w_folios[i] = mmap_folio; wc->w_target_locked = true; } else if (index >= target_index && index <= end_index && wc->w_type == OCFS2_WRITE_DIRECT) { /* Direct write has no mapping page. */ wc->w_folios[i] = NULL; continue; } else { wc->w_folios[i] = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); if (IS_ERR(wc->w_folios[i])) { ret = PTR_ERR(wc->w_folios[i]); mlog_errno(ret); goto out; } } folio_wait_stable(wc->w_folios[i]); if (index == target_index) wc->w_target_folio = wc->w_folios[i]; } out: if (ret) wc->w_target_locked = false; return ret; } /* * Prepare a single cluster for write one cluster into the file. */ static int ocfs2_write_cluster(struct address_space *mapping, u32 *phys, unsigned int new, unsigned int clear_unwritten, unsigned int should_zero, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos, unsigned user_len) { int ret, i; u64 p_blkno; struct inode *inode = mapping->host; struct ocfs2_extent_tree et; int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1); if (new) { u32 tmp_pos; /* * This is safe to call with the page locks - it won't take * any additional semaphores or cluster locks. */ tmp_pos = cpos; ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode, &tmp_pos, 1, !clear_unwritten, wc->w_di_bh, wc->w_handle, data_ac, meta_ac, NULL); /* * This shouldn't happen because we must have already * calculated the correct meta data allocation required. The * internal tree allocation code should know how to increase * transaction credits itself. * * If need be, we could handle -EAGAIN for a * RESTART_TRANS here. */ mlog_bug_on_msg(ret == -EAGAIN, "Inode %llu: EAGAIN return during allocation.\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); if (ret < 0) { mlog_errno(ret); goto out; } } else if (clear_unwritten) { ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), wc->w_di_bh); ret = ocfs2_mark_extent_written(inode, &et, wc->w_handle, cpos, 1, *phys, meta_ac, &wc->w_dealloc); if (ret < 0) { mlog_errno(ret); goto out; } } /* * The only reason this should fail is due to an inability to * find the extent added. */ ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL); if (ret < 0) { mlog(ML_ERROR, "Get physical blkno failed for inode %llu, " "at logical cluster %u", (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos); goto out; } BUG_ON(*phys == 0); p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys); if (!should_zero) p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1); for (i = 0; i < wc->w_num_folios; i++) { int tmpret; /* This is the direct io target page. */ if (wc->w_folios[i] == NULL) { p_blkno += (1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits)); continue; } tmpret = ocfs2_prepare_folio_for_write(inode, &p_blkno, wc, wc->w_folios[i], cpos, user_pos, user_len, should_zero); if (tmpret) { mlog_errno(tmpret); if (ret == 0) ret = tmpret; } } /* * We only have cleanup to do in case of allocating write. */ if (ret && new) ocfs2_write_failure(inode, wc, user_pos, user_len); out: return ret; } static int ocfs2_write_cluster_by_desc(struct address_space *mapping, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct ocfs2_write_ctxt *wc, loff_t pos, unsigned len) { int ret, i; loff_t cluster_off; unsigned int local_len = len; struct ocfs2_write_cluster_desc *desc; struct ocfs2_super *osb = OCFS2_SB(mapping->host->i_sb); for (i = 0; i < wc->w_clen; i++) { desc = &wc->w_desc[i]; /* * We have to make sure that the total write passed in * doesn't extend past a single cluster. */ local_len = len; cluster_off = pos & (osb->s_clustersize - 1); if ((cluster_off + local_len) > osb->s_clustersize) local_len = osb->s_clustersize - cluster_off; ret = ocfs2_write_cluster(mapping, &desc->c_phys, desc->c_new, desc->c_clear_unwritten, desc->c_needs_zero, data_ac, meta_ac, wc, desc->c_cpos, pos, local_len); if (ret) { mlog_errno(ret); goto out; } len -= local_len; pos += local_len; } ret = 0; out: return ret; } /* * ocfs2_write_end() wants to know which parts of the target page it * should complete the write on. It's easiest to compute them ahead of * time when a more complete view of the write is available. */ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb, struct ocfs2_write_ctxt *wc, loff_t pos, unsigned len, int alloc) { struct ocfs2_write_cluster_desc *desc; wc->w_target_from = pos & (PAGE_SIZE - 1); wc->w_target_to = wc->w_target_from + len; if (alloc == 0) return; /* * Allocating write - we may have different boundaries based * on page size and cluster size. * * NOTE: We can no longer compute one value from the other as * the actual write length and user provided length may be * different. */ if (wc->w_large_pages) { /* * We only care about the 1st and last cluster within * our range and whether they should be zero'd or not. Either * value may be extended out to the start/end of a * newly allocated cluster. */ desc = &wc->w_desc[0]; if (desc->c_needs_zero) ocfs2_figure_cluster_boundaries(osb, desc->c_cpos, &wc->w_target_from, NULL); desc = &wc->w_desc[wc->w_clen - 1]; if (desc->c_needs_zero) ocfs2_figure_cluster_boundaries(osb, desc->c_cpos, NULL, &wc->w_target_to); } else { wc->w_target_from = 0; wc->w_target_to = PAGE_SIZE; } } /* * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to * do the zero work. And should not to clear UNWRITTEN since it will be cleared * by the direct io procedure. * If this is a new extent that allocated by direct io, we should mark it in * the ip_unwritten_list. */ static int ocfs2_unwritten_check(struct inode *inode, struct ocfs2_write_ctxt *wc, struct ocfs2_write_cluster_desc *desc) { struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_unwritten_extent *ue = NULL, *new = NULL; int ret = 0; if (!desc->c_needs_zero) return 0; retry: spin_lock(&oi->ip_lock); /* Needs not to zero no metter buffer or direct. The one who is zero * the cluster is doing zero. And he will clear unwritten after all * cluster io finished. */ list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) { if (desc->c_cpos == ue->ue_cpos) { BUG_ON(desc->c_new); desc->c_needs_zero = 0; desc->c_clear_unwritten = 0; goto unlock; } } if (wc->w_type != OCFS2_WRITE_DIRECT) goto unlock; if (new == NULL) { spin_unlock(&oi->ip_lock); new = kmalloc(sizeof(struct ocfs2_unwritten_extent), GFP_NOFS); if (new == NULL) { ret = -ENOMEM; goto out; } goto retry; } /* This direct write will doing zero. */ new->ue_cpos = desc->c_cpos; new->ue_phys = desc->c_phys; desc->c_clear_unwritten = 0; list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list); list_add_tail(&new->ue_node, &wc->w_unwritten_list); wc->w_unwritten_count++; new = NULL; unlock: spin_unlock(&oi->ip_lock); out: kfree(new); return ret; } /* * Populate each single-cluster write descriptor in the write context * with information about the i/o to be done. * * Returns the number of clusters that will have to be allocated, as * well as a worst case estimate of the number of extent records that * would have to be created during a write to an unwritten region. */ static int ocfs2_populate_write_desc(struct inode *inode, struct ocfs2_write_ctxt *wc, unsigned int *clusters_to_alloc, unsigned int *extents_to_split) { int ret; struct ocfs2_write_cluster_desc *desc; unsigned int num_clusters = 0; unsigned int ext_flags = 0; u32 phys = 0; int i; *clusters_to_alloc = 0; *extents_to_split = 0; for (i = 0; i < wc->w_clen; i++) { desc = &wc->w_desc[i]; desc->c_cpos = wc->w_cpos + i; if (num_clusters == 0) { /* * Need to look up the next extent record. */ ret = ocfs2_get_clusters(inode, desc->c_cpos, &phys, &num_clusters, &ext_flags); if (ret) { mlog_errno(ret); goto out; } /* We should already CoW the refcountd extent. */ BUG_ON(ext_flags & OCFS2_EXT_REFCOUNTED); /* * Assume worst case - that we're writing in * the middle of the extent. * * We can assume that the write proceeds from * left to right, in which case the extent * insert code is smart enough to coalesce the * next splits into the previous records created. */ if (ext_flags & OCFS2_EXT_UNWRITTEN) *extents_to_split = *extents_to_split + 2; } else if (phys) { /* * Only increment phys if it doesn't describe * a hole. */ phys++; } /* * If w_first_new_cpos is < UINT_MAX, we have a non-sparse * file that got extended. w_first_new_cpos tells us * where the newly allocated clusters are so we can * zero them. */ if (desc->c_cpos >= wc->w_first_new_cpos) { BUG_ON(phys == 0); desc->c_needs_zero = 1; } desc->c_phys = phys; if (phys == 0) { desc->c_new = 1; desc->c_needs_zero = 1; desc->c_clear_unwritten = 1; *clusters_to_alloc = *clusters_to_alloc + 1; } if (ext_flags & OCFS2_EXT_UNWRITTEN) { desc->c_clear_unwritten = 1; desc->c_needs_zero = 1; } ret = ocfs2_unwritten_check(inode, wc, desc); if (ret) { mlog_errno(ret); goto out; } num_clusters--; } ret = 0; out: return ret; } static int ocfs2_write_begin_inline(struct address_space *mapping, struct inode *inode, struct ocfs2_write_ctxt *wc) { int ret; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct folio *folio; handle_t *handle; struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } folio = __filemap_get_folio(mapping, 0, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); if (IS_ERR(folio)) { ocfs2_commit_trans(osb, handle); ret = PTR_ERR(folio); mlog_errno(ret); goto out; } /* * If we don't set w_num_folios then this folio won't get unlocked * and freed on cleanup of the write context. */ wc->w_target_folio = folio; wc->w_folios[0] = folio; wc->w_num_folios = 1; ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { ocfs2_commit_trans(osb, handle); mlog_errno(ret); goto out; } if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) ocfs2_set_inode_data_inline(inode, di); if (!folio_test_uptodate(folio)) { ret = ocfs2_read_inline_data(inode, folio, wc->w_di_bh); if (ret) { ocfs2_commit_trans(osb, handle); goto out; } } wc->w_handle = handle; out: return ret; } int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size) { struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; if (new_size <= le16_to_cpu(di->id2.i_data.id_count)) return 1; return 0; } static int ocfs2_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, size_t len, struct folio *mmap_folio, struct ocfs2_write_ctxt *wc) { int ret, written = 0; loff_t end = pos + len; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_dinode *di = NULL; trace_ocfs2_try_to_write_inline_data((unsigned long long)oi->ip_blkno, len, (unsigned long long)pos, oi->ip_dyn_features); /* * Handle inodes which already have inline data 1st. */ if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) { if (mmap_folio == NULL && ocfs2_size_fits_inline_data(wc->w_di_bh, end)) goto do_inline_write; /* * The write won't fit - we have to give this inode an * inline extent list now. */ ret = ocfs2_convert_inline_data_to_extents(inode, wc->w_di_bh); if (ret) mlog_errno(ret); goto out; } /* * Check whether the inode can accept inline data. */ if (oi->ip_clusters != 0 || i_size_read(inode) != 0) return 0; /* * Check whether the write can fit. */ di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; if (mmap_folio || end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) return 0; do_inline_write: ret = ocfs2_write_begin_inline(mapping, inode, wc); if (ret) { mlog_errno(ret); goto out; } /* * This signals to the caller that the data can be written * inline. */ written = 1; out: return written ? written : ret; } /* * This function only does anything for file systems which can't * handle sparse files. * * What we want to do here is fill in any hole between the current end * of allocation and the end of our write. That way the rest of the * write path can treat it as an non-allocating write, which has no * special case code for sparse/nonsparse files. */ static int ocfs2_expand_nonsparse_inode(struct inode *inode, struct buffer_head *di_bh, loff_t pos, unsigned len, struct ocfs2_write_ctxt *wc) { int ret; loff_t newsize = pos + len; BUG_ON(ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))); if (newsize <= i_size_read(inode)) return 0; ret = ocfs2_extend_no_holes(inode, di_bh, newsize, pos); if (ret) mlog_errno(ret); /* There is no wc if this is call from direct. */ if (wc) wc->w_first_new_cpos = ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)); return ret; } static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh, loff_t pos) { int ret = 0; BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))); if (pos > i_size_read(inode)) ret = ocfs2_zero_extend(inode, di_bh, pos); return ret; } int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, ocfs2_write_type_t type, struct folio **foliop, void **fsdata, struct buffer_head *di_bh, struct folio *mmap_folio) { int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS; unsigned int clusters_to_alloc, extents_to_split, clusters_need = 0; struct ocfs2_write_ctxt *wc; struct inode *inode = mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; handle_t *handle; struct ocfs2_extent_tree et; int try_free = 1, ret1; try_again: ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh); if (ret) { mlog_errno(ret); return ret; } if (ocfs2_supports_inline_data(osb)) { ret = ocfs2_try_to_write_inline_data(mapping, inode, pos, len, mmap_folio, wc); if (ret == 1) { ret = 0; goto success; } if (ret < 0) { mlog_errno(ret); goto out; } } /* Direct io change i_size late, should not zero tail here. */ if (type != OCFS2_WRITE_DIRECT) { if (ocfs2_sparse_alloc(osb)) ret = ocfs2_zero_tail(inode, di_bh, pos); else ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len, wc); if (ret) { mlog_errno(ret); goto out; } } ret = ocfs2_check_range_for_refcount(inode, pos, len); if (ret < 0) { mlog_errno(ret); goto out; } else if (ret == 1) { clusters_need = wc->w_clen; ret = ocfs2_refcount_cow(inode, di_bh, wc->w_cpos, wc->w_clen, UINT_MAX); if (ret) { mlog_errno(ret); goto out; } } ret = ocfs2_populate_write_desc(inode, wc, &clusters_to_alloc, &extents_to_split); if (ret) { mlog_errno(ret); goto out; } clusters_need += clusters_to_alloc; di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; trace_ocfs2_write_begin_nolock( (unsigned long long)OCFS2_I(inode)->ip_blkno, (long long)i_size_read(inode), le32_to_cpu(di->i_clusters), pos, len, type, mmap_folio, clusters_to_alloc, extents_to_split); /* * We set w_target_from, w_target_to here so that * ocfs2_write_end() knows which range in the target page to * write out. An allocation requires that we write the entire * cluster range. */ if (clusters_to_alloc || extents_to_split) { /* * XXX: We are stretching the limits of * ocfs2_lock_allocators(). It greatly over-estimates * the work to be done. */ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), wc->w_di_bh); ret = ocfs2_lock_allocators(inode, &et, clusters_to_alloc, extents_to_split, &data_ac, &meta_ac); if (ret) { mlog_errno(ret); goto out; } if (data_ac) data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv; credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list); } else if (type == OCFS2_WRITE_DIRECT) /* direct write needs not to start trans if no extents alloc. */ goto success; /* * We have to zero sparse allocated clusters, unwritten extent clusters, * and non-sparse clusters we just extended. For non-sparse writes, * we know zeros will only be needed in the first and/or last cluster. */ if (wc->w_clen && (wc->w_desc[0].c_needs_zero || wc->w_desc[wc->w_clen - 1].c_needs_zero)) cluster_of_pages = 1; else cluster_of_pages = 0; ocfs2_set_target_boundaries(osb, wc, pos, len, cluster_of_pages); handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } wc->w_handle = handle; if (clusters_to_alloc) { ret = dquot_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc)); if (ret) goto out_commit; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_quota; } /* * Fill our folio array first. That way we've grabbed enough so * that we can zero and flush if we error after adding the * extent. */ ret = ocfs2_grab_folios_for_write(mapping, wc, wc->w_cpos, pos, len, cluster_of_pages, mmap_folio); if (ret) { /* * ocfs2_grab_folios_for_write() returns -EAGAIN if it * could not lock the target folio. In this case, we exit * with no error and no target folio. This will trigger * the caller, page_mkwrite(), to re-try the operation. */ if (type == OCFS2_WRITE_MMAP && ret == -EAGAIN) { BUG_ON(wc->w_target_folio); ret = 0; goto out_quota; } mlog_errno(ret); goto out_quota; } ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos, len); if (ret) { mlog_errno(ret); goto out_quota; } if (data_ac) ocfs2_free_alloc_context(data_ac); if (meta_ac) ocfs2_free_alloc_context(meta_ac); success: if (foliop) *foliop = wc->w_target_folio; *fsdata = wc; return 0; out_quota: if (clusters_to_alloc) dquot_free_space(inode, ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc)); out_commit: ocfs2_commit_trans(osb, handle); out: /* * The mmapped page won't be unlocked in ocfs2_free_write_ctxt(), * even in case of error here like ENOSPC and ENOMEM. So, we need * to unlock the target page manually to prevent deadlocks when * retrying again on ENOSPC, or when returning non-VM_FAULT_LOCKED * to VM code. */ if (wc->w_target_locked) folio_unlock(mmap_folio); ocfs2_free_write_ctxt(inode, wc); if (data_ac) { ocfs2_free_alloc_context(data_ac); data_ac = NULL; } if (meta_ac) { ocfs2_free_alloc_context(meta_ac); meta_ac = NULL; } if (ret == -ENOSPC && try_free) { /* * Try to free some truncate log so that we can have enough * clusters to allocate. */ try_free = 0; ret1 = ocfs2_try_to_free_truncate_log(osb, clusters_need); if (ret1 == 1) goto try_again; if (ret1 < 0) mlog_errno(ret1); } return ret; } static int ocfs2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; struct buffer_head *di_bh = NULL; struct inode *inode = mapping->host; ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret) { mlog_errno(ret); return ret; } /* * Take alloc sem here to prevent concurrent lookups. That way * the mapping, zeroing and tree manipulation within * ocfs2_write() will be safe against ->read_folio(). This * should also serve to lock out allocation from a shared * writeable region. */ down_write(&OCFS2_I(inode)->ip_alloc_sem); ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER, foliop, fsdata, di_bh, NULL); if (ret) { mlog_errno(ret); goto out_fail; } brelse(di_bh); return 0; out_fail: up_write(&OCFS2_I(inode)->ip_alloc_sem); brelse(di_bh); ocfs2_inode_unlock(inode, 1); return ret; } static void ocfs2_write_end_inline(struct inode *inode, loff_t pos, unsigned len, unsigned *copied, struct ocfs2_dinode *di, struct ocfs2_write_ctxt *wc) { if (unlikely(*copied < len)) { if (!folio_test_uptodate(wc->w_target_folio)) { *copied = 0; return; } } memcpy_from_folio(di->id2.i_data.id_data + pos, wc->w_target_folio, pos, *copied); trace_ocfs2_write_end_inline( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)pos, *copied, le16_to_cpu(di->id2.i_data.id_count), le16_to_cpu(di->i_dyn_features)); } int ocfs2_write_end_nolock(struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, void *fsdata) { int i, ret; size_t from, to, start = pos & (PAGE_SIZE - 1); struct inode *inode = mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_write_ctxt *wc = fsdata; struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; handle_t *handle = wc->w_handle; BUG_ON(!list_empty(&wc->w_unwritten_list)); if (handle) { ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { copied = ret; mlog_errno(ret); goto out; } } if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { ocfs2_write_end_inline(inode, pos, len, &copied, di, wc); goto out_write_size; } if (unlikely(copied < len) && wc->w_target_folio) { loff_t new_isize; if (!folio_test_uptodate(wc->w_target_folio)) copied = 0; new_isize = max_t(loff_t, i_size_read(inode), pos + copied); if (new_isize > folio_pos(wc->w_target_folio)) ocfs2_zero_new_buffers(wc->w_target_folio, start+copied, start+len); else { /* * When folio is fully beyond new isize (data copy * failed), do not bother zeroing the folio. Invalidate * it instead so that writeback does not get confused * put page & buffer dirty bits into inconsistent * state. */ block_invalidate_folio(wc->w_target_folio, 0, folio_size(wc->w_target_folio)); } } if (wc->w_target_folio) flush_dcache_folio(wc->w_target_folio); for (i = 0; i < wc->w_num_folios; i++) { struct folio *folio = wc->w_folios[i]; /* This is the direct io target folio */ if (folio == NULL) continue; if (folio == wc->w_target_folio) { from = wc->w_target_from; to = wc->w_target_to; BUG_ON(from > folio_size(folio) || to > folio_size(folio) || to < from); } else { /* * Pages adjacent to the target (if any) imply * a hole-filling write in which case we want * to flush their entire range. */ from = 0; to = folio_size(folio); } if (folio_buffers(folio)) { if (handle && ocfs2_should_order_data(inode)) { loff_t start_byte = folio_pos(folio) + from; loff_t length = to - from; ocfs2_jbd2_inode_add_write(handle, inode, start_byte, length); } block_commit_write(&folio->page, from, to); } } out_write_size: /* Direct io do not update i_size here. */ if (wc->w_type != OCFS2_WRITE_DIRECT) { pos += copied; if (pos > i_size_read(inode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } inode->i_blocks = ocfs2_inode_sector_count(inode); di->i_size = cpu_to_le64((u64)i_size_read(inode)); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); di->i_mtime = di->i_ctime = cpu_to_le64(inode_get_mtime_sec(inode)); di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); if (handle) ocfs2_update_inode_fsync_trans(handle, inode, 1); } if (handle) ocfs2_journal_dirty(handle, wc->w_di_bh); out: /* unlock pages before dealloc since it needs acquiring j_trans_barrier * lock, or it will cause a deadlock since journal commit threads holds * this lock and will ask for the page lock when flushing the data. * put it here to preserve the unlock order. */ ocfs2_unlock_folios(wc); if (handle) ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); brelse(wc->w_di_bh); kfree(wc); return copied; } static int ocfs2_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { int ret; struct inode *inode = mapping->host; ret = ocfs2_write_end_nolock(mapping, pos, len, copied, fsdata); up_write(&OCFS2_I(inode)->ip_alloc_sem); ocfs2_inode_unlock(inode, 1); return ret; } struct ocfs2_dio_write_ctxt { struct list_head dw_zero_list; unsigned dw_zero_count; int dw_orphaned; pid_t dw_writer_pid; }; static struct ocfs2_dio_write_ctxt * ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc) { struct ocfs2_dio_write_ctxt *dwc = NULL; if (bh->b_private) return bh->b_private; dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS); if (dwc == NULL) return NULL; INIT_LIST_HEAD(&dwc->dw_zero_list); dwc->dw_zero_count = 0; dwc->dw_orphaned = 0; dwc->dw_writer_pid = task_pid_nr(current); bh->b_private = dwc; *alloc = 1; return dwc; } static void ocfs2_dio_free_write_ctx(struct inode *inode, struct ocfs2_dio_write_ctxt *dwc) { ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list); kfree(dwc); } /* * TODO: Make this into a generic get_blocks function. * * From do_direct_io in direct-io.c: * "So what we do is to permit the ->get_blocks function to populate * bh.b_size with the size of IO which is permitted at this offset and * this i_blkbits." * * This function is called directly from get_more_blocks in direct-io.c. * * called like this: dio->get_blocks(dio->inode, fs_startblk, * fs_count, map_bh, dio->rw == WRITE); */ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_write_ctxt *wc; struct ocfs2_write_cluster_desc *desc = NULL; struct ocfs2_dio_write_ctxt *dwc = NULL; struct buffer_head *di_bh = NULL; u64 p_blkno; unsigned int i_blkbits = inode->i_sb->s_blocksize_bits; loff_t pos = iblock << i_blkbits; sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits; unsigned len, total_len = bh_result->b_size; int ret = 0, first_get_block = 0; len = osb->s_clustersize - (pos & (osb->s_clustersize - 1)); len = min(total_len, len); /* * bh_result->b_size is count in get_more_blocks according to write * "pos" and "end", we need map twice to return different buffer state: * 1. area in file size, not set NEW; * 2. area out file size, set NEW. * * iblock endblk * |--------|---------|---------|--------- * |<-------area in file------->| */ if ((iblock <= endblk) && ((iblock + ((len - 1) >> i_blkbits)) > endblk)) len = (endblk - iblock + 1) << i_blkbits; mlog(0, "get block of %lu at %llu:%u req %u\n", inode->i_ino, pos, len, total_len); /* * Because we need to change file size in ocfs2_dio_end_io_write(), or * we may need to add it to orphan dir. So can not fall to fast path * while file size will be changed. */ if (pos + total_len <= i_size_read(inode)) { /* This is the fast path for re-write. */ ret = ocfs2_lock_get_block(inode, iblock, bh_result, create); if (buffer_mapped(bh_result) && !buffer_new(bh_result) && ret == 0) goto out; /* Clear state set by ocfs2_get_block. */ bh_result->b_state = 0; } dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block); if (unlikely(dwc == NULL)) { ret = -ENOMEM; mlog_errno(ret); goto out; } if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) > ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) && !dwc->dw_orphaned) { /* * when we are going to alloc extents beyond file size, add the * inode to orphan dir, so we can recall those spaces when * system crashed during write. */ ret = ocfs2_add_inode_to_orphan(osb, inode); if (ret < 0) { mlog_errno(ret); goto out; } dwc->dw_orphaned = 1; } ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret) { mlog_errno(ret); goto out; } down_write(&oi->ip_alloc_sem); if (first_get_block) { if (ocfs2_sparse_alloc(osb)) ret = ocfs2_zero_tail(inode, di_bh, pos); else ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, total_len, NULL); if (ret < 0) { mlog_errno(ret); goto unlock; } } ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len, OCFS2_WRITE_DIRECT, NULL, (void **)&wc, di_bh, NULL); if (ret) { mlog_errno(ret); goto unlock; } desc = &wc->w_desc[0]; p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys); BUG_ON(p_blkno == 0); p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1); map_bh(bh_result, inode->i_sb, p_blkno); bh_result->b_size = len; if (desc->c_needs_zero) set_buffer_new(bh_result); if (iblock > endblk) set_buffer_new(bh_result); /* May sleep in end_io. It should not happen in a irq context. So defer * it to dio work queue. */ set_buffer_defer_completion(bh_result); if (!list_empty(&wc->w_unwritten_list)) { struct ocfs2_unwritten_extent *ue = NULL; ue = list_first_entry(&wc->w_unwritten_list, struct ocfs2_unwritten_extent, ue_node); BUG_ON(ue->ue_cpos != desc->c_cpos); /* The physical address may be 0, fill it. */ ue->ue_phys = desc->c_phys; list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list); dwc->dw_zero_count += wc->w_unwritten_count; } ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, wc); BUG_ON(ret != len); ret = 0; unlock: up_write(&oi->ip_alloc_sem); ocfs2_inode_unlock(inode, 1); brelse(di_bh); out: return ret; } static int ocfs2_dio_end_io_write(struct inode *inode, struct ocfs2_dio_write_ctxt *dwc, loff_t offset, ssize_t bytes) { struct ocfs2_cached_dealloc_ctxt dealloc; struct ocfs2_extent_tree et; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_unwritten_extent *ue = NULL; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; handle_t *handle = NULL; loff_t end = offset + bytes; int ret = 0, credits = 0; ocfs2_init_dealloc_ctxt(&dealloc); /* We do clear unwritten, delete orphan, change i_size here. If neither * of these happen, we can skip all this. */ if (list_empty(&dwc->dw_zero_list) && end <= i_size_read(inode) && !dwc->dw_orphaned) goto out; ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret < 0) { mlog_errno(ret); goto out; } down_write(&oi->ip_alloc_sem); /* Delete orphan before acquire i_rwsem. */ if (dwc->dw_orphaned) { BUG_ON(dwc->dw_writer_pid != task_pid_nr(current)); end = end > i_size_read(inode) ? end : 0; ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, !!end, end); if (ret < 0) mlog_errno(ret); } di = (struct ocfs2_dinode *)di_bh->b_data; ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh); /* Attach dealloc with extent tree in case that we may reuse extents * which are already unlinked from current extent tree due to extent * rotation and merging. */ et.et_dealloc = &dealloc; ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2, &data_ac, &meta_ac); if (ret) { mlog_errno(ret); goto unlock; } credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list); handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto unlock; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto commit; } list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) { ret = ocfs2_assure_trans_credits(handle, credits); if (ret < 0) { mlog_errno(ret); break; } ret = ocfs2_mark_extent_written(inode, &et, handle, ue->ue_cpos, 1, ue->ue_phys, meta_ac, &dealloc); if (ret < 0) { mlog_errno(ret); break; } } if (end > i_size_read(inode)) { ret = ocfs2_set_inode_size(handle, inode, di_bh, end); if (ret < 0) mlog_errno(ret); } commit: ocfs2_commit_trans(osb, handle); unlock: up_write(&oi->ip_alloc_sem); ocfs2_inode_unlock(inode, 1); brelse(di_bh); out: if (data_ac) ocfs2_free_alloc_context(data_ac); if (meta_ac) ocfs2_free_alloc_context(meta_ac); ocfs2_run_deallocs(osb, &dealloc); ocfs2_dio_free_write_ctx(inode, dwc); return ret; } /* * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're * particularly interested in the aio/dio case. We use the rw_lock DLM lock * to protect io on one node from truncation on another. */ static int ocfs2_dio_end_io(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private) { struct inode *inode = file_inode(iocb->ki_filp); int level; int ret = 0; /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); if (bytes <= 0) mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld", (long long)bytes); if (private) { if (bytes > 0) ret = ocfs2_dio_end_io_write(inode, private, offset, bytes); else ocfs2_dio_free_write_ctx(inode, private); } ocfs2_iocb_clear_rw_locked(iocb); level = ocfs2_iocb_rw_locked_level(iocb); ocfs2_rw_unlock(inode, level); return ret; } static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); get_block_t *get_block; /* * Fallback to buffered I/O if we see an inode without * extents. */ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; /* Fallback to buffered I/O if we do not support append dio. */ if (iocb->ki_pos + iter->count > i_size_read(inode) && !ocfs2_supports_append_dio(osb)) return 0; if (iov_iter_rw(iter) == READ) get_block = ocfs2_lock_get_block; else get_block = ocfs2_dio_wr_get_block; return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, ocfs2_dio_end_io, 0); } const struct address_space_operations ocfs2_aops = { .dirty_folio = block_dirty_folio, .read_folio = ocfs2_read_folio, .readahead = ocfs2_readahead, .writepages = ocfs2_writepages, .write_begin = ocfs2_write_begin, .write_end = ocfs2_write_end, .bmap = ocfs2_bmap, .direct_IO = ocfs2_direct_IO, .invalidate_folio = block_invalidate_folio, .release_folio = ocfs2_release_folio, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, }; |
| 10088 8222 3 8000 9829 7783 6 769 1 53 526 211 5740 3423 1900 21 4028 378 223 66 806 4810 54 757 1686 12 171 333 5581 1 3148 3935 812 1616 56 4134 3963 471 1975 254 396 261 12 2 261 2 2 53 1 448 8883 5 914 136 136 6 1 812 814 809 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the pageflags directly. Use the PageFoo macros. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_writeback, /* Page is under writeback */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_head, /* Must be in bit 6 */ PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, PG_owner_priv_1, /* Owner use. If pagecache, fs may use */ PG_owner_2, /* Owner use. If pagecache, fs may use */ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ PG_dropbehind, /* drop pages on IO completion */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_2 PG_arch_2, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_3 PG_arch_3, #endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, /* Anonymous memory (and shmem) */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Some filesystems */ PG_checked = PG_owner_priv_1, /* * Depending on the way an anonymous folio can be mapped into a page * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped * THP), PG_anon_exclusive may be set only for the head page or for * tail pages of an anonymous folio. For now, we only expect it to be * set on tail pages for PTE-mapped THP. */ PG_anon_exclusive = PG_owner_2, /* * Set if all buffer heads in the folio are mapped. * Filesystems which do not use BHs can use it for their own purpose. */ PG_mappedtodisk = PG_owner_2, /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, #ifdef CONFIG_MEMORY_HOTPLUG /* For self-hosted memmap pages */ PG_vmemmap_self_hosted = PG_owner_priv_1, #endif /* * Flags only valid for compound pages. Stored in first tail page's * flags word. Cannot use the first 8 flags or any flag marked as * PF_ANY. */ /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) #ifndef __GENERATING_BOUNDS_H #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); /* * Return the real head page struct iff the @page is a fake head page, otherwise * return the @page itself. See Documentation/mm/vmemmap_dedup.rst. */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key)) return page; /* * Only addresses aligned with PAGE_SIZE of struct page may be fake head * struct page. The alignment check aims to avoid access the fields ( * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly) * cold cacheline in some cases. */ if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && test_bit(PG_head, &page->flags)) { /* * We can safely access the field of the @page[1] with PG_head * because the @page is a compound page composed with at least * two contiguous pages. */ unsigned long head = READ_ONCE(page[1].compound_head); if (likely(head & 1)) return (const struct page *)(head - 1); } return page; } #else static inline const struct page *page_fixed_fake_head(const struct page *page) { return page; } #endif static __always_inline int page_is_fake_head(const struct page *page) { return page_fixed_fake_head(page) != page; } static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return head - 1; return (unsigned long)page_fixed_fake_head(page); } #define compound_head(page) ((typeof(page))_compound_head(page)) /** * page_folio - Converts from page to folio. * @p: The page. * * Every page is part of a folio. This function cannot be called on a * NULL pointer. * * Context: No reference, nor lock is required on @page. If the caller * does not hold a reference, this call may race with a folio split, so * it should re-check the folio still contains this page after gaining * a reference on the folio. * Return: The folio which contains this page. */ #define page_folio(p) (_Generic((p), \ const struct page *: (const struct folio *)_compound_head(p), \ struct page *: (struct folio *)_compound_head(p))) /** * folio_page - Return a page from a folio. * @folio: The folio. * @n: The page number to return. * * @n is relative to the start of the folio. This function does not * check that the page number lies within @folio; the caller is presumed * to have a reference to the page. */ #define folio_page(folio, n) nth_page(&(folio)->page, n) static __always_inline int PageTail(const struct page *page) { return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } static __always_inline int PageCompound(const struct page *page) { return test_bit(PG_head, &page->flags) || READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif static const unsigned long *const_folio_flags(const struct folio *folio, unsigned n) { const struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* Which page is the flag stored in */ #define FOLIO_PF_ANY 0 #define FOLIO_PF_HEAD 0 #define FOLIO_PF_NO_TAIL 0 #define FOLIO_PF_NO_COMPOUND 0 #define FOLIO_PF_SECOND 1 #define FOLIO_HEAD_PAGE 0 #define FOLIO_SECOND_PAGE 1 /* * Macros to create function definitions for page flags */ #define FOLIO_TEST_FLAG(name, page) \ static __always_inline bool folio_test_##name(const struct folio *folio) \ { return test_bit(PG_##name, const_folio_flags(folio, page)); } #define FOLIO_SET_FLAG(name, page) \ static __always_inline void folio_set_##name(struct folio *folio) \ { set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void folio_clear_##name(struct folio *folio) \ { clear_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_SET_FLAG(name, page) \ static __always_inline void __folio_set_##name(struct folio *folio) \ { __set_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void __folio_clear_##name(struct folio *folio) \ { __clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_SET_FLAG(name, page) \ static __always_inline bool folio_test_set_##name(struct folio *folio) \ { return test_and_set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_CLEAR_FLAG(name, page) \ static __always_inline bool folio_test_clear_##name(struct folio *folio) \ { return test_and_clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_FLAG(name, page) \ FOLIO_TEST_FLAG(name, page) \ FOLIO_SET_FLAG(name, page) \ FOLIO_CLEAR_FLAG(name, page) #define TESTPAGEFLAG(uname, lname, policy) \ FOLIO_TEST_FLAG(lname, FOLIO_##policy) \ static __always_inline int Page##uname(const struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ __FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ __FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define FOLIO_TEST_FLAG_FALSE(name) \ static inline bool folio_test_##name(const struct folio *folio) \ { return false; } #define FOLIO_SET_FLAG_NOOP(name) \ static inline void folio_set_##name(struct folio *folio) { } #define FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void folio_clear_##name(struct folio *folio) { } #define __FOLIO_SET_FLAG_NOOP(name) \ static inline void __folio_set_##name(struct folio *folio) { } #define __FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void __folio_clear_##name(struct folio *folio) { } #define FOLIO_TEST_SET_FLAG_FALSE(name) \ static inline bool folio_test_set_##name(struct folio *folio) \ { return false; } #define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ static inline bool folio_test_clear_##name(struct folio *folio) \ { return false; } #define FOLIO_FLAG_FALSE(name) \ FOLIO_TEST_FLAG_FALSE(name) \ FOLIO_SET_FLAG_NOOP(name) \ FOLIO_CLEAR_FLAG_NOOP(name) #define TESTPAGEFLAG_FALSE(uname, lname) \ FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ __FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname) #define TESTSCFLAG_FALSE(uname, lname) \ TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD) FOLIO_FLAG(active, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE) /* owner_2 can be set on tail pages for anon memory */ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #define folio_test_highmem(__f) is_highmem_idx(folio_zonenum(__f)) #else PAGEFLAG_FALSE(HighMem, highmem) #endif #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { return folio_test_swapbacked(folio) && test_bit(PG_swapcache, const_folio_flags(folio, 0)); } FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE) FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(swapcache) #endif FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(mlocked) __FOLIO_CLEAR_FLAG_NOOP(mlocked) FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked) FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif #ifdef CONFIG_PAGE_IDLE_FLAG #ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif /* See page_idle.h for !64BIT workaround */ #else /* !CONFIG_PAGE_IDLE_FLAG */ FOLIO_FLAG_FALSE(young) FOLIO_TEST_CLEAR_FLAG_FALSE(young) FOLIO_FLAG_FALSE(idle) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #ifdef CONFIG_MEMORY_HOTPLUG PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) #else PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* * On an anonymous folio mapped into a user virtual memory area, * folio->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable * page and then folio->mapping points to a struct movable_operations. * * Please note that, confusingly, "folio_mapping" refers to the inode * address_space which maps the folio from disk; whereas "folio_mapped" * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its * internal states, the folio->mapping does not exist as such, nor do * these flags below. So in order to avoid testing non-existent bits, * please make sure that folio_test_slab(folio) actually evaluates to * false before calling the following functions (e.g., folio_test_anon). * See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) /* * Different with flags above, this flag is used only for fsdax mode. It * indicates that this page->mapping is now under reflink case. */ #define PAGE_MAPPING_DAX_SHARED ((void *)0x1) static __always_inline bool folio_mapping_flags(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool folio_test_anon(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } static __always_inline bool PageAnonNotKsm(const struct page *page) { unsigned long flags = (unsigned long)page_folio(page)->mapping; return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON; } static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); } static __always_inline bool __folio_test_movable(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } static __always_inline bool __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline bool folio_test_ksm(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } #else FOLIO_TEST_FLAG_FALSE(ksm) #endif u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. * @folio: The folio. * @mask: Bits set in this word will be changed. * * This must only be used for flags which are changed with the folio * lock held. For example, it is unsafe to use for PG_dirty as that * can be set without the folio lock held. It can also only be used * on flags which are in the range 0-6 as some of the implementations * only affect those bits. * * Return: Whether there are tasks waiting on the folio. */ static inline bool folio_xor_flags_has_waiters(struct folio *folio, unsigned long mask) { return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0)); } /** * folio_test_uptodate - Is this folio up to date? * @folio: The folio. * * The uptodate flag is set on a folio when every byte in the folio is * at least as new as the corresponding bytes on storage. Anonymous * and CoW folios are always uptodate. If the folio is not uptodate, * some of the bytes in it may be; see the is_partially_uptodate() * address_space operation. */ static inline bool folio_test_uptodate(const struct folio *folio) { bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0)); /* * Must ensure that the data we read out of the folio is loaded * _after_ we've loaded folio->flags to check the uptodate bit. * We can skip the barrier if the folio is not uptodate, because * we wouldn't be reading anything from it. * * See folio_mark_uptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } static __always_inline void __folio_mark_uptodate(struct folio *folio) { smp_wmb(); __set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void folio_mark_uptodate(struct folio *folio) { /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the folio * uptodate are actually visible before folio_test_uptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void __SetPageUptodate(struct page *page) { __folio_mark_uptodate((struct folio *)page); } static __always_inline void SetPageUptodate(struct page *page) { folio_mark_uptodate((struct folio *)page); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) void __folio_start_writeback(struct folio *folio, bool keep_write); void set_page_writeback(struct page *page); #define folio_start_writeback(folio) \ __folio_start_writeback(folio, false) #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) static __always_inline bool folio_test_head(const struct folio *folio) { return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY)); } static __always_inline int PageHead(const struct page *page) { PF_POISONED_CHECK(page); return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); } __SETPAGEFLAG(Head, head, PF_ANY) __CLEARPAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? * @folio: The folio to test. * * Return: True if the folio is larger than one page. */ static inline bool folio_test_large(const struct folio *folio) { return folio_test_head(folio); } static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) FOLIO_FLAG_FALSE(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for * normal or transparent huge pages. * * PageTransHuge() returns true for both transparent huge and * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ static inline int PageTransHuge(const struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); } /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } #else TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) /* * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the * compound page. * * This flag is set by hwpoison handler. Cleared by THP split or free page. */ FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(has_hwpoisoned) #endif /* * For pages that do not use mapcount, page_type may be used. * The low 24 bits of pagetype may be used for your own purposes, as long * as you are careful to not affect the top 8 bits. The low bits of * pagetype will be overwritten when you clear the page_type from the page. */ enum pagetype { /* 0x00-0x7f are positive numbers, ie mapcount */ /* Reserve 0x80-0xef for mapcount overflow. */ PGTY_buddy = 0xf0, PGTY_offline = 0xf1, PGTY_table = 0xf2, PGTY_guard = 0xf3, PGTY_hugetlb = 0xf4, PGTY_slab = 0xf5, PGTY_zsmalloc = 0xf6, PGTY_unaccepted = 0xf7, PGTY_mapcount_underflow = 0xff }; static inline bool page_type_has_type(int page_type) { return page_type < (PGTY_mapcount_underflow << 24); } /* This takes a mapcount which is one more than page->_mapcount */ static inline bool page_mapcount_is_type(unsigned int mapcount) { return page_type_has_type(mapcount - 1); } static inline bool page_has_type(const struct page *page) { return page_mapcount_is_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ static __always_inline bool folio_test_##fname(const struct folio *folio) \ { \ return data_race(folio->page.page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ if (folio_test_##fname(folio)) \ return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ if (folio->page.page_type == UINT_MAX) \ return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } #define PAGE_TYPE_OPS(uname, lname, fname) \ FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return data_race(page->page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ if (Page##uname(page)) \ return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ if (page->page_type == UINT_MAX) \ return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * When a memory block gets onlined, all pages are initialized with a * refcount of 1 and PageOffline(). generic_online_page() will * take care of clearing PageOffline(). * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free (unmanaged) * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require not giving them to the buddy via generic_online_page(). * * Memory offlining code will not adjust the managed page count for any * PageOffline() pages, treating them like they were never exposed to the * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random * pages should check PageOffline() and synchronize with such drivers using * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline, offline) extern void page_offline_freeze(void); extern void page_offline_thaw(void); extern void page_offline_begin(void); extern void page_offline_end(void); /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table, pgtable) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard, guard) FOLIO_TYPE_OPS(slab, slab) /** * PageSlab - Determine if the page belongs to the slab allocator * @page: The page to test. * * Context: Any context. * Return: True for slab pages, false for any other kind of page. */ static inline bool PageSlab(const struct page *page) { return folio_test_slab(page_folio(page)); } #ifdef CONFIG_HUGETLB_PAGE FOLIO_TYPE_OPS(hugetlb, hugetlb) #else FOLIO_TEST_FLAG_FALSE(hugetlb) #endif PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) /* * Mark pages that has to be accepted before touched for the first time. * * Serialized with zone lock. */ PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. * * Context: Any context. * Return: True for hugetlbfs pages, false for anon pages or pages * belonging to other filesystems. */ static inline bool PageHuge(const struct page *page) { return folio_test_hugetlb(page_folio(page)); } /* * Check if a page is currently marked HWPoisoned. Note that this check is * best effort only and inherently racy: there is no way to synchronize with * failing hardware. */ static inline bool is_page_hwpoison(const struct page *page) { const struct folio *folio; if (PageHWPoison(page)) return true; folio = page_folio(page); return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); /* * HugeTLB stores this information on the head page; THP keeps it per * page */ if (PageHuge(page)) page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void SetPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void __ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) /* * Flags stored in the second page of a compound page. They may overlap * the CHECK_AT_FREE flags above, so need to be cleared. */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ 1UL << PG_large_rmappable | 1UL << PG_partially_mapped) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * folio_has_private - Determine if folio has private stuff * @folio: The folio to be checked * * Determine if a folio has private stuff, indicating that release routines * should be invoked upon it. */ static inline int folio_has_private(const struct folio *folio) { return !!(folio->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ |
| 10 6 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/syscalls.h> #include <linux/time_namespace.h> #include "futex.h" /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. * * Implementation: user-space maintains a per-thread list of locks it * is holding. Upon do_exit(), the kernel carefully walks this list, * and marks all locks that are owned by this thread with the * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is * always manipulated with the lock held, so the list is private and * per-thread. Userspace also maintains a per-thread 'list_op_pending' * field, to allow the kernel to clean up if the thread dies after * acquiring the lock, but just before it could have added itself to * the list. There can only be one such pending lock. */ /** * sys_set_robust_list() - Set the robust-futex list head of a task * @head: pointer to the list-head * @len: length of the list-head, as userspace expects */ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) { /* * The kernel knows only one size for now: */ if (unlikely(len != sizeof(*head))) return -EINVAL; current->robust_list = head; return 0; } /** * sys_get_robust_list() - Get the robust-futex list head of a task * @pid: pid of the process [zero for current task] * @head_ptr: pointer to a list-head pointer, the kernel fills it in * @len_ptr: pointer to a length field, the kernel fills in the header size */ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, size_t __user *, len_ptr) { struct robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); err_unlock: rcu_read_unlock(); return ret; } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { unsigned int flags = futex_to_flags(op); int cmd = op & FUTEX_CMD_MASK; if (flags & FLAGS_CLOCKRT) { if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && cmd != FUTEX_LOCK_PI2) return -ENOSYS; } switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAIT_BITSET: return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0); case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: flags |= FLAGS_CLOCKRT; fallthrough; case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, uaddr2); case FUTEX_CMP_REQUEUE_PI: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1); } return -ENOSYS; } static __always_inline bool futex_cmd_has_timeout(u32 cmd) { switch (cmd) { case FUTEX_WAIT: case FUTEX_LOCK_PI: case FUTEX_LOCK_PI2: case FUTEX_WAIT_BITSET: case FUTEX_WAIT_REQUEUE_PI: return true; } return false; } static __always_inline int futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) { if (!timespec64_valid(ts)) return -EINVAL; *t = timespec64_to_ktime(*ts); if (cmd == FUTEX_WAIT) *t = ktime_add_safe(ktime_get(), *t); else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); return 0; } SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, const struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) return -EFAULT; if (get_timespec64(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } /** * futex_parse_waitv - Parse a waitv array from userspace * @futexv: Kernel side list of waiters to be filled * @uwaitv: Userspace list to be parsed * @nr_futexes: Length of futexv * @wake: Wake to call when futex is woken * @wake_data: Data for the wake handler * * Return: Error code on failure, 0 on success */ int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data) { struct futex_waitv aux; unsigned int i; for (i = 0; i < nr_futexes; i++) { unsigned int flags; if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) return -EFAULT; if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) return -EINVAL; flags = futex2_to_flags(aux.flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, aux.val)) return -EINVAL; futexv[i].w.flags = flags; futexv[i].w.val = aux.val; futexv[i].w.uaddr = aux.uaddr; futexv[i].q = futex_q_init; futexv[i].q.wake = wake; futexv[i].q.wake_data = wake_data; } return 0; } static int futex2_setup_timeout(struct __kernel_timespec __user *timeout, clockid_t clockid, struct hrtimer_sleeper *to) { int flag_clkid = 0, flag_init = 0; struct timespec64 ts; ktime_t time; int ret; if (!timeout) return 0; if (clockid == CLOCK_REALTIME) { flag_clkid = FLAGS_CLOCKRT; flag_init = FUTEX_CLOCK_REALTIME; } if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) return -EINVAL; if (get_timespec64(&ts, timeout)) return -EFAULT; /* * Since there's no opcode for futex_waitv, use * FUTEX_WAIT_BITSET that uses absolute timeout as well */ ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); if (ret) return ret; futex_setup_timer(&time, to, flag_clkid, 0); return 0; } static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to) { hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); } /** * sys_futex_waitv - Wait on a list of futexes * @waiters: List of futexes to wait on * @nr_futexes: Length of futexv * @flags: Flag for timeout (monotonic/realtime) * @timeout: Optional absolute timeout. * @clockid: Clock to be used for the timeout, realtime or monotonic. * * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes * if a futex_wake() is performed at any uaddr. The syscall returns immediately * if any waiter has *uaddr != val. *timeout is an optional timeout value for * the operation. Each waiter has individual flags. The `flags` argument for * the syscall should be used solely for specifying the timeout as realtime, if * needed. Flags for private futexes, sizes, etc. should be used on the * individual flags of each waiter. * * Returns the array index of one of the woken futexes. No further information * is provided: any number of other futexes may also have been woken by the * same event, and if more than one futex was woken, the retrned index may * refer to any one of them. (It is not necessaryily the futex with the * smallest index, nor the one most recently woken, nor...) */ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, unsigned int, nr_futexes, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; struct futex_vector *futexv; int ret; /* This syscall supports no flags for now */ if (flags) return -EINVAL; if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); if (!futexv) { ret = -ENOMEM; goto destroy_timer; } ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark, NULL); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); kfree(futexv); destroy_timer: if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_wake - Wake a number of futexes * @uaddr: Address of the futex(es) to wake * @mask: bitmask * @nr: Number of the futexes to wake * @flags: FUTEX2 flags * * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_wake, void __user *, uaddr, unsigned long, mask, int, nr, unsigned int, flags) { if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, mask)) return -EINVAL; return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); } /* * sys_futex_wait - Wait on a futex * @uaddr: Address of the futex to wait on * @val: Value of @uaddr * @mask: bitmask * @flags: FUTEX2 flags * @timeout: Optional absolute timeout * @clockid: Clock to be used for the timeout, realtime or monotonic * * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the * futex2 familiy of calls. */ SYSCALL_DEFINE6(futex_wait, void __user *, uaddr, unsigned long, val, unsigned long, mask, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; int ret; if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, val) || !futex_validate_input(flags, mask)) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask); if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_requeue - Requeue a waiter from one futex to another * @waiters: array describing the source and destination futex * @flags: unused * @nr_wake: number of futexes to wake * @nr_requeue: number of futexes to requeue * * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_requeue, struct futex_waitv __user *, waiters, unsigned int, flags, int, nr_wake, int, nr_requeue) { struct futex_vector futexes[2]; u32 cmpval; int ret; if (flags) return -EINVAL; if (!waiters) return -EINVAL; ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL); if (ret) return ret; cmpval = futexes[0].w.val; return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags, u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags, nr_wake, nr_requeue, &cmpval, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, compat_size_t, len) { if (unlikely(len != sizeof(*head))) return -EINVAL; current->compat_robust_list = head; return 0; } COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, compat_uptr_t __user *, head_ptr, compat_size_t __user *, len_ptr) { struct compat_robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->compat_robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(ptr_to_compat(head), head_ptr); err_unlock: rcu_read_unlock(); return ret; } #endif /* CONFIG_COMPAT */ #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (get_old_timespec32(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #endif /* CONFIG_COMPAT_32BIT_TIME */ |
| 1940 173 1835 912 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef MM_SLAB_H #define MM_SLAB_H #include <linux/reciprocal_div.h> #include <linux/list_lru.h> #include <linux/local_lock.h> #include <linux/random.h> #include <linux/kobject.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <linux/kfence.h> #include <linux/kasan.h> /* * Internal slab definitions */ #ifdef CONFIG_64BIT # ifdef system_has_cmpxchg128 # define system_has_freelist_aba() system_has_cmpxchg128() # define try_cmpxchg_freelist try_cmpxchg128 # endif #define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg128 typedef u128 freelist_full_t; #else /* CONFIG_64BIT */ # ifdef system_has_cmpxchg64 # define system_has_freelist_aba() system_has_cmpxchg64() # define try_cmpxchg_freelist try_cmpxchg64 # endif #define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg64 typedef u64 freelist_full_t; #endif /* CONFIG_64BIT */ #if defined(system_has_freelist_aba) && !defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) #undef system_has_freelist_aba #endif /* * Freelist pointer and counter to cmpxchg together, avoids the typical ABA * problems with cmpxchg of just a pointer. */ typedef union { struct { void *freelist; unsigned long counter; }; freelist_full_t full; } freelist_aba_t; /* Reuses the bits in struct page */ struct slab { unsigned long __page_flags; struct kmem_cache *slab_cache; union { struct { union { struct list_head slab_list; #ifdef CONFIG_SLUB_CPU_PARTIAL struct { struct slab *next; int slabs; /* Nr of slabs left */ }; #endif }; /* Double-word boundary */ union { struct { void *freelist; /* first free object */ union { unsigned long counters; struct { unsigned inuse:16; unsigned objects:15; /* * If slab debugging is enabled then the * frozen bit can be reused to indicate * that the slab was corrupted */ unsigned frozen:1; }; }; }; #ifdef system_has_freelist_aba freelist_aba_t freelist_counter; #endif }; }; struct rcu_head rcu_head; }; unsigned int __page_type; atomic_t __page_refcount; #ifdef CONFIG_SLAB_OBJ_EXT unsigned long obj_exts; #endif }; #define SLAB_MATCH(pg, sl) \ static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl)) SLAB_MATCH(flags, __page_flags); SLAB_MATCH(compound_head, slab_cache); /* Ensure bit 0 is clear */ SLAB_MATCH(_refcount, __page_refcount); #ifdef CONFIG_MEMCG SLAB_MATCH(memcg_data, obj_exts); #elif defined(CONFIG_SLAB_OBJ_EXT) SLAB_MATCH(_unused_slab_obj_exts, obj_exts); #endif #undef SLAB_MATCH static_assert(sizeof(struct slab) <= sizeof(struct page)); #if defined(system_has_freelist_aba) static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t))); #endif /** * folio_slab - Converts from folio to slab. * @folio: The folio. * * Currently struct slab is a different representation of a folio where * folio_test_slab() is true. * * Return: The slab which contains this folio. */ #define folio_slab(folio) (_Generic((folio), \ const struct folio *: (const struct slab *)(folio), \ struct folio *: (struct slab *)(folio))) /** * slab_folio - The folio allocated for a slab * @s: The slab. * * Slabs are allocated as folios that contain the individual objects and are * using some fields in the first struct page of the folio - those fields are * now accessed by struct slab. It is occasionally necessary to convert back to * a folio in order to communicate with the rest of the mm. Please use this * helper function instead of casting yourself, as the implementation may change * in the future. */ #define slab_folio(s) (_Generic((s), \ const struct slab *: (const struct folio *)s, \ struct slab *: (struct folio *)s)) /** * page_slab - Converts from first struct page to slab. * @p: The first (either head of compound or single) page of slab. * * A temporary wrapper to convert struct page to struct slab in situations where * we know the page is the compound head, or single order-0 page. * * Long-term ideally everything would work with struct slab directly or go * through folio to struct slab. * * Return: The slab which contains this page */ #define page_slab(p) (_Generic((p), \ const struct page *: (const struct slab *)(p), \ struct page *: (struct slab *)(p))) /** * slab_page - The first struct page allocated for a slab * @s: The slab. * * A convenience wrapper for converting slab to the first struct page of the * underlying folio, to communicate with code not yet converted to folio or * struct slab. */ #define slab_page(s) folio_page(slab_folio(s), 0) /* * If network-based swap is enabled, sl*b must keep track of whether pages * were allocated from pfmemalloc reserves. */ static inline bool slab_test_pfmemalloc(const struct slab *slab) { return folio_test_active(slab_folio(slab)); } static inline void slab_set_pfmemalloc(struct slab *slab) { folio_set_active(slab_folio(slab)); } static inline void slab_clear_pfmemalloc(struct slab *slab) { folio_clear_active(slab_folio(slab)); } static inline void __slab_clear_pfmemalloc(struct slab *slab) { __folio_clear_active(slab_folio(slab)); } static inline void *slab_address(const struct slab *slab) { return folio_address(slab_folio(slab)); } static inline int slab_nid(const struct slab *slab) { return folio_nid(slab_folio(slab)); } static inline pg_data_t *slab_pgdat(const struct slab *slab) { return folio_pgdat(slab_folio(slab)); } static inline struct slab *virt_to_slab(const void *addr) { struct folio *folio = virt_to_folio(addr); if (!folio_test_slab(folio)) return NULL; return folio_slab(folio); } static inline int slab_order(const struct slab *slab) { return folio_order(slab_folio(slab)); } static inline size_t slab_size(const struct slab *slab) { return PAGE_SIZE << slab_order(slab); } #ifdef CONFIG_SLUB_CPU_PARTIAL #define slub_percpu_partial(c) ((c)->partial) #define slub_set_percpu_partial(c, p) \ ({ \ slub_percpu_partial(c) = (p)->next; \ }) #define slub_percpu_partial_read_once(c) READ_ONCE(slub_percpu_partial(c)) #else #define slub_percpu_partial(c) NULL #define slub_set_percpu_partial(c, p) #define slub_percpu_partial_read_once(c) NULL #endif // CONFIG_SLUB_CPU_PARTIAL /* * Word size structure that can be atomically updated or read and that * contains both the order and the number of objects that a slab of the * given order would contain. */ struct kmem_cache_order_objects { unsigned int x; }; /* * Slab cache management. */ struct kmem_cache { #ifndef CONFIG_SLUB_TINY struct kmem_cache_cpu __percpu *cpu_slab; #endif /* Used for retrieving partial slabs, etc. */ slab_flags_t flags; unsigned long min_partial; unsigned int size; /* Object size including metadata */ unsigned int object_size; /* Object size without metadata */ struct reciprocal_value reciprocal_size; unsigned int offset; /* Free pointer offset */ #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; /* Number of per cpu partial slabs to keep around */ unsigned int cpu_partial_slabs; #endif struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ void (*ctor)(void *object); /* Object constructor */ unsigned int inuse; /* Offset to metadata */ unsigned int align; /* Alignment */ unsigned int red_left_pad; /* Left redzone padding size */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ #endif #ifdef CONFIG_SLAB_FREELIST_HARDENED unsigned long random; #endif #ifdef CONFIG_NUMA /* * Defragmentation by allocating from a remote node. */ unsigned int remote_node_defrag_ratio; #endif #ifdef CONFIG_SLAB_FREELIST_RANDOM unsigned int *random_seq; #endif #ifdef CONFIG_KASAN_GENERIC struct kasan_cache kasan_info; #endif #ifdef CONFIG_HARDENED_USERCOPY unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ #endif struct kmem_cache_node *node[MAX_NUMNODES]; }; #if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY) #define SLAB_SUPPORTS_SYSFS 1 void sysfs_slab_unlink(struct kmem_cache *s); void sysfs_slab_release(struct kmem_cache *s); #else static inline void sysfs_slab_unlink(struct kmem_cache *s) { } static inline void sysfs_slab_release(struct kmem_cache *s) { } #endif void *fixup_red_left(struct kmem_cache *s, void *p); static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab, void *x) { void *object = x - (x - slab_address(slab)) % cache->size; void *last_object = slab_address(slab) + (slab->objects - 1) * cache->size; void *result = (unlikely(object > last_object)) ? last_object : object; result = fixup_red_left(cache, result); return result; } /* Determine object index from a given position */ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, void *addr, void *obj) { return reciprocal_divide(kasan_reset_tag(obj) - addr, cache->reciprocal_size); } static inline unsigned int obj_to_index(const struct kmem_cache *cache, const struct slab *slab, void *obj) { if (is_kfence_address(obj)) return 0; return __obj_to_index(cache, slab_address(slab), obj); } static inline int objs_per_slab(const struct kmem_cache *cache, const struct slab *slab) { return slab->objects; } /* * State of the slab allocator. * * This is used to describe the states of the allocator during bootup. * Allocators use this to gradually bootstrap themselves. Most allocators * have the problem that the structures used for managing slab caches are * allocated from slab caches themselves. */ enum slab_state { DOWN, /* No slab functionality yet */ PARTIAL, /* SLUB: kmem_cache_node available */ UP, /* Slab caches usable but not all extras yet */ FULL /* Everything is working */ }; extern enum slab_state slab_state; /* The slab cache mutex protects the management structures during changes */ extern struct mutex slab_mutex; /* The list of all slab caches on the system */ extern struct list_head slab_caches; /* The slab cache that manages slab cache information */ extern struct kmem_cache *kmem_cache; /* A table of kmalloc cache names and sizes */ extern const struct kmalloc_info_struct { const char *name[NR_KMALLOC_TYPES]; unsigned int size; } kmalloc_info[]; /* Kmalloc array related functions */ void setup_kmalloc_cache_index_table(void); void create_kmalloc_caches(void); extern u8 kmalloc_size_index[24]; static inline unsigned int size_index_elem(unsigned int bytes) { return (bytes - 1) / 8; } /* * Find the kmem_cache structure that serves a given size of * allocation * * This assumes size is larger than zero and not larger than * KMALLOC_MAX_CACHE_SIZE and the caller must check that. */ static inline struct kmem_cache * kmalloc_slab(size_t size, kmem_buckets *b, gfp_t flags, unsigned long caller) { unsigned int index; if (!b) b = &kmalloc_caches[kmalloc_type(flags, caller)]; if (size <= 192) index = kmalloc_size_index[size_index_elem(size)]; else index = fls(size - 1); return (*b)[index]; } gfp_t kmalloc_fix_flags(gfp_t flags); /* Functions provided by the slab allocators */ int do_kmem_cache_create(struct kmem_cache *s, const char *name, unsigned int size, struct kmem_cache_args *args, slab_flags_t flags); void __init kmem_cache_init(void); extern void create_boot_cache(struct kmem_cache *, const char *name, unsigned int size, slab_flags_t flags, unsigned int useroffset, unsigned int usersize); int slab_unmergeable(struct kmem_cache *s); struct kmem_cache *find_mergeable(unsigned size, unsigned align, slab_flags_t flags, const char *name, void (*ctor)(void *)); struct kmem_cache * __kmem_cache_alias(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); slab_flags_t kmem_cache_flags(slab_flags_t flags, const char *name); static inline bool is_kmalloc_cache(struct kmem_cache *s) { return (s->flags & SLAB_KMALLOC); } static inline bool is_kmalloc_normal(struct kmem_cache *s) { if (!is_kmalloc_cache(s)) return false; return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT)); } /* Legal flag mask for kmem_cache_create(), for various configurations */ #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ SLAB_CACHE_DMA32 | SLAB_PANIC | \ SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS ) #ifdef CONFIG_SLUB_DEBUG #define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ SLAB_TRACE | SLAB_CONSISTENCY_CHECKS) #else #define SLAB_DEBUG_FLAGS (0) #endif #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \ SLAB_TEMPORARY | SLAB_ACCOUNT | \ SLAB_NO_USER_FLAGS | SLAB_KMALLOC | SLAB_NO_MERGE) /* Common flags available with current configuration */ #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS) /* Common flags permitted for kmem_cache_create */ #define SLAB_FLAGS_PERMITTED (SLAB_CORE_FLAGS | \ SLAB_RED_ZONE | \ SLAB_POISON | \ SLAB_STORE_USER | \ SLAB_TRACE | \ SLAB_CONSISTENCY_CHECKS | \ SLAB_NOLEAKTRACE | \ SLAB_RECLAIM_ACCOUNT | \ SLAB_TEMPORARY | \ SLAB_ACCOUNT | \ SLAB_KMALLOC | \ SLAB_NO_MERGE | \ SLAB_NO_USER_FLAGS) bool __kmem_cache_empty(struct kmem_cache *); int __kmem_cache_shutdown(struct kmem_cache *); void __kmem_cache_release(struct kmem_cache *); int __kmem_cache_shrink(struct kmem_cache *); void slab_kmem_cache_release(struct kmem_cache *); struct seq_file; struct file; struct slabinfo { unsigned long active_objs; unsigned long num_objs; unsigned long active_slabs; unsigned long num_slabs; unsigned long shared_avail; unsigned int limit; unsigned int batchcount; unsigned int shared; unsigned int objects_per_slab; unsigned int cache_order; }; void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo); #ifdef CONFIG_SLUB_DEBUG #ifdef CONFIG_SLUB_DEBUG_ON DECLARE_STATIC_KEY_TRUE(slub_debug_enabled); #else DECLARE_STATIC_KEY_FALSE(slub_debug_enabled); #endif extern void print_tracking(struct kmem_cache *s, void *object); long validate_slab_cache(struct kmem_cache *s); static inline bool __slub_debug_enabled(void) { return static_branch_unlikely(&slub_debug_enabled); } #else static inline void print_tracking(struct kmem_cache *s, void *object) { } static inline bool __slub_debug_enabled(void) { return false; } #endif /* * Returns true if any of the specified slab_debug flags is enabled for the * cache. Use only for flags parsed by setup_slub_debug() as it also enables * the static key. */ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags) { if (IS_ENABLED(CONFIG_SLUB_DEBUG)) VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS)); if (__slub_debug_enabled()) return s->flags & flags; return false; } #if IS_ENABLED(CONFIG_SLUB_DEBUG) && IS_ENABLED(CONFIG_KUNIT) bool slab_in_kunit_test(void); #else static inline bool slab_in_kunit_test(void) { return false; } #endif #ifdef CONFIG_SLAB_OBJ_EXT /* * slab_obj_exts - get the pointer to the slab object extension vector * associated with a slab. * @slab: a pointer to the slab struct * * Returns a pointer to the object extension vector associated with the slab, * or NULL if no such vector has been associated yet. */ static inline struct slabobj_ext *slab_obj_exts(struct slab *slab) { unsigned long obj_exts = READ_ONCE(slab->obj_exts); #ifdef CONFIG_MEMCG VM_BUG_ON_PAGE(obj_exts && !(obj_exts & MEMCG_DATA_OBJEXTS), slab_page(slab)); VM_BUG_ON_PAGE(obj_exts & MEMCG_DATA_KMEM, slab_page(slab)); #endif return (struct slabobj_ext *)(obj_exts & ~OBJEXTS_FLAGS_MASK); } int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, gfp_t gfp, bool new_slab); #else /* CONFIG_SLAB_OBJ_EXT */ static inline struct slabobj_ext *slab_obj_exts(struct slab *slab) { return NULL; } #endif /* CONFIG_SLAB_OBJ_EXT */ static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s) { return (s->flags & SLAB_RECLAIM_ACCOUNT) ? NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B; } #ifdef CONFIG_MEMCG bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, gfp_t flags, size_t size, void **p); void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, int objects, struct slabobj_ext *obj_exts); #endif size_t __ksize(const void *objp); static inline size_t slab_ksize(const struct kmem_cache *s) { #ifdef CONFIG_SLUB_DEBUG /* * Debugging requires use of the padding between object * and whatever may come after it. */ if (s->flags & (SLAB_RED_ZONE | SLAB_POISON)) return s->object_size; #endif if (s->flags & SLAB_KASAN) return s->object_size; /* * If we have the need to store the freelist pointer * back there or track user information then we can * only use the space before that information. */ if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER)) return s->inuse; /* * Else we can use all the padding etc for the allocation */ return s->size; } #ifdef CONFIG_SLUB_DEBUG void dump_unreclaimable_slab(void); #else static inline void dump_unreclaimable_slab(void) { } #endif void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr); #ifdef CONFIG_SLAB_FREELIST_RANDOM int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, gfp_t gfp); void cache_random_seq_destroy(struct kmem_cache *cachep); #else static inline int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, gfp_t gfp) { return 0; } static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { } #endif /* CONFIG_SLAB_FREELIST_RANDOM */ static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c) { if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc)) { if (c->ctor) return false; if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) return flags & __GFP_ZERO; return true; } return flags & __GFP_ZERO; } static inline bool slab_want_init_on_free(struct kmem_cache *c) { if (static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, &init_on_free)) return !(c->ctor || (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))); return false; } #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG) void debugfs_slab_release(struct kmem_cache *); #else static inline void debugfs_slab_release(struct kmem_cache *s) { } #endif #ifdef CONFIG_PRINTK #define KS_ADDRS_COUNT 16 struct kmem_obj_info { void *kp_ptr; struct slab *kp_slab; void *kp_objp; unsigned long kp_data_offset; struct kmem_cache *kp_slab_cache; void *kp_ret; void *kp_stack[KS_ADDRS_COUNT]; void *kp_free_stack[KS_ADDRS_COUNT]; }; void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); #endif void __check_heap_object(const void *ptr, unsigned long n, const struct slab *slab, bool to_user); static inline bool slub_debug_orig_size(struct kmem_cache *s) { return (kmem_cache_debug_flags(s, SLAB_STORE_USER) && (s->flags & SLAB_KMALLOC)); } #ifdef CONFIG_SLUB_DEBUG void skip_orig_size_check(struct kmem_cache *s, const void *object); #endif #endif /* MM_SLAB_H */ |
| 219 1 1 218 1 217 1 219 219 143 72 167 1 4 166 1 10 168 9 167 167 163 14 1 14 1 1 168 168 14 14 5 3 167 168 164 168 114 1 167 2 11 3 3 220 101 170 10 10 1 166 219 2 213 213 67 165 6 6 165 219 220 220 46 131 46 2 119 45 131 131 38 111 111 131 131 131 131 57 74 46 131 57 74 46 88 10 10 86 55 55 55 55 6 9 44 127 52 7 126 191 91 70 189 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0-only /* * directory.c * * PURPOSE * Directory related functions * */ #include "udfdecl.h" #include "udf_i.h" #include <linux/fs.h> #include <linux/string.h> #include <linux/bio.h> #include <linux/crc-itu-t.h> #include <linux/iversion.h> static int udf_verify_fi(struct udf_fileident_iter *iter) { unsigned int len; if (iter->fi.descTag.tagIdent != cpu_to_le16(TAG_IDENT_FID)) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry at pos %llu with incorrect tag %x\n", iter->dir->i_ino, (unsigned long long)iter->pos, le16_to_cpu(iter->fi.descTag.tagIdent)); return -EFSCORRUPTED; } len = udf_dir_entry_len(&iter->fi); if (le16_to_cpu(iter->fi.lengthOfImpUse) & 3) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry at pos %llu with unaligned length of impUse field\n", iter->dir->i_ino, (unsigned long long)iter->pos); return -EFSCORRUPTED; } /* * This is in fact allowed by the spec due to long impUse field but * we don't support it. If there is real media with this large impUse * field, support can be added. */ if (len > 1 << iter->dir->i_blkbits) { udf_err(iter->dir->i_sb, "directory (ino %lu) has too big (%u) entry at pos %llu\n", iter->dir->i_ino, len, (unsigned long long)iter->pos); return -EFSCORRUPTED; } if (iter->pos + len > iter->dir->i_size) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry past directory size at pos %llu\n", iter->dir->i_ino, (unsigned long long)iter->pos); return -EFSCORRUPTED; } if (udf_dir_entry_len(&iter->fi) != sizeof(struct tag) + le16_to_cpu(iter->fi.descTag.descCRCLength)) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry where CRC length (%u) does not match entry length (%u)\n", iter->dir->i_ino, (unsigned)le16_to_cpu(iter->fi.descTag.descCRCLength), (unsigned)(udf_dir_entry_len(&iter->fi) - sizeof(struct tag))); return -EFSCORRUPTED; } return 0; } static int udf_copy_fi(struct udf_fileident_iter *iter) { struct udf_inode_info *iinfo = UDF_I(iter->dir); u32 blksize = 1 << iter->dir->i_blkbits; u32 off, len, nameoff; int err; /* Skip copying when we are at EOF */ if (iter->pos >= iter->dir->i_size) { iter->name = NULL; return 0; } if (iter->dir->i_size < iter->pos + sizeof(struct fileIdentDesc)) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry straddling EOF\n", iter->dir->i_ino); return -EFSCORRUPTED; } if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { memcpy(&iter->fi, iinfo->i_data + iinfo->i_lenEAttr + iter->pos, sizeof(struct fileIdentDesc)); err = udf_verify_fi(iter); if (err < 0) return err; iter->name = iinfo->i_data + iinfo->i_lenEAttr + iter->pos + sizeof(struct fileIdentDesc) + le16_to_cpu(iter->fi.lengthOfImpUse); return 0; } off = iter->pos & (blksize - 1); len = min_t(u32, sizeof(struct fileIdentDesc), blksize - off); memcpy(&iter->fi, iter->bh[0]->b_data + off, len); if (len < sizeof(struct fileIdentDesc)) memcpy((char *)(&iter->fi) + len, iter->bh[1]->b_data, sizeof(struct fileIdentDesc) - len); err = udf_verify_fi(iter); if (err < 0) return err; /* Handle directory entry name */ nameoff = off + sizeof(struct fileIdentDesc) + le16_to_cpu(iter->fi.lengthOfImpUse); if (off + udf_dir_entry_len(&iter->fi) <= blksize) { iter->name = iter->bh[0]->b_data + nameoff; } else if (nameoff >= blksize) { iter->name = iter->bh[1]->b_data + (nameoff - blksize); } else { iter->name = iter->namebuf; len = blksize - nameoff; memcpy(iter->name, iter->bh[0]->b_data + nameoff, len); memcpy(iter->name + len, iter->bh[1]->b_data, iter->fi.lengthFileIdent - len); } return 0; } /* Readahead 8k once we are at 8k boundary */ static void udf_readahead_dir(struct udf_fileident_iter *iter) { unsigned int ralen = 16 >> (iter->dir->i_blkbits - 9); struct buffer_head *tmp, *bha[16]; int i, num; udf_pblk_t blk; if (iter->loffset & (ralen - 1)) return; if (iter->loffset + ralen > (iter->elen >> iter->dir->i_blkbits)) ralen = (iter->elen >> iter->dir->i_blkbits) - iter->loffset; num = 0; for (i = 0; i < ralen; i++) { blk = udf_get_lb_pblock(iter->dir->i_sb, &iter->eloc, iter->loffset + i); tmp = sb_getblk(iter->dir->i_sb, blk); if (tmp && !buffer_uptodate(tmp) && !buffer_locked(tmp)) bha[num++] = tmp; else brelse(tmp); } if (num) { bh_readahead_batch(num, bha, REQ_RAHEAD); for (i = 0; i < num; i++) brelse(bha[i]); } } static struct buffer_head *udf_fiiter_bread_blk(struct udf_fileident_iter *iter) { udf_pblk_t blk; udf_readahead_dir(iter); blk = udf_get_lb_pblock(iter->dir->i_sb, &iter->eloc, iter->loffset); return sb_bread(iter->dir->i_sb, blk); } /* * Updates loffset to point to next directory block; eloc, elen & epos are * updated if we need to traverse to the next extent as well. */ static int udf_fiiter_advance_blk(struct udf_fileident_iter *iter) { int8_t etype = -1; int err = 0; iter->loffset++; if (iter->loffset < DIV_ROUND_UP(iter->elen, 1<<iter->dir->i_blkbits)) return 0; iter->loffset = 0; err = udf_next_aext(iter->dir, &iter->epos, &iter->eloc, &iter->elen, &etype, 1); if (err < 0) return err; else if (err == 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { if (iter->pos == iter->dir->i_size) { iter->elen = 0; return 0; } udf_err(iter->dir->i_sb, "extent after position %llu not allocated in directory (ino %lu)\n", (unsigned long long)iter->pos, iter->dir->i_ino); return -EFSCORRUPTED; } return 0; } static int udf_fiiter_load_bhs(struct udf_fileident_iter *iter) { int blksize = 1 << iter->dir->i_blkbits; int off = iter->pos & (blksize - 1); int err; struct fileIdentDesc *fi; /* Is there any further extent we can map from? */ if (!iter->bh[0] && iter->elen) { iter->bh[0] = udf_fiiter_bread_blk(iter); if (!iter->bh[0]) { err = -ENOMEM; goto out_brelse; } if (!buffer_uptodate(iter->bh[0])) { err = -EIO; goto out_brelse; } } /* There's no next block so we are done */ if (iter->pos >= iter->dir->i_size) return 0; /* Need to fetch next block as well? */ if (off + sizeof(struct fileIdentDesc) > blksize) goto fetch_next; fi = (struct fileIdentDesc *)(iter->bh[0]->b_data + off); /* Need to fetch next block to get name? */ if (off + udf_dir_entry_len(fi) > blksize) { fetch_next: err = udf_fiiter_advance_blk(iter); if (err) goto out_brelse; iter->bh[1] = udf_fiiter_bread_blk(iter); if (!iter->bh[1]) { err = -ENOMEM; goto out_brelse; } if (!buffer_uptodate(iter->bh[1])) { err = -EIO; goto out_brelse; } } return 0; out_brelse: brelse(iter->bh[0]); brelse(iter->bh[1]); iter->bh[0] = iter->bh[1] = NULL; return err; } int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, loff_t pos) { struct udf_inode_info *iinfo = UDF_I(dir); int err = 0; int8_t etype; iter->dir = dir; iter->bh[0] = iter->bh[1] = NULL; iter->pos = pos; iter->elen = 0; iter->epos.bh = NULL; iter->name = NULL; /* * When directory is verified, we don't expect directory iteration to * fail and it can be difficult to undo without corrupting filesystem. * So just do not allow memory allocation failures here. */ iter->namebuf = kmalloc(UDF_NAME_LEN_CS0, GFP_KERNEL | __GFP_NOFAIL); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { err = udf_copy_fi(iter); goto out; } err = inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos, &iter->eloc, &iter->elen, &iter->loffset, &etype); if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { if (pos == dir->i_size) return 0; udf_err(dir->i_sb, "position %llu not allocated in directory (ino %lu)\n", (unsigned long long)pos, dir->i_ino); err = -EFSCORRUPTED; goto out; } err = udf_fiiter_load_bhs(iter); if (err < 0) goto out; err = udf_copy_fi(iter); out: if (err < 0) udf_fiiter_release(iter); return err; } int udf_fiiter_advance(struct udf_fileident_iter *iter) { unsigned int oldoff, len; int blksize = 1 << iter->dir->i_blkbits; int err; oldoff = iter->pos & (blksize - 1); len = udf_dir_entry_len(&iter->fi); iter->pos += len; if (UDF_I(iter->dir)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { if (oldoff + len >= blksize) { brelse(iter->bh[0]); iter->bh[0] = NULL; /* Next block already loaded? */ if (iter->bh[1]) { iter->bh[0] = iter->bh[1]; iter->bh[1] = NULL; } else { err = udf_fiiter_advance_blk(iter); if (err < 0) return err; } } err = udf_fiiter_load_bhs(iter); if (err < 0) return err; } return udf_copy_fi(iter); } void udf_fiiter_release(struct udf_fileident_iter *iter) { iter->dir = NULL; brelse(iter->bh[0]); brelse(iter->bh[1]); iter->bh[0] = iter->bh[1] = NULL; kfree(iter->namebuf); iter->namebuf = NULL; } static void udf_copy_to_bufs(void *buf1, int len1, void *buf2, int len2, int off, void *src, int len) { int copy; if (off >= len1) { off -= len1; } else { copy = min(off + len, len1) - off; memcpy(buf1 + off, src, copy); src += copy; len -= copy; off = 0; } if (len > 0) { if (WARN_ON_ONCE(off + len > len2 || !buf2)) return; memcpy(buf2 + off, src, len); } } static uint16_t udf_crc_fi_bufs(void *buf1, int len1, void *buf2, int len2, int off, int len) { int copy; uint16_t crc = 0; if (off >= len1) { off -= len1; } else { copy = min(off + len, len1) - off; crc = crc_itu_t(crc, buf1 + off, copy); len -= copy; off = 0; } if (len > 0) { if (WARN_ON_ONCE(off + len > len2 || !buf2)) return 0; crc = crc_itu_t(crc, buf2 + off, len); } return crc; } static void udf_copy_fi_to_bufs(char *buf1, int len1, char *buf2, int len2, int off, struct fileIdentDesc *fi, uint8_t *impuse, uint8_t *name) { uint16_t crc; int fioff = off; int crcoff = off + sizeof(struct tag); unsigned int crclen = udf_dir_entry_len(fi) - sizeof(struct tag); char zeros[UDF_NAME_PAD] = {}; int endoff = off + udf_dir_entry_len(fi); udf_copy_to_bufs(buf1, len1, buf2, len2, off, fi, sizeof(struct fileIdentDesc)); off += sizeof(struct fileIdentDesc); if (impuse) udf_copy_to_bufs(buf1, len1, buf2, len2, off, impuse, le16_to_cpu(fi->lengthOfImpUse)); off += le16_to_cpu(fi->lengthOfImpUse); if (name) { udf_copy_to_bufs(buf1, len1, buf2, len2, off, name, fi->lengthFileIdent); off += fi->lengthFileIdent; udf_copy_to_bufs(buf1, len1, buf2, len2, off, zeros, endoff - off); } crc = udf_crc_fi_bufs(buf1, len1, buf2, len2, crcoff, crclen); fi->descTag.descCRC = cpu_to_le16(crc); fi->descTag.descCRCLength = cpu_to_le16(crclen); fi->descTag.tagChecksum = udf_tag_checksum(&fi->descTag); udf_copy_to_bufs(buf1, len1, buf2, len2, fioff, fi, sizeof(struct tag)); } void udf_fiiter_write_fi(struct udf_fileident_iter *iter, uint8_t *impuse) { struct udf_inode_info *iinfo = UDF_I(iter->dir); void *buf1, *buf2 = NULL; int len1, len2 = 0, off; int blksize = 1 << iter->dir->i_blkbits; off = iter->pos & (blksize - 1); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { buf1 = iinfo->i_data + iinfo->i_lenEAttr; len1 = iter->dir->i_size; } else { buf1 = iter->bh[0]->b_data; len1 = blksize; if (iter->bh[1]) { buf2 = iter->bh[1]->b_data; len2 = blksize; } } udf_copy_fi_to_bufs(buf1, len1, buf2, len2, off, &iter->fi, impuse, iter->name == iter->namebuf ? iter->name : NULL); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { mark_inode_dirty(iter->dir); } else { mark_buffer_dirty_inode(iter->bh[0], iter->dir); if (iter->bh[1]) mark_buffer_dirty_inode(iter->bh[1], iter->dir); } inode_inc_iversion(iter->dir); } void udf_fiiter_update_elen(struct udf_fileident_iter *iter, uint32_t new_elen) { struct udf_inode_info *iinfo = UDF_I(iter->dir); int diff = new_elen - iter->elen; /* Skip update when we already went past the last extent */ if (!iter->elen) return; iter->elen = new_elen; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) iter->epos.offset -= sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) iter->epos.offset -= sizeof(struct long_ad); udf_write_aext(iter->dir, &iter->epos, &iter->eloc, iter->elen, 1); iinfo->i_lenExtents += diff; mark_inode_dirty(iter->dir); } /* Append new block to directory. @iter is expected to point at EOF */ int udf_fiiter_append_blk(struct udf_fileident_iter *iter) { struct udf_inode_info *iinfo = UDF_I(iter->dir); int blksize = 1 << iter->dir->i_blkbits; struct buffer_head *bh; sector_t block; uint32_t old_elen = iter->elen; int err; int8_t etype; if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) return -EINVAL; /* Round up last extent in the file */ udf_fiiter_update_elen(iter, ALIGN(iter->elen, blksize)); /* Allocate new block and refresh mapping information */ block = iinfo->i_lenExtents >> iter->dir->i_blkbits; bh = udf_bread(iter->dir, block, 1, &err); if (!bh) { udf_fiiter_update_elen(iter, old_elen); return err; } err = inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen, &iter->loffset, &etype); if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { udf_err(iter->dir->i_sb, "block %llu not allocated in directory (ino %lu)\n", (unsigned long long)block, iter->dir->i_ino); return -EFSCORRUPTED; } if (!(iter->pos & (blksize - 1))) { brelse(iter->bh[0]); iter->bh[0] = bh; } else { iter->bh[1] = bh; } return 0; } struct short_ad *udf_get_fileshortad(uint8_t *ptr, int maxoffset, uint32_t *offset, int inc) { struct short_ad *sa; if ((!ptr) || (!offset)) { pr_err("%s: invalidparms\n", __func__); return NULL; } if ((*offset + sizeof(struct short_ad)) > maxoffset) return NULL; else { sa = (struct short_ad *)ptr; if (sa->extLength == 0) return NULL; } if (inc) *offset += sizeof(struct short_ad); return sa; } struct long_ad *udf_get_filelongad(uint8_t *ptr, int maxoffset, uint32_t *offset, int inc) { struct long_ad *la; if ((!ptr) || (!offset)) { pr_err("%s: invalidparms\n", __func__); return NULL; } if ((*offset + sizeof(struct long_ad)) > maxoffset) return NULL; else { la = (struct long_ad *)ptr; if (la->extLength == 0) return NULL; } if (inc) *offset += sizeof(struct long_ad); return la; } |
| 6 6 6 6 2 2 2 6 6 6 2 4 4 1 1 5 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | // SPDX-License-Identifier: GPL-2.0-only /* * In memory quota format relies on quota infrastructure to store dquot * information for us. While conventional quota formats for file systems * with persistent storage can load quota information into dquot from the * storage on-demand and hence quota dquot shrinker can free any dquot * that is not currently being used, it must be avoided here. Otherwise we * can lose valuable information, user provided limits, because there is * no persistent storage to load the information from afterwards. * * One information that in-memory quota format needs to keep track of is * a sorted list of ids for each quota type. This is done by utilizing * an rb tree which root is stored in mem_dqinfo->dqi_priv for each quota * type. * * This format can be used to support quota on file system without persistent * storage such as tmpfs. * * Author: Lukas Czerner <lczerner@redhat.com> * Carlos Maiolino <cmaiolino@redhat.com> * * Copyright (C) 2023 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/shmem_fs.h> #include <linux/quotaops.h> #include <linux/quota.h> /* * The following constants define the amount of time given a user * before the soft limits are treated as hard limits (usually resulting * in an allocation failure). The timer is started when the user crosses * their soft limit, it is reset when they go below their soft limit. */ #define SHMEM_MAX_IQ_TIME 604800 /* (7*24*60*60) 1 week */ #define SHMEM_MAX_DQ_TIME 604800 /* (7*24*60*60) 1 week */ struct quota_id { struct rb_node node; qid_t id; qsize_t bhardlimit; qsize_t bsoftlimit; qsize_t ihardlimit; qsize_t isoftlimit; }; static int shmem_check_quota_file(struct super_block *sb, int type) { /* There is no real quota file, nothing to do */ return 1; } /* * There is no real quota file. Just allocate rb_root for quota ids and * set limits */ static int shmem_read_file_info(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; info->dqi_priv = kzalloc(sizeof(struct rb_root), GFP_NOFS); if (!info->dqi_priv) return -ENOMEM; info->dqi_max_spc_limit = SHMEM_QUOTA_MAX_SPC_LIMIT; info->dqi_max_ino_limit = SHMEM_QUOTA_MAX_INO_LIMIT; info->dqi_bgrace = SHMEM_MAX_DQ_TIME; info->dqi_igrace = SHMEM_MAX_IQ_TIME; info->dqi_flags = 0; return 0; } static int shmem_write_file_info(struct super_block *sb, int type) { /* There is no real quota file, nothing to do */ return 0; } /* * Free all the quota_id entries in the rb tree and rb_root. */ static int shmem_free_file_info(struct super_block *sb, int type) { struct mem_dqinfo *info = &sb_dqopt(sb)->info[type]; struct rb_root *root = info->dqi_priv; struct quota_id *entry; struct rb_node *node; info->dqi_priv = NULL; node = rb_first(root); while (node) { entry = rb_entry(node, struct quota_id, node); node = rb_next(&entry->node); rb_erase(&entry->node, root); kfree(entry); } kfree(root); return 0; } static int shmem_get_next_id(struct super_block *sb, struct kqid *qid) { struct mem_dqinfo *info = sb_dqinfo(sb, qid->type); struct rb_node *node; qid_t id = from_kqid(&init_user_ns, *qid); struct quota_info *dqopt = sb_dqopt(sb); struct quota_id *entry = NULL; int ret = 0; if (!sb_has_quota_active(sb, qid->type)) return -ESRCH; down_read(&dqopt->dqio_sem); node = ((struct rb_root *)info->dqi_priv)->rb_node; while (node) { entry = rb_entry(node, struct quota_id, node); if (id < entry->id) node = node->rb_left; else if (id > entry->id) node = node->rb_right; else goto got_next_id; } if (!entry) { ret = -ENOENT; goto out_unlock; } if (id > entry->id) { node = rb_next(&entry->node); if (!node) { ret = -ENOENT; goto out_unlock; } entry = rb_entry(node, struct quota_id, node); } got_next_id: *qid = make_kqid(&init_user_ns, qid->type, entry->id); out_unlock: up_read(&dqopt->dqio_sem); return ret; } /* * Load dquot with limits from existing entry, or create the new entry if * it does not exist. */ static int shmem_acquire_dquot(struct dquot *dquot) { struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type); struct rb_node **n; struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info; struct rb_node *parent = NULL, *new_node = NULL; struct quota_id *new_entry, *entry; qid_t id = from_kqid(&init_user_ns, dquot->dq_id); struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret = 0; mutex_lock(&dquot->dq_lock); down_write(&dqopt->dqio_sem); n = &((struct rb_root *)info->dqi_priv)->rb_node; while (*n) { parent = *n; entry = rb_entry(parent, struct quota_id, node); if (id < entry->id) n = &(*n)->rb_left; else if (id > entry->id) n = &(*n)->rb_right; else goto found; } /* We don't have entry for this id yet, create it */ new_entry = kzalloc(sizeof(struct quota_id), GFP_NOFS); if (!new_entry) { ret = -ENOMEM; goto out_unlock; } new_entry->id = id; if (dquot->dq_id.type == USRQUOTA) { new_entry->bhardlimit = sbinfo->qlimits.usrquota_bhardlimit; new_entry->ihardlimit = sbinfo->qlimits.usrquota_ihardlimit; } else if (dquot->dq_id.type == GRPQUOTA) { new_entry->bhardlimit = sbinfo->qlimits.grpquota_bhardlimit; new_entry->ihardlimit = sbinfo->qlimits.grpquota_ihardlimit; } new_node = &new_entry->node; rb_link_node(new_node, parent, n); rb_insert_color(new_node, (struct rb_root *)info->dqi_priv); entry = new_entry; found: /* Load the stored limits from the tree */ spin_lock(&dquot->dq_dqb_lock); dquot->dq_dqb.dqb_bhardlimit = entry->bhardlimit; dquot->dq_dqb.dqb_bsoftlimit = entry->bsoftlimit; dquot->dq_dqb.dqb_ihardlimit = entry->ihardlimit; dquot->dq_dqb.dqb_isoftlimit = entry->isoftlimit; if (!dquot->dq_dqb.dqb_bhardlimit && !dquot->dq_dqb.dqb_bsoftlimit && !dquot->dq_dqb.dqb_ihardlimit && !dquot->dq_dqb.dqb_isoftlimit) set_bit(DQ_FAKE_B, &dquot->dq_flags); spin_unlock(&dquot->dq_dqb_lock); /* Make sure flags update is visible after dquot has been filled */ smp_mb__before_atomic(); set_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_unlock: up_write(&dqopt->dqio_sem); mutex_unlock(&dquot->dq_lock); return ret; } static bool shmem_is_empty_dquot(struct dquot *dquot) { struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info; qsize_t bhardlimit; qsize_t ihardlimit; if (dquot->dq_id.type == USRQUOTA) { bhardlimit = sbinfo->qlimits.usrquota_bhardlimit; ihardlimit = sbinfo->qlimits.usrquota_ihardlimit; } else if (dquot->dq_id.type == GRPQUOTA) { bhardlimit = sbinfo->qlimits.grpquota_bhardlimit; ihardlimit = sbinfo->qlimits.grpquota_ihardlimit; } if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || (dquot->dq_dqb.dqb_curspace == 0 && dquot->dq_dqb.dqb_curinodes == 0 && dquot->dq_dqb.dqb_bhardlimit == bhardlimit && dquot->dq_dqb.dqb_ihardlimit == ihardlimit)) return true; return false; } /* * Store limits from dquot in the tree unless it's fake. If it is fake * remove the id from the tree since there is no useful information in * there. */ static int shmem_release_dquot(struct dquot *dquot) { struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type); struct rb_node *node; qid_t id = from_kqid(&init_user_ns, dquot->dq_id); struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); struct quota_id *entry = NULL; mutex_lock(&dquot->dq_lock); /* Check whether we are not racing with some other dqget() */ if (dquot_is_busy(dquot)) goto out_dqlock; down_write(&dqopt->dqio_sem); node = ((struct rb_root *)info->dqi_priv)->rb_node; while (node) { entry = rb_entry(node, struct quota_id, node); if (id < entry->id) node = node->rb_left; else if (id > entry->id) node = node->rb_right; else goto found; } /* We should always find the entry in the rb tree */ WARN_ONCE(1, "quota id %u from dquot %p, not in rb tree!\n", id, dquot); up_write(&dqopt->dqio_sem); mutex_unlock(&dquot->dq_lock); return -ENOENT; found: if (shmem_is_empty_dquot(dquot)) { /* Remove entry from the tree */ rb_erase(&entry->node, info->dqi_priv); kfree(entry); } else { /* Store the limits in the tree */ spin_lock(&dquot->dq_dqb_lock); entry->bhardlimit = dquot->dq_dqb.dqb_bhardlimit; entry->bsoftlimit = dquot->dq_dqb.dqb_bsoftlimit; entry->ihardlimit = dquot->dq_dqb.dqb_ihardlimit; entry->isoftlimit = dquot->dq_dqb.dqb_isoftlimit; spin_unlock(&dquot->dq_dqb_lock); } clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); up_write(&dqopt->dqio_sem); out_dqlock: mutex_unlock(&dquot->dq_lock); return 0; } static int shmem_mark_dquot_dirty(struct dquot *dquot) { return 0; } static int shmem_dquot_write_info(struct super_block *sb, int type) { return 0; } static const struct quota_format_ops shmem_format_ops = { .check_quota_file = shmem_check_quota_file, .read_file_info = shmem_read_file_info, .write_file_info = shmem_write_file_info, .free_file_info = shmem_free_file_info, }; struct quota_format_type shmem_quota_format = { .qf_fmt_id = QFMT_SHMEM, .qf_ops = &shmem_format_ops, .qf_owner = THIS_MODULE }; const struct dquot_operations shmem_quota_operations = { .acquire_dquot = shmem_acquire_dquot, .release_dquot = shmem_release_dquot, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .write_info = shmem_dquot_write_info, .mark_dirty = shmem_mark_dquot_dirty, .get_next_id = shmem_get_next_id, }; |
| 1848 1851 1847 1851 2 2 2 1844 1851 31 1879 1881 1880 1884 1886 3 1852 1853 1855 1850 1852 1854 1881 1850 1851 1848 1848 3 3 1846 1851 1849 1854 1843 1883 1889 1889 1880 1883 1848 1851 549 6 5 6 5 4 5 5 5 5 5 4 2 5 5 5 5 5 2 4 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NETLINK Kernel-user communication protocol. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Patrick McHardy <kaber@trash.net> * * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith * added netlink_proto_exit * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br> * use nlk_sk, as sk->protinfo is on a diet 8) * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org> * - inc module use count of module that owns * the kernel socket in case userspace opens * socket of same protocol * - remove all module support, since netlink is * mandatory if CONFIG_NET=y these days */ #include <linux/module.h> #include <linux/bpf.h> #include <linux/capability.h> #include <linux/kernel.h> #include <linux/filter.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/un.h> #include <linux/fcntl.h> #include <linux/termios.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/security.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/bitops.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/audit.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> #include <linux/rhashtable.h> #include <asm/cacheflush.h> #include <linux/hash.h> #include <linux/net_namespace.h> #include <linux/nospec.h> #include <linux/btf_ids.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/scm.h> #include <net/netlink.h> #define CREATE_TRACE_POINTS #include <trace/events/netlink.h> #include "af_netlink.h" #include "genetlink.h" struct listeners { struct rcu_head rcu; unsigned long masks[]; }; /* state bits */ #define NETLINK_S_CONGESTED 0x0 static inline int netlink_is_kernel(struct sock *sk) { return nlk_test_bit(KERNEL_SOCKET, sk); } struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS]; static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { "nlk_cb_mutex-ROUTE", "nlk_cb_mutex-1", "nlk_cb_mutex-USERSOCK", "nlk_cb_mutex-FIREWALL", "nlk_cb_mutex-SOCK_DIAG", "nlk_cb_mutex-NFLOG", "nlk_cb_mutex-XFRM", "nlk_cb_mutex-SELINUX", "nlk_cb_mutex-ISCSI", "nlk_cb_mutex-AUDIT", "nlk_cb_mutex-FIB_LOOKUP", "nlk_cb_mutex-CONNECTOR", "nlk_cb_mutex-NETFILTER", "nlk_cb_mutex-IP6_FW", "nlk_cb_mutex-DNRTMSG", "nlk_cb_mutex-KOBJECT_UEVENT", "nlk_cb_mutex-GENERIC", "nlk_cb_mutex-17", "nlk_cb_mutex-SCSITRANSPORT", "nlk_cb_mutex-ECRYPTFS", "nlk_cb_mutex-RDMA", "nlk_cb_mutex-CRYPTO", "nlk_cb_mutex-SMC", "nlk_cb_mutex-23", "nlk_cb_mutex-24", "nlk_cb_mutex-25", "nlk_cb_mutex-26", "nlk_cb_mutex-27", "nlk_cb_mutex-28", "nlk_cb_mutex-29", "nlk_cb_mutex-30", "nlk_cb_mutex-31", "nlk_cb_mutex-MAX_LINKS" }; static int netlink_dump(struct sock *sk, bool lock_taken); /* nl_table locking explained: * Lookup and traversal are protected with an RCU read-side lock. Insertion * and removal are protected with per bucket lock while using RCU list * modification primitives and may run in parallel to RCU protected lookups. * Destruction of the Netlink socket may only occur *after* nl_table_lock has * been acquired * either during or after the socket has been removed from * the list and after an RCU grace period. */ DEFINE_RWLOCK(nl_table_lock); EXPORT_SYMBOL_GPL(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); static BLOCKING_NOTIFIER_HEAD(netlink_chain); static const struct rhashtable_params netlink_rhashtable_params; void do_trace_netlink_extack(const char *msg) { trace_netlink_extack(msg); } EXPORT_SYMBOL(do_trace_netlink_extack); static inline u32 netlink_group_mask(u32 group) { if (group > 32) return 0; return group ? 1 << (group - 1) : 0; } static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); if (new == NULL) return NULL; NETLINK_CB(new).portid = NETLINK_CB(skb).portid; NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; NETLINK_CB(new).creds = NETLINK_CB(skb).creds; skb_put_data(new, skb->data, len); return new; } static unsigned int netlink_tap_net_id; struct netlink_tap_net { struct list_head netlink_tap_all; struct mutex netlink_tap_lock; }; int netlink_add_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); if (unlikely(nt->dev->type != ARPHRD_NETLINK)) return -EINVAL; mutex_lock(&nn->netlink_tap_lock); list_add_rcu(&nt->list, &nn->netlink_tap_all); mutex_unlock(&nn->netlink_tap_lock); __module_get(nt->module); return 0; } EXPORT_SYMBOL_GPL(netlink_add_tap); static int __netlink_remove_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); bool found = false; struct netlink_tap *tmp; mutex_lock(&nn->netlink_tap_lock); list_for_each_entry(tmp, &nn->netlink_tap_all, list) { if (nt == tmp) { list_del_rcu(&nt->list); found = true; goto out; } } pr_warn("__netlink_remove_tap: %p not found\n", nt); out: mutex_unlock(&nn->netlink_tap_lock); if (found) module_put(nt->module); return found ? 0 : -ENODEV; } int netlink_remove_tap(struct netlink_tap *nt) { int ret; ret = __netlink_remove_tap(nt); synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(netlink_remove_tap); static __net_init int netlink_tap_init_net(struct net *net) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); INIT_LIST_HEAD(&nn->netlink_tap_all); mutex_init(&nn->netlink_tap_lock); return 0; } static struct pernet_operations netlink_tap_net_ops = { .init = netlink_tap_init_net, .id = &netlink_tap_net_id, .size = sizeof(struct netlink_tap_net), }; static bool netlink_filter_tap(const struct sk_buff *skb) { struct sock *sk = skb->sk; /* We take the more conservative approach and * whitelist socket protocols that may pass. */ switch (sk->sk_protocol) { case NETLINK_ROUTE: case NETLINK_USERSOCK: case NETLINK_SOCK_DIAG: case NETLINK_NFLOG: case NETLINK_XFRM: case NETLINK_FIB_LOOKUP: case NETLINK_NETFILTER: case NETLINK_GENERIC: return true; } return false; } static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *nskb; struct sock *sk = skb->sk; int ret = -ENOMEM; if (!net_eq(dev_net(dev), sock_net(sk))) return 0; dev_hold(dev); if (is_vmalloc_addr(skb->head)) nskb = netlink_to_full_skb(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); } dev_put(dev); return ret; } static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn) { int ret; struct netlink_tap *tmp; if (!netlink_filter_tap(skb)) return; list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) { ret = __netlink_deliver_tap_skb(skb, tmp->dev); if (unlikely(ret)) break; } } static void netlink_deliver_tap(struct net *net, struct sk_buff *skb) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); rcu_read_lock(); if (unlikely(!list_empty(&nn->netlink_tap_all))) __netlink_deliver_tap(skb, nn); rcu_read_unlock(); } static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, struct sk_buff *skb) { if (!(netlink_is_kernel(dst) && netlink_is_kernel(src))) netlink_deliver_tap(sock_net(dst), skb); } static void netlink_overrun(struct sock *sk) { if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { WRITE_ONCE(sk->sk_err, ENOBUFS); sk_error_report(sk); } } atomic_inc(&sk->sk_drops); } static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); } static void netlink_skb_destructor(struct sk_buff *skb) { if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) vfree_atomic(skb->head); skb->head = NULL; } if (skb->sk != NULL) sock_rfree(skb); } static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static void netlink_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(nlk_sk(sk)->groups); } /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves * this, _but_ remember, it adds useless work on UP machines. */ void netlink_table_grab(void) __acquires(nl_table_lock) { might_sleep(); write_lock_irq(&nl_table_lock); if (atomic_read(&nl_table_users)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&nl_table_wait, &wait); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&nl_table_users) == 0) break; write_unlock_irq(&nl_table_lock); schedule(); write_lock_irq(&nl_table_lock); } __set_current_state(TASK_RUNNING); remove_wait_queue(&nl_table_wait, &wait); } } void netlink_table_ungrab(void) __releases(nl_table_lock) { write_unlock_irq(&nl_table_lock); wake_up(&nl_table_wait); } static inline void netlink_lock_table(void) { unsigned long flags; /* read_lock() synchronizes us to netlink_table_grab */ read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); read_unlock_irqrestore(&nl_table_lock, flags); } static inline void netlink_unlock_table(void) { if (atomic_dec_and_test(&nl_table_users)) wake_up(&nl_table_wait); } struct netlink_compare_arg { possible_net_t pnet; u32 portid; }; /* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ #define netlink_compare_arg_len \ (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) static inline int netlink_compare(struct rhashtable_compare_arg *arg, const void *ptr) { const struct netlink_compare_arg *x = arg->key; const struct netlink_sock *nlk = ptr; return nlk->portid != x->portid || !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); } static void netlink_compare_arg_init(struct netlink_compare_arg *arg, struct net *net, u32 portid) { memset(arg, 0, sizeof(*arg)); write_pnet(&arg->pnet, net); arg->portid = portid; } static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, struct net *net) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, net, portid); return rhashtable_lookup_fast(&table->hash, &arg, netlink_rhashtable_params); } static int __netlink_insert(struct netlink_table *table, struct sock *sk) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); return rhashtable_lookup_insert_key(&table->hash, &arg, &nlk_sk(sk)->node, netlink_rhashtable_params); } static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { struct netlink_table *table = &nl_table[protocol]; struct sock *sk; rcu_read_lock(); sk = __netlink_lookup(table, portid, net); if (sk) sock_hold(sk); rcu_read_unlock(); return sk; } static const struct proto_ops netlink_ops; static void netlink_update_listeners(struct sock *sk) { struct netlink_table *tbl = &nl_table[sk->sk_protocol]; unsigned long mask; unsigned int i; struct listeners *listeners; listeners = nl_deref_protected(tbl->listeners); if (!listeners) return; for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; sk_for_each_bound(sk, &tbl->mc_list) { if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } listeners->masks[i] = mask; } /* this function is only called with the netlink table "grabbed", which * makes sure updates are visible before bind or setsockopt return. */ } static int netlink_insert(struct sock *sk, u32 portid) { struct netlink_table *table = &nl_table[sk->sk_protocol]; int err; lock_sock(sk); err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; if (nlk_sk(sk)->bound) goto err; /* portid can be read locklessly from netlink_getname(). */ WRITE_ONCE(nlk_sk(sk)->portid, portid); sock_hold(sk); err = __netlink_insert(table, sk); if (err) { /* In case the hashtable backend returns with -EBUSY * from here, it must not escape to the caller. */ if (unlikely(err == -EBUSY)) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; sock_put(sk); goto err; } /* We need to ensure that the socket is hashed and visible. */ smp_wmb(); /* Paired with lockless reads from netlink_bind(), * netlink_connect() and netlink_sendmsg(). */ WRITE_ONCE(nlk_sk(sk)->bound, portid); err: release_sock(sk); return err; } static void netlink_remove(struct sock *sk) { struct netlink_table *table; table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, netlink_rhashtable_params)) { WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } netlink_table_grab(); if (nlk_sk(sk)->subscriptions) { __sk_del_bind_node(sk); netlink_update_listeners(sk); } if (sk->sk_protocol == NETLINK_GENERIC) atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } static struct proto netlink_proto = { .name = "NETLINK", .owner = THIS_MODULE, .obj_size = sizeof(struct netlink_sock), }; static int __netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct netlink_sock *nlk; sock->ops = &netlink_ops; sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); nlk = nlk_sk(sk); mutex_init(&nlk->nl_cb_mutex); lockdep_set_class_and_name(&nlk->nl_cb_mutex, nlk_cb_mutex_keys + protocol, nlk_cb_mutex_key_strings[protocol]); init_waitqueue_head(&nlk->wait); sk->sk_destruct = netlink_sock_destruct; sk->sk_protocol = protocol; return 0; } static int netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct module *module = NULL; struct netlink_sock *nlk; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); void (*release)(struct sock *sock, unsigned long *groups); int err = 0; sock->state = SS_UNCONNECTED; if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES if (!nl_table[protocol].registered) { netlink_unlock_table(); request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); netlink_lock_table(); } #endif if (nl_table[protocol].registered && try_module_get(nl_table[protocol].module)) module = nl_table[protocol].module; else err = -EPROTONOSUPPORT; bind = nl_table[protocol].bind; unbind = nl_table[protocol].unbind; release = nl_table[protocol].release; netlink_unlock_table(); if (err < 0) goto out; err = __netlink_create(net, sock, protocol, kern); if (err < 0) goto out_module; sock_prot_inuse_add(net, &netlink_proto, 1); nlk = nlk_sk(sock->sk); nlk->module = module; nlk->netlink_bind = bind; nlk->netlink_unbind = unbind; nlk->netlink_release = release; out: return err; out_module: module_put(module); goto out; } static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); struct sock *sk = &nlk->sk; kfree(nlk->groups); nlk->groups = NULL; if (!refcount_dec_and_test(&sk->sk_refcnt)) return; sk_free(sk); } static int netlink_release(struct socket *sock) { struct sock *sk = sock->sk; struct netlink_sock *nlk; if (!sk) return 0; netlink_remove(sk); sock_orphan(sk); nlk = nlk_sk(sk); /* * OK. Socket is unlinked, any packets that arrive now * will be purged. */ if (nlk->netlink_release) nlk->netlink_release(sk, nlk->groups); /* must not acquire netlink_table_lock in any way again before unbind * and notifying genetlink is done as otherwise it might deadlock */ if (nlk->netlink_unbind) { int i; for (i = 0; i < nlk->ngroups; i++) if (test_bit(i, nlk->groups)) nlk->netlink_unbind(sock_net(sk), i + 1); } if (sk->sk_protocol == NETLINK_GENERIC && atomic_dec_return(&genl_sk_destructing_cnt) == 0) wake_up(&genl_sk_destructing_waitq); sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); skb_queue_purge(&sk->sk_write_queue); if (nlk->portid && nlk->bound) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, .portid = nlk->portid, }; blocking_notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n); } /* Terminate any outstanding dump */ if (nlk->cb_running) { if (nlk->cb.done) nlk->cb.done(&nlk->cb); module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); } module_put(nlk->module); if (netlink_is_kernel(sk)) { netlink_table_grab(); BUG_ON(nl_table[sk->sk_protocol].registered == 0); if (--nl_table[sk->sk_protocol].registered == 0) { struct listeners *old; old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; nl_table[sk->sk_protocol].unbind = NULL; nl_table[sk->sk_protocol].flags = 0; nl_table[sk->sk_protocol].registered = 0; } netlink_table_ungrab(); } sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); /* Because struct net might disappear soon, do not keep a pointer. */ if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) { __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); /* Because of deferred_put_nlk_sk and use of work queue, * it is possible netns will be freed before this socket. */ sock_net_set(sk, &init_net); __netns_tracker_alloc(&init_net, &sk->ns_tracker, false, GFP_KERNEL); } call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_table *table = &nl_table[sk->sk_protocol]; s32 portid = task_tgid_vnr(current); int err; s32 rover = -4096; bool ok; retry: cond_resched(); rcu_read_lock(); ok = !__netlink_lookup(table, portid, net); rcu_read_unlock(); if (!ok) { /* Bind collision, search negative portid values. */ if (rover == -4096) /* rover will be in range [S32_MIN, -4097] */ rover = S32_MIN + get_random_u32_below(-4096 - S32_MIN); else if (rover >= -4096) rover = -4097; portid = rover--; goto retry; } err = netlink_insert(sk, portid); if (err == -EADDRINUSE) goto retry; /* If 2 threads race to autobind, that is fine. */ if (err == -EBUSY) err = 0; return err; } /** * __netlink_ns_capable - General netlink message capability test * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) { return ((nsp->flags & NETLINK_SKB_DST) || file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(__netlink_ns_capable); /** * netlink_ns_capable - General netlink message capability test * @skb: socket buffer holding a netlink command from userspace * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) { return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); } EXPORT_SYMBOL(netlink_ns_capable); /** * netlink_capable - Netlink global message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, &init_user_ns, cap); } EXPORT_SYMBOL(netlink_capable); /** * netlink_net_capable - Netlink network namespace message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); } EXPORT_SYMBOL(netlink_net_capable); static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); } static void netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions) { struct netlink_sock *nlk = nlk_sk(sk); if (nlk->subscriptions && !subscriptions) __sk_del_bind_node(sk); else if (!nlk->subscriptions && subscriptions) sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); nlk->subscriptions = subscriptions; } static int netlink_realloc_groups(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); unsigned int groups; unsigned long *new_groups; int err = 0; netlink_table_grab(); groups = nl_table[sk->sk_protocol].groups; if (!nl_table[sk->sk_protocol].registered) { err = -ENOENT; goto out_unlock; } if (nlk->ngroups >= groups) goto out_unlock; new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC); if (new_groups == NULL) { err = -ENOMEM; goto out_unlock; } memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); nlk->groups = new_groups; nlk->ngroups = groups; out_unlock: netlink_table_ungrab(); return err; } static void netlink_undo_bind(int group, long unsigned int groups, struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); int undo; if (!nlk->netlink_unbind) return; for (undo = 0; undo < group; undo++) if (test_bit(undo, &groups)) nlk->netlink_unbind(sock_net(sk), undo + 1); } static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; unsigned long groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; if (nladdr->nl_family != AF_NETLINK) return -EINVAL; groups = nladdr->nl_groups; /* Only superuser is allowed to listen multicasts */ if (groups) { if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; } if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; /* Paired with WRITE_ONCE() in netlink_insert() */ bound = READ_ONCE(nlk->bound); if (bound) { /* Ensure nlk->portid is up-to-date. */ smp_rmb(); if (nladdr->nl_pid != nlk->portid) return -EINVAL; } if (nlk->netlink_bind && groups) { int group; /* nl_groups is a u32, so cap the maximum groups we can bind */ for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); if (!err) continue; netlink_undo_bind(group, groups, sk); return err; } } /* No need for barriers here as we return to user-space without * using any of the bound attributes. */ netlink_lock_table(); if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) goto unlock; netlink_unlock_table(); netlink_table_grab(); netlink_update_subscriptions(sk, nlk->subscriptions + hweight32(groups) - hweight32(nlk->groups[0])); nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; netlink_update_listeners(sk); netlink_table_ungrab(); return 0; unlock: netlink_unlock_table(); return err; } static int netlink_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { int err = 0; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; if (alen < sizeof(addr->sa_family)) return -EINVAL; if (addr->sa_family == AF_UNSPEC) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, 0); WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) return -EINVAL; if (alen < sizeof(struct sockaddr_nl)) return -EINVAL; if ((nladdr->nl_groups || nladdr->nl_pid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; /* No need for barriers here as we return to user-space without * using any of the bound attributes. * Paired with WRITE_ONCE() in netlink_insert(). */ if (!READ_ONCE(nlk->bound)) err = netlink_autobind(sock); if (err == 0) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; } static int netlink_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; if (peer) { /* Paired with WRITE_ONCE() in netlink_connect() */ nladdr->nl_pid = READ_ONCE(nlk->dst_portid); nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { /* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); } return sizeof(*nladdr); } static int netlink_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* try to hand this ioctl down to the NIC drivers. */ return -ENOIOCTLCMD; } static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) { struct sock *sock; struct netlink_sock *nlk; sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); if (!sock) return ERR_PTR(-ECONNREFUSED); /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); /* dst_portid and sk_state can be changed in netlink_connect() */ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } return sock; } struct sock *netlink_getsockbyfd(int fd) { CLASS(fd, f)(fd); struct inode *inode; struct sock *sock; if (fd_empty(f)) return ERR_PTR(-EBADF); inode = file_inode(fd_file(f)); if (!S_ISSOCK(inode->i_mode)) return ERR_PTR(-ENOTSOCK); sock = SOCKET_I(inode)->sk; if (sock->sk_family != AF_NETLINK) return ERR_PTR(-EINVAL); sock_hold(sock); return sock; } struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) { size_t head_size = SKB_HEAD_ALIGN(size); struct sk_buff *skb; void *data; if (head_size <= PAGE_SIZE || broadcast) return alloc_skb(size, GFP_KERNEL); data = kvmalloc(head_size, GFP_KERNEL); if (!data) return NULL; skb = __build_skb(data, head_size); if (!skb) kvfree(data); else if (is_vmalloc_addr(data)) skb->destructor = netlink_skb_destructor; return skb; } /* * Attach a skb to a netlink socket. * The caller must hold a reference to the destination socket. On error, the * reference is dropped. The skb is not send to the destination, just all * all error checks are performed and memory in the queue is reserved. * Return values: * < 0: error. skb freed, reference to sock dropped. * 0: continue * 1: repeat lookup - reference dropped while waiting for socket memory. */ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { struct netlink_sock *nlk; nlk = nlk_sk(sk); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(NETLINK_S_CONGESTED, &nlk->state))) { DECLARE_WAITQUEUE(wait, current); if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) netlink_overrun(sk); sock_put(sk); kfree_skb(skb); return -EAGAIN; } __set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&nlk->wait, &wait); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(NETLINK_S_CONGESTED, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) *timeo = schedule_timeout(*timeo); __set_current_state(TASK_RUNNING); remove_wait_queue(&nlk->wait, &wait); sock_put(sk); if (signal_pending(current)) { kfree_skb(skb); return sock_intr_errno(*timeo); } return 1; } netlink_skb_set_owner_r(skb, sk); return 0; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = skb->len; netlink_deliver_tap(sock_net(sk), skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); return len; } int netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = __netlink_sendskb(sk, skb); sock_put(sk); return len; } void netlink_detachskb(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); sock_put(sk); } static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) { int delta; skb_assert_len(skb); WARN_ON(skb->sk != NULL); delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) return skb; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, allocation); if (!nskb) return skb; consume_skb(skb); skb = nskb; } pskb_expand_head(skb, 0, -delta, (allocation & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); return skb; } static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, struct sock *ssk) { int ret; struct netlink_sock *nlk = nlk_sk(sk); ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); nlk->netlink_rcv(skb); consume_skb(skb); } else { kfree_skb(skb); } sock_put(sk); return ret; } int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 portid, int nonblock) { struct sock *sk; int err; long timeo; skb = netlink_trim(skb, gfp_any()); timeo = sock_sndtimeo(ssk, nonblock); retry: sk = netlink_getsockbyportid(ssk, portid); if (IS_ERR(sk)) { kfree_skb(skb); return PTR_ERR(sk); } if (netlink_is_kernel(sk)) return netlink_unicast_kernel(sk, skb, ssk); if (sk_filter(sk, skb)) { err = skb->len; kfree_skb(skb); sock_put(sk); return err; } err = netlink_attachskb(sk, skb, &timeo, ssk); if (err == 1) goto retry; if (err) return err; return netlink_sendskb(sk, skb); } EXPORT_SYMBOL(netlink_unicast); int netlink_has_listeners(struct sock *sk, unsigned int group) { int res = 0; struct listeners *listeners; BUG_ON(!netlink_is_kernel(sk)); rcu_read_lock(); listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) res = test_bit(group - 1, listeners->masks); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(netlink_has_listeners); bool netlink_strict_get_check(struct sk_buff *skb) { return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); } EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); } return -1; } struct netlink_broadcast_data { struct sock *exclude_sk; struct net *net; u32 portid; u32 group; int failure; int delivery_failure; int congested; int delivered; gfp_t allocation; struct sk_buff *skb, *skb2; int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); void *tx_data; }; static void do_one_broadcast(struct sock *sk, struct netlink_broadcast_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int val; if (p->exclude_sk == sk) return; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) return; if (!net_eq(sock_net(sk), p->net)) { if (!nlk_test_bit(LISTEN_ALL_NSID, sk)) return; if (!peernet_has_id(sock_net(sk), p->net)) return; if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns, CAP_NET_BROADCAST)) return; } if (p->failure) { netlink_overrun(sk); return; } sock_hold(sk); if (p->skb2 == NULL) { if (skb_shared(p->skb)) { p->skb2 = skb_clone(p->skb, p->allocation); } else { p->skb2 = skb_get(p->skb); /* * skb ownership may have been set when * delivered to a previous socket. */ skb_orphan(p->skb2); } } if (p->skb2 == NULL) { netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; goto out; } if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED) NETLINK_CB(p->skb2).nsid_is_set = true; val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; p->skb2 = NULL; } out: sock_put(sk); } int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation, netlink_filter_fn filter, void *filter_data) { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; struct sock *sk; skb = netlink_trim(skb, allocation); info.exclude_sk = ssk; info.net = net; info.portid = portid; info.group = group; info.failure = 0; info.delivery_failure = 0; info.congested = 0; info.delivered = 0; info.allocation = allocation; info.skb = skb; info.skb2 = NULL; info.tx_filter = filter; info.tx_data = filter_data; /* While we sleep in clone, do not allow to change socket list */ netlink_lock_table(); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); consume_skb(skb); netlink_unlock_table(); if (info.delivery_failure) { kfree_skb(info.skb2); return -ENOBUFS; } consume_skb(info.skb2); if (info.delivered) { if (info.congested && gfpflags_allow_blocking(allocation)) yield(); return 0; } return -ESRCH; } EXPORT_SYMBOL(netlink_broadcast_filtered); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation) { return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, NULL, NULL); } EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { struct sock *exclude_sk; u32 portid; u32 group; int code; }; static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int ret = 0; if (sk == p->exclude_sk) goto out; if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) goto out; if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) { ret = 1; goto out; } WRITE_ONCE(sk->sk_err, p->code); sk_error_report(sk); out: return ret; } /** * netlink_set_err - report error to broadcast listeners * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_NO_ENOBUFS socket option. */ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; unsigned long flags; struct sock *sk; int ret = 0; info.exclude_sk = ssk; info.portid = portid; info.group = group; /* sk->sk_err wants a positive error value */ info.code = -code; read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); /* must be called with netlink table grabbed */ static void netlink_update_socket_mc(struct netlink_sock *nlk, unsigned int group, int is_new) { int old, new = !!is_new, subscriptions; old = test_bit(group - 1, nlk->groups); subscriptions = nlk->subscriptions - old + new; __assign_bit(group - 1, nlk->groups, new); netlink_update_subscriptions(&nlk->sk, subscriptions); netlink_update_listeners(&nlk->sk); } static int netlink_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int val = 0; int nr = -1; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (optlen >= sizeof(int) && copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case NETLINK_PKTINFO: nr = NETLINK_F_RECV_PKTINFO; break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { int err; if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; if (!val || val - 1 >= nlk->ngroups) return -EINVAL; if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { err = nlk->netlink_bind(sock_net(sk), val); if (err) return err; } netlink_table_grab(); netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) nlk->netlink_unbind(sock_net(sk), val); break; } case NETLINK_BROADCAST_ERROR: nr = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val); if (val) { clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); } break; case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; nr = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: nr = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: nr = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: nr = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (nr >= 0) assign_bit(nr, &nlk->flags, val); return 0; } static int netlink_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int flag; int len, val; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case NETLINK_PKTINFO: flag = NETLINK_F_RECV_PKTINFO; break; case NETLINK_BROADCAST_ERROR: flag = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: flag = NETLINK_F_RECV_NO_ENOBUFS; break; case NETLINK_LIST_MEMBERSHIPS: { int pos, idx, shift, err = 0; netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; idx = pos / sizeof(unsigned long); shift = (pos % sizeof(unsigned long)) * 8; if (put_user((u32)(nlk->groups[idx] >> shift), (u32 __user *)(optval + pos))) { err = -EFAULT; break; } } if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; } case NETLINK_LISTEN_ALL_NSID: flag = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: flag = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: flag = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: flag = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = test_bit(flag, &nlk->flags); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct nl_pktinfo info; info.group = NETLINK_CB(skb).dst_group; put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); } static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { if (!NETLINK_CB(skb).nsid_is_set) return; put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int), &NETLINK_CB(skb).nsid); } static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); u32 dst_portid; u32 dst_group; struct sk_buff *skb; int err; struct scm_cookie scm; u32 netlink_skb_flags = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; if (len == 0) { pr_warn_once("Zero length message leads to an empty skb\n"); return -ENODATA; } err = scm_send(sock, msg, &scm, true); if (err < 0) return err; if (msg->msg_namelen) { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_nl)) goto out; if (addr->nl_family != AF_NETLINK) goto out; dst_portid = addr->nl_pid; dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { /* Paired with WRITE_ONCE() in netlink_connect() */ dst_portid = READ_ONCE(nlk->dst_portid); dst_group = READ_ONCE(nlk->dst_group); } /* Paired with WRITE_ONCE() in netlink_insert() */ if (!READ_ONCE(nlk->bound)) { err = netlink_autobind(sock); if (err) goto out; } else { /* Ensure nlk is hashed and visible. */ smp_rmb(); } err = -EMSGSIZE; if (len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = netlink_alloc_large_skb(len, dst_group); if (skb == NULL) goto out; NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = scm.creds; NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_from_msg(skb_put(skb, len), msg, len)) { kfree_skb(skb); goto out; } err = security_netlink_send(sk, skb); if (err) { kfree_skb(skb); goto out; } if (dst_group) { refcount_inc(&skb->users); netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT); out: scm_destroy(&scm); return err; } static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; if (flags & MSG_OOB) return -EOPNOTSUPP; copied = 0; skb = skb_recv_datagram(sk, flags, &err); if (skb == NULL) goto out; data_skb = skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES if (unlikely(skb_shinfo(skb)->frag_list)) { /* * If this skb has a frag_list, then here that means that we * will have to use the frag_list skb's data for compat tasks * and the regular skb's data for normal (non-compat) tasks. * * If we need to send the compat skb, assign it to the * 'data_skb' variable so that it will be used below for data * copying. We keep 'skb' for everything else, including * freeing both later. */ if (flags & MSG_CMSG_COMPAT) data_skb = skb_shinfo(skb)->frag_list; } #endif /* Record the max length of recvmsg() calls for future allocations */ max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); max_recvmsg_len = min_t(size_t, max_recvmsg_len, SKB_WITH_OVERHEAD(32768)); WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); addr->nl_family = AF_NETLINK; addr->nl_pad = 0; addr->nl_pid = NETLINK_CB(skb).portid; addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); msg->msg_namelen = sizeof(*addr); } if (nlk_test_bit(RECV_PKTINFO, sk)) netlink_cmsg_recv_pktinfo(msg, skb); if (nlk_test_bit(LISTEN_ALL_NSID, sk)) netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); scm.creds = *NETLINK_CREDS(skb); if (flags & MSG_TRUNC) copied = data_skb->len; skb_free_datagram(sk, skb); if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk, false); if (ret) { WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); } } scm_recv(sock, msg, &scm, flags); out: netlink_rcv_wake(sk); return err ? : copied; } static void netlink_data_ready(struct sock *sk) { BUG(); } /* * We export these functions to other modules. They provide a * complete set of kernel non-blocking support for message * queueing. */ struct sock * __netlink_kernel_create(struct net *net, int unit, struct module *module, struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; unsigned int groups; BUG_ON(!nl_table); if (unit < 0 || unit >= MAX_LINKS) return NULL; if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; if (__netlink_create(net, sock, unit, 1) < 0) goto out_sock_release_nosk; sk = sock->sk; if (!cfg || cfg->groups < 32) groups = 32; else groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; if (cfg && cfg->input) nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, 0)) goto out_sock_release; nlk = nlk_sk(sk); set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags); netlink_table_grab(); if (!nl_table[unit].registered) { nl_table[unit].groups = groups; rcu_assign_pointer(nl_table[unit].listeners, listeners); nl_table[unit].module = module; if (cfg) { nl_table[unit].bind = cfg->bind; nl_table[unit].unbind = cfg->unbind; nl_table[unit].release = cfg->release; nl_table[unit].flags = cfg->flags; } nl_table[unit].registered = 1; } else { kfree(listeners); nl_table[unit].registered++; } netlink_table_ungrab(); return sk; out_sock_release: kfree(listeners); netlink_kernel_release(sk); return NULL; out_sock_release_nosk: sock_release(sock); return NULL; } EXPORT_SYMBOL(__netlink_kernel_create); void netlink_kernel_release(struct sock *sk) { if (sk == NULL || sk->sk_socket == NULL) return; sock_release(sk->sk_socket); } EXPORT_SYMBOL(netlink_kernel_release); int __netlink_change_ngroups(struct sock *sk, unsigned int groups) { struct listeners *new, *old; struct netlink_table *tbl = &nl_table[sk->sk_protocol]; if (groups < 32) groups = 32; if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; old = nl_deref_protected(tbl->listeners); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); kfree_rcu(old, rcu); } tbl->groups = groups; return 0; } /** * netlink_change_ngroups - change number of multicast groups * * This changes the number of multicast groups that are available * on a certain netlink family. Note that it is not possible to * change the number of groups to below 32. Also note that it does * not implicitly call netlink_clear_multicast_users() when the * number of groups is reduced. * * @sk: The kernel netlink socket, as returned by netlink_kernel_create(). * @groups: The new number of groups. */ int netlink_change_ngroups(struct sock *sk, unsigned int groups) { int err; netlink_table_grab(); err = __netlink_change_ngroups(sk, groups); netlink_table_ungrab(); return err; } void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { struct sock *sk; struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; struct hlist_node *tmp; sk_for_each_bound_safe(sk, tmp, &tbl->mc_list) netlink_update_socket_mc(nlk_sk(sk), group, 0); } struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); nlh = skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; nlh->nlmsg_pid = portid; nlh->nlmsg_seq = seq; if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size); return nlh; } EXPORT_SYMBOL(__nlmsg_put); static size_t netlink_ack_tlv_len(struct netlink_sock *nlk, int err, const struct netlink_ext_ack *extack) { size_t tlvlen; if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) return 0; tlvlen = 0; if (extack->_msg) tlvlen += nla_total_size(strlen(extack->_msg) + 1); if (extack->cookie_len) tlvlen += nla_total_size(extack->cookie_len); /* Following attributes are only reported as error (not warning) */ if (!err) return tlvlen; if (extack->bad_attr) tlvlen += nla_total_size(sizeof(u32)); if (extack->policy) tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); if (extack->miss_type) tlvlen += nla_total_size(sizeof(u32)); if (extack->miss_nest) tlvlen += nla_total_size(sizeof(u32)); return tlvlen; } static bool nlmsg_check_in_payload(const struct nlmsghdr *nlh, const void *addr) { return !WARN_ON(addr < nlmsg_data(nlh) || addr - (const void *) nlh >= nlh->nlmsg_len); } static void netlink_ack_tlv_fill(struct sk_buff *skb, const struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { if (extack->_msg) WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, extack->cookie_len, extack->cookie)); if (!err) return; if (extack->bad_attr && nlmsg_check_in_payload(nlh, extack->bad_attr)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - (const u8 *)nlh)); if (extack->policy) netlink_policy_dump_write_attr(skb, extack->policy, NLMSGERR_ATTR_POLICY); if (extack->miss_type) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE, extack->miss_type)); if (extack->miss_nest && nlmsg_check_in_payload(nlh, extack->miss_nest)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST, (u8 *)extack->miss_nest - (const u8 *)nlh)); } /* * It looks a bit ugly. * It would be better to create kernel thread. */ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, struct netlink_callback *cb, struct netlink_ext_ack *extack) { struct nlmsghdr *nlh; size_t extack_len; nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), NLM_F_MULTI | cb->answer_flags); if (WARN_ON(!nlh)) return -ENOBUFS; nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); extack_len = netlink_ack_tlv_len(nlk, nlk->dump_done_errno, extack); if (extack_len) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; if (skb_tailroom(skb) >= extack_len) { netlink_ack_tlv_fill(skb, cb->nlh, nlk->dump_done_errno, extack); nlmsg_end(skb, nlh); } } return 0; } static int netlink_dump(struct sock *sk, bool lock_taken) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; int alloc_size; if (!lock_taken) mutex_lock(&nlk->nl_cb_mutex); if (!nlk->cb_running) { err = -EINVAL; goto errout_skb; } if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 32KiB allocation * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); if (alloc_min_size < max_recvmsg_len) { alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; skb = alloc_skb(alloc_size, GFP_KERNEL); } if (!skb) goto errout_skb; /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as * could fit within the allocated skb. skb is typically allocated * with larger space than required (could be as much as near 2x the * requested size with align to next power of 2 approach). Allowing * dump to use the excess space makes it difficult for a user to have a * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); /* Make sure malicious BPF programs can not read unitialized memory * from skb->head -> skb->data */ skb_reset_network_header(skb); skb_reset_mac_header(skb); netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { cb->extack = &extack; nlk->dump_done_errno = cb->dump(skb, cb); /* EMSGSIZE plus something already in the skb means * that there's more to dump but current skb has filled up. * If the callback really wants to return EMSGSIZE to user space * it needs to do so again, on the next cb->dump() call, * without putting data in the skb. */ if (nlk->dump_done_errno == -EMSGSIZE && skb->len) nlk->dump_done_errno = skb->len; cb->extack = NULL; } if (nlk->dump_done_errno > 0 || skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { mutex_unlock(&nlk->nl_cb_mutex); if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); return 0; } if (netlink_dump_done(nlk, skb, cb, &extack)) goto errout_skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES /* frag_list skb's data is used for compat tasks * and the regular skb's data for normal (non-compat) tasks. * See netlink_recvmsg(). */ if (unlikely(skb_shinfo(skb)->frag_list)) { if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack)) goto errout_skb; } #endif if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); if (cb->done) cb->done(cb); WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(&nlk->nl_cb_mutex); module_put(module); consume_skb(skb); return 0; errout_skb: mutex_unlock(&nlk->nl_cb_mutex); kfree_skb(skb); return err; } int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { struct netlink_callback *cb; struct netlink_sock *nlk; struct sock *sk; int ret; refcount_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { ret = -ECONNREFUSED; goto error_free; } nlk = nlk_sk(sk); mutex_lock(&nlk->nl_cb_mutex); /* A dump is in progress... */ if (nlk->cb_running) { ret = -EBUSY; goto error_unlock; } /* add reference of module which cb->dump belongs to */ if (!try_module_get(control->module)) { ret = -EPROTONOSUPPORT; goto error_unlock; } cb = &nlk->cb; memset(cb, 0, sizeof(*cb)); cb->dump = control->dump; cb->done = control->done; cb->nlh = nlh; cb->data = control->data; cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; cb->flags = control->flags; cb->skb = skb; cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); if (control->start) { cb->extack = control->extack; ret = control->start(cb); cb->extack = NULL; if (ret) goto error_put; } WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; ret = netlink_dump(sk, true); sock_put(sk); if (ret) return ret; /* We successfully started a dump, by returning -EINTR we * signal not to send ACK even if it was requested. */ return -EINTR; error_put: module_put(control->module); error_unlock: sock_put(sk); mutex_unlock(&nlk->nl_cb_mutex); error_free: kfree_skb(skb); return ret; } EXPORT_SYMBOL(__netlink_dump_start); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct sk_buff *skb; struct nlmsghdr *rep; struct nlmsgerr *errmsg; size_t payload = sizeof(*errmsg); struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); unsigned int flags = 0; size_t tlvlen; /* Error messages get the original request appened, unless the user * requests to cap the error message, and get extra error data if * requested. */ if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; tlvlen = netlink_ack_tlv_len(nlk, err, extack); if (tlvlen) flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) goto err_skb; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, sizeof(*errmsg), flags); if (!rep) goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; errmsg->msg = *nlh; if (!(flags & NLM_F_CAPPED)) { if (!nlmsg_append(skb, nlmsg_len(nlh))) goto err_bad_put; memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), nlmsg_len(nlh)); } if (tlvlen) netlink_ack_tlv_fill(skb, nlh, err, extack); nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); return; err_bad_put: nlmsg_free(skb); err_skb: WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)) { struct netlink_ext_ack extack; struct nlmsghdr *nlh; int err; while (skb->len >= nlmsg_total_size(0)) { int msglen; memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return 0; /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) goto ack; /* Skip control messages */ if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) netlink_ack(skb, nlh, err, &extack); skip: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } return 0; } EXPORT_SYMBOL(netlink_rcv_skb); /** * nlmsg_notify - send a notification netlink message * @sk: netlink socket to use * @skb: notification message * @portid: destination netlink portid for reports or 0 * @group: destination multicast group or 0 * @report: 1 to report back, 0 to disable * @flags: allocation flags */ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags) { int err = 0; if (group) { int exclude_portid = 0; if (report) { refcount_inc(&skb->users); exclude_portid = portid; } /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); if (err == -ESRCH) err = 0; } if (report) { int err2; err2 = nlmsg_unicast(sk, skb, portid); if (!err) err = err2; } return err; } EXPORT_SYMBOL(nlmsg_notify); #ifdef CONFIG_PROC_FS struct nl_seq_iter { struct seq_net_private p; struct rhashtable_iter hti; int link; }; static void netlink_walk_start(struct nl_seq_iter *iter) { rhashtable_walk_enter(&nl_table[iter->link].hash, &iter->hti); rhashtable_walk_start(&iter->hti); } static void netlink_walk_stop(struct nl_seq_iter *iter) { rhashtable_walk_stop(&iter->hti); rhashtable_walk_exit(&iter->hti); } static void *__netlink_seq_next(struct seq_file *seq) { struct nl_seq_iter *iter = seq->private; struct netlink_sock *nlk; do { for (;;) { nlk = rhashtable_walk_next(&iter->hti); if (IS_ERR(nlk)) { if (PTR_ERR(nlk) == -EAGAIN) continue; return nlk; } if (nlk) break; netlink_walk_stop(iter); if (++iter->link >= MAX_LINKS) return NULL; netlink_walk_start(iter); } } while (sock_net(&nlk->sk) != seq_file_net(seq)); return nlk; } static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) __acquires(RCU) { struct nl_seq_iter *iter = seq->private; void *obj = SEQ_START_TOKEN; loff_t pos; iter->link = 0; netlink_walk_start(iter); for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) obj = __netlink_seq_next(seq); return obj; } static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return __netlink_seq_next(seq); } static void netlink_native_seq_stop(struct seq_file *seq, void *v) { struct nl_seq_iter *iter = seq->private; if (iter->link >= MAX_LINKS) return; netlink_walk_stop(iter); } static int netlink_native_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk Eth Pid Groups " "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8u %-8lu\n", s, s->sk_protocol, nlk->portid, nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) ); } return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__netlink { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct netlink_sock *, sk); }; DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk) static int netlink_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__netlink ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk = nlk_sk((struct sock *)v); return bpf_iter_run_prog(prog, &ctx); } static int netlink_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return netlink_native_seq_show(seq, v); if (v != SEQ_START_TOKEN) return netlink_prog_seq_show(prog, &meta, v); return 0; } static void netlink_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)netlink_prog_seq_show(prog, &meta, v); } netlink_native_seq_stop(seq, v); } #else static int netlink_seq_show(struct seq_file *seq, void *v) { return netlink_native_seq_show(seq, v); } static void netlink_seq_stop(struct seq_file *seq, void *v) { netlink_native_seq_stop(seq, v); } #endif static const struct seq_operations netlink_seq_ops = { .start = netlink_seq_start, .next = netlink_seq_next, .stop = netlink_seq_stop, .show = netlink_seq_show, }; #endif int netlink_register_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_register_notifier); int netlink_unregister_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_unregister_notifier); static const struct proto_ops netlink_ops = { .family = PF_NETLINK, .owner = THIS_MODULE, .release = netlink_release, .bind = netlink_bind, .connect = netlink_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = netlink_getname, .poll = datagram_poll, .ioctl = netlink_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = netlink_setsockopt, .getsockopt = netlink_getsockopt, .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, .mmap = sock_no_mmap, }; static const struct net_proto_family netlink_family_ops = { .family = PF_NETLINK, .create = netlink_create, .owner = THIS_MODULE, /* for consistency 8) */ }; static int __net_init netlink_net_init(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops, sizeof(struct nl_seq_iter))) return -ENOMEM; #endif return 0; } static void __net_exit netlink_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("netlink", net->proc_net); #endif } static void __init netlink_add_usersock_entry(void) { struct listeners *listeners; int groups = 32; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) panic("netlink_add_usersock_entry: Cannot allocate listeners\n"); netlink_table_grab(); nl_table[NETLINK_USERSOCK].groups = groups; rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); nl_table[NETLINK_USERSOCK].module = THIS_MODULE; nl_table[NETLINK_USERSOCK].registered = 1; nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND; netlink_table_ungrab(); } static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, }; static inline u32 netlink_hash(const void *data, u32 len, u32 seed) { const struct netlink_sock *nlk = data; struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); } static const struct rhashtable_params netlink_rhashtable_params = { .head_offset = offsetof(struct netlink_sock, node), .key_len = netlink_compare_arg_len, .obj_hashfn = netlink_hash, .obj_cmpfn = netlink_compare, .automatic_shrinking = true, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) BTF_ID_LIST(btf_netlink_sock_id) BTF_ID(struct, netlink_sock) static const struct bpf_iter_seq_info netlink_seq_info = { .seq_ops = &netlink_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct nl_seq_iter), }; static struct bpf_iter_reg netlink_reg_info = { .target = "netlink", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__netlink, sk), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &netlink_seq_info, }; static int __init bpf_iter_register(void) { netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id; return bpf_iter_reg_target(&netlink_reg_info); } #endif static int __init netlink_proto_init(void) { int i; int err = proto_register(&netlink_proto, 0); if (err != 0) goto out; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) err = bpf_iter_register(); if (err) goto out; #endif BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) goto panic; for (i = 0; i < MAX_LINKS; i++) { if (rhashtable_init(&nl_table[i].hash, &netlink_rhashtable_params) < 0) goto panic; } netlink_add_usersock_entry(); sock_register(&netlink_family_ops); register_pernet_subsys(&netlink_net_ops); register_pernet_subsys(&netlink_tap_net_ops); /* The netlink device handler may be needed early. */ rtnetlink_init(); out: return err; panic: panic("netlink_init: Cannot allocate nl_table\n"); } core_initcall(netlink_proto_init); |
| 2 4 1 1 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 1 1 1 1 2 1 1 1 1 2 1 1 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/array.c * * Copyright (C) 1992 by Linus Torvalds * based on ideas by Darren Senn * * Fixes: * Michael. K. Johnson: stat,statm extensions. * <johnsonm@stolaf.edu> * * Pauline Middelink : Made cmdline,envline only break at '\0's, to * make sure SET_PROCTITLE works. Also removed * bad '!' which forced address recalculation for * EVERY character on the current page. * <middelin@polyware.iaf.nl> * * Danny ter Haar : added cpuinfo * <dth@cistron.nl> * * Alessandro Rubini : profile extension. * <rubini@ipvvis.unipv.it> * * Jeff Tranter : added BogoMips field to cpuinfo * <Jeff_Tranter@Mitel.COM> * * Bruno Haible : remove 4K limit for the maps file * <haible@ma2s2.mathematik.uni-karlsruhe.de> * * Yves Arrouye : remove removal of trailing spaces in get_array. * <Yves.Arrouye@marin.fdn.fr> * * Jerome Forissier : added per-CPU time information to /proc/stat * and /proc/<pid>/cpu extension * <forissier@isia.cma.fr> * - Incorporation and non-SMP safe operation * of forissier patch in 2.1.78 by * Hans Marcus <crowbar@concepts.nl> * * aeb@cwi.nl : /proc/partitions * * * Alan Cox : security fixes. * <alan@lxorguk.ukuu.org.uk> * * Al Viro : safe handling of mm_struct * * Gerhard Wichert : added BIGMEM support * Siemens AG <Gerhard.Wichert@pdb.siemens.de> * * Al Viro & Jeff Garzik : moved most of the thing into base.c and * : proc_misc.c. The rest may eventually go into * : base.c too. */ #include <linux/types.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/time_namespace.h> #include <linux/kernel.h> #include <linux/kernel_stat.h> #include <linux/tty.h> #include <linux/string.h> #include <linux/mman.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task_stack.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/proc_fs.h> #include <linux/ioport.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/smp.h> #include <linux/signal.h> #include <linux/highmem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/times.h> #include <linux/cpuset.h> #include <linux/rcupdate.h> #include <linux/delayacct.h> #include <linux/seq_file.h> #include <linux/pid_namespace.h> #include <linux/prctl.h> #include <linux/ptrace.h> #include <linux/string_helpers.h> #include <linux/user_namespace.h> #include <linux/fs_struct.h> #include <linux/kthread.h> #include <linux/mmu_context.h> #include <asm/processor.h> #include "internal.h" void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { char tcomm[64]; /* * Test before PF_KTHREAD because all workqueue worker threads are * kernel threads. */ if (p->flags & PF_WQ_WORKER) wq_worker_comm(tcomm, sizeof(tcomm), p); else if (p->flags & PF_KTHREAD) get_kthread_comm(tcomm, sizeof(tcomm), p); else get_task_comm(tcomm, p); if (escape) seq_escape_str(m, tcomm, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); else seq_printf(m, "%.64s", tcomm); } /* * The task state array is a strange "bitmap" of * reasons to sleep. Thus "running" is zero, and * you can test for combinations of others with * simple bit tests. */ static const char * const task_state_array[] = { /* states in TASK_REPORT: */ "R (running)", /* 0x00 */ "S (sleeping)", /* 0x01 */ "D (disk sleep)", /* 0x02 */ "T (stopped)", /* 0x04 */ "t (tracing stop)", /* 0x08 */ "X (dead)", /* 0x10 */ "Z (zombie)", /* 0x20 */ "P (parked)", /* 0x40 */ /* states beyond TASK_REPORT: */ "I (idle)", /* 0x80 */ }; static inline const char *get_task_state(struct task_struct *tsk) { BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array)); return task_state_array[task_state_index(tsk)]; } static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *p) { struct user_namespace *user_ns = seq_user_ns(m); struct group_info *group_info; int g, umask = -1; struct task_struct *tracer; const struct cred *cred; pid_t ppid, tpid = 0, tgid, ngid; unsigned int max_fds = 0; rcu_read_lock(); ppid = pid_alive(p) ? task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0; tracer = ptrace_parent(p); if (tracer) tpid = task_pid_nr_ns(tracer, ns); tgid = task_tgid_nr_ns(p, ns); ngid = task_numa_group_id(p); cred = get_task_cred(p); task_lock(p); if (p->fs) umask = p->fs->umask; if (p->files) max_fds = files_fdtable(p->files)->max_fds; task_unlock(p); rcu_read_unlock(); if (umask >= 0) seq_printf(m, "Umask:\t%#04o\n", umask); seq_puts(m, "State:\t"); seq_puts(m, get_task_state(p)); seq_put_decimal_ull(m, "\nTgid:\t", tgid); seq_put_decimal_ull(m, "\nNgid:\t", ngid); seq_put_decimal_ull(m, "\nPid:\t", pid_nr_ns(pid, ns)); seq_put_decimal_ull(m, "\nPPid:\t", ppid); seq_put_decimal_ull(m, "\nTracerPid:\t", tpid); seq_put_decimal_ull(m, "\nUid:\t", from_kuid_munged(user_ns, cred->uid)); seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->euid)); seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->suid)); seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->fsuid)); seq_put_decimal_ull(m, "\nGid:\t", from_kgid_munged(user_ns, cred->gid)); seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->egid)); seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->sgid)); seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->fsgid)); seq_put_decimal_ull(m, "\nFDSize:\t", max_fds); seq_puts(m, "\nGroups:\t"); group_info = cred->group_info; for (g = 0; g < group_info->ngroups; g++) seq_put_decimal_ull(m, g ? " " : "", from_kgid_munged(user_ns, group_info->gid[g])); put_cred(cred); /* Trailing space shouldn't have been added in the first place. */ seq_putc(m, ' '); #ifdef CONFIG_PID_NS seq_puts(m, "\nNStgid:"); for (g = ns->level; g <= pid->level; g++) seq_put_decimal_ull(m, "\t", task_tgid_nr_ns(p, pid->numbers[g].ns)); seq_puts(m, "\nNSpid:"); for (g = ns->level; g <= pid->level; g++) seq_put_decimal_ull(m, "\t", task_pid_nr_ns(p, pid->numbers[g].ns)); seq_puts(m, "\nNSpgid:"); for (g = ns->level; g <= pid->level; g++) seq_put_decimal_ull(m, "\t", task_pgrp_nr_ns(p, pid->numbers[g].ns)); seq_puts(m, "\nNSsid:"); for (g = ns->level; g <= pid->level; g++) seq_put_decimal_ull(m, "\t", task_session_nr_ns(p, pid->numbers[g].ns)); #endif seq_putc(m, '\n'); seq_printf(m, "Kthread:\t%c\n", p->flags & PF_KTHREAD ? '1' : '0'); } void render_sigset_t(struct seq_file *m, const char *header, sigset_t *set) { int i; seq_puts(m, header); i = _NSIG; do { int x = 0; i -= 4; if (sigismember(set, i+1)) x |= 1; if (sigismember(set, i+2)) x |= 2; if (sigismember(set, i+3)) x |= 4; if (sigismember(set, i+4)) x |= 8; seq_putc(m, hex_asc[x]); } while (i >= 4); seq_putc(m, '\n'); } static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *sigign, sigset_t *sigcatch) { struct k_sigaction *k; int i; k = p->sighand->action; for (i = 1; i <= _NSIG; ++i, ++k) { if (k->sa.sa_handler == SIG_IGN) sigaddset(sigign, i); else if (k->sa.sa_handler != SIG_DFL) sigaddset(sigcatch, i); } } static inline void task_sig(struct seq_file *m, struct task_struct *p) { unsigned long flags; sigset_t pending, shpending, blocked, ignored, caught; int num_threads = 0; unsigned int qsize = 0; unsigned long qlim = 0; sigemptyset(&pending); sigemptyset(&shpending); sigemptyset(&blocked); sigemptyset(&ignored); sigemptyset(&caught); if (lock_task_sighand(p, &flags)) { pending = p->pending.signal; shpending = p->signal->shared_pending.signal; blocked = p->blocked; collect_sigign_sigcatch(p, &ignored, &caught); num_threads = get_nr_threads(p); rcu_read_lock(); /* FIXME: is this correct? */ qsize = get_rlimit_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); qlim = task_rlimit(p, RLIMIT_SIGPENDING); unlock_task_sighand(p, &flags); } seq_put_decimal_ull(m, "Threads:\t", num_threads); seq_put_decimal_ull(m, "\nSigQ:\t", qsize); seq_put_decimal_ull(m, "/", qlim); /* render them all */ render_sigset_t(m, "\nSigPnd:\t", &pending); render_sigset_t(m, "ShdPnd:\t", &shpending); render_sigset_t(m, "SigBlk:\t", &blocked); render_sigset_t(m, "SigIgn:\t", &ignored); render_sigset_t(m, "SigCgt:\t", &caught); } static void render_cap_t(struct seq_file *m, const char *header, kernel_cap_t *a) { seq_puts(m, header); seq_put_hex_ll(m, NULL, a->val, 16); seq_putc(m, '\n'); } static inline void task_cap(struct seq_file *m, struct task_struct *p) { const struct cred *cred; kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset, cap_ambient; rcu_read_lock(); cred = __task_cred(p); cap_inheritable = cred->cap_inheritable; cap_permitted = cred->cap_permitted; cap_effective = cred->cap_effective; cap_bset = cred->cap_bset; cap_ambient = cred->cap_ambient; rcu_read_unlock(); render_cap_t(m, "CapInh:\t", &cap_inheritable); render_cap_t(m, "CapPrm:\t", &cap_permitted); render_cap_t(m, "CapEff:\t", &cap_effective); render_cap_t(m, "CapBnd:\t", &cap_bset); render_cap_t(m, "CapAmb:\t", &cap_ambient); } static inline void task_seccomp(struct seq_file *m, struct task_struct *p) { seq_put_decimal_ull(m, "NoNewPrivs:\t", task_no_new_privs(p)); #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #ifdef CONFIG_SECCOMP_FILTER seq_put_decimal_ull(m, "\nSeccomp_filters:\t", atomic_read(&p->seccomp.filter_count)); #endif #endif seq_puts(m, "\nSpeculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { case -EINVAL: seq_puts(m, "unknown"); break; case PR_SPEC_NOT_AFFECTED: seq_puts(m, "not vulnerable"); break; case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: seq_puts(m, "thread force mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_DISABLE: seq_puts(m, "thread mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_ENABLE: seq_puts(m, "thread vulnerable"); break; case PR_SPEC_DISABLE: seq_puts(m, "globally mitigated"); break; default: seq_puts(m, "vulnerable"); break; } seq_puts(m, "\nSpeculationIndirectBranch:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_INDIRECT_BRANCH)) { case -EINVAL: seq_puts(m, "unsupported"); break; case PR_SPEC_NOT_AFFECTED: seq_puts(m, "not affected"); break; case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: seq_puts(m, "conditional force disabled"); break; case PR_SPEC_PRCTL | PR_SPEC_DISABLE: seq_puts(m, "conditional disabled"); break; case PR_SPEC_PRCTL | PR_SPEC_ENABLE: seq_puts(m, "conditional enabled"); break; case PR_SPEC_ENABLE: seq_puts(m, "always enabled"); break; case PR_SPEC_DISABLE: seq_puts(m, "always disabled"); break; default: seq_puts(m, "unknown"); break; } seq_putc(m, '\n'); } static inline void task_context_switch_counts(struct seq_file *m, struct task_struct *p) { seq_put_decimal_ull(m, "voluntary_ctxt_switches:\t", p->nvcsw); seq_put_decimal_ull(m, "\nnonvoluntary_ctxt_switches:\t", p->nivcsw); seq_putc(m, '\n'); } static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Cpus_allowed:\t%*pb\n", cpumask_pr_args(&task->cpus_mask)); seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", cpumask_pr_args(&task->cpus_mask)); } static inline void task_core_dumping(struct seq_file *m, struct task_struct *task) { seq_put_decimal_ull(m, "CoreDumping:\t", !!task->signal->core_state); seq_putc(m, '\n'); } static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) { bool thp_enabled = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE); if (thp_enabled) thp_enabled = !test_bit(MMF_DISABLE_THP, &mm->flags); seq_printf(m, "THP_enabled:\t%d\n", thp_enabled); } static inline void task_untag_mask(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "untag_mask:\t%#lx\n", mm_untag_mask(mm)); } __weak void arch_proc_pid_thread_features(struct seq_file *m, struct task_struct *task) { } int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm = get_task_mm(task); seq_puts(m, "Name:\t"); proc_task_name(m, task, true); seq_putc(m, '\n'); task_state(m, ns, pid, task); if (mm) { task_mem(m, mm); task_core_dumping(m, task); task_thp_status(m, mm); task_untag_mask(m, mm); mmput(mm); } task_sig(m, task); task_cap(m, task); task_seccomp(m, task); task_cpus_allowed(m, task); cpuset_task_status_allowed(m, task); task_context_switch_counts(m, task); arch_proc_pid_thread_features(m, task); return 0; } static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task, int whole) { unsigned long vsize, eip, esp, wchan = 0; int priority, nice; int tty_pgrp = -1, tty_nr = 0; sigset_t sigign, sigcatch; char state; pid_t ppid = 0, pgid = -1, sid = -1; int num_threads = 0; int permitted; struct mm_struct *mm; unsigned long long start_time; unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt; u64 cutime, cstime, cgtime, utime, stime, gtime; unsigned long rsslim = 0; unsigned long flags; int exit_code = task->exit_code; struct signal_struct *sig = task->signal; unsigned int seq = 1; state = *get_task_state(task); vsize = eip = esp = 0; permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT); mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); /* * esp and eip are intentionally zeroed out. There is no * non-racy way to read them without freezing the task. * Programs that need reliable values can use ptrace(2). * * The only exception is if the task is core dumping because * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE|PF_POSTCOREDUMP))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); put_task_stack(task); } } } sigemptyset(&sigign); sigemptyset(&sigcatch); if (lock_task_sighand(task, &flags)) { if (sig->tty) { struct pid *pgrp = tty_get_pgrp(sig->tty); tty_pgrp = pid_nr_ns(pgrp, ns); put_pid(pgrp); tty_nr = new_encode_dev(tty_devnum(sig->tty)); } num_threads = get_nr_threads(task); collect_sigign_sigcatch(task, &sigign, &sigcatch); rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); if (whole) { if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) exit_code = sig->group_exit_code; } sid = task_session_nr_ns(task, ns); ppid = task_tgid_nr_ns(task->real_parent, ns); pgid = task_pgrp_nr_ns(task, ns); unlock_task_sighand(task, &flags); } if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); do { seq++; /* 2 on the 1st/lockless path, otherwise odd */ flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); cmin_flt = sig->cmin_flt; cmaj_flt = sig->cmaj_flt; cutime = sig->cutime; cstime = sig->cstime; cgtime = sig->cgtime; if (whole) { struct task_struct *t; min_flt = sig->min_flt; maj_flt = sig->maj_flt; gtime = sig->gtime; rcu_read_lock(); __for_each_thread(sig, t) { min_flt += t->min_flt; maj_flt += t->maj_flt; gtime += task_gtime(t); } rcu_read_unlock(); } } while (need_seqretry(&sig->stats_lock, seq)); done_seqretry_irqrestore(&sig->stats_lock, seq, flags); if (whole) { thread_group_cputime_adjusted(task, &utime, &stime); } else { task_cputime_adjusted(task, &utime, &stime); min_flt = task->min_flt; maj_flt = task->maj_flt; gtime = task_gtime(task); } /* scale priority and nice values from timeslices to -20..20 */ /* to make it look like a "normal" Unix priority/nice value */ priority = task_prio(task); nice = task_nice(task); /* apply timens offset for boottime and convert nsec -> ticks */ start_time = nsec_to_clock_t(timens_add_boottime_ns(task->start_boottime)); seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); seq_puts(m, " ("); proc_task_name(m, task, false); seq_puts(m, ") "); seq_putc(m, state); seq_put_decimal_ll(m, " ", ppid); seq_put_decimal_ll(m, " ", pgid); seq_put_decimal_ll(m, " ", sid); seq_put_decimal_ll(m, " ", tty_nr); seq_put_decimal_ll(m, " ", tty_pgrp); seq_put_decimal_ull(m, " ", task->flags); seq_put_decimal_ull(m, " ", min_flt); seq_put_decimal_ull(m, " ", cmin_flt); seq_put_decimal_ull(m, " ", maj_flt); seq_put_decimal_ull(m, " ", cmaj_flt); seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime)); seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime)); seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime)); seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime)); seq_put_decimal_ll(m, " ", priority); seq_put_decimal_ll(m, " ", nice); seq_put_decimal_ll(m, " ", num_threads); seq_put_decimal_ull(m, " ", 0); seq_put_decimal_ull(m, " ", start_time); seq_put_decimal_ull(m, " ", vsize); seq_put_decimal_ull(m, " ", mm ? get_mm_rss(mm) : 0); seq_put_decimal_ull(m, " ", rsslim); seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->start_code : 1) : 0); seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->end_code : 1) : 0); seq_put_decimal_ull(m, " ", (permitted && mm) ? mm->start_stack : 0); seq_put_decimal_ull(m, " ", esp); seq_put_decimal_ull(m, " ", eip); /* The signal information here is obsolete. * It must be decimal for Linux 2.0 compatibility. * Use /proc/#/status for real-time signals. */ seq_put_decimal_ull(m, " ", task->pending.signal.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, " ", task->blocked.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, " ", sigign.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, " ", sigcatch.sig[0] & 0x7fffffffUL); /* * We used to output the absolute kernel address, but that's an * information leak - so instead we show a 0/1 flag here, to signal * to user-space whether there's a wchan field in /proc/PID/wchan. * * This works with older implementations of procps as well. */ seq_put_decimal_ull(m, " ", wchan); seq_put_decimal_ull(m, " ", 0); seq_put_decimal_ull(m, " ", 0); seq_put_decimal_ll(m, " ", task->exit_signal); seq_put_decimal_ll(m, " ", task_cpu(task)); seq_put_decimal_ull(m, " ", task->rt_priority); seq_put_decimal_ull(m, " ", task->policy); seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task)); seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime)); seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime)); if (mm && permitted) { seq_put_decimal_ull(m, " ", mm->start_data); seq_put_decimal_ull(m, " ", mm->end_data); seq_put_decimal_ull(m, " ", mm->start_brk); seq_put_decimal_ull(m, " ", mm->arg_start); seq_put_decimal_ull(m, " ", mm->arg_end); seq_put_decimal_ull(m, " ", mm->env_start); seq_put_decimal_ull(m, " ", mm->env_end); } else seq_puts(m, " 0 0 0 0 0 0 0"); if (permitted) seq_put_decimal_ll(m, " ", exit_code); else seq_puts(m, " 0"); seq_putc(m, '\n'); if (mm) mmput(mm); return 0; } int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_task_stat(m, ns, pid, task, 0); } int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_task_stat(m, ns, pid, task, 1); } int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm = get_task_mm(task); if (mm) { unsigned long size; unsigned long resident = 0; unsigned long shared = 0; unsigned long text = 0; unsigned long data = 0; size = task_statm(mm, &shared, &text, &data, &resident); mmput(mm); /* * For quick read, open code by putting numbers directly * expected format is * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n", * size, resident, shared, text, data); */ seq_put_decimal_ull(m, "", size); seq_put_decimal_ull(m, " ", resident); seq_put_decimal_ull(m, " ", shared); seq_put_decimal_ull(m, " ", text); seq_put_decimal_ull(m, " ", 0); seq_put_decimal_ull(m, " ", data); seq_put_decimal_ull(m, " ", 0); seq_putc(m, '\n'); } else { seq_write(m, "0 0 0 0 0 0 0\n", 14); } return 0; } #ifdef CONFIG_PROC_CHILDREN static struct pid * get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos) { struct task_struct *start, *task; struct pid *pid = NULL; read_lock(&tasklist_lock); start = pid_task(proc_pid(inode), PIDTYPE_PID); if (!start) goto out; /* * Lets try to continue searching first, this gives * us significant speedup on children-rich processes. */ if (pid_prev) { task = pid_task(pid_prev, PIDTYPE_PID); if (task && task->real_parent == start && !(list_empty(&task->sibling))) { if (list_is_last(&task->sibling, &start->children)) goto out; task = list_first_entry(&task->sibling, struct task_struct, sibling); pid = get_pid(task_pid(task)); goto out; } } /* * Slow search case. * * We might miss some children here if children * are exited while we were not holding the lock, * but it was never promised to be accurate that * much. * * "Just suppose that the parent sleeps, but N children * exit after we printed their tids. Now the slow paths * skips N extra children, we miss N tasks." (c) * * So one need to stop or freeze the leader and all * its children to get a precise result. */ list_for_each_entry(task, &start->children, sibling) { if (pos-- == 0) { pid = get_pid(task_pid(task)); break; } } out: read_unlock(&tasklist_lock); return pid; } static int children_seq_show(struct seq_file *seq, void *v) { struct inode *inode = file_inode(seq->file); seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode->i_sb))); return 0; } static void *children_seq_start(struct seq_file *seq, loff_t *pos) { return get_children_pid(file_inode(seq->file), NULL, *pos); } static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct pid *pid; pid = get_children_pid(file_inode(seq->file), v, *pos + 1); put_pid(v); ++*pos; return pid; } static void children_seq_stop(struct seq_file *seq, void *v) { put_pid(v); } static const struct seq_operations children_seq_ops = { .start = children_seq_start, .next = children_seq_next, .stop = children_seq_stop, .show = children_seq_show, }; static int children_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &children_seq_ops); } const struct file_operations proc_tid_children_operations = { .open = children_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; #endif /* CONFIG_PROC_CHILDREN */ |
| 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Functions to manage eBPF programs attached to cgroups * * Copyright (c) 2016 Daniel Mack */ #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/cgroup.h> #include <linux/filter.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/string.h> #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_lsm.h> #include <linux/bpf_verifier.h> #include <net/sock.h> #include <net/bpf_sk_storage.h> #include "../cgroup/cgroup-internal.h" DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE); EXPORT_SYMBOL(cgroup_bpf_enabled_key); /* * cgroup bpf destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup bpf * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. */ static struct workqueue_struct *cgroup_bpf_destroy_wq; static int __init cgroup_bpf_wq_init(void) { cgroup_bpf_destroy_wq = alloc_workqueue("cgroup_bpf_destroy", 0, 1); if (!cgroup_bpf_destroy_wq) panic("Failed to alloc workqueue for cgroup bpf destroy.\n"); return 0; } core_initcall(cgroup_bpf_wq_init); /* __always_inline is necessary to prevent indirect call through run_prog * function pointer. */ static __always_inline int bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, enum cgroup_bpf_attach_type atype, const void *ctx, bpf_prog_run_fn run_prog, int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; u32 func_ret; run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(cgrp->effective[atype]); item = &array->items[0]; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); if (ret_flags) { *(ret_flags) |= (func_ret >> 1); func_ret &= 1; } if (!func_ret && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); return run_ctx.retval; } unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, const struct bpf_insn *insn) { const struct bpf_prog *shim_prog; struct sock *sk; struct cgroup *cgrp; int ret = 0; u64 *args; args = (u64 *)ctx; sk = (void *)(unsigned long)args[0]; /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); if (likely(cgrp)) ret = bpf_prog_run_array_cg(&cgrp->bpf, shim_prog->aux->cgroup_atype, ctx, bpf_prog_run, 0, NULL); return ret; } unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, const struct bpf_insn *insn) { const struct bpf_prog *shim_prog; struct socket *sock; struct cgroup *cgrp; int ret = 0; u64 *args; args = (u64 *)ctx; sock = (void *)(unsigned long)args[0]; /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); cgrp = sock_cgroup_ptr(&sock->sk->sk_cgrp_data); if (likely(cgrp)) ret = bpf_prog_run_array_cg(&cgrp->bpf, shim_prog->aux->cgroup_atype, ctx, bpf_prog_run, 0, NULL); return ret; } unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, const struct bpf_insn *insn) { const struct bpf_prog *shim_prog; struct cgroup *cgrp; int ret = 0; /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); /* We rely on trampoline's __bpf_prog_enter_lsm_cgroup to grab RCU read lock. */ cgrp = task_dfl_cgroup(current); if (likely(cgrp)) ret = bpf_prog_run_array_cg(&cgrp->bpf, shim_prog->aux->cgroup_atype, ctx, bpf_prog_run, 0, NULL); return ret; } #ifdef CONFIG_BPF_LSM struct cgroup_lsm_atype { u32 attach_btf_id; int refcnt; }; static struct cgroup_lsm_atype cgroup_lsm_atype[CGROUP_LSM_NUM]; static enum cgroup_bpf_attach_type bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) { int i; lockdep_assert_held(&cgroup_mutex); if (attach_type != BPF_LSM_CGROUP) return to_cgroup_bpf_attach_type(attach_type); for (i = 0; i < ARRAY_SIZE(cgroup_lsm_atype); i++) if (cgroup_lsm_atype[i].attach_btf_id == attach_btf_id) return CGROUP_LSM_START + i; for (i = 0; i < ARRAY_SIZE(cgroup_lsm_atype); i++) if (cgroup_lsm_atype[i].attach_btf_id == 0) return CGROUP_LSM_START + i; return -E2BIG; } void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) { int i = cgroup_atype - CGROUP_LSM_START; lockdep_assert_held(&cgroup_mutex); WARN_ON_ONCE(cgroup_lsm_atype[i].attach_btf_id && cgroup_lsm_atype[i].attach_btf_id != attach_btf_id); cgroup_lsm_atype[i].attach_btf_id = attach_btf_id; cgroup_lsm_atype[i].refcnt++; } void bpf_cgroup_atype_put(int cgroup_atype) { int i = cgroup_atype - CGROUP_LSM_START; cgroup_lock(); if (--cgroup_lsm_atype[i].refcnt <= 0) cgroup_lsm_atype[i].attach_btf_id = 0; WARN_ON_ONCE(cgroup_lsm_atype[i].refcnt < 0); cgroup_unlock(); } #else static enum cgroup_bpf_attach_type bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) { if (attach_type != BPF_LSM_CGROUP) return to_cgroup_bpf_attach_type(attach_type); return -EOPNOTSUPP; } #endif /* CONFIG_BPF_LSM */ void cgroup_bpf_offline(struct cgroup *cgrp) { cgroup_get(cgrp); percpu_ref_kill(&cgrp->bpf.refcnt); } static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[]) { enum bpf_cgroup_storage_type stype; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storages[stype]); } static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[], struct bpf_cgroup_storage *new_storages[], enum bpf_attach_type type, struct bpf_prog *prog, struct cgroup *cgrp) { enum bpf_cgroup_storage_type stype; struct bpf_cgroup_storage_key key; struct bpf_map *map; key.cgroup_inode_id = cgroup_id(cgrp); key.attach_type = type; for_each_cgroup_storage_type(stype) { map = prog->aux->cgroup_storage[stype]; if (!map) continue; storages[stype] = cgroup_storage_lookup((void *)map, &key, false); if (storages[stype]) continue; storages[stype] = bpf_cgroup_storage_alloc(prog, stype); if (IS_ERR(storages[stype])) { bpf_cgroup_storages_free(new_storages); return -ENOMEM; } new_storages[stype] = storages[stype]; } return 0; } static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[], struct bpf_cgroup_storage *src[]) { enum bpf_cgroup_storage_type stype; for_each_cgroup_storage_type(stype) dst[stype] = src[stype]; } static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[], struct cgroup *cgrp, enum bpf_attach_type attach_type) { enum bpf_cgroup_storage_type stype; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_link(storages[stype], cgrp, attach_type); } /* Called when bpf_cgroup_link is auto-detached from dying cgroup. * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It * doesn't free link memory, which will eventually be done by bpf_link's * release() callback, when its last FD is closed. */ static void bpf_cgroup_link_auto_detach(struct bpf_cgroup_link *link) { cgroup_put(link->cgroup); link->cgroup = NULL; } /** * cgroup_bpf_release() - put references of all bpf programs and * release all cgroup bpf data * @work: work structure embedded into the cgroup to modify */ static void cgroup_bpf_release(struct work_struct *work) { struct cgroup *p, *cgrp = container_of(work, struct cgroup, bpf.release_work); struct bpf_prog_array *old_array; struct list_head *storages = &cgrp->bpf.storages; struct bpf_cgroup_storage *storage, *stmp; unsigned int atype; cgroup_lock(); for (atype = 0; atype < ARRAY_SIZE(cgrp->bpf.progs); atype++) { struct hlist_head *progs = &cgrp->bpf.progs[atype]; struct bpf_prog_list *pl; struct hlist_node *pltmp; hlist_for_each_entry_safe(pl, pltmp, progs, node) { hlist_del(&pl->node); if (pl->prog) { if (pl->prog->expected_attach_type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(pl->prog); bpf_prog_put(pl->prog); } if (pl->link) { if (pl->link->link.prog->expected_attach_type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(pl->link->link.prog); bpf_cgroup_link_auto_detach(pl->link); } kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key[atype]); } old_array = rcu_dereference_protected( cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); bpf_prog_array_free(old_array); } list_for_each_entry_safe(storage, stmp, storages, list_cg) { bpf_cgroup_storage_unlink(storage); bpf_cgroup_storage_free(storage); } cgroup_unlock(); for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_put(p); percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } /** * cgroup_bpf_release_fn() - callback used to schedule releasing * of bpf cgroup data * @ref: percpu ref counter structure */ static void cgroup_bpf_release_fn(struct percpu_ref *ref) { struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt); INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release); queue_work(cgroup_bpf_destroy_wq, &cgrp->bpf.release_work); } /* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through * link or direct prog. */ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) { if (pl->prog) return pl->prog; if (pl->link) return pl->link->link.prog; return NULL; } /* count number of elements in the list. * it's slow but the list cannot be long */ static u32 prog_list_length(struct hlist_head *head) { struct bpf_prog_list *pl; u32 cnt = 0; hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; cnt++; } return cnt; } /* if parent has non-overridable prog attached, * disallow attaching new programs to the descendent cgroup. * if parent has overridable or multi-prog, allow attaching */ static bool hierarchy_allows_attach(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype) { struct cgroup *p; p = cgroup_parent(cgrp); if (!p) return true; do { u32 flags = p->bpf.flags[atype]; u32 cnt; if (flags & BPF_F_ALLOW_MULTI) return true; cnt = prog_list_length(&p->bpf.progs[atype]); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); p = cgroup_parent(p); } while (p); return true; } /* compute a chain of effective programs for a given cgroup: * start from the list of programs in this cgroup and add * all parent programs. * Note that parent's F_ALLOW_OVERRIDE-type program is yielding * to programs in this cgroup */ static int compute_effective_progs(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype, struct bpf_prog_array **array) { struct bpf_prog_array_item *item; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; int cnt = 0; /* count number of effective programs by walking parents */ do { if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) cnt += prog_list_length(&p->bpf.progs[atype]); p = cgroup_parent(p); } while (p); progs = bpf_prog_array_alloc(cnt, GFP_KERNEL); if (!progs) return -ENOMEM; /* populate the array with effective progs */ cnt = 0; p = cgrp; do { if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; item = &progs->items[cnt]; item->prog = prog_list_prog(pl); bpf_cgroup_storages_assign(item->cgroup_storage, pl->storage); cnt++; } } while ((p = cgroup_parent(p))); *array = progs; return 0; } static void activate_effective_progs(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype, struct bpf_prog_array *old_array) { old_array = rcu_replace_pointer(cgrp->bpf.effective[atype], old_array, lockdep_is_held(&cgroup_mutex)); /* free prog array after grace period, since __cgroup_bpf_run_*() * might be still walking the array */ bpf_prog_array_free(old_array); } /** * cgroup_bpf_inherit() - inherit effective programs from parent * @cgrp: the cgroup to modify */ int cgroup_bpf_inherit(struct cgroup *cgrp) { /* has to use marco instead of const int, since compiler thinks * that array below is variable length */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, GFP_KERNEL); if (ret) return ret; for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_get(p); for (i = 0; i < NR; i++) INIT_HLIST_HEAD(&cgrp->bpf.progs[i]); INIT_LIST_HEAD(&cgrp->bpf.storages); for (i = 0; i < NR; i++) if (compute_effective_progs(cgrp, i, &arrays[i])) goto cleanup; for (i = 0; i < NR; i++) activate_effective_progs(cgrp, i, arrays[i]); return 0; cleanup: for (i = 0; i < NR; i++) bpf_prog_array_free(arrays[i]); for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_put(p); percpu_ref_exit(&cgrp->bpf.refcnt); return -ENOMEM; } static int update_effective_progs(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype) { struct cgroup_subsys_state *css; int err; /* allocate and recompute effective prog arrays */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; err = compute_effective_progs(desc, atype, &desc->bpf.inactive); if (err) goto cleanup; } /* all allocations were successful. Activate all prog arrays */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) { if (unlikely(desc->bpf.inactive)) { bpf_prog_array_free(desc->bpf.inactive); desc->bpf.inactive = NULL; } continue; } activate_effective_progs(desc, atype, desc->bpf.inactive); desc->bpf.inactive = NULL; } return 0; cleanup: /* oom while computing effective. Free all computed effective arrays * since they were not activated */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); bpf_prog_array_free(desc->bpf.inactive); desc->bpf.inactive = NULL; } return err; } #define BPF_CGROUP_MAX_PROGS 64 static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs, struct bpf_prog *prog, struct bpf_cgroup_link *link, struct bpf_prog *replace_prog, bool allow_multi) { struct bpf_prog_list *pl; /* single-attach case */ if (!allow_multi) { if (hlist_empty(progs)) return NULL; return hlist_entry(progs->first, typeof(*pl), node); } hlist_for_each_entry(pl, progs, node) { if (prog && pl->prog == prog && prog != replace_prog) /* disallow attaching the same prog twice */ return ERR_PTR(-EINVAL); if (link && pl->link == link) /* disallow attaching the same link twice */ return ERR_PTR(-EINVAL); } /* direct prog multi-attach w/ replacement case */ if (replace_prog) { hlist_for_each_entry(pl, progs, node) { if (pl->prog == replace_prog) /* a match found */ return pl; } /* prog to replace not found for cgroup */ return ERR_PTR(-ENOENT); } return NULL; } /** * __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach * @link: A link to attach * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set * @type: Type of attach operation * @flags: Option flags * * Exactly one of @prog or @link can be non-null. * Must be called with cgroup_mutex held. */ static int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *replace_prog, struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags) { u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_prog *new_prog = prog ? : link->link.prog; enum cgroup_bpf_attach_type atype; struct bpf_prog_list *pl; struct hlist_head *progs; int err; if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI))) /* invalid combination */ return -EINVAL; if (link && (prog || replace_prog)) /* only either link or prog/replace_prog can be specified */ return -EINVAL; if (!!replace_prog != !!(flags & BPF_F_REPLACE)) /* replace_prog implies BPF_F_REPLACE, and vice versa */ return -EINVAL; atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; progs = &cgrp->bpf.progs[atype]; if (!hierarchy_allows_attach(cgrp, atype)) return -EPERM; if (!hlist_empty(progs) && cgrp->bpf.flags[atype] != saved_flags) /* Disallow attaching non-overridable on top * of existing overridable in this cgroup. * Disallow attaching multi-prog if overridable or none */ return -EPERM; if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; pl = find_attach_entry(progs, prog, link, replace_prog, flags & BPF_F_ALLOW_MULTI); if (IS_ERR(pl)) return PTR_ERR(pl); if (bpf_cgroup_storages_alloc(storage, new_storage, type, prog ? : link->link.prog, cgrp)) return -ENOMEM; if (pl) { old_prog = pl->prog; } else { struct hlist_node *last = NULL; pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { bpf_cgroup_storages_free(new_storage); return -ENOMEM; } if (hlist_empty(progs)) hlist_add_head(&pl->node, progs); else hlist_for_each(last, progs) { if (last->next) continue; hlist_add_behind(&pl->node, last); break; } } pl->prog = prog; pl->link = link; bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[atype] = saved_flags; if (type == BPF_LSM_CGROUP) { err = bpf_trampoline_link_cgroup_shim(new_prog, atype); if (err) goto cleanup; } err = update_effective_progs(cgrp, atype); if (err) goto cleanup_trampoline; if (old_prog) { if (type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); } else { static_branch_inc(&cgroup_bpf_enabled_key[atype]); } bpf_cgroup_storages_link(new_storage, cgrp, type); return 0; cleanup_trampoline: if (type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(new_prog); cleanup: if (old_prog) { pl->prog = old_prog; pl->link = NULL; } bpf_cgroup_storages_free(new_storage); if (!old_prog) { hlist_del(&pl->node); kfree(pl); } return err; } static int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *replace_prog, struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags) { int ret; cgroup_lock(); ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); cgroup_unlock(); return ret; } /* Swap updated BPF program for given link in effective program arrays across * all descendant cgroups. This function is guaranteed to succeed. */ static void replace_effective_prog(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype, struct bpf_cgroup_link *link) { struct bpf_prog_array_item *item; struct cgroup_subsys_state *css; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct hlist_head *head; struct cgroup *cg; int pos; css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; /* find position of link in effective progs array */ for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; head = &cg->bpf.progs[atype]; hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; if (pl->link == link) goto found; pos++; } } found: BUG_ON(!cg); progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); item = &progs->items[pos]; WRITE_ONCE(item->prog, link->link.prog); } } /** * __cgroup_bpf_replace() - Replace link's program and propagate the change * to descendants * @cgrp: The cgroup which descendants to traverse * @link: A link for which to replace BPF program * @new_prog: &struct bpf_prog for the target BPF program with its refcnt * incremented * * Must be called with cgroup_mutex held. */ static int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, struct bpf_prog *new_prog) { enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; struct bpf_prog_list *pl; struct hlist_head *progs; bool found = false; atype = bpf_cgroup_atype_find(link->type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; progs = &cgrp->bpf.progs[atype]; if (link->link.prog->type != new_prog->type) return -EINVAL; hlist_for_each_entry(pl, progs, node) { if (pl->link == link) { found = true; break; } } if (!found) return -ENOENT; old_prog = xchg(&link->link.prog, new_prog); replace_effective_prog(cgrp, atype, link); bpf_prog_put(old_prog); return 0; } static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_cgroup_link *cg_link; int ret; cg_link = container_of(link, struct bpf_cgroup_link, link); cgroup_lock(); /* link might have been auto-released by dying cgroup, so fail */ if (!cg_link->cgroup) { ret = -ENOLINK; goto out_unlock; } if (old_prog && link->prog != old_prog) { ret = -EPERM; goto out_unlock; } ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); out_unlock: cgroup_unlock(); return ret; } static struct bpf_prog_list *find_detach_entry(struct hlist_head *progs, struct bpf_prog *prog, struct bpf_cgroup_link *link, bool allow_multi) { struct bpf_prog_list *pl; if (!allow_multi) { if (hlist_empty(progs)) /* report error when trying to detach and nothing is attached */ return ERR_PTR(-ENOENT); /* to maintain backward compatibility NONE and OVERRIDE cgroups * allow detaching with invalid FD (prog==NULL) in legacy mode */ return hlist_entry(progs->first, typeof(*pl), node); } if (!prog && !link) /* to detach MULTI prog the user has to specify valid FD * of the program or link to be detached */ return ERR_PTR(-EINVAL); /* find the prog or link and detach it */ hlist_for_each_entry(pl, progs, node) { if (pl->prog == prog && pl->link == link) return pl; } return ERR_PTR(-ENOENT); } /** * purge_effective_progs() - After compute_effective_progs fails to alloc new * cgrp->bpf.inactive table we can recover by * recomputing the array in place. * * @cgrp: The cgroup which descendants to travers * @prog: A program to detach or NULL * @link: A link to detach or NULL * @atype: Type of detach operation */ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_cgroup_link *link, enum cgroup_bpf_attach_type atype) { struct cgroup_subsys_state *css; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct hlist_head *head; struct cgroup *cg; int pos; /* recompute effective prog array in place */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; /* find position of link or prog in effective progs array */ for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; head = &cg->bpf.progs[atype]; hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; if (pl->prog == prog && pl->link == link) goto found; pos++; } } /* no link or prog match, skip the cgroup of this layer */ continue; found: progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); /* Remove the program from the array */ WARN_ONCE(bpf_prog_array_delete_safe_at(progs, pos), "Failed to purge a prog from array at index %d", pos); } } /** * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to detach or NULL * @link: A link to detach or NULL * @type: Type of detach operation * * At most one of @prog or @link can be non-NULL. * Must be called with cgroup_mutex held. */ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_cgroup_link *link, enum bpf_attach_type type) { enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; struct bpf_prog_list *pl; struct hlist_head *progs; u32 attach_btf_id = 0; u32 flags; if (prog) attach_btf_id = prog->aux->attach_btf_id; if (link) attach_btf_id = link->link.prog->aux->attach_btf_id; atype = bpf_cgroup_atype_find(type, attach_btf_id); if (atype < 0) return -EINVAL; progs = &cgrp->bpf.progs[atype]; flags = cgrp->bpf.flags[atype]; if (prog && link) /* only one of prog or link can be specified */ return -EINVAL; pl = find_detach_entry(progs, prog, link, flags & BPF_F_ALLOW_MULTI); if (IS_ERR(pl)) return PTR_ERR(pl); /* mark it deleted, so it's ignored while recomputing effective */ old_prog = pl->prog; pl->prog = NULL; pl->link = NULL; if (update_effective_progs(cgrp, atype)) { /* if update effective array failed replace the prog with a dummy prog*/ pl->prog = old_prog; pl->link = link; purge_effective_progs(cgrp, old_prog, link, atype); } /* now can actually delete it from this cgroup list */ hlist_del(&pl->node); kfree(pl); if (hlist_empty(progs)) /* last program was detached, reset flags to zero */ cgrp->bpf.flags[atype] = 0; if (old_prog) { if (type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); } static_branch_dec(&cgroup_bpf_enabled_key[atype]); return 0; } static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type) { int ret; cgroup_lock(); ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); cgroup_unlock(); return ret; } /* Must be called with cgroup_mutex held to avoid races. */ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr) { __u32 __user *prog_attach_flags = u64_to_user_ptr(attr->query.prog_attach_flags); bool effective_query = attr->query.query_flags & BPF_F_QUERY_EFFECTIVE; __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); enum bpf_attach_type type = attr->query.attach_type; enum cgroup_bpf_attach_type from_atype, to_atype; enum cgroup_bpf_attach_type atype; struct bpf_prog_array *effective; int cnt, ret = 0, i; int total_cnt = 0; u32 flags; if (effective_query && prog_attach_flags) return -EINVAL; if (type == BPF_LSM_CGROUP) { if (!effective_query && attr->query.prog_cnt && prog_ids && !prog_attach_flags) return -EINVAL; from_atype = CGROUP_LSM_START; to_atype = CGROUP_LSM_END; flags = 0; } else { from_atype = to_cgroup_bpf_attach_type(type); if (from_atype < 0) return -EINVAL; to_atype = from_atype; flags = cgrp->bpf.flags[from_atype]; } for (atype = from_atype; atype <= to_atype; atype++) { if (effective_query) { effective = rcu_dereference_protected(cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); total_cnt += bpf_prog_array_length(effective); } else { total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); } } /* always output uattr->query.attach_flags as 0 during effective query */ flags = effective_query ? 0 : flags; if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt))) return -EFAULT; if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt) /* return early if user requested only program count + flags */ return 0; if (attr->query.prog_cnt < total_cnt) { total_cnt = attr->query.prog_cnt; ret = -ENOSPC; } for (atype = from_atype; atype <= to_atype && total_cnt; atype++) { if (effective_query) { effective = rcu_dereference_protected(cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); cnt = min_t(int, bpf_prog_array_length(effective), total_cnt); ret = bpf_prog_array_copy_to_user(effective, prog_ids, cnt); } else { struct hlist_head *progs; struct bpf_prog_list *pl; struct bpf_prog *prog; u32 id; progs = &cgrp->bpf.progs[atype]; cnt = min_t(int, prog_list_length(progs), total_cnt); i = 0; hlist_for_each_entry(pl, progs, node) { prog = prog_list_prog(pl); id = prog->aux->id; if (copy_to_user(prog_ids + i, &id, sizeof(id))) return -EFAULT; if (++i == cnt) break; } if (prog_attach_flags) { flags = cgrp->bpf.flags[atype]; for (i = 0; i < cnt; i++) if (copy_to_user(prog_attach_flags + i, &flags, sizeof(flags))) return -EFAULT; prog_attach_flags += cnt; } } prog_ids += cnt; total_cnt -= cnt; } return ret; } static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr) { int ret; cgroup_lock(); ret = __cgroup_bpf_query(cgrp, attr, uattr); cgroup_unlock(); return ret; } int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { struct bpf_prog *replace_prog = NULL; struct cgroup *cgrp; int ret; cgrp = cgroup_get_from_fd(attr->target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); if ((attr->attach_flags & BPF_F_ALLOW_MULTI) && (attr->attach_flags & BPF_F_REPLACE)) { replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype); if (IS_ERR(replace_prog)) { cgroup_put(cgrp); return PTR_ERR(replace_prog); } } ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL, attr->attach_type, attr->attach_flags); if (replace_prog) bpf_prog_put(replace_prog); cgroup_put(cgrp); return ret; } int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { struct bpf_prog *prog; struct cgroup *cgrp; int ret; cgrp = cgroup_get_from_fd(attr->target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) prog = NULL; ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type); if (prog) bpf_prog_put(prog); cgroup_put(cgrp); return ret; } static void bpf_cgroup_link_release(struct bpf_link *link) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); struct cgroup *cg; /* link might have been auto-detached by dying cgroup already, * in that case our work is done here */ if (!cg_link->cgroup) return; cgroup_lock(); /* re-check cgroup under lock again */ if (!cg_link->cgroup) { cgroup_unlock(); return; } WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link, cg_link->type)); if (cg_link->type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog); cg = cg_link->cgroup; cg_link->cgroup = NULL; cgroup_unlock(); cgroup_put(cg); } static void bpf_cgroup_link_dealloc(struct bpf_link *link) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); kfree(cg_link); } static int bpf_cgroup_link_detach(struct bpf_link *link) { bpf_cgroup_link_release(link); return 0; } static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); cgroup_unlock(); seq_printf(seq, "cgroup_id:\t%llu\n" "attach_type:\t%d\n", cg_id, cg_link->type); } static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); cgroup_unlock(); info->cgroup.cgroup_id = cg_id; info->cgroup.attach_type = cg_link->type; return 0; } static const struct bpf_link_ops bpf_cgroup_link_lops = { .release = bpf_cgroup_link_release, .dealloc = bpf_cgroup_link_dealloc, .detach = bpf_cgroup_link_detach, .update_prog = cgroup_bpf_replace, .show_fdinfo = bpf_cgroup_link_show_fdinfo, .fill_link_info = bpf_cgroup_link_fill_link_info, }; int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct bpf_cgroup_link *link; struct cgroup *cgrp; int err; if (attr->link_create.flags) return -EINVAL; cgrp = cgroup_get_from_fd(attr->link_create.target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_cgroup; } bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops, prog); link->cgroup = cgrp; link->type = attr->link_create.attach_type; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_cgroup; } err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, BPF_F_ALLOW_MULTI); if (err) { bpf_link_cleanup(&link_primer); goto out_put_cgroup; } return bpf_link_settle(&link_primer); out_put_cgroup: cgroup_put(cgrp); return err; } int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { struct cgroup *cgrp; int ret; cgrp = cgroup_get_from_fd(attr->query.target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); ret = cgroup_bpf_query(cgrp, attr, uattr); cgroup_put(cgrp); return ret; } /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic * @skb: The skb that is being sent or received * @atype: The type of program to be executed * * If no socket is passed, or the socket is not of type INET or INET6, * this function does nothing and returns 0. * * The program type passed in via @type must be suitable for network * filtering. No further check is performed to assert that. * * For egress packets, this function can return: * NET_XMIT_SUCCESS (0) - continue with packet output * NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr * NET_XMIT_CN (2) - continue with packet output and notify TCP * to call cwr * -err - drop packet * * For ingress packets, this function will return -EPERM if any * attached program was found and if it returned != 1 during execution. * Otherwise 0 is returned. */ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype) { unsigned int offset = -skb_network_offset(skb); struct sock *save_sk; void *saved_data_end; struct cgroup *cgrp; int ret; if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); save_sk = skb->sk; skb->sk = sk; __skb_push(skb, offset); /* compute pointers for the bpf prog */ bpf_compute_and_save_data_end(skb, &saved_data_end); if (atype == CGROUP_INET_EGRESS) { u32 flags = 0; bool cn; ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb, __bpf_prog_run_save_cb, 0, &flags); /* Return values of CGROUP EGRESS BPF programs are: * 0: drop packet * 1: keep packet * 2: drop packet and cn * 3: keep packet and cn * * The returned value is then converted to one of the NET_XMIT * or an error code that is then interpreted as drop packet * (and no cn): * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn * 3: -err skb should be dropped */ cn = flags & BPF_RET_SET_CN; if (ret && !IS_ERR_VALUE((long)ret)) ret = -EFAULT; if (!ret) ret = (cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); else ret = (cn ? NET_XMIT_DROP : ret); } else { ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb, __bpf_prog_run_save_cb, 0, NULL); if (ret && !IS_ERR_VALUE((long)ret)) ret = -EFAULT; } bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); /** * __cgroup_bpf_run_filter_sk() - Run a program on a sock * @sk: sock structure to manipulate * @atype: The type of program to be executed * * socket is passed is expected to be of type INET or INET6. * * The program type passed in via @type must be suitable for sock * filtering. No further check is performed to assert that. * * This function will return %-EPERM if any if an attached program was found * and if it returned != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0, NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); /** * __cgroup_bpf_run_filter_sock_addr() - Run a program on a sock and * provided by user sockaddr * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user * @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is * read-only for AF_INET[6] uaddr but can be modified for AF_UNIX * uaddr. * @atype: The type of program to be executed * @t_ctx: Pointer to attach type specific context * @flags: Pointer to u32 which contains higher bits of BPF program * return value (OR'ed together). * * socket is expected to be of type INET, INET6 or UNIX. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags) { struct bpf_sock_addr_kern ctx = { .sk = sk, .uaddr = uaddr, .t_ctx = t_ctx, }; struct sockaddr_storage unspec; struct cgroup *cgrp; int ret; /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). */ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 && sk->sk_family != AF_UNIX) return 0; if (!ctx.uaddr) { memset(&unspec, 0, sizeof(unspec)); ctx.uaddr = (struct sockaddr *)&unspec; ctx.uaddrlen = 0; } else { ctx.uaddrlen = *uaddrlen; } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, flags); if (!ret && uaddr) *uaddrlen = ctx.uaddrlen; return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); /** * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock * @sk: socket to get cgroup from * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains * sk with connection information (IP addresses, etc.) May not contain * cgroup info if it is a req sock. * @atype: The type of program to be executed * * socket passed is expected to be of type INET or INET6. * * The program type passed in via @type must be suitable for sock_ops * filtering. No further check is performed to assert that. * * This function will return %-EPERM if any if an attached program was found * and if it returned != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return bpf_prog_run_array_cg(&cgrp->bpf, atype, sock_ops, bpf_prog_run, 0, NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp; struct bpf_cgroup_dev_ctx ctx = { .access_type = (access << 16) | dev_type, .major = major, .minor = minor, }; int ret; rcu_read_lock(); cgrp = task_dfl_cgroup(current); ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, NULL); rcu_read_unlock(); return ret; } BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { /* flags argument is not used now, * but provides an ability to extend the API. * verifier checks that its value is correct. */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); struct bpf_cgroup_storage *storage; struct bpf_cg_run_ctx *ctx; void *ptr; /* get current cgroup storage from BPF run context */ ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); storage = ctx->prog_item->cgroup_storage[stype]; if (stype == BPF_CGROUP_STORAGE_SHARED) ptr = &READ_ONCE(storage->buf)->data[0]; else ptr = this_cpu_ptr(storage->percpu_buf); return (unsigned long)ptr; } const struct bpf_func_proto bpf_get_local_storage_proto = { .func = bpf_get_local_storage, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_0(bpf_get_retval) { struct bpf_cg_run_ctx *ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); return ctx->retval; } const struct bpf_func_proto bpf_get_retval_proto = { .func = bpf_get_retval, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_set_retval, int, retval) { struct bpf_cg_run_ctx *ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); ctx->retval = retval; return 0; } const struct bpf_func_proto bpf_set_retval_proto = { .func = bpf_set_retval, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; static const struct bpf_func_proto * cgroup_dev_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; func_proto = cgroup_current_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool cgroup_dev_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 (type == BPF_WRITE) return false; if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; switch (off) { case bpf_ctx_range(struct bpf_cgroup_dev_ctx, access_type): bpf_ctx_record_field_size(info, size_default); if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; break; default: if (size != size_default) return false; } return true; } const struct bpf_prog_ops cg_dev_prog_ops = { }; const struct bpf_verifier_ops cg_dev_verifier_ops = { .get_func_proto = cgroup_dev_func_proto, .is_valid_access = cgroup_dev_is_valid_access, }; /** * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl * * @head: sysctl table header * @table: sysctl table * @write: sysctl is being read (= 0) or written (= 1) * @buf: pointer to buffer (in and out) * @pcount: value-result argument: value is size of buffer pointed to by @buf, * result is size of @new_buf if program set new value, initial value * otherwise * @ppos: value-result argument: value is position at which read from or write * to sysctl is happening, result is new position if program overrode it, * initial value otherwise * @atype: type of program to be executed * * Program is run when sysctl is being accessed, either read or written, and * can allow or deny such access. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases 0 is returned. */ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, const struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, enum cgroup_bpf_attach_type atype) { struct bpf_sysctl_kern ctx = { .head = head, .table = table, .write = write, .ppos = ppos, .cur_val = NULL, .cur_len = PAGE_SIZE, .new_val = NULL, .new_len = 0, .new_updated = 0, }; struct cgroup *cgrp; loff_t pos = 0; int ret; ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL); if (!ctx.cur_val || table->proc_handler(table, 0, ctx.cur_val, &ctx.cur_len, &pos)) { /* Let BPF program decide how to proceed. */ ctx.cur_len = 0; } if (write && *buf && *pcount) { /* BPF program should be able to override new value with a * buffer bigger than provided by user. */ ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL); ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount); if (ctx.new_val) { memcpy(ctx.new_val, *buf, ctx.new_len); } else { /* Let BPF program decide how to proceed. */ ctx.new_len = 0; } } rcu_read_lock(); cgrp = task_dfl_cgroup(current); ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, NULL); rcu_read_unlock(); kfree(ctx.cur_val); if (ret == 1 && ctx.new_updated) { kfree(*buf); *buf = ctx.new_val; *pcount = ctx.new_len; } else { kfree(ctx.new_val); } return ret; } #ifdef CONFIG_NET static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen, struct bpf_sockopt_buf *buf) { if (unlikely(max_optlen < 0)) return -EINVAL; if (unlikely(max_optlen > PAGE_SIZE)) { /* We don't expose optvals that are greater than PAGE_SIZE * to the BPF program. */ max_optlen = PAGE_SIZE; } if (max_optlen <= sizeof(buf->data)) { /* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE * bytes avoid the cost of kzalloc. */ ctx->optval = buf->data; ctx->optval_end = ctx->optval + max_optlen; return max_optlen; } ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; return max_optlen; } static void sockopt_free_buf(struct bpf_sockopt_kern *ctx, struct bpf_sockopt_buf *buf) { if (ctx->optval == buf->data) return; kfree(ctx->optval); } static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx, struct bpf_sockopt_buf *buf) { return ctx->optval != buf->data; } int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, int *optname, sockptr_t optval, int *optlen, char **kernel_optval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = *level, .optname = *optname, }; int ret, max_optlen; /* Allocate a bit more than the initial user buffer for * BPF program. The canonical use case is overriding * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic). */ max_optlen = max_t(int, 16, *optlen); max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; ctx.optlen = *optlen; if (copy_from_sockptr(ctx.optval, optval, min(*optlen, max_optlen))) { ret = -EFAULT; goto out; } lock_sock(sk); ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_SETSOCKOPT, &ctx, bpf_prog_run, 0, NULL); release_sock(sk); if (ret) goto out; if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ ret = 1; } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ if (*optlen > PAGE_SIZE && ctx.optlen >= 0) { pr_info_once("bpf setsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", ctx.optlen, max_optlen); ret = 0; goto out; } ret = -EFAULT; } else { /* optlen within bounds, run kernel handler */ ret = 0; /* export any potential modifications */ *level = ctx.level; *optname = ctx.optname; /* optlen == 0 from BPF indicates that we should * use original userspace data. */ if (ctx.optlen != 0) { *optlen = ctx.optlen; /* We've used bpf_sockopt_kern->buf as an intermediary * storage, but the BPF program indicates that we need * to pass this data to the kernel setsockopt handler. * No way to export on-stack buf, have to allocate a * new buffer. */ if (!sockopt_buf_allocated(&ctx, &buf)) { void *p = kmalloc(ctx.optlen, GFP_USER); if (!p) { ret = -ENOMEM; goto out; } memcpy(p, ctx.optval, ctx.optlen); *kernel_optval = p; } else { *kernel_optval = ctx.optval; } /* export and don't free sockopt buf */ return 0; } } out: sockopt_free_buf(&ctx, &buf); return ret; } int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen, int max_optlen, int retval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = level, .optname = optname, .current_task = current, }; int orig_optlen; int ret; orig_optlen = max_optlen; ctx.optlen = max_optlen; max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back * into our temporary buffer. Set optlen to the * one that kernel returned as well to let * BPF programs inspect the value. */ if (copy_from_sockptr(&ctx.optlen, optlen, sizeof(ctx.optlen))) { ret = -EFAULT; goto out; } if (ctx.optlen < 0) { ret = -EFAULT; goto out; } orig_optlen = ctx.optlen; if (copy_from_sockptr(ctx.optval, optval, min(ctx.optlen, max_optlen))) { ret = -EFAULT; goto out; } } lock_sock(sk); ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, &ctx, bpf_prog_run, retval, NULL); release_sock(sk); if (ret < 0) goto out; if (!sockptr_is_null(optval) && (ctx.optlen > max_optlen || ctx.optlen < 0)) { if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) { pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", ctx.optlen, max_optlen); ret = retval; goto out; } ret = -EFAULT; goto out; } if (ctx.optlen != 0) { if (!sockptr_is_null(optval) && copy_to_sockptr(optval, ctx.optval, ctx.optlen)) { ret = -EFAULT; goto out; } if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) { ret = -EFAULT; goto out; } } out: sockopt_free_buf(&ctx, &buf); return ret; } int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, int optname, void *optval, int *optlen, int retval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_sockopt_kern ctx = { .sk = sk, .level = level, .optname = optname, .optlen = *optlen, .optval = optval, .optval_end = optval + *optlen, .current_task = current, }; int ret; /* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy * user data back into BPF buffer when reval != 0. This is * done as an optimization to avoid extra copy, assuming * kernel won't populate the data in case of an error. * Here we always pass the data and memset() should * be called if that data shouldn't be "exported". */ ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, &ctx, bpf_prog_run, retval, NULL); if (ret < 0) return ret; if (ctx.optlen > *optlen) return -EFAULT; /* BPF programs can shrink the buffer, export the modifications. */ if (ctx.optlen != 0) *optlen = ctx.optlen; return ret; } #endif static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, size_t *lenp) { ssize_t tmp_ret = 0, ret; if (dir->header.parent) { tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp); if (tmp_ret < 0) return tmp_ret; } ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp); if (ret < 0) return ret; *bufp += ret; *lenp -= ret; ret += tmp_ret; /* Avoid leading slash. */ if (!ret) return ret; tmp_ret = strscpy(*bufp, "/", *lenp); if (tmp_ret < 0) return tmp_ret; *bufp += tmp_ret; *lenp -= tmp_ret; return ret + tmp_ret; } BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf, size_t, buf_len, u64, flags) { ssize_t tmp_ret = 0, ret; if (!buf) return -EINVAL; if (!(flags & BPF_F_SYSCTL_BASE_NAME)) { if (!ctx->head) return -EINVAL; tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len); if (tmp_ret < 0) return tmp_ret; } ret = strscpy(buf, ctx->table->procname, buf_len); return ret < 0 ? ret : tmp_ret + ret; } static const struct bpf_func_proto bpf_sysctl_get_name_proto = { .func = bpf_sysctl_get_name, .gpl_only = false, .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 int copy_sysctl_value(char *dst, size_t dst_len, char *src, size_t src_len) { if (!dst) return -EINVAL; if (!dst_len) return -E2BIG; if (!src || !src_len) { memset(dst, 0, dst_len); return -EINVAL; } memcpy(dst, src, min(dst_len, src_len)); if (dst_len > src_len) { memset(dst + src_len, '\0', dst_len - src_len); return src_len; } dst[dst_len - 1] = '\0'; return -E2BIG; } BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx, char *, buf, size_t, buf_len) { return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len); } static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = { .func = bpf_sysctl_get_current_value, .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, }; BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf, size_t, buf_len) { if (!ctx->write) { if (buf && buf_len) memset(buf, '\0', buf_len); return -EINVAL; } return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len); } static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = { .func = bpf_sysctl_get_new_value, .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, }; BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx, const char *, buf, size_t, buf_len) { if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len) return -EINVAL; if (buf_len > PAGE_SIZE - 1) return -E2BIG; memcpy(ctx->new_val, buf, buf_len); ctx->new_len = buf_len; ctx->new_updated = 1; return 0; } static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = { .func = bpf_sysctl_set_new_value, .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 * sysctl_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; func_proto = cgroup_current_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; case BPF_FUNC_sysctl_get_current_value: return &bpf_sysctl_get_current_value_proto; case BPF_FUNC_sysctl_get_new_value: return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool sysctl_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 + size > sizeof(struct bpf_sysctl) || off % size) return false; switch (off) { case bpf_ctx_range(struct bpf_sysctl, write): if (type != BPF_READ) return false; bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sysctl, file_pos): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); } else { return size == size_default; } default: return false; } } static u32 sysctl_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; u32 read_size; switch (si->off) { case offsetof(struct bpf_sysctl, write): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sysctl_kern, write, sizeof_field(struct bpf_sysctl_kern, write), target_size)); break; case offsetof(struct bpf_sysctl, file_pos): /* ppos is a pointer so it should be accessed via indirect * loads and stores. Also for stores additional temporary * register is used since neither src_reg nor dst_reg can be * overridden. */ if (type == BPF_WRITE) { int treg = BPF_REG_9; if (si->src_reg == treg || si->dst_reg == treg) --treg; if (si->src_reg == treg || si->dst_reg == treg) --treg; *insn++ = BPF_STX_MEM( BPF_DW, si->dst_reg, treg, offsetof(struct bpf_sysctl_kern, tmp_reg)); *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); *insn++ = BPF_RAW_INSN( BPF_CLASS(si->code) | BPF_MEM | BPF_SIZEOF(u32), treg, si->src_reg, bpf_ctx_narrow_access_offset( 0, sizeof(u32), sizeof(loff_t)), si->imm); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); } else { *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), si->dst_reg, si->src_reg, offsetof(struct bpf_sysctl_kern, ppos)); read_size = bpf_size_to_bytes(BPF_SIZE(si->code)); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->dst_reg, bpf_ctx_narrow_access_offset( 0, read_size, sizeof(loff_t))); } *target_size = sizeof(u32); break; } return insn - insn_buf; } const struct bpf_verifier_ops cg_sysctl_verifier_ops = { .get_func_proto = sysctl_func_proto, .is_valid_access = sysctl_is_valid_access, .convert_ctx_access = sysctl_convert_ctx_access, }; const struct bpf_prog_ops cg_sysctl_prog_ops = { }; #ifdef CONFIG_NET BPF_CALL_1(bpf_get_netns_cookie_sockopt, struct bpf_sockopt_kern *, ctx) { const struct net *net = ctx ? sock_net(ctx->sk) : &init_net; return net->net_cookie; } static const struct bpf_func_proto bpf_get_netns_cookie_sockopt_proto = { .func = bpf_get_netns_cookie_sockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; #endif static const struct bpf_func_proto * cg_sockopt_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; func_proto = cgroup_current_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sockopt_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_setsockopt: if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT) return &bpf_sk_setsockopt_proto; return NULL; case BPF_FUNC_getsockopt: if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT) return &bpf_sk_getsockopt_proto; return NULL; #endif #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool cg_sockopt_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_sockopt)) return false; if (off % size != 0) return false; if (type == BPF_WRITE) { switch (off) { case offsetof(struct bpf_sockopt, retval): if (size != size_default) return false; return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; case offsetof(struct bpf_sockopt, optname): fallthrough; case offsetof(struct bpf_sockopt, level): if (size != size_default) return false; return prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT; case offsetof(struct bpf_sockopt, optlen): return size == size_default; default: return false; } } switch (off) { case offsetof(struct bpf_sockopt, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case offsetof(struct bpf_sockopt, optval): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; case offsetof(struct bpf_sockopt, optval_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; case offsetof(struct bpf_sockopt, retval): if (size != size_default) return false; return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; default: if (size != size_default) return false; break; } return true; } #define CG_SOCKOPT_READ_FIELD(F) \ BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sockopt_kern, F)) #define CG_SOCKOPT_WRITE_FIELD(F) \ BPF_RAW_INSN((BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F) | \ BPF_MEM | BPF_CLASS(si->code)), \ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sockopt_kern, F), \ si->imm) static u32 cg_sockopt_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_sockopt, sk): *insn++ = CG_SOCKOPT_READ_FIELD(sk); break; case offsetof(struct bpf_sockopt, level): if (type == BPF_WRITE) *insn++ = CG_SOCKOPT_WRITE_FIELD(level); else *insn++ = CG_SOCKOPT_READ_FIELD(level); break; case offsetof(struct bpf_sockopt, optname): if (type == BPF_WRITE) *insn++ = CG_SOCKOPT_WRITE_FIELD(optname); else *insn++ = CG_SOCKOPT_READ_FIELD(optname); break; case offsetof(struct bpf_sockopt, optlen): if (type == BPF_WRITE) *insn++ = CG_SOCKOPT_WRITE_FIELD(optlen); else *insn++ = CG_SOCKOPT_READ_FIELD(optlen); break; case offsetof(struct bpf_sockopt, retval): BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0); if (type == BPF_WRITE) { int treg = BPF_REG_9; if (si->src_reg == treg || si->dst_reg == treg) --treg; if (si->src_reg == treg || si->dst_reg == treg) --treg; *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg, offsetof(struct bpf_sockopt_kern, tmp_reg)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), treg, si->dst_reg, offsetof(struct bpf_sockopt_kern, current_task)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), treg, treg, offsetof(struct task_struct, bpf_ctx)); *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_MEM | BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), treg, si->src_reg, offsetof(struct bpf_cg_run_ctx, retval), si->imm); *insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sockopt_kern, tmp_reg)); } else { *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), si->dst_reg, si->src_reg, offsetof(struct bpf_sockopt_kern, current_task)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), si->dst_reg, si->dst_reg, offsetof(struct task_struct, bpf_ctx)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), si->dst_reg, si->dst_reg, offsetof(struct bpf_cg_run_ctx, retval)); } break; case offsetof(struct bpf_sockopt, optval): *insn++ = CG_SOCKOPT_READ_FIELD(optval); break; case offsetof(struct bpf_sockopt, optval_end): *insn++ = CG_SOCKOPT_READ_FIELD(optval_end); break; } return insn - insn_buf; } static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { /* Nothing to do for sockopt argument. The data is kzalloc'ated. */ return 0; } const struct bpf_verifier_ops cg_sockopt_verifier_ops = { .get_func_proto = cg_sockopt_func_proto, .is_valid_access = cg_sockopt_is_valid_access, .convert_ctx_access = cg_sockopt_convert_ctx_access, .gen_prologue = cg_sockopt_get_prologue, }; const struct bpf_prog_ops cg_sockopt_prog_ops = { }; /* Common helpers for cgroup hooks. */ const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_get_retval: switch (prog->expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: 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 NULL; default: return &bpf_get_retval_proto; } case BPF_FUNC_set_retval: switch (prog->expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: 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 NULL; default: return &bpf_set_retval_proto; } default: return NULL; } } /* Common helpers for cgroup hooks with valid process context. */ const struct bpf_func_proto * cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; #endif case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; default: return NULL; } } |
| 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 | /* SPDX-License-Identifier: GPL-2.0 * * IO cost model based controller. * * Copyright (C) 2019 Tejun Heo <tj@kernel.org> * Copyright (C) 2019 Andy Newell <newella@fb.com> * Copyright (C) 2019 Facebook * * One challenge of controlling IO resources is the lack of trivially * observable cost metric. This is distinguished from CPU and memory where * wallclock time and the number of bytes can serve as accurate enough * approximations. * * Bandwidth and iops are the most commonly used metrics for IO devices but * depending on the type and specifics of the device, different IO patterns * easily lead to multiple orders of magnitude variations rendering them * useless for the purpose of IO capacity distribution. While on-device * time, with a lot of clutches, could serve as a useful approximation for * non-queued rotational devices, this is no longer viable with modern * devices, even the rotational ones. * * While there is no cost metric we can trivially observe, it isn't a * complete mystery. For example, on a rotational device, seek cost * dominates while a contiguous transfer contributes a smaller amount * proportional to the size. If we can characterize at least the relative * costs of these different types of IOs, it should be possible to * implement a reasonable work-conserving proportional IO resource * distribution. * * 1. IO Cost Model * * IO cost model estimates the cost of an IO given its basic parameters and * history (e.g. the end sector of the last IO). The cost is measured in * device time. If a given IO is estimated to cost 10ms, the device should * be able to process ~100 of those IOs in a second. * * Currently, there's only one builtin cost model - linear. Each IO is * classified as sequential or random and given a base cost accordingly. * On top of that, a size cost proportional to the length of the IO is * added. While simple, this model captures the operational * characteristics of a wide varienty of devices well enough. Default * parameters for several different classes of devices are provided and the * parameters can be configured from userspace via * /sys/fs/cgroup/io.cost.model. * * If needed, tools/cgroup/iocost_coef_gen.py can be used to generate * device-specific coefficients. * * 2. Control Strategy * * The device virtual time (vtime) is used as the primary control metric. * The control strategy is composed of the following three parts. * * 2-1. Vtime Distribution * * When a cgroup becomes active in terms of IOs, its hierarchical share is * calculated. Please consider the following hierarchy where the numbers * inside parentheses denote the configured weights. * * root * / \ * A (w:100) B (w:300) * / \ * A0 (w:100) A1 (w:100) * * If B is idle and only A0 and A1 are actively issuing IOs, as the two are * of equal weight, each gets 50% share. If then B starts issuing IOs, B * gets 300/(100+300) or 75% share, and A0 and A1 equally splits the rest, * 12.5% each. The distribution mechanism only cares about these flattened * shares. They're called hweights (hierarchical weights) and always add * upto 1 (WEIGHT_ONE). * * A given cgroup's vtime runs slower in inverse proportion to its hweight. * For example, with 12.5% weight, A0's time runs 8 times slower (100/12.5) * against the device vtime - an IO which takes 10ms on the underlying * device is considered to take 80ms on A0. * * This constitutes the basis of IO capacity distribution. Each cgroup's * vtime is running at a rate determined by its hweight. A cgroup tracks * the vtime consumed by past IOs and can issue a new IO if doing so * wouldn't outrun the current device vtime. Otherwise, the IO is * suspended until the vtime has progressed enough to cover it. * * 2-2. Vrate Adjustment * * It's unrealistic to expect the cost model to be perfect. There are too * many devices and even on the same device the overall performance * fluctuates depending on numerous factors such as IO mixture and device * internal garbage collection. The controller needs to adapt dynamically. * * This is achieved by adjusting the overall IO rate according to how busy * the device is. If the device becomes overloaded, we're sending down too * many IOs and should generally slow down. If there are waiting issuers * but the device isn't saturated, we're issuing too few and should * generally speed up. * * To slow down, we lower the vrate - the rate at which the device vtime * passes compared to the wall clock. For example, if the vtime is running * at the vrate of 75%, all cgroups added up would only be able to issue * 750ms worth of IOs per second, and vice-versa for speeding up. * * Device business is determined using two criteria - rq wait and * completion latencies. * * When a device gets saturated, the on-device and then the request queues * fill up and a bio which is ready to be issued has to wait for a request * to become available. When this delay becomes noticeable, it's a clear * indication that the device is saturated and we lower the vrate. This * saturation signal is fairly conservative as it only triggers when both * hardware and software queues are filled up, and is used as the default * busy signal. * * As devices can have deep queues and be unfair in how the queued commands * are executed, solely depending on rq wait may not result in satisfactory * control quality. For a better control quality, completion latency QoS * parameters can be configured so that the device is considered saturated * if N'th percentile completion latency rises above the set point. * * The completion latency requirements are a function of both the * underlying device characteristics and the desired IO latency quality of * service. There is an inherent trade-off - the tighter the latency QoS, * the higher the bandwidth lossage. Latency QoS is disabled by default * and can be set through /sys/fs/cgroup/io.cost.qos. * * 2-3. Work Conservation * * Imagine two cgroups A and B with equal weights. A is issuing a small IO * periodically while B is sending out enough parallel IOs to saturate the * device on its own. Let's say A's usage amounts to 100ms worth of IO * cost per second, i.e., 10% of the device capacity. The naive * distribution of half and half would lead to 60% utilization of the * device, a significant reduction in the total amount of work done * compared to free-for-all competition. This is too high a cost to pay * for IO control. * * To conserve the total amount of work done, we keep track of how much * each active cgroup is actually using and yield part of its weight if * there are other cgroups which can make use of it. In the above case, * A's weight will be lowered so that it hovers above the actual usage and * B would be able to use the rest. * * As we don't want to penalize a cgroup for donating its weight, the * surplus weight adjustment factors in a margin and has an immediate * snapback mechanism in case the cgroup needs more IO vtime for itself. * * Note that adjusting down surplus weights has the same effects as * accelerating vtime for other cgroups and work conservation can also be * implemented by adjusting vrate dynamically. However, squaring who can * donate and should take back how much requires hweight propagations * anyway making it easier to implement and understand as a separate * mechanism. * * 3. Monitoring * * Instead of debugfs or other clumsy monitoring mechanisms, this * controller uses a drgn based monitoring script - * tools/cgroup/iocost_monitor.py. For details on drgn, please see * https://github.com/osandov/drgn. The output looks like the following. * * sdb RUN per=300ms cur_per=234.218:v203.695 busy= +1 vrate= 62.12% * active weight hweight% inflt% dbt delay usages% * test/a * 50/ 50 33.33/ 33.33 27.65 2 0*041 033:033:033 * test/b * 100/ 100 66.67/ 66.67 17.56 0 0*000 066:079:077 * * - per : Timer period * - cur_per : Internal wall and device vtime clock * - vrate : Device virtual time rate against wall clock * - weight : Surplus-adjusted and configured weights * - hweight : Surplus-adjusted and configured hierarchical weights * - inflt : The percentage of in-flight IO cost at the end of last period * - del_ms : Deferred issuer delay induction level and duration * - usages : Usage history */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/time64.h> #include <linux/parser.h> #include <linux/sched/signal.h> #include <asm/local.h> #include <asm/local64.h> #include "blk-rq-qos.h" #include "blk-stat.h" #include "blk-wbt.h" #include "blk-cgroup.h" #ifdef CONFIG_TRACEPOINTS /* copied from TRACE_CGROUP_PATH, see cgroup-internal.h */ #define TRACE_IOCG_PATH_LEN 1024 static DEFINE_SPINLOCK(trace_iocg_path_lock); static char trace_iocg_path[TRACE_IOCG_PATH_LEN]; #define TRACE_IOCG_PATH(type, iocg, ...) \ do { \ unsigned long flags; \ if (trace_iocost_##type##_enabled()) { \ spin_lock_irqsave(&trace_iocg_path_lock, flags); \ cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup, \ trace_iocg_path, TRACE_IOCG_PATH_LEN); \ trace_iocost_##type(iocg, trace_iocg_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_iocg_path_lock, flags); \ } \ } while (0) #else /* CONFIG_TRACE_POINTS */ #define TRACE_IOCG_PATH(type, iocg, ...) do { } while (0) #endif /* CONFIG_TRACE_POINTS */ enum { MILLION = 1000000, /* timer period is calculated from latency requirements, bound it */ MIN_PERIOD = USEC_PER_MSEC, MAX_PERIOD = USEC_PER_SEC, /* * iocg->vtime is targeted at 50% behind the device vtime, which * serves as its IO credit buffer. Surplus weight adjustment is * immediately canceled if the vtime margin runs below 10%. */ MARGIN_MIN_PCT = 10, MARGIN_LOW_PCT = 20, MARGIN_TARGET_PCT = 50, INUSE_ADJ_STEP_PCT = 25, /* Have some play in timer operations */ TIMER_SLACK_PCT = 1, /* 1/64k is granular enough and can easily be handled w/ u32 */ WEIGHT_ONE = 1 << 16, }; enum { /* * As vtime is used to calculate the cost of each IO, it needs to * be fairly high precision. For example, it should be able to * represent the cost of a single page worth of discard with * suffificient accuracy. At the same time, it should be able to * represent reasonably long enough durations to be useful and * convenient during operation. * * 1s worth of vtime is 2^37. This gives us both sub-nanosecond * granularity and days of wrap-around time even at extreme vrates. */ VTIME_PER_SEC_SHIFT = 37, VTIME_PER_SEC = 1LLU << VTIME_PER_SEC_SHIFT, VTIME_PER_USEC = VTIME_PER_SEC / USEC_PER_SEC, VTIME_PER_NSEC = VTIME_PER_SEC / NSEC_PER_SEC, /* bound vrate adjustments within two orders of magnitude */ VRATE_MIN_PPM = 10000, /* 1% */ VRATE_MAX_PPM = 100000000, /* 10000% */ VRATE_MIN = VTIME_PER_USEC * VRATE_MIN_PPM / MILLION, VRATE_CLAMP_ADJ_PCT = 4, /* switch iff the conditions are met for longer than this */ AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, }; enum { /* if IOs end up waiting for requests, issue less */ RQ_WAIT_BUSY_PCT = 5, /* unbusy hysterisis */ UNBUSY_THR_PCT = 75, /* * The effect of delay is indirect and non-linear and a huge amount of * future debt can accumulate abruptly while unthrottled. Linearly scale * up delay as debt is going up and then let it decay exponentially. * This gives us quick ramp ups while delay is accumulating and long * tails which can help reducing the frequency of debt explosions on * unthrottle. The parameters are experimentally determined. * * The delay mechanism provides adequate protection and behavior in many * cases. However, this is far from ideal and falls shorts on both * fronts. The debtors are often throttled too harshly costing a * significant level of fairness and possibly total work while the * protection against their impacts on the system can be choppy and * unreliable. * * The shortcoming primarily stems from the fact that, unlike for page * cache, the kernel doesn't have well-defined back-pressure propagation * mechanism and policies for anonymous memory. Fully addressing this * issue will likely require substantial improvements in the area. */ MIN_DELAY_THR_PCT = 500, MAX_DELAY_THR_PCT = 25000, MIN_DELAY = 250, MAX_DELAY = 250 * USEC_PER_MSEC, /* halve debts if avg usage over 100ms is under 50% */ DFGV_USAGE_PCT = 50, DFGV_PERIOD = 100 * USEC_PER_MSEC, /* don't let cmds which take a very long time pin lagging for too long */ MAX_LAGGING_PERIODS = 10, /* * Count IO size in 4k pages. The 12bit shift helps keeping * size-proportional components of cost calculation in closer * numbers of digits to per-IO cost components. */ IOC_PAGE_SHIFT = 12, IOC_PAGE_SIZE = 1 << IOC_PAGE_SHIFT, IOC_SECT_TO_PAGE_SHIFT = IOC_PAGE_SHIFT - SECTOR_SHIFT, /* if apart further than 16M, consider randio for linear model */ LCOEF_RANDIO_PAGES = 4096, }; enum ioc_running { IOC_IDLE, IOC_RUNNING, IOC_STOP, }; /* io.cost.qos controls including per-dev enable of the whole controller */ enum { QOS_ENABLE, QOS_CTRL, NR_QOS_CTRL_PARAMS, }; /* io.cost.qos params */ enum { QOS_RPPM, QOS_RLAT, QOS_WPPM, QOS_WLAT, QOS_MIN, QOS_MAX, NR_QOS_PARAMS, }; /* io.cost.model controls */ enum { COST_CTRL, COST_MODEL, NR_COST_CTRL_PARAMS, }; /* builtin linear cost model coefficients */ enum { I_LCOEF_RBPS, I_LCOEF_RSEQIOPS, I_LCOEF_RRANDIOPS, I_LCOEF_WBPS, I_LCOEF_WSEQIOPS, I_LCOEF_WRANDIOPS, NR_I_LCOEFS, }; enum { LCOEF_RPAGE, LCOEF_RSEQIO, LCOEF_RRANDIO, LCOEF_WPAGE, LCOEF_WSEQIO, LCOEF_WRANDIO, NR_LCOEFS, }; enum { AUTOP_INVALID, AUTOP_HDD, AUTOP_SSD_QD1, AUTOP_SSD_DFL, AUTOP_SSD_FAST, }; struct ioc_params { u32 qos[NR_QOS_PARAMS]; u64 i_lcoefs[NR_I_LCOEFS]; u64 lcoefs[NR_LCOEFS]; u32 too_fast_vrate_pct; u32 too_slow_vrate_pct; }; struct ioc_margins { s64 min; s64 low; s64 target; }; struct ioc_missed { local_t nr_met; local_t nr_missed; u32 last_met; u32 last_missed; }; struct ioc_pcpu_stat { struct ioc_missed missed[2]; local64_t rq_wait_ns; u64 last_rq_wait_ns; }; /* per device */ struct ioc { struct rq_qos rqos; bool enabled; struct ioc_params params; struct ioc_margins margins; u32 period_us; u32 timer_slack_ns; u64 vrate_min; u64 vrate_max; spinlock_t lock; struct timer_list timer; struct list_head active_iocgs; /* active cgroups */ struct ioc_pcpu_stat __percpu *pcpu_stat; enum ioc_running running; atomic64_t vtime_rate; u64 vtime_base_rate; s64 vtime_err; seqcount_spinlock_t period_seqcount; u64 period_at; /* wallclock starttime */ u64 period_at_vtime; /* vtime starttime */ atomic64_t cur_period; /* inc'd each period */ int busy_level; /* saturation history */ bool weights_updated; atomic_t hweight_gen; /* for lazy hweights */ /* debt forgivness */ u64 dfgv_period_at; u64 dfgv_period_rem; u64 dfgv_usage_us_sum; u64 autop_too_fast_at; u64 autop_too_slow_at; int autop_idx; bool user_qos_params:1; bool user_cost_model:1; }; struct iocg_pcpu_stat { local64_t abs_vusage; }; struct iocg_stat { u64 usage_us; u64 wait_us; u64 indebt_us; u64 indelay_us; }; /* per device-cgroup pair */ struct ioc_gq { struct blkg_policy_data pd; struct ioc *ioc; /* * A iocg can get its weight from two sources - an explicit * per-device-cgroup configuration or the default weight of the * cgroup. `cfg_weight` is the explicit per-device-cgroup * configuration. `weight` is the effective considering both * sources. * * When an idle cgroup becomes active its `active` goes from 0 to * `weight`. `inuse` is the surplus adjusted active weight. * `active` and `inuse` are used to calculate `hweight_active` and * `hweight_inuse`. * * `last_inuse` remembers `inuse` while an iocg is idle to persist * surplus adjustments. * * `inuse` may be adjusted dynamically during period. `saved_*` are used * to determine and track adjustments. */ u32 cfg_weight; u32 weight; u32 active; u32 inuse; u32 last_inuse; s64 saved_margin; sector_t cursor; /* to detect randio */ /* * `vtime` is this iocg's vtime cursor which progresses as IOs are * issued. If lagging behind device vtime, the delta represents * the currently available IO budget. If running ahead, the * overage. * * `vtime_done` is the same but progressed on completion rather * than issue. The delta behind `vtime` represents the cost of * currently in-flight IOs. */ atomic64_t vtime; atomic64_t done_vtime; u64 abs_vdebt; /* current delay in effect and when it started */ u64 delay; u64 delay_at; /* * The period this iocg was last active in. Used for deactivation * and invalidating `vtime`. */ atomic64_t active_period; struct list_head active_list; /* see __propagate_weights() and current_hweight() for details */ u64 child_active_sum; u64 child_inuse_sum; u64 child_adjusted_sum; int hweight_gen; u32 hweight_active; u32 hweight_inuse; u32 hweight_donating; u32 hweight_after_donation; struct list_head walk_list; struct list_head surplus_list; struct wait_queue_head waitq; struct hrtimer waitq_timer; /* timestamp at the latest activation */ u64 activated_at; /* statistics */ struct iocg_pcpu_stat __percpu *pcpu_stat; struct iocg_stat stat; struct iocg_stat last_stat; u64 last_stat_abs_vusage; u64 usage_delta_us; u64 wait_since; u64 indebt_since; u64 indelay_since; /* this iocg's depth in the hierarchy and ancestors including self */ int level; struct ioc_gq *ancestors[]; }; /* per cgroup */ struct ioc_cgrp { struct blkcg_policy_data cpd; unsigned int dfl_weight; }; struct ioc_now { u64 now_ns; u64 now; u64 vnow; }; struct iocg_wait { struct wait_queue_entry wait; struct bio *bio; u64 abs_cost; bool committed; }; struct iocg_wake_ctx { struct ioc_gq *iocg; u32 hw_inuse; s64 vbudget; }; static const struct ioc_params autop[] = { [AUTOP_HDD] = { .qos = { [QOS_RLAT] = 250000, /* 250ms */ [QOS_WLAT] = 250000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 174019176, [I_LCOEF_RSEQIOPS] = 41708, [I_LCOEF_RRANDIOPS] = 370, [I_LCOEF_WBPS] = 178075866, [I_LCOEF_WSEQIOPS] = 42705, [I_LCOEF_WRANDIOPS] = 378, }, }, [AUTOP_SSD_QD1] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 245855193, [I_LCOEF_RSEQIOPS] = 61575, [I_LCOEF_RRANDIOPS] = 6946, [I_LCOEF_WBPS] = 141365009, [I_LCOEF_WSEQIOPS] = 33716, [I_LCOEF_WRANDIOPS] = 26796, }, }, [AUTOP_SSD_DFL] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 488636629, [I_LCOEF_RSEQIOPS] = 8932, [I_LCOEF_RRANDIOPS] = 8518, [I_LCOEF_WBPS] = 427891549, [I_LCOEF_WSEQIOPS] = 28755, [I_LCOEF_WRANDIOPS] = 21940, }, .too_fast_vrate_pct = 500, }, [AUTOP_SSD_FAST] = { .qos = { [QOS_RLAT] = 5000, /* 5ms */ [QOS_WLAT] = 5000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 3102524156LLU, [I_LCOEF_RSEQIOPS] = 724816, [I_LCOEF_RRANDIOPS] = 778122, [I_LCOEF_WBPS] = 1742780862LLU, [I_LCOEF_WSEQIOPS] = 425702, [I_LCOEF_WRANDIOPS] = 443193, }, .too_slow_vrate_pct = 10, }, }; /* * vrate adjust percentages indexed by ioc->busy_level. We adjust up on * vtime credit shortage and down on device saturation. */ static const u32 vrate_adj_pct[] = { 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 16 }; static struct blkcg_policy blkcg_policy_iocost; /* accessors and helpers */ static struct ioc *rqos_to_ioc(struct rq_qos *rqos) { return container_of(rqos, struct ioc, rqos); } static struct ioc *q_to_ioc(struct request_queue *q) { return rqos_to_ioc(rq_qos_id(q, RQ_QOS_COST)); } static const char __maybe_unused *ioc_name(struct ioc *ioc) { struct gendisk *disk = ioc->rqos.disk; if (!disk) return "<unknown>"; return disk->disk_name; } static struct ioc_gq *pd_to_iocg(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct ioc_gq, pd) : NULL; } static struct ioc_gq *blkg_to_iocg(struct blkcg_gq *blkg) { return pd_to_iocg(blkg_to_pd(blkg, &blkcg_policy_iocost)); } static struct blkcg_gq *iocg_to_blkg(struct ioc_gq *iocg) { return pd_to_blkg(&iocg->pd); } static struct ioc_cgrp *blkcg_to_iocc(struct blkcg *blkcg) { return container_of(blkcg_to_cpd(blkcg, &blkcg_policy_iocost), struct ioc_cgrp, cpd); } /* * Scale @abs_cost to the inverse of @hw_inuse. The lower the hierarchical * weight, the more expensive each IO. Must round up. */ static u64 abs_cost_to_cost(u64 abs_cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(abs_cost * WEIGHT_ONE, hw_inuse); } /* * The inverse of abs_cost_to_cost(). Must round up. */ static u64 cost_to_abs_cost(u64 cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(cost * hw_inuse, WEIGHT_ONE); } static void iocg_commit_bio(struct ioc_gq *iocg, struct bio *bio, u64 abs_cost, u64 cost) { struct iocg_pcpu_stat *gcs; bio->bi_iocost_cost = cost; atomic64_add(cost, &iocg->vtime); gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_lock(struct ioc_gq *iocg, bool lock_ioc, unsigned long *flags) { if (lock_ioc) { spin_lock_irqsave(&iocg->ioc->lock, *flags); spin_lock(&iocg->waitq.lock); } else { spin_lock_irqsave(&iocg->waitq.lock, *flags); } } static void iocg_unlock(struct ioc_gq *iocg, bool unlock_ioc, unsigned long *flags) { if (unlock_ioc) { spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&iocg->ioc->lock, *flags); } else { spin_unlock_irqrestore(&iocg->waitq.lock, *flags); } } #define CREATE_TRACE_POINTS #include <trace/events/iocost.h> static void ioc_refresh_margins(struct ioc *ioc) { struct ioc_margins *margins = &ioc->margins; u32 period_us = ioc->period_us; u64 vrate = ioc->vtime_base_rate; margins->min = (period_us * MARGIN_MIN_PCT / 100) * vrate; margins->low = (period_us * MARGIN_LOW_PCT / 100) * vrate; margins->target = (period_us * MARGIN_TARGET_PCT / 100) * vrate; } /* latency Qos params changed, update period_us and all the dependent params */ static void ioc_refresh_period_us(struct ioc *ioc) { u32 ppm, lat, multi, period_us; lockdep_assert_held(&ioc->lock); /* pick the higher latency target */ if (ioc->params.qos[QOS_RLAT] >= ioc->params.qos[QOS_WLAT]) { ppm = ioc->params.qos[QOS_RPPM]; lat = ioc->params.qos[QOS_RLAT]; } else { ppm = ioc->params.qos[QOS_WPPM]; lat = ioc->params.qos[QOS_WLAT]; } /* * We want the period to be long enough to contain a healthy number * of IOs while short enough for granular control. Define it as a * multiple of the latency target. Ideally, the multiplier should * be scaled according to the percentile so that it would nominally * contain a certain number of requests. Let's be simpler and * scale it linearly so that it's 2x >= pct(90) and 10x at pct(50). */ if (ppm) multi = max_t(u32, (MILLION - ppm) / 50000, 2); else multi = 2; period_us = multi * lat; period_us = clamp_t(u32, period_us, MIN_PERIOD, MAX_PERIOD); /* calculate dependent params */ ioc->period_us = period_us; ioc->timer_slack_ns = div64_u64( (u64)period_us * NSEC_PER_USEC * TIMER_SLACK_PCT, 100); ioc_refresh_margins(ioc); } /* * ioc->rqos.disk isn't initialized when this function is called from * the init path. */ static int ioc_autop_idx(struct ioc *ioc, struct gendisk *disk) { int idx = ioc->autop_idx; const struct ioc_params *p = &autop[idx]; u32 vrate_pct; u64 now_ns; /* rotational? */ if (!blk_queue_nonrot(disk->queue)) return AUTOP_HDD; /* handle SATA SSDs w/ broken NCQ */ if (blk_queue_depth(disk->queue) == 1) return AUTOP_SSD_QD1; /* use one of the normal ssd sets */ if (idx < AUTOP_SSD_DFL) return AUTOP_SSD_DFL; /* if user is overriding anything, maintain what was there */ if (ioc->user_qos_params || ioc->user_cost_model) return idx; /* step up/down based on the vrate */ vrate_pct = div64_u64(ioc->vtime_base_rate * 100, VTIME_PER_USEC); now_ns = blk_time_get_ns(); if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) { if (!ioc->autop_too_fast_at) ioc->autop_too_fast_at = now_ns; if (now_ns - ioc->autop_too_fast_at >= AUTOP_CYCLE_NSEC) return idx + 1; } else { ioc->autop_too_fast_at = 0; } if (p->too_slow_vrate_pct && p->too_slow_vrate_pct >= vrate_pct) { if (!ioc->autop_too_slow_at) ioc->autop_too_slow_at = now_ns; if (now_ns - ioc->autop_too_slow_at >= AUTOP_CYCLE_NSEC) return idx - 1; } else { ioc->autop_too_slow_at = 0; } return idx; } /* * Take the followings as input * * @bps maximum sequential throughput * @seqiops maximum sequential 4k iops * @randiops maximum random 4k iops * * and calculate the linear model cost coefficients. * * *@page per-page cost 1s / (@bps / 4096) * *@seqio base cost of a seq IO max((1s / @seqiops) - *@page, 0) * @randiops base cost of a rand IO max((1s / @randiops) - *@page, 0) */ static void calc_lcoefs(u64 bps, u64 seqiops, u64 randiops, u64 *page, u64 *seqio, u64 *randio) { u64 v; *page = *seqio = *randio = 0; if (bps) { u64 bps_pages = DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE); if (bps_pages) *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, bps_pages); else *page = 1; } if (seqiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, seqiops); if (v > *page) *seqio = v - *page; } if (randiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, randiops); if (v > *page) *randio = v - *page; } } static void ioc_refresh_lcoefs(struct ioc *ioc) { u64 *u = ioc->params.i_lcoefs; u64 *c = ioc->params.lcoefs; calc_lcoefs(u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], &c[LCOEF_RPAGE], &c[LCOEF_RSEQIO], &c[LCOEF_RRANDIO]); calc_lcoefs(u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS], &c[LCOEF_WPAGE], &c[LCOEF_WSEQIO], &c[LCOEF_WRANDIO]); } /* * struct gendisk is required as an argument because ioc->rqos.disk * is not properly initialized when called from the init path. */ static bool ioc_refresh_params_disk(struct ioc *ioc, bool force, struct gendisk *disk) { const struct ioc_params *p; int idx; lockdep_assert_held(&ioc->lock); idx = ioc_autop_idx(ioc, disk); p = &autop[idx]; if (idx == ioc->autop_idx && !force) return false; if (idx != ioc->autop_idx) { atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); ioc->vtime_base_rate = VTIME_PER_USEC; } ioc->autop_idx = idx; ioc->autop_too_fast_at = 0; ioc->autop_too_slow_at = 0; if (!ioc->user_qos_params) memcpy(ioc->params.qos, p->qos, sizeof(p->qos)); if (!ioc->user_cost_model) memcpy(ioc->params.i_lcoefs, p->i_lcoefs, sizeof(p->i_lcoefs)); ioc_refresh_period_us(ioc); ioc_refresh_lcoefs(ioc); ioc->vrate_min = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MIN] * VTIME_PER_USEC, MILLION); ioc->vrate_max = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MAX] * VTIME_PER_USEC, MILLION); return true; } static bool ioc_refresh_params(struct ioc *ioc, bool force) { return ioc_refresh_params_disk(ioc, force, ioc->rqos.disk); } /* * When an iocg accumulates too much vtime or gets deactivated, we throw away * some vtime, which lowers the overall device utilization. As the exact amount * which is being thrown away is known, we can compensate by accelerating the * vrate accordingly so that the extra vtime generated in the current period * matches what got lost. */ static void ioc_refresh_vrate(struct ioc *ioc, struct ioc_now *now) { s64 pleft = ioc->period_at + ioc->period_us - now->now; s64 vperiod = ioc->period_us * ioc->vtime_base_rate; s64 vcomp, vcomp_min, vcomp_max; lockdep_assert_held(&ioc->lock); /* we need some time left in this period */ if (pleft <= 0) goto done; /* * Calculate how much vrate should be adjusted to offset the error. * Limit the amount of adjustment and deduct the adjusted amount from * the error. */ vcomp = -div64_s64(ioc->vtime_err, pleft); vcomp_min = -(ioc->vtime_base_rate >> 1); vcomp_max = ioc->vtime_base_rate; vcomp = clamp(vcomp, vcomp_min, vcomp_max); ioc->vtime_err += vcomp * pleft; atomic64_set(&ioc->vtime_rate, ioc->vtime_base_rate + vcomp); done: /* bound how much error can accumulate */ ioc->vtime_err = clamp(ioc->vtime_err, -vperiod, vperiod); } static void ioc_adjust_base_vrate(struct ioc *ioc, u32 rq_wait_pct, int nr_lagging, int nr_shortages, int prev_busy_level, u32 *missed_ppm) { u64 vrate = ioc->vtime_base_rate; u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max; if (!ioc->busy_level || (ioc->busy_level < 0 && nr_lagging)) { if (ioc->busy_level != prev_busy_level || nr_lagging) trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); return; } /* * If vrate is out of bounds, apply clamp gradually as the * bounds can change abruptly. Otherwise, apply busy_level * based adjustment. */ if (vrate < vrate_min) { vrate = div64_u64(vrate * (100 + VRATE_CLAMP_ADJ_PCT), 100); vrate = min(vrate, vrate_min); } else if (vrate > vrate_max) { vrate = div64_u64(vrate * (100 - VRATE_CLAMP_ADJ_PCT), 100); vrate = max(vrate, vrate_max); } else { int idx = min_t(int, abs(ioc->busy_level), ARRAY_SIZE(vrate_adj_pct) - 1); u32 adj_pct = vrate_adj_pct[idx]; if (ioc->busy_level > 0) adj_pct = 100 - adj_pct; else adj_pct = 100 + adj_pct; vrate = clamp(DIV64_U64_ROUND_UP(vrate * adj_pct, 100), vrate_min, vrate_max); } trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); ioc->vtime_base_rate = vrate; ioc_refresh_margins(ioc); } /* take a snapshot of the current [v]time and vrate */ static void ioc_now(struct ioc *ioc, struct ioc_now *now) { unsigned seq; u64 vrate; now->now_ns = blk_time_get_ns(); now->now = ktime_to_us(now->now_ns); vrate = atomic64_read(&ioc->vtime_rate); /* * The current vtime is * * vtime at period start + (wallclock time since the start) * vrate * * As a consistent snapshot of `period_at_vtime` and `period_at` is * needed, they're seqcount protected. */ do { seq = read_seqcount_begin(&ioc->period_seqcount); now->vnow = ioc->period_at_vtime + (now->now - ioc->period_at) * vrate; } while (read_seqcount_retry(&ioc->period_seqcount, seq)); } static void ioc_start_period(struct ioc *ioc, struct ioc_now *now) { WARN_ON_ONCE(ioc->running != IOC_RUNNING); write_seqcount_begin(&ioc->period_seqcount); ioc->period_at = now->now; ioc->period_at_vtime = now->vnow; write_seqcount_end(&ioc->period_seqcount); ioc->timer.expires = jiffies + usecs_to_jiffies(ioc->period_us); add_timer(&ioc->timer); } /* * Update @iocg's `active` and `inuse` to @active and @inuse, update level * weight sums and propagate upwards accordingly. If @save, the current margin * is saved to be used as reference for later inuse in-period adjustments. */ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; int lvl; lockdep_assert_held(&ioc->lock); /* * For an active leaf node, its inuse shouldn't be zero or exceed * @active. An active internal node's inuse is solely determined by the * inuse to active ratio of its children regardless of @inuse. */ if (list_empty(&iocg->active_list) && iocg->child_active_sum) { inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, iocg->child_active_sum); } else { /* * It may be tempting to turn this into a clamp expression with * a lower limit of 1 but active may be 0, which cannot be used * as an upper limit in that situation. This expression allows * active to clamp inuse unless it is 0, in which case inuse * becomes 1. */ inuse = min(inuse, active) ?: 1; } iocg->last_inuse = iocg->inuse; if (save) iocg->saved_margin = now->vnow - atomic64_read(&iocg->vtime); if (active == iocg->active && inuse == iocg->inuse) return; for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u32 parent_active = 0, parent_inuse = 0; /* update the level sums */ parent->child_active_sum += (s32)(active - child->active); parent->child_inuse_sum += (s32)(inuse - child->inuse); /* apply the updates */ child->active = active; child->inuse = inuse; /* * The delta between inuse and active sums indicates that * much of weight is being given away. Parent's inuse * and active should reflect the ratio. */ if (parent->child_active_sum) { parent_active = parent->weight; parent_inuse = DIV64_U64_ROUND_UP( parent_active * parent->child_inuse_sum, parent->child_active_sum); } /* do we need to keep walking up? */ if (parent_active == parent->active && parent_inuse == parent->inuse) break; active = parent_active; inuse = parent_inuse; } ioc->weights_updated = true; } static void commit_weights(struct ioc *ioc) { lockdep_assert_held(&ioc->lock); if (ioc->weights_updated) { /* paired with rmb in current_hweight(), see there */ smp_wmb(); atomic_inc(&ioc->hweight_gen); ioc->weights_updated = false; } } static void propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { __propagate_weights(iocg, active, inuse, save, now); commit_weights(iocg->ioc); } static void current_hweight(struct ioc_gq *iocg, u32 *hw_activep, u32 *hw_inusep) { struct ioc *ioc = iocg->ioc; int lvl; u32 hwa, hwi; int ioc_gen; /* hot path - if uptodate, use cached */ ioc_gen = atomic_read(&ioc->hweight_gen); if (ioc_gen == iocg->hweight_gen) goto out; /* * Paired with wmb in commit_weights(). If we saw the updated * hweight_gen, all the weight updates from __propagate_weights() are * visible too. * * We can race with weight updates during calculation and get it * wrong. However, hweight_gen would have changed and a future * reader will recalculate and we're guaranteed to discard the * wrong result soon. */ smp_rmb(); hwa = hwi = WEIGHT_ONE; for (lvl = 0; lvl <= iocg->level - 1; lvl++) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u64 active_sum = READ_ONCE(parent->child_active_sum); u64 inuse_sum = READ_ONCE(parent->child_inuse_sum); u32 active = READ_ONCE(child->active); u32 inuse = READ_ONCE(child->inuse); /* we can race with deactivations and either may read as zero */ if (!active_sum || !inuse_sum) continue; active_sum = max_t(u64, active, active_sum); hwa = div64_u64((u64)hwa * active, active_sum); inuse_sum = max_t(u64, inuse, inuse_sum); hwi = div64_u64((u64)hwi * inuse, inuse_sum); } iocg->hweight_active = max_t(u32, hwa, 1); iocg->hweight_inuse = max_t(u32, hwi, 1); iocg->hweight_gen = ioc_gen; out: if (hw_activep) *hw_activep = iocg->hweight_active; if (hw_inusep) *hw_inusep = iocg->hweight_inuse; } /* * Calculate the hweight_inuse @iocg would get with max @inuse assuming all the * other weights stay unchanged. */ static u32 current_hweight_max(struct ioc_gq *iocg) { u32 hwm = WEIGHT_ONE; u32 inuse = iocg->active; u64 child_inuse_sum; int lvl; lockdep_assert_held(&iocg->ioc->lock); for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; child_inuse_sum = parent->child_inuse_sum + inuse - child->inuse; hwm = div64_u64((u64)hwm * inuse, child_inuse_sum); inuse = DIV64_U64_ROUND_UP(parent->active * child_inuse_sum, parent->child_active_sum); } return max_t(u32, hwm, 1); } static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); struct ioc_cgrp *iocc = blkcg_to_iocc(blkg->blkcg); u32 weight; lockdep_assert_held(&ioc->lock); weight = iocg->cfg_weight ?: iocc->dfl_weight; if (weight != iocg->weight && iocg->active) propagate_weights(iocg, weight, iocg->inuse, true, now); iocg->weight = weight; } static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 __maybe_unused last_period, cur_period; u64 vtime, vtarget; int i; /* * If seem to be already active, just update the stamp to tell the * timer that we're still active. We don't mind occassional races. */ if (!list_empty(&iocg->active_list)) { ioc_now(ioc, now); cur_period = atomic64_read(&ioc->cur_period); if (atomic64_read(&iocg->active_period) != cur_period) atomic64_set(&iocg->active_period, cur_period); return true; } /* racy check on internal node IOs, treat as root level IOs */ if (iocg->child_active_sum) return false; spin_lock_irq(&ioc->lock); ioc_now(ioc, now); /* update period */ cur_period = atomic64_read(&ioc->cur_period); last_period = atomic64_read(&iocg->active_period); atomic64_set(&iocg->active_period, cur_period); /* already activated or breaking leaf-only constraint? */ if (!list_empty(&iocg->active_list)) goto succeed_unlock; for (i = iocg->level - 1; i > 0; i--) if (!list_empty(&iocg->ancestors[i]->active_list)) goto fail_unlock; if (iocg->child_active_sum) goto fail_unlock; /* * Always start with the target budget. On deactivation, we throw away * anything above it. */ vtarget = now->vnow - ioc->margins.target; vtime = atomic64_read(&iocg->vtime); atomic64_add(vtarget - vtime, &iocg->vtime); atomic64_add(vtarget - vtime, &iocg->done_vtime); vtime = vtarget; /* * Activate, propagate weight and start period timer if not * running. Reset hweight_gen to avoid accidental match from * wrapping. */ iocg->hweight_gen = atomic_read(&ioc->hweight_gen) - 1; list_add(&iocg->active_list, &ioc->active_iocgs); propagate_weights(iocg, iocg->weight, iocg->last_inuse ?: iocg->weight, true, now); TRACE_IOCG_PATH(iocg_activate, iocg, now, last_period, cur_period, vtime); iocg->activated_at = now->now; if (ioc->running == IOC_IDLE) { ioc->running = IOC_RUNNING; ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc_start_period(ioc, now); } succeed_unlock: spin_unlock_irq(&ioc->lock); return true; fail_unlock: spin_unlock_irq(&ioc->lock); return false; } static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); /* * If the delay is set by another CPU, we may be in the past. No need to * change anything if so. This avoids decay calculation underflow. */ if (time_before64(now->now, iocg->delay_at)) return false; /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; shift = div64_u64(tdelta, USEC_PER_SEC); if (iocg->delay && shift < BITS_PER_LONG) delay = iocg->delay >> shift; else delay = 0; /* calculate the new delay from the debt amount */ current_hweight(iocg, &hwa, NULL); vover = atomic64_read(&iocg->vtime) + abs_cost_to_cost(iocg->abs_vdebt, hwa) - now->vnow; vover_pct = div64_s64(100 * vover, ioc->period_us * ioc->vtime_base_rate); if (vover_pct <= MIN_DELAY_THR_PCT) new_delay = 0; else if (vover_pct >= MAX_DELAY_THR_PCT) new_delay = MAX_DELAY; else new_delay = MIN_DELAY + div_u64((MAX_DELAY - MIN_DELAY) * (vover_pct - MIN_DELAY_THR_PCT), MAX_DELAY_THR_PCT - MIN_DELAY_THR_PCT); /* pick the higher one and apply */ if (new_delay > delay) { iocg->delay = new_delay; iocg->delay_at = now->now; delay = new_delay; } if (delay >= MIN_DELAY) { if (!iocg->indelay_since) iocg->indelay_since = now->now; blkcg_set_delay(blkg, delay * NSEC_PER_USEC); return true; } else { if (iocg->indelay_since) { iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = 0; } iocg->delay = 0; blkcg_clear_delay(blkg); return false; } } static void iocg_incur_debt(struct ioc_gq *iocg, u64 abs_cost, struct ioc_now *now) { struct iocg_pcpu_stat *gcs; lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); WARN_ON_ONCE(list_empty(&iocg->active_list)); /* * Once in debt, debt handling owns inuse. @iocg stays at the minimum * inuse donating all of it share to others until its debt is paid off. */ if (!iocg->abs_vdebt && abs_cost) { iocg->indebt_since = now->now; propagate_weights(iocg, iocg->active, 0, false, now); } iocg->abs_vdebt += abs_cost; gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, struct ioc_now *now) { lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); /* * make sure that nobody messed with @iocg. Check iocg->pd.online * to avoid warn when removing blkcg or disk. */ WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); /* if debt is paid in full, restore inuse */ if (!iocg->abs_vdebt) { iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = 0; propagate_weights(iocg, iocg->active, iocg->last_inuse, false, now); } } static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key) { struct iocg_wait *wait = container_of(wq_entry, struct iocg_wait, wait); struct iocg_wake_ctx *ctx = key; u64 cost = abs_cost_to_cost(wait->abs_cost, ctx->hw_inuse); ctx->vbudget -= cost; if (ctx->vbudget < 0) return -1; iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost); wait->committed = true; /* * autoremove_wake_function() removes the wait entry only when it * actually changed the task state. We want the wait always removed. * Remove explicitly and use default_wake_function(). Note that the * order of operations is important as finish_wait() tests whether * @wq_entry is removed without grabbing the lock. */ default_wake_function(wq_entry, mode, flags, key); list_del_init_careful(&wq_entry->entry); return 0; } /* * Calculate the accumulated budget, pay debt if @pay_debt and wake up waiters * accordingly. When @pay_debt is %true, the caller must be holding ioc->lock in * addition to iocg->waitq.lock. */ static void iocg_kick_waitq(struct ioc_gq *iocg, bool pay_debt, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 vshortage, expires, oexpires; s64 vbudget; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); current_hweight(iocg, &hwa, NULL); vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ if (pay_debt && iocg->abs_vdebt && vbudget > 0) { u64 abs_vbudget = cost_to_abs_cost(vbudget, hwa); u64 abs_vpay = min_t(u64, abs_vbudget, iocg->abs_vdebt); u64 vpay = abs_cost_to_cost(abs_vpay, hwa); lockdep_assert_held(&ioc->lock); atomic64_add(vpay, &iocg->vtime); atomic64_add(vpay, &iocg->done_vtime); iocg_pay_debt(iocg, abs_vpay, now); vbudget -= vpay; } if (iocg->abs_vdebt || iocg->delay) iocg_kick_delay(iocg, now); /* * Debt can still be outstanding if we haven't paid all yet or the * caller raced and called without @pay_debt. Shouldn't wake up waiters * under debt. Make sure @vbudget reflects the outstanding amount and is * not positive. */ if (iocg->abs_vdebt) { s64 vdebt = abs_cost_to_cost(iocg->abs_vdebt, hwa); vbudget = min_t(s64, 0, vbudget - vdebt); } /* * Wake up the ones which are due and see how much vtime we'll need for * the next one. As paying off debt restores hw_inuse, it must be read * after the above debt payment. */ ctx.vbudget = vbudget; current_hweight(iocg, NULL, &ctx.hw_inuse); __wake_up_locked_key(&iocg->waitq, TASK_NORMAL, &ctx); if (!waitqueue_active(&iocg->waitq)) { if (iocg->wait_since) { iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = 0; } return; } if (!iocg->wait_since) iocg->wait_since = now->now; if (WARN_ON_ONCE(ctx.vbudget >= 0)) return; /* determine next wakeup, add a timer margin to guarantee chunking */ vshortage = -ctx.vbudget; expires = now->now_ns + DIV64_U64_ROUND_UP(vshortage, ioc->vtime_base_rate) * NSEC_PER_USEC; expires += ioc->timer_slack_ns; /* if already active and close enough, don't bother */ oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->waitq_timer)); if (hrtimer_is_queued(&iocg->waitq_timer) && abs(oexpires - expires) <= ioc->timer_slack_ns) return; hrtimer_start_range_ns(&iocg->waitq_timer, ns_to_ktime(expires), ioc->timer_slack_ns, HRTIMER_MODE_ABS); } static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, waitq_timer); bool pay_debt = READ_ONCE(iocg->abs_vdebt); struct ioc_now now; unsigned long flags; ioc_now(iocg->ioc, &now); iocg_lock(iocg, pay_debt, &flags); iocg_kick_waitq(iocg, pay_debt, &now); iocg_unlock(iocg, pay_debt, &flags); return HRTIMER_NORESTART; } static void ioc_lat_stat(struct ioc *ioc, u32 *missed_ppm_ar, u32 *rq_wait_pct_p) { u32 nr_met[2] = { }; u32 nr_missed[2] = { }; u64 rq_wait_ns = 0; int cpu, rw; for_each_online_cpu(cpu) { struct ioc_pcpu_stat *stat = per_cpu_ptr(ioc->pcpu_stat, cpu); u64 this_rq_wait_ns; for (rw = READ; rw <= WRITE; rw++) { u32 this_met = local_read(&stat->missed[rw].nr_met); u32 this_missed = local_read(&stat->missed[rw].nr_missed); nr_met[rw] += this_met - stat->missed[rw].last_met; nr_missed[rw] += this_missed - stat->missed[rw].last_missed; stat->missed[rw].last_met = this_met; stat->missed[rw].last_missed = this_missed; } this_rq_wait_ns = local64_read(&stat->rq_wait_ns); rq_wait_ns += this_rq_wait_ns - stat->last_rq_wait_ns; stat->last_rq_wait_ns = this_rq_wait_ns; } for (rw = READ; rw <= WRITE; rw++) { if (nr_met[rw] + nr_missed[rw]) missed_ppm_ar[rw] = DIV64_U64_ROUND_UP((u64)nr_missed[rw] * MILLION, nr_met[rw] + nr_missed[rw]); else missed_ppm_ar[rw] = 0; } *rq_wait_pct_p = div64_u64(rq_wait_ns * 100, ioc->period_us * NSEC_PER_USEC); } /* was iocg idle this period? */ static bool iocg_is_idle(struct ioc_gq *iocg) { struct ioc *ioc = iocg->ioc; /* did something get issued this period? */ if (atomic64_read(&iocg->active_period) == atomic64_read(&ioc->cur_period)) return false; /* is something in flight? */ if (atomic64_read(&iocg->done_vtime) != atomic64_read(&iocg->vtime)) return false; return true; } /* * Call this function on the target leaf @iocg's to build pre-order traversal * list of all the ancestors in @inner_walk. The inner nodes are linked through * ->walk_list and the caller is responsible for dissolving the list after use. */ static void iocg_build_inner_walk(struct ioc_gq *iocg, struct list_head *inner_walk) { int lvl; WARN_ON_ONCE(!list_empty(&iocg->walk_list)); /* find the first ancestor which hasn't been visited yet */ for (lvl = iocg->level - 1; lvl >= 0; lvl--) { if (!list_empty(&iocg->ancestors[lvl]->walk_list)) break; } /* walk down and visit the inner nodes to get pre-order traversal */ while (++lvl <= iocg->level - 1) { struct ioc_gq *inner = iocg->ancestors[lvl]; /* record traversal order */ list_add_tail(&inner->walk_list, inner_walk); } } /* propagate the deltas to the parent */ static void iocg_flush_stat_upward(struct ioc_gq *iocg) { if (iocg->level > 0) { struct iocg_stat *parent_stat = &iocg->ancestors[iocg->level - 1]->stat; parent_stat->usage_us += iocg->stat.usage_us - iocg->last_stat.usage_us; parent_stat->wait_us += iocg->stat.wait_us - iocg->last_stat.wait_us; parent_stat->indebt_us += iocg->stat.indebt_us - iocg->last_stat.indebt_us; parent_stat->indelay_us += iocg->stat.indelay_us - iocg->last_stat.indelay_us; } iocg->last_stat = iocg->stat; } /* collect per-cpu counters and propagate the deltas to the parent */ static void iocg_flush_stat_leaf(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 abs_vusage = 0; u64 vusage_delta; int cpu; lockdep_assert_held(&iocg->ioc->lock); /* collect per-cpu counters */ for_each_possible_cpu(cpu) { abs_vusage += local64_read( per_cpu_ptr(&iocg->pcpu_stat->abs_vusage, cpu)); } vusage_delta = abs_vusage - iocg->last_stat_abs_vusage; iocg->last_stat_abs_vusage = abs_vusage; iocg->usage_delta_us = div64_u64(vusage_delta, ioc->vtime_base_rate); iocg->stat.usage_us += iocg->usage_delta_us; iocg_flush_stat_upward(iocg); } /* get stat counters ready for reading on all active iocgs */ static void iocg_flush_stat(struct list_head *target_iocgs, struct ioc_now *now) { LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg; /* flush leaves and build inner node walk list */ list_for_each_entry(iocg, target_iocgs, active_list) { iocg_flush_stat_leaf(iocg, now); iocg_build_inner_walk(iocg, &inner_walk); } /* keep flushing upwards by walking the inner list backwards */ list_for_each_entry_safe_reverse(iocg, tiocg, &inner_walk, walk_list) { iocg_flush_stat_upward(iocg); list_del_init(&iocg->walk_list); } } /* * Determine what @iocg's hweight_inuse should be after donating unused * capacity. @hwm is the upper bound and used to signal no donation. This * function also throws away @iocg's excess budget. */ static u32 hweight_after_donation(struct ioc_gq *iocg, u32 old_hwi, u32 hwm, u32 usage, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 vtime = atomic64_read(&iocg->vtime); s64 excess, delta, target, new_hwi; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return 1; /* see whether minimum margin requirement is met */ if (waitqueue_active(&iocg->waitq) || time_after64(vtime, now->vnow - ioc->margins.min)) return hwm; /* throw away excess above target */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { atomic64_add(excess, &iocg->vtime); atomic64_add(excess, &iocg->done_vtime); vtime += excess; ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } /* * Let's say the distance between iocg's and device's vtimes as a * fraction of period duration is delta. Assuming that the iocg will * consume the usage determined above, we want to determine new_hwi so * that delta equals MARGIN_TARGET at the end of the next period. * * We need to execute usage worth of IOs while spending the sum of the * new budget (1 - MARGIN_TARGET) and the leftover from the last period * (delta): * * usage = (1 - MARGIN_TARGET + delta) * new_hwi * * Therefore, the new_hwi is: * * new_hwi = usage / (1 - MARGIN_TARGET + delta) */ delta = div64_s64(WEIGHT_ONE * (now->vnow - vtime), now->vnow - ioc->period_at_vtime); target = WEIGHT_ONE * MARGIN_TARGET_PCT / 100; new_hwi = div64_s64(WEIGHT_ONE * usage, WEIGHT_ONE - target + delta); return clamp_t(s64, new_hwi, 1, hwm); } /* * For work-conservation, an iocg which isn't using all of its share should * donate the leftover to other iocgs. There are two ways to achieve this - 1. * bumping up vrate accordingly 2. lowering the donating iocg's inuse weight. * * #1 is mathematically simpler but has the drawback of requiring synchronous * global hweight_inuse updates when idle iocg's get activated or inuse weights * change due to donation snapbacks as it has the possibility of grossly * overshooting what's allowed by the model and vrate. * * #2 is inherently safe with local operations. The donating iocg can easily * snap back to higher weights when needed without worrying about impacts on * other nodes as the impacts will be inherently correct. This also makes idle * iocg activations safe. The only effect activations have is decreasing * hweight_inuse of others, the right solution to which is for those iocgs to * snap back to higher weights. * * So, we go with #2. The challenge is calculating how each donating iocg's * inuse should be adjusted to achieve the target donation amounts. This is done * using Andy's method described in the following pdf. * * https://drive.google.com/file/d/1PsJwxPFtjUnwOY1QJ5AeICCcsL7BM3bo * * Given the weights and target after-donation hweight_inuse values, Andy's * method determines how the proportional distribution should look like at each * sibling level to maintain the relative relationship between all non-donating * pairs. To roughly summarize, it divides the tree into donating and * non-donating parts, calculates global donation rate which is used to * determine the target hweight_inuse for each node, and then derives per-level * proportions. * * The following pdf shows that global distribution calculated this way can be * achieved by scaling inuse weights of donating leaves and propagating the * adjustments upwards proportionally. * * https://drive.google.com/file/d/1vONz1-fzVO7oY5DXXsLjSxEtYYQbOvsE * * Combining the above two, we can determine how each leaf iocg's inuse should * be adjusted to achieve the target donation. * * https://drive.google.com/file/d/1WcrltBOSPN0qXVdBgnKm4mdp9FhuEFQN * * The inline comments use symbols from the last pdf. * * b is the sum of the absolute budgets in the subtree. 1 for the root node. * f is the sum of the absolute budgets of non-donating nodes in the subtree. * t is the sum of the absolute budgets of donating nodes in the subtree. * w is the weight of the node. w = w_f + w_t * w_f is the non-donating portion of w. w_f = w * f / b * w_b is the donating portion of w. w_t = w * t / b * s is the sum of all sibling weights. s = Sum(w) for siblings * s_f and s_t are the non-donating and donating portions of s. * * Subscript p denotes the parent's counterpart and ' the adjusted value - e.g. * w_pt is the donating portion of the parent's weight and w'_pt the same value * after adjustments. Subscript r denotes the root node's values. */ static void transfer_surpluses(struct list_head *surpluses, struct ioc_now *now) { LIST_HEAD(over_hwa); LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg, *root_iocg; u32 after_sum, over_sum, over_target, gamma; /* * It's pretty unlikely but possible for the total sum of * hweight_after_donation's to be higher than WEIGHT_ONE, which will * confuse the following calculations. If such condition is detected, * scale down everyone over its full share equally to keep the sum below * WEIGHT_ONE. */ after_sum = 0; over_sum = 0; list_for_each_entry(iocg, surpluses, surplus_list) { u32 hwa; current_hweight(iocg, &hwa, NULL); after_sum += iocg->hweight_after_donation; if (iocg->hweight_after_donation > hwa) { over_sum += iocg->hweight_after_donation; list_add(&iocg->walk_list, &over_hwa); } } if (after_sum >= WEIGHT_ONE) { /* * The delta should be deducted from the over_sum, calculate * target over_sum value. */ u32 over_delta = after_sum - (WEIGHT_ONE - 1); WARN_ON_ONCE(over_sum <= over_delta); over_target = over_sum - over_delta; } else { over_target = 0; } list_for_each_entry_safe(iocg, tiocg, &over_hwa, walk_list) { if (over_target) iocg->hweight_after_donation = div_u64((u64)iocg->hweight_after_donation * over_target, over_sum); list_del_init(&iocg->walk_list); } /* * Build pre-order inner node walk list and prepare for donation * adjustment calculations. */ list_for_each_entry(iocg, surpluses, surplus_list) { iocg_build_inner_walk(iocg, &inner_walk); } root_iocg = list_first_entry(&inner_walk, struct ioc_gq, walk_list); WARN_ON_ONCE(root_iocg->level > 0); list_for_each_entry(iocg, &inner_walk, walk_list) { iocg->child_adjusted_sum = 0; iocg->hweight_donating = 0; iocg->hweight_after_donation = 0; } /* * Propagate the donating budget (b_t) and after donation budget (b'_t) * up the hierarchy. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } list_for_each_entry_reverse(iocg, &inner_walk, walk_list) { if (iocg->level > 0) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } } /* * Calculate inner hwa's (b) and make sure the donation values are * within the accepted ranges as we're doing low res calculations with * roundups. */ list_for_each_entry(iocg, &inner_walk, walk_list) { if (iocg->level) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; iocg->hweight_active = DIV64_U64_ROUND_UP( (u64)parent->hweight_active * iocg->active, parent->child_active_sum); } iocg->hweight_donating = min(iocg->hweight_donating, iocg->hweight_active); iocg->hweight_after_donation = min(iocg->hweight_after_donation, iocg->hweight_donating - 1); if (WARN_ON_ONCE(iocg->hweight_active <= 1 || iocg->hweight_donating <= 1 || iocg->hweight_after_donation == 0)) { pr_warn("iocg: invalid donation weights in "); pr_cont_cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup); pr_cont(": active=%u donating=%u after=%u\n", iocg->hweight_active, iocg->hweight_donating, iocg->hweight_after_donation); } } /* * Calculate the global donation rate (gamma) - the rate to adjust * non-donating budgets by. * * No need to use 64bit multiplication here as the first operand is * guaranteed to be smaller than WEIGHT_ONE (1<<16). * * We know that there are beneficiary nodes and the sum of the donating * hweights can't be whole; however, due to the round-ups during hweight * calculations, root_iocg->hweight_donating might still end up equal to * or greater than whole. Limit the range when calculating the divider. * * gamma = (1 - t_r') / (1 - t_r) */ gamma = DIV_ROUND_UP( (WEIGHT_ONE - root_iocg->hweight_after_donation) * WEIGHT_ONE, WEIGHT_ONE - min_t(u32, root_iocg->hweight_donating, WEIGHT_ONE - 1)); /* * Calculate adjusted hwi, child_adjusted_sum and inuse for the inner * nodes. */ list_for_each_entry(iocg, &inner_walk, walk_list) { struct ioc_gq *parent; u32 inuse, wpt, wptp; u64 st, sf; if (iocg->level == 0) { /* adjusted weight sum for 1st level: s' = s * b_pf / b'_pf */ iocg->child_adjusted_sum = DIV64_U64_ROUND_UP( iocg->child_active_sum * (WEIGHT_ONE - iocg->hweight_donating), WEIGHT_ONE - iocg->hweight_after_donation); continue; } parent = iocg->ancestors[iocg->level - 1]; /* b' = gamma * b_f + b_t' */ iocg->hweight_inuse = DIV64_U64_ROUND_UP( (u64)gamma * (iocg->hweight_active - iocg->hweight_donating), WEIGHT_ONE) + iocg->hweight_after_donation; /* w' = s' * b' / b'_p */ inuse = DIV64_U64_ROUND_UP( (u64)parent->child_adjusted_sum * iocg->hweight_inuse, parent->hweight_inuse); /* adjusted weight sum for children: s' = s_f + s_t * w'_pt / w_pt */ st = DIV64_U64_ROUND_UP( iocg->child_active_sum * iocg->hweight_donating, iocg->hweight_active); sf = iocg->child_active_sum - st; wpt = DIV64_U64_ROUND_UP( (u64)iocg->active * iocg->hweight_donating, iocg->hweight_active); wptp = DIV64_U64_ROUND_UP( (u64)inuse * iocg->hweight_after_donation, iocg->hweight_inuse); iocg->child_adjusted_sum = sf + DIV64_U64_ROUND_UP(st * wptp, wpt); } /* * All inner nodes now have ->hweight_inuse and ->child_adjusted_sum and * we can finally determine leaf adjustments. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; u32 inuse; /* * In-debt iocgs participated in the donation calculation with * the minimum target hweight_inuse. Configuring inuse * accordingly would work fine but debt handling expects * @iocg->inuse stay at the minimum and we don't wanna * interfere. */ if (iocg->abs_vdebt) { WARN_ON_ONCE(iocg->inuse > 1); continue; } /* w' = s' * b' / b'_p, note that b' == b'_t for donating leaves */ inuse = DIV64_U64_ROUND_UP( parent->child_adjusted_sum * iocg->hweight_after_donation, parent->hweight_inuse); TRACE_IOCG_PATH(inuse_transfer, iocg, now, iocg->inuse, inuse, iocg->hweight_inuse, iocg->hweight_after_donation); __propagate_weights(iocg, iocg->active, inuse, true, now); } /* walk list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &inner_walk, walk_list) list_del_init(&iocg->walk_list); } /* * A low weight iocg can amass a large amount of debt, for example, when * anonymous memory gets reclaimed aggressively. If the system has a lot of * memory paired with a slow IO device, the debt can span multiple seconds or * more. If there are no other subsequent IO issuers, the in-debt iocg may end * up blocked paying its debt while the IO device is idle. * * The following protects against such cases. If the device has been * sufficiently idle for a while, the debts are halved and delays are * recalculated. */ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, struct ioc_now *now) { struct ioc_gq *iocg; u64 dur, usage_pct, nr_cycles, nr_cycles_shift; /* if no debtor, reset the cycle */ if (!nr_debtors) { ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc->dfgv_usage_us_sum = 0; return; } /* * Debtors can pass through a lot of writes choking the device and we * don't want to be forgiving debts while the device is struggling from * write bursts. If we're missing latency targets, consider the device * fully utilized. */ if (ioc->busy_level > 0) usage_us_sum = max_t(u64, usage_us_sum, ioc->period_us); ioc->dfgv_usage_us_sum += usage_us_sum; if (time_before64(now->now, ioc->dfgv_period_at + DFGV_PERIOD)) return; /* * At least DFGV_PERIOD has passed since the last period. Calculate the * average usage and reset the period counters. */ dur = now->now - ioc->dfgv_period_at; usage_pct = div64_u64(100 * ioc->dfgv_usage_us_sum, dur); ioc->dfgv_period_at = now->now; ioc->dfgv_usage_us_sum = 0; /* if was too busy, reset everything */ if (usage_pct > DFGV_USAGE_PCT) { ioc->dfgv_period_rem = 0; return; } /* * Usage is lower than threshold. Let's forgive some debts. Debt * forgiveness runs off of the usual ioc timer but its period usually * doesn't match ioc's. Compensate the difference by performing the * reduction as many times as would fit in the duration since the last * run and carrying over the left-over duration in @ioc->dfgv_period_rem * - if ioc period is 75% of DFGV_PERIOD, one out of three consecutive * reductions is doubled. */ nr_cycles = dur + ioc->dfgv_period_rem; ioc->dfgv_period_rem = do_div(nr_cycles, DFGV_PERIOD); list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 __maybe_unused old_debt, __maybe_unused old_delay; if (!iocg->abs_vdebt && !iocg->delay) continue; spin_lock(&iocg->waitq.lock); old_debt = iocg->abs_vdebt; old_delay = iocg->delay; nr_cycles_shift = min_t(u64, nr_cycles, BITS_PER_LONG - 1); if (iocg->abs_vdebt) iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles_shift ?: 1; if (iocg->delay) iocg->delay = iocg->delay >> nr_cycles_shift ?: 1; iocg_kick_waitq(iocg, true, now); TRACE_IOCG_PATH(iocg_forgive_debt, iocg, now, usage_pct, old_debt, iocg->abs_vdebt, old_delay, iocg->delay); spin_unlock(&iocg->waitq.lock); } } /* * Check the active iocgs' state to avoid oversleeping and deactive * idle iocgs. * * Since waiters determine the sleep durations based on the vrate * they saw at the time of sleep, if vrate has increased, some * waiters could be sleeping for too long. Wake up tardy waiters * which should have woken up in the last period and expire idle * iocgs. */ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now) { int nr_debtors = 0; struct ioc_gq *iocg, *tiocg; list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && !iocg->delay && !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); /* flush wait and indebt stat deltas */ if (iocg->wait_since) { iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = now->now; } if (iocg->indebt_since) { iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = now->now; } if (iocg->indelay_since) { iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = now->now; } if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt || iocg->delay) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, true, now); if (iocg->abs_vdebt || iocg->delay) nr_debtors++; } else if (iocg_is_idle(iocg)) { /* no waiter and idle, deactivate */ u64 vtime = atomic64_read(&iocg->vtime); s64 excess; /* * @iocg has been inactive for a full duration and will * have a high budget. Account anything above target as * error and throw away. On reactivation, it'll start * with the target budget. */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { u32 old_hwi; current_hweight(iocg, NULL, &old_hwi); ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } TRACE_IOCG_PATH(iocg_idle, iocg, now, atomic64_read(&iocg->active_period), atomic64_read(&ioc->cur_period), vtime); __propagate_weights(iocg, 0, 0, false, now); list_del_init(&iocg->active_list); } spin_unlock(&iocg->waitq.lock); } commit_weights(ioc); return nr_debtors; } static void ioc_timer_fn(struct timer_list *timer) { struct ioc *ioc = container_of(timer, struct ioc, timer); struct ioc_gq *iocg, *tiocg; struct ioc_now now; LIST_HEAD(surpluses); int nr_debtors, nr_shortages = 0, nr_lagging = 0; u64 usage_us_sum = 0; u32 ppm_rthr; u32 ppm_wthr; u32 missed_ppm[2], rq_wait_pct; u64 period_vtime; int prev_busy_level; /* how were the latencies during the period? */ ioc_lat_stat(ioc, missed_ppm, &rq_wait_pct); /* take care of active iocgs */ spin_lock_irq(&ioc->lock); ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM]; ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM]; ioc_now(ioc, &now); period_vtime = now.vnow - ioc->period_at_vtime; if (WARN_ON_ONCE(!period_vtime)) { spin_unlock_irq(&ioc->lock); return; } nr_debtors = ioc_check_iocgs(ioc, &now); /* * Wait and indebt stat are flushed above and the donation calculation * below needs updated usage stat. Let's bring stat up-to-date. */ iocg_flush_stat(&ioc->active_iocgs, &now); /* calc usage and see whether some weights need to be moved around */ list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 vdone, vtime, usage_us; u32 hw_active, hw_inuse; /* * Collect unused and wind vtime closer to vnow to prevent * iocgs from accumulating a large amount of budget. */ vdone = atomic64_read(&iocg->done_vtime); vtime = atomic64_read(&iocg->vtime); current_hweight(iocg, &hw_active, &hw_inuse); /* * Latency QoS detection doesn't account for IOs which are * in-flight for longer than a period. Detect them by * comparing vdone against period start. If lagging behind * IOs from past periods, don't increase vrate. */ if ((ppm_rthr != MILLION || ppm_wthr != MILLION) && !atomic_read(&iocg_to_blkg(iocg)->use_delay) && time_after64(vtime, vdone) && time_after64(vtime, now.vnow - MAX_LAGGING_PERIODS * period_vtime) && time_before64(vdone, now.vnow - period_vtime)) nr_lagging++; /* * Determine absolute usage factoring in in-flight IOs to avoid * high-latency completions appearing as idle. */ usage_us = iocg->usage_delta_us; usage_us_sum += usage_us; /* see whether there's surplus vtime */ WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); if (hw_inuse < hw_active || (!waitqueue_active(&iocg->waitq) && time_before64(vtime, now.vnow - ioc->margins.low))) { u32 hwa, old_hwi, hwm, new_hwi, usage; u64 usage_dur; if (vdone != vtime) { u64 inflight_us = DIV64_U64_ROUND_UP( cost_to_abs_cost(vtime - vdone, hw_inuse), ioc->vtime_base_rate); usage_us = max(usage_us, inflight_us); } /* convert to hweight based usage ratio */ if (time_after64(iocg->activated_at, ioc->period_at)) usage_dur = max_t(u64, now.now - iocg->activated_at, 1); else usage_dur = max_t(u64, now.now - ioc->period_at, 1); usage = clamp_t(u32, DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE, usage_dur), 1, WEIGHT_ONE); /* * Already donating or accumulated enough to start. * Determine the donation amount. */ current_hweight(iocg, &hwa, &old_hwi); hwm = current_hweight_max(iocg); new_hwi = hweight_after_donation(iocg, old_hwi, hwm, usage, &now); /* * Donation calculation assumes hweight_after_donation * to be positive, a condition that a donor w/ hwa < 2 * can't meet. Don't bother with donation if hwa is * below 2. It's not gonna make a meaningful difference * anyway. */ if (new_hwi < hwm && hwa >= 2) { iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); } else if (!iocg->abs_vdebt) { /* * @iocg doesn't have enough to donate. Reset * its inuse to active. * * Don't reset debtors as their inuse's are * owned by debt handling. This shouldn't affect * donation calculuation in any meaningful way * as @iocg doesn't have a meaningful amount of * share anyway. */ TRACE_IOCG_PATH(inuse_shortage, iocg, &now, iocg->inuse, iocg->active, iocg->hweight_inuse, new_hwi); __propagate_weights(iocg, iocg->active, iocg->active, true, &now); nr_shortages++; } } else { /* genuinely short on vtime */ nr_shortages++; } } if (!list_empty(&surpluses) && nr_shortages) transfer_surpluses(&surpluses, &now); commit_weights(ioc); /* surplus list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &surpluses, surplus_list) list_del_init(&iocg->surplus_list); /* * If q is getting clogged or we're missing too much, we're issuing * too much IO and should lower vtime rate. If we're not missing * and experiencing shortages but not surpluses, we're too stingy * and should increase vtime rate. */ prev_busy_level = ioc->busy_level; if (rq_wait_pct > RQ_WAIT_BUSY_PCT || missed_ppm[READ] > ppm_rthr || missed_ppm[WRITE] > ppm_wthr) { /* clearly missing QoS targets, slow down vrate */ ioc->busy_level = max(ioc->busy_level, 0); ioc->busy_level++; } else if (rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 && missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 && missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) { /* QoS targets are being met with >25% margin */ if (nr_shortages) { /* * We're throttling while the device has spare * capacity. If vrate was being slowed down, stop. */ ioc->busy_level = min(ioc->busy_level, 0); /* * If there are IOs spanning multiple periods, wait * them out before pushing the device harder. */ if (!nr_lagging) ioc->busy_level--; } else { /* * Nobody is being throttled and the users aren't * issuing enough IOs to saturate the device. We * simply don't know how close the device is to * saturation. Coast. */ ioc->busy_level = 0; } } else { /* inside the hysterisis margin, we're good */ ioc->busy_level = 0; } ioc->busy_level = clamp(ioc->busy_level, -1000, 1000); ioc_adjust_base_vrate(ioc, rq_wait_pct, nr_lagging, nr_shortages, prev_busy_level, missed_ppm); ioc_refresh_params(ioc, false); ioc_forgive_debts(ioc, usage_us_sum, nr_debtors, &now); /* * This period is done. Move onto the next one. If nothing's * going on with the device, stop the timer. */ atomic64_inc(&ioc->cur_period); if (ioc->running != IOC_STOP) { if (!list_empty(&ioc->active_iocgs)) { ioc_start_period(ioc, &now); } else { ioc->busy_level = 0; ioc->vtime_err = 0; ioc->running = IOC_IDLE; } ioc_refresh_vrate(ioc, &now); } spin_unlock_irq(&ioc->lock); } static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, u64 abs_cost, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct ioc_margins *margins = &ioc->margins; u32 __maybe_unused old_inuse = iocg->inuse, __maybe_unused old_hwi; u32 hwi, adj_step; s64 margin; u64 cost, new_inuse; unsigned long flags; current_hweight(iocg, NULL, &hwi); old_hwi = hwi; cost = abs_cost_to_cost(abs_cost, hwi); margin = now->vnow - vtime - cost; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return cost; /* * We only increase inuse during period and do so if the margin has * deteriorated since the previous adjustment. */ if (margin >= iocg->saved_margin || margin >= margins->low || iocg->inuse == iocg->active) return cost; spin_lock_irqsave(&ioc->lock, flags); /* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { spin_unlock_irqrestore(&ioc->lock, flags); return cost; } /* * Bump up inuse till @abs_cost fits in the existing budget. * adj_step must be determined after acquiring ioc->lock - we might * have raced and lost to another thread for activation and could * be reading 0 iocg->active before ioc->lock which will lead to * infinite loop. */ new_inuse = iocg->inuse; adj_step = DIV_ROUND_UP(iocg->active * INUSE_ADJ_STEP_PCT, 100); do { new_inuse = new_inuse + adj_step; propagate_weights(iocg, iocg->active, new_inuse, true, now); current_hweight(iocg, NULL, &hwi); cost = abs_cost_to_cost(abs_cost, hwi); } while (time_after64(vtime + cost, now->vnow) && iocg->inuse != iocg->active); spin_unlock_irqrestore(&ioc->lock, flags); TRACE_IOCG_PATH(inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi); return cost; } static void calc_vtime_cost_builtin(struct bio *bio, struct ioc_gq *iocg, bool is_merge, u64 *costp) { struct ioc *ioc = iocg->ioc; u64 coef_seqio, coef_randio, coef_page; u64 pages = max_t(u64, bio_sectors(bio) >> IOC_SECT_TO_PAGE_SHIFT, 1); u64 seek_pages = 0; u64 cost = 0; /* Can't calculate cost for empty bio */ if (!bio->bi_iter.bi_size) goto out; switch (bio_op(bio)) { case REQ_OP_READ: coef_seqio = ioc->params.lcoefs[LCOEF_RSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_RRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: coef_seqio = ioc->params.lcoefs[LCOEF_WSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_WRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_WPAGE]; break; default: goto out; } if (iocg->cursor) { seek_pages = abs(bio->bi_iter.bi_sector - iocg->cursor); seek_pages >>= IOC_SECT_TO_PAGE_SHIFT; } if (!is_merge) { if (seek_pages > LCOEF_RANDIO_PAGES) { cost += coef_randio; } else { cost += coef_seqio; } } cost += pages * coef_page; out: *costp = cost; } static u64 calc_vtime_cost(struct bio *bio, struct ioc_gq *iocg, bool is_merge) { u64 cost; calc_vtime_cost_builtin(bio, iocg, is_merge, &cost); return cost; } static void calc_size_vtime_cost_builtin(struct request *rq, struct ioc *ioc, u64 *costp) { unsigned int pages = blk_rq_stats_sectors(rq) >> IOC_SECT_TO_PAGE_SHIFT; switch (req_op(rq)) { case REQ_OP_READ: *costp = pages * ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: *costp = pages * ioc->params.lcoefs[LCOEF_WPAGE]; break; default: *costp = 0; } } static u64 calc_size_vtime_cost(struct request *rq, struct ioc *ioc) { u64 cost; calc_size_vtime_cost_builtin(rq, ioc, &cost); return cost; } static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_gq *iocg = blkg_to_iocg(blkg); struct ioc_now now; struct iocg_wait wait; u64 abs_cost, cost, vtime; bool use_debt, ioc_locked; unsigned long flags; /* bypass IOs if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; /* calculate the absolute vtime cost */ abs_cost = calc_vtime_cost(bio, iocg, false); if (!abs_cost) return; if (!iocg_activate(iocg, &now)) return; iocg->cursor = bio_end_sector(bio); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* * If no one's waiting and within budget, issue right away. The * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. This can be handled in two ways. IOs which may * cause priority inversions are punted to @ioc->aux_iocg and charged as * debt. Otherwise, the issuer is blocked on @iocg->waitq. Debt handling * requires @ioc->lock, waitq handling @iocg->waitq.lock. Determine * whether debt handling is needed and acquire locks accordingly. */ use_debt = bio_issue_as_root_blkg(bio) || fatal_signal_pending(current); ioc_locked = use_debt || READ_ONCE(iocg->abs_vdebt); retry_lock: iocg_lock(iocg, ioc_locked, &flags); /* * @iocg must stay activated for debt and waitq handling. Deactivation * is synchronized against both ioc->lock and waitq.lock and we won't * get deactivated as long as we're waiting or has debt, so we're good * if we're activated here. In the unlikely cases that we aren't, just * issue the IO. */ if (unlikely(list_empty(&iocg->active_list))) { iocg_unlock(iocg, ioc_locked, &flags); iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. If @bio has to be issued regardless, remember * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay * off the debt before waking more IOs. * * This way, the debt is continuously paid off each period with the * actual budget available to the cgroup. If we just wound vtime, we * would incorrectly use the current hw_inuse for the entire amount * which, for example, can lead to the cgroup staying blocked for a * long time even with substantially raised hw_inuse. * * An iocg with vdebt should stay online so that the timer can keep * deducting its vdebt and [de]activate use_delay mechanism * accordingly. We don't want to race against the timer trying to * clear them and leave @iocg inactive w/ dangling use_delay heavily * penalizing the cgroup and its descendants. */ if (use_debt) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); iocg_unlock(iocg, ioc_locked, &flags); return; } /* guarantee that iocgs w/ waiters have maximum inuse */ if (!iocg->abs_vdebt && iocg->inuse != iocg->active) { if (!ioc_locked) { iocg_unlock(iocg, false, &flags); ioc_locked = true; goto retry_lock; } propagate_weights(iocg, iocg->active, iocg->active, true, &now); } /* * Append self to the waitq and schedule the wakeup timer if we're * the first waiter. The timer duration is calculated based on the * current vrate. vtime and hweight changes can make it too short * or too long. Each wait entry records the absolute cost it's * waiting for to allow re-evaluation using a custom wait entry. * * If too short, the timer simply reschedules itself. If too long, * the period timer will notice and trigger wakeups. * * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; wait.abs_cost = abs_cost; wait.committed = false; /* will be set true by waker */ __add_wait_queue_entry_tail(&iocg->waitq, &wait.wait); iocg_kick_waitq(iocg, ioc_locked, &now); iocg_unlock(iocg, ioc_locked, &flags); while (true) { set_current_state(TASK_UNINTERRUPTIBLE); if (wait.committed) break; io_schedule(); } /* waker already committed us, proceed */ finish_wait(&iocg->waitq, &wait.wait); } static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); struct ioc *ioc = rqos_to_ioc(rqos); sector_t bio_end = bio_end_sector(bio); struct ioc_now now; u64 vtime, abs_cost, cost; unsigned long flags; /* bypass if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; abs_cost = calc_vtime_cost(bio, iocg, true); if (!abs_cost) return; ioc_now(ioc, &now); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* update cursor if backmerging into the request at the cursor */ if (blk_rq_pos(rq) < bio_end && blk_rq_pos(rq) + blk_rq_sectors(rq) == iocg->cursor) iocg->cursor = bio_end; /* * Charge if there's enough vtime budget and the existing request has * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * Otherwise, account it as debt if @iocg is online, which it should * be for the vast majority of cases. See debt handling in * ioc_rqos_throttle() for details. */ spin_lock_irqsave(&ioc->lock, flags); spin_lock(&iocg->waitq.lock); if (likely(!list_empty(&iocg->active_list))) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); } else { iocg_commit_bio(iocg, bio, abs_cost, cost); } spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); if (iocg && bio->bi_iocost_cost) atomic64_add(bio->bi_iocost_cost, &iocg->done_vtime); } static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq) { struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_pcpu_stat *ccs; u64 on_q_ns, rq_wait_ns, size_nsec; int pidx, rw; if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns) return; switch (req_op(rq)) { case REQ_OP_READ: pidx = QOS_RLAT; rw = READ; break; case REQ_OP_WRITE: pidx = QOS_WLAT; rw = WRITE; break; default: return; } on_q_ns = blk_time_get_ns() - rq->alloc_time_ns; rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns; size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC); ccs = get_cpu_ptr(ioc->pcpu_stat); if (on_q_ns <= size_nsec || on_q_ns - size_nsec <= ioc->params.qos[pidx] * NSEC_PER_USEC) local_inc(&ccs->missed[rw].nr_met); else local_inc(&ccs->missed[rw].nr_missed); local64_add(rq_wait_ns, &ccs->rq_wait_ns); put_cpu_ptr(ccs); } static void ioc_rqos_queue_depth_changed(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); spin_lock_irq(&ioc->lock); ioc_refresh_params(ioc, false); spin_unlock_irq(&ioc->lock); } static void ioc_rqos_exit(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); blkcg_deactivate_policy(rqos->disk, &blkcg_policy_iocost); spin_lock_irq(&ioc->lock); ioc->running = IOC_STOP; spin_unlock_irq(&ioc->lock); timer_shutdown_sync(&ioc->timer); free_percpu(ioc->pcpu_stat); kfree(ioc); } static const struct rq_qos_ops ioc_rqos_ops = { .throttle = ioc_rqos_throttle, .merge = ioc_rqos_merge, .done_bio = ioc_rqos_done_bio, .done = ioc_rqos_done, .queue_depth_changed = ioc_rqos_queue_depth_changed, .exit = ioc_rqos_exit, }; static int blk_iocost_init(struct gendisk *disk) { struct ioc *ioc; int i, cpu, ret; ioc = kzalloc(sizeof(*ioc), GFP_KERNEL); if (!ioc) return -ENOMEM; ioc->pcpu_stat = alloc_percpu(struct ioc_pcpu_stat); if (!ioc->pcpu_stat) { kfree(ioc); return -ENOMEM; } for_each_possible_cpu(cpu) { struct ioc_pcpu_stat *ccs = per_cpu_ptr(ioc->pcpu_stat, cpu); for (i = 0; i < ARRAY_SIZE(ccs->missed); i++) { local_set(&ccs->missed[i].nr_met, 0); local_set(&ccs->missed[i].nr_missed, 0); } local64_set(&ccs->rq_wait_ns, 0); } spin_lock_init(&ioc->lock); timer_setup(&ioc->timer, ioc_timer_fn, 0); INIT_LIST_HEAD(&ioc->active_iocgs); ioc->running = IOC_IDLE; ioc->vtime_base_rate = VTIME_PER_USEC; atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock); ioc->period_at = ktime_to_us(blk_time_get()); atomic64_set(&ioc->cur_period, 0); atomic_set(&ioc->hweight_gen, 0); spin_lock_irq(&ioc->lock); ioc->autop_idx = AUTOP_INVALID; ioc_refresh_params_disk(ioc, true, disk); spin_unlock_irq(&ioc->lock); /* * rqos must be added before activation to allow ioc_pd_init() to * lookup the ioc from q. This means that the rqos methods may get * called before policy activation completion, can't assume that the * target bio has an iocg associated and need to test for NULL iocg. */ ret = rq_qos_add(&ioc->rqos, disk, RQ_QOS_COST, &ioc_rqos_ops); if (ret) goto err_free_ioc; ret = blkcg_activate_policy(disk, &blkcg_policy_iocost); if (ret) goto err_del_qos; return 0; err_del_qos: rq_qos_del(&ioc->rqos); err_free_ioc: free_percpu(ioc->pcpu_stat); kfree(ioc); return ret; } static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp) { struct ioc_cgrp *iocc; iocc = kzalloc(sizeof(struct ioc_cgrp), gfp); if (!iocc) return NULL; iocc->dfl_weight = CGROUP_WEIGHT_DFL * WEIGHT_ONE; return &iocc->cpd; } static void ioc_cpd_free(struct blkcg_policy_data *cpd) { kfree(container_of(cpd, struct ioc_cgrp, cpd)); } static struct blkg_policy_data *ioc_pd_alloc(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp) { int levels = blkcg->css.cgroup->level + 1; struct ioc_gq *iocg; iocg = kzalloc_node(struct_size(iocg, ancestors, levels), gfp, disk->node_id); if (!iocg) return NULL; iocg->pcpu_stat = alloc_percpu_gfp(struct iocg_pcpu_stat, gfp); if (!iocg->pcpu_stat) { kfree(iocg); return NULL; } return &iocg->pd; } static void ioc_pd_init(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct blkcg_gq *blkg = pd_to_blkg(&iocg->pd); struct ioc *ioc = q_to_ioc(blkg->q); struct ioc_now now; struct blkcg_gq *tblkg; unsigned long flags; ioc_now(ioc, &now); iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); INIT_LIST_HEAD(&iocg->walk_list); INIT_LIST_HEAD(&iocg->surplus_list); iocg->hweight_active = WEIGHT_ONE; iocg->hweight_inuse = WEIGHT_ONE; init_waitqueue_head(&iocg->waitq); hrtimer_init(&iocg->waitq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); iocg->waitq_timer.function = iocg_waitq_timer_fn; iocg->level = blkg->blkcg->css.cgroup->level; for (tblkg = blkg; tblkg; tblkg = tblkg->parent) { struct ioc_gq *tiocg = blkg_to_iocg(tblkg); iocg->ancestors[tiocg->level] = tiocg; } spin_lock_irqsave(&ioc->lock, flags); weight_updated(iocg, &now); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_pd_free(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; unsigned long flags; if (ioc) { spin_lock_irqsave(&ioc->lock, flags); if (!list_empty(&iocg->active_list)) { struct ioc_now now; ioc_now(ioc, &now); propagate_weights(iocg, 0, 0, false, &now); list_del_init(&iocg->active_list); } WARN_ON_ONCE(!list_empty(&iocg->walk_list)); WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); spin_unlock_irqrestore(&ioc->lock, flags); hrtimer_cancel(&iocg->waitq_timer); } free_percpu(iocg->pcpu_stat); kfree(iocg); } static void ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; if (!ioc->enabled) return; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( ioc->vtime_base_rate * 10000, VTIME_PER_USEC); seq_printf(s, " cost.vrate=%u.%02u", vp10k / 100, vp10k % 100); } seq_printf(s, " cost.usage=%llu", iocg->last_stat.usage_us); if (blkcg_debug_stats) seq_printf(s, " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", iocg->last_stat.wait_us, iocg->last_stat.indebt_us, iocg->last_stat.indelay_us); } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc_gq *iocg = pd_to_iocg(pd); if (dname && iocg->cfg_weight) seq_printf(sf, "%s %u\n", dname, iocg->cfg_weight / WEIGHT_ONE); return 0; } static int ioc_weight_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); seq_printf(sf, "default %u\n", iocc->dfl_weight / WEIGHT_ONE); blkcg_print_blkgs(sf, blkcg, ioc_weight_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); struct blkg_conf_ctx ctx; struct ioc_now now; struct ioc_gq *iocg; u32 v; int ret; if (!strchr(buf, ':')) { struct blkcg_gq *blkg; if (!sscanf(buf, "default %u", &v) && !sscanf(buf, "%u", &v)) return -EINVAL; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) return -EINVAL; spin_lock_irq(&blkcg->lock); iocc->dfl_weight = v * WEIGHT_ONE; hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct ioc_gq *iocg = blkg_to_iocg(blkg); if (iocg) { spin_lock(&iocg->ioc->lock); ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); } } spin_unlock_irq(&blkcg->lock); return nbytes; } blkg_conf_init(&ctx, buf); ret = blkg_conf_prep(blkcg, &blkcg_policy_iocost, &ctx); if (ret) goto err; iocg = blkg_to_iocg(ctx.blkg); if (!strncmp(ctx.body, "default", 7)) { v = 0; } else { if (!sscanf(ctx.body, "%u", &v)) goto einval; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) goto einval; } spin_lock(&iocg->ioc->lock); iocg->cfg_weight = v * WEIGHT_ONE; ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); blkg_conf_exit(&ctx); return nbytes; einval: ret = -EINVAL; err: blkg_conf_exit(&ctx); return ret; } static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; if (!dname) return 0; spin_lock(&ioc->lock); seq_printf(sf, "%s enable=%d ctrl=%s rpct=%u.%02u rlat=%u wpct=%u.%02u wlat=%u min=%u.%02u max=%u.%02u\n", dname, ioc->enabled, ioc->user_qos_params ? "user" : "auto", ioc->params.qos[QOS_RPPM] / 10000, ioc->params.qos[QOS_RPPM] % 10000 / 100, ioc->params.qos[QOS_RLAT], ioc->params.qos[QOS_WPPM] / 10000, ioc->params.qos[QOS_WPPM] % 10000 / 100, ioc->params.qos[QOS_WLAT], ioc->params.qos[QOS_MIN] / 10000, ioc->params.qos[QOS_MIN] % 10000 / 100, ioc->params.qos[QOS_MAX] / 10000, ioc->params.qos[QOS_MAX] % 10000 / 100); spin_unlock(&ioc->lock); return 0; } static int ioc_qos_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_qos_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t qos_ctrl_tokens = { { QOS_ENABLE, "enable=%u" }, { QOS_CTRL, "ctrl=%s" }, { NR_QOS_CTRL_PARAMS, NULL }, }; static const match_table_t qos_tokens = { { QOS_RPPM, "rpct=%s" }, { QOS_RLAT, "rlat=%u" }, { QOS_WPPM, "wpct=%s" }, { QOS_WLAT, "wlat=%u" }, { QOS_MIN, "min=%s" }, { QOS_MAX, "max=%s" }, { NR_QOS_PARAMS, NULL }, }; static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct blkg_conf_ctx ctx; struct gendisk *disk; struct ioc *ioc; u32 qos[NR_QOS_PARAMS]; bool enable, user; char *body, *p; int ret; blkg_conf_init(&ctx, input); ret = blkg_conf_open_bdev(&ctx); if (ret) goto err; body = ctx.body; disk = ctx.bdev->bd_disk; if (!queue_is_mq(disk->queue)) { ret = -EOPNOTSUPP; goto err; } ioc = q_to_ioc(disk->queue); if (!ioc) { ret = blk_iocost_init(disk); if (ret) goto err; ioc = q_to_ioc(disk->queue); } blk_mq_freeze_queue(disk->queue); blk_mq_quiesce_queue(disk->queue); spin_lock_irq(&ioc->lock); memcpy(qos, ioc->params.qos, sizeof(qos)); enable = ioc->enabled; user = ioc->user_qos_params; while ((p = strsep(&body, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; s64 v; if (!*p) continue; switch (match_token(p, qos_ctrl_tokens, args)) { case QOS_ENABLE: if (match_u64(&args[0], &v)) goto einval; enable = v; continue; case QOS_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; } tok = match_token(p, qos_tokens, args); switch (tok) { case QOS_RPPM: case QOS_WPPM: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0 || v > 10000) goto einval; qos[tok] = v * 100; break; case QOS_RLAT: case QOS_WLAT: if (match_u64(&args[0], &v)) goto einval; qos[tok] = v; break; case QOS_MIN: case QOS_MAX: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0) goto einval; qos[tok] = clamp_t(s64, v * 100, VRATE_MIN_PPM, VRATE_MAX_PPM); break; default: goto einval; } user = true; } if (qos[QOS_MIN] > qos[QOS_MAX]) goto einval; if (enable && !ioc->enabled) { blk_stat_enable_accounting(disk->queue); blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = true; } else if (!enable && ioc->enabled) { blk_stat_disable_accounting(disk->queue); blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = false; } if (user) { memcpy(ioc->params.qos, qos, sizeof(qos)); ioc->user_qos_params = true; } else { ioc->user_qos_params = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); if (enable) wbt_disable_default(disk); else wbt_enable_default(disk); blk_mq_unquiesce_queue(disk->queue); blk_mq_unfreeze_queue(disk->queue); blkg_conf_exit(&ctx); return nbytes; einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(disk->queue); blk_mq_unfreeze_queue(disk->queue); ret = -EINVAL; err: blkg_conf_exit(&ctx); return ret; } static u64 ioc_cost_model_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; u64 *u = ioc->params.i_lcoefs; if (!dname) return 0; spin_lock(&ioc->lock); seq_printf(sf, "%s ctrl=%s model=linear " "rbps=%llu rseqiops=%llu rrandiops=%llu " "wbps=%llu wseqiops=%llu wrandiops=%llu\n", dname, ioc->user_cost_model ? "user" : "auto", u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]); spin_unlock(&ioc->lock); return 0; } static int ioc_cost_model_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_cost_model_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t cost_ctrl_tokens = { { COST_CTRL, "ctrl=%s" }, { COST_MODEL, "model=%s" }, { NR_COST_CTRL_PARAMS, NULL }, }; static const match_table_t i_lcoef_tokens = { { I_LCOEF_RBPS, "rbps=%u" }, { I_LCOEF_RSEQIOPS, "rseqiops=%u" }, { I_LCOEF_RRANDIOPS, "rrandiops=%u" }, { I_LCOEF_WBPS, "wbps=%u" }, { I_LCOEF_WSEQIOPS, "wseqiops=%u" }, { I_LCOEF_WRANDIOPS, "wrandiops=%u" }, { NR_I_LCOEFS, NULL }, }; static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct blkg_conf_ctx ctx; struct request_queue *q; struct ioc *ioc; u64 u[NR_I_LCOEFS]; bool user; char *body, *p; int ret; blkg_conf_init(&ctx, input); ret = blkg_conf_open_bdev(&ctx); if (ret) goto err; body = ctx.body; q = bdev_get_queue(ctx.bdev); if (!queue_is_mq(q)) { ret = -EOPNOTSUPP; goto err; } ioc = q_to_ioc(q); if (!ioc) { ret = blk_iocost_init(ctx.bdev->bd_disk); if (ret) goto err; ioc = q_to_ioc(q); } blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); spin_lock_irq(&ioc->lock); memcpy(u, ioc->params.i_lcoefs, sizeof(u)); user = ioc->user_cost_model; while ((p = strsep(&body, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; u64 v; if (!*p) continue; switch (match_token(p, cost_ctrl_tokens, args)) { case COST_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; case COST_MODEL: match_strlcpy(buf, &args[0], sizeof(buf)); if (strcmp(buf, "linear")) goto einval; continue; } tok = match_token(p, i_lcoef_tokens, args); if (tok == NR_I_LCOEFS) goto einval; if (match_u64(&args[0], &v)) goto einval; u[tok] = v; user = true; } if (user) { memcpy(ioc->params.i_lcoefs, u, sizeof(u)); ioc->user_cost_model = true; } else { ioc->user_cost_model = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); blkg_conf_exit(&ctx); return nbytes; einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); ret = -EINVAL; err: blkg_conf_exit(&ctx); return ret; } static struct cftype ioc_files[] = { { .name = "weight", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = ioc_weight_show, .write = ioc_weight_write, }, { .name = "cost.qos", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_qos_show, .write = ioc_qos_write, }, { .name = "cost.model", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_cost_model_show, .write = ioc_cost_model_write, }, {} }; static struct blkcg_policy blkcg_policy_iocost = { .dfl_cftypes = ioc_files, .cpd_alloc_fn = ioc_cpd_alloc, .cpd_free_fn = ioc_cpd_free, .pd_alloc_fn = ioc_pd_alloc, .pd_init_fn = ioc_pd_init, .pd_free_fn = ioc_pd_free, .pd_stat_fn = ioc_pd_stat, }; static int __init ioc_init(void) { return blkcg_policy_register(&blkcg_policy_iocost); } static void __exit ioc_exit(void) { blkcg_policy_unregister(&blkcg_policy_iocost); } module_init(ioc_init); module_exit(ioc_exit); |
| 54 54 168 169 169 67 14 54 54 54 159 159 159 63 63 76 76 224 224 223 186 54 54 175 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "btree_key_cache.h" #include "btree_update.h" #include "errcode.h" #include "error.h" #include "fs.h" #include "snapshot.h" #include "subvolume.h" #include <linux/random.h> static int bch2_subvolume_delete(struct btree_trans *, u32); static struct bpos subvolume_children_pos(struct bkey_s_c k) { if (k.k->type != KEY_TYPE_subvolume) return POS_MIN; struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); if (!s.v->fs_path_parent) return POS_MIN; return POS(le32_to_cpu(s.v->fs_path_parent), s.k->p.offset); } static int check_subvol(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct bkey_s_c_subvolume subvol; struct btree_iter subvol_children_iter = {}; struct bch_snapshot snapshot; struct printbuf buf = PRINTBUF; unsigned snapid; int ret = 0; if (k.k->type != KEY_TYPE_subvolume) return 0; subvol = bkey_s_c_to_subvolume(k); snapid = le32_to_cpu(subvol.v->snapshot); ret = bch2_snapshot_lookup(trans, snapid, &snapshot); if (bch2_err_matches(ret, ENOENT)) bch_err(c, "subvolume %llu points to nonexistent snapshot %u", k.k->p.offset, snapid); if (ret) return ret; if (BCH_SUBVOLUME_UNLINKED(subvol.v)) { ret = bch2_subvolume_delete(trans, iter->pos.offset); bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset); return ret ?: -BCH_ERR_transaction_restart_nested; } if (fsck_err_on(subvol.k->p.offset == BCACHEFS_ROOT_SUBVOL && subvol.v->fs_path_parent, trans, subvol_root_fs_path_parent_nonzero, "root subvolume has nonzero fs_path_parent\n%s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { struct bkey_i_subvolume *n = bch2_bkey_make_mut_typed(trans, iter, &subvol.s_c, 0, subvolume); ret = PTR_ERR_OR_ZERO(n); if (ret) goto err; n->v.fs_path_parent = 0; } if (subvol.v->fs_path_parent) { struct bpos pos = subvolume_children_pos(k); struct bkey_s_c subvol_children_k = bch2_bkey_get_iter(trans, &subvol_children_iter, BTREE_ID_subvolume_children, pos, 0); ret = bkey_err(subvol_children_k); if (ret) goto err; if (fsck_err_on(subvol_children_k.k->type != KEY_TYPE_set, trans, subvol_children_not_set, "subvolume not set in subvolume_children btree at %llu:%llu\n%s", pos.inode, pos.offset, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = bch2_btree_bit_mod(trans, BTREE_ID_subvolume_children, pos, true); if (ret) goto err; } } struct bch_inode_unpacked inode; ret = bch2_inode_find_by_inum_nowarn_trans(trans, (subvol_inum) { k.k->p.offset, le64_to_cpu(subvol.v->inode) }, &inode); if (!ret) { if (fsck_err_on(inode.bi_subvol != subvol.k->p.offset, trans, subvol_root_wrong_bi_subvol, "subvol root %llu:%u has wrong bi_subvol field: got %u, should be %llu", inode.bi_inum, inode.bi_snapshot, inode.bi_subvol, subvol.k->p.offset)) { inode.bi_subvol = subvol.k->p.offset; inode.bi_snapshot = le32_to_cpu(subvol.v->snapshot); ret = __bch2_fsck_write_inode(trans, &inode); if (ret) goto err; } } else if (bch2_err_matches(ret, ENOENT)) { if (fsck_err(trans, subvol_to_missing_root, "subvolume %llu points to missing subvolume root %llu:%u", k.k->p.offset, le64_to_cpu(subvol.v->inode), le32_to_cpu(subvol.v->snapshot))) { ret = bch2_subvolume_delete(trans, iter->pos.offset); bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset); ret = ret ?: -BCH_ERR_transaction_restart_nested; goto err; } } else { goto err; } if (!BCH_SUBVOLUME_SNAP(subvol.v)) { u32 snapshot_root = bch2_snapshot_root(c, le32_to_cpu(subvol.v->snapshot)); u32 snapshot_tree; struct bch_snapshot_tree st; rcu_read_lock(); snapshot_tree = snapshot_t(c, snapshot_root)->tree; rcu_read_unlock(); ret = bch2_snapshot_tree_lookup(trans, snapshot_tree, &st); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), c, "%s: snapshot tree %u not found", __func__, snapshot_tree); if (ret) goto err; if (fsck_err_on(le32_to_cpu(st.master_subvol) != subvol.k->p.offset, trans, subvol_not_master_and_not_snapshot, "subvolume %llu is not set as snapshot but is not master subvolume", k.k->p.offset)) { struct bkey_i_subvolume *s = bch2_bkey_make_mut_typed(trans, iter, &subvol.s_c, 0, subvolume); ret = PTR_ERR_OR_ZERO(s); if (ret) goto err; SET_BCH_SUBVOLUME_SNAP(&s->v, true); } } err: fsck_err: bch2_trans_iter_exit(trans, &subvol_children_iter); printbuf_exit(&buf); return ret; } int bch2_check_subvols(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_subvol(trans, &iter, k))); bch_err_fn(c, ret); return ret; } static int check_subvol_child(struct btree_trans *trans, struct btree_iter *child_iter, struct bkey_s_c child_k) { struct bch_subvolume s; int ret = bch2_bkey_get_val_typed(trans, BTREE_ID_subvolumes, POS(0, child_k.k->p.offset), 0, subvolume, &s); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if (fsck_err_on(ret || le32_to_cpu(s.fs_path_parent) != child_k.k->p.inode, trans, subvol_children_bad, "incorrect entry in subvolume_children btree %llu:%llu", child_k.k->p.inode, child_k.k->p.offset)) { ret = bch2_btree_delete_at(trans, child_iter, 0); if (ret) goto err; } err: fsck_err: return ret; } int bch2_check_subvol_children(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_subvolume_children, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_subvol_child(trans, &iter, k))); bch_err_fn(c, ret); return 0; } /* Subvolumes: */ int bch2_subvolume_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { struct bkey_s_c_subvolume subvol = bkey_s_c_to_subvolume(k); int ret = 0; bkey_fsck_err_on(bkey_lt(k.k->p, SUBVOL_POS_MIN) || bkey_gt(k.k->p, SUBVOL_POS_MAX), c, subvol_pos_bad, "invalid pos"); bkey_fsck_err_on(!subvol.v->snapshot, c, subvol_snapshot_bad, "invalid snapshot"); bkey_fsck_err_on(!subvol.v->inode, c, subvol_inode_bad, "invalid inode"); fsck_err: return ret; } void bch2_subvolume_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); prt_printf(out, "root %llu snapshot id %u", le64_to_cpu(s.v->inode), le32_to_cpu(s.v->snapshot)); if (bkey_val_bytes(s.k) > offsetof(struct bch_subvolume, creation_parent)) { prt_printf(out, " creation_parent %u", le32_to_cpu(s.v->creation_parent)); prt_printf(out, " fs_parent %u", le32_to_cpu(s.v->fs_path_parent)); } } static int subvolume_children_mod(struct btree_trans *trans, struct bpos pos, bool set) { return !bpos_eq(pos, POS_MIN) ? bch2_btree_bit_mod(trans, BTREE_ID_subvolume_children, pos, set) : 0; } int bch2_subvolume_trigger(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c old, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { if (flags & BTREE_TRIGGER_transactional) { struct bpos children_pos_old = subvolume_children_pos(old); struct bpos children_pos_new = subvolume_children_pos(new.s_c); if (!bpos_eq(children_pos_old, children_pos_new)) { int ret = subvolume_children_mod(trans, children_pos_old, false) ?: subvolume_children_mod(trans, children_pos_new, true); if (ret) return ret; } } return 0; } int bch2_subvol_has_children(struct btree_trans *trans, u32 subvol) { struct btree_iter iter; bch2_trans_iter_init(trans, &iter, BTREE_ID_subvolume_children, POS(subvol, 0), 0); struct bkey_s_c k = bch2_btree_iter_peek(&iter); bch2_trans_iter_exit(trans, &iter); return bkey_err(k) ?: k.k && k.k->p.inode == subvol ? -BCH_ERR_ENOTEMPTY_subvol_not_empty : 0; } static __always_inline int bch2_subvolume_get_inlined(struct btree_trans *trans, unsigned subvol, bool inconsistent_if_not_found, struct bch_subvolume *s) { int ret = bch2_bkey_get_val_typed(trans, BTREE_ID_subvolumes, POS(0, subvol), BTREE_ITER_cached| BTREE_ITER_with_updates, subvolume, s); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT) && inconsistent_if_not_found, trans->c, "missing subvolume %u", subvol); return ret; } int bch2_subvolume_get(struct btree_trans *trans, unsigned subvol, bool inconsistent_if_not_found, struct bch_subvolume *s) { return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, s); } int bch2_subvol_is_ro_trans(struct btree_trans *trans, u32 subvol) { struct bch_subvolume s; int ret = bch2_subvolume_get_inlined(trans, subvol, true, &s); if (ret) return ret; if (BCH_SUBVOLUME_RO(&s)) return -EROFS; return 0; } int bch2_subvol_is_ro(struct bch_fs *c, u32 subvol) { return bch2_trans_do(c, bch2_subvol_is_ro_trans(trans, subvol)); } int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot, struct bch_subvolume *subvol) { struct bch_snapshot snap; return bch2_snapshot_lookup(trans, snapshot, &snap) ?: bch2_subvolume_get(trans, le32_to_cpu(snap.subvol), true, subvol); } int __bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, u32 *snapid, bool warn) { struct btree_iter iter; struct bkey_s_c_subvolume subvol; int ret; subvol = bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_subvolumes, POS(0, subvolid), BTREE_ITER_cached|BTREE_ITER_with_updates, subvolume); ret = bkey_err(subvol); bch2_fs_inconsistent_on(warn && bch2_err_matches(ret, ENOENT), trans->c, "missing subvolume %u", subvolid); if (likely(!ret)) *snapid = le32_to_cpu(subvol.v->snapshot); bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid, u32 *snapid) { return __bch2_subvolume_get_snapshot(trans, subvolid, snapid, true); } static int bch2_subvolume_reparent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, u32 old_parent, u32 new_parent) { struct bkey_i_subvolume *s; int ret; if (k.k->type != KEY_TYPE_subvolume) return 0; if (bkey_val_bytes(k.k) > offsetof(struct bch_subvolume, creation_parent) && le32_to_cpu(bkey_s_c_to_subvolume(k).v->creation_parent) != old_parent) return 0; s = bch2_bkey_make_mut_typed(trans, iter, &k, 0, subvolume); ret = PTR_ERR_OR_ZERO(s); if (ret) return ret; s->v.creation_parent = cpu_to_le32(new_parent); return 0; } /* * Separate from the snapshot tree in the snapshots btree, we record the tree * structure of how snapshot subvolumes were created - the parent subvolume of * each snapshot subvolume. * * When a subvolume is deleted, we scan for child subvolumes and reparant them, * to avoid dangling references: */ static int bch2_subvolumes_reparent(struct btree_trans *trans, u32 subvolid_to_delete) { struct bch_subvolume s; return lockrestart_do(trans, bch2_subvolume_get(trans, subvolid_to_delete, true, &s)) ?: for_each_btree_key_commit(trans, iter, BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_subvolume_reparent(trans, &iter, k, subvolid_to_delete, le32_to_cpu(s.creation_parent))); } /* * Delete subvolume, mark snapshot ID as deleted, queue up snapshot * deletion/cleanup: */ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid) { struct btree_iter subvol_iter = {}, snapshot_iter = {}, snapshot_tree_iter = {}; struct bkey_s_c_subvolume subvol = bch2_bkey_get_iter_typed(trans, &subvol_iter, BTREE_ID_subvolumes, POS(0, subvolid), BTREE_ITER_cached|BTREE_ITER_intent, subvolume); int ret = bkey_err(subvol); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing subvolume %u", subvolid); if (ret) goto err; u32 snapid = le32_to_cpu(subvol.v->snapshot); struct bkey_s_c_snapshot snapshot = bch2_bkey_get_iter_typed(trans, &snapshot_iter, BTREE_ID_snapshots, POS(0, snapid), 0, snapshot); ret = bkey_err(subvol); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing snapshot %u", snapid); if (ret) goto err; u32 treeid = le32_to_cpu(snapshot.v->tree); struct bkey_s_c_snapshot_tree snapshot_tree = bch2_bkey_get_iter_typed(trans, &snapshot_tree_iter, BTREE_ID_snapshot_trees, POS(0, treeid), 0, snapshot_tree); if (le32_to_cpu(snapshot_tree.v->master_subvol) == subvolid) { struct bkey_i_snapshot_tree *snapshot_tree_mut = bch2_bkey_make_mut_typed(trans, &snapshot_tree_iter, &snapshot_tree.s_c, 0, snapshot_tree); ret = PTR_ERR_OR_ZERO(snapshot_tree_mut); if (ret) goto err; snapshot_tree_mut->v.master_subvol = 0; } ret = bch2_btree_delete_at(trans, &subvol_iter, 0) ?: bch2_snapshot_node_set_deleted(trans, snapid); err: bch2_trans_iter_exit(trans, &snapshot_tree_iter); bch2_trans_iter_exit(trans, &snapshot_iter); bch2_trans_iter_exit(trans, &subvol_iter); return ret; } static int bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid) { return bch2_subvolumes_reparent(trans, subvolid) ?: commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, __bch2_subvolume_delete(trans, subvolid)); } static void bch2_subvolume_wait_for_pagecache_and_delete(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, snapshot_wait_for_pagecache_and_delete_work); snapshot_id_list s; u32 *id; int ret = 0; while (!ret) { mutex_lock(&c->snapshots_unlinked_lock); s = c->snapshots_unlinked; darray_init(&c->snapshots_unlinked); mutex_unlock(&c->snapshots_unlinked_lock); if (!s.nr) break; bch2_evict_subvolume_inodes(c, &s); for (id = s.data; id < s.data + s.nr; id++) { ret = bch2_trans_run(c, bch2_subvolume_delete(trans, *id)); bch_err_msg(c, ret, "deleting subvolume %u", *id); if (ret) break; } darray_exit(&s); } bch2_write_ref_put(c, BCH_WRITE_REF_snapshot_delete_pagecache); } struct subvolume_unlink_hook { struct btree_trans_commit_hook h; u32 subvol; }; static int bch2_subvolume_wait_for_pagecache_and_delete_hook(struct btree_trans *trans, struct btree_trans_commit_hook *_h) { struct subvolume_unlink_hook *h = container_of(_h, struct subvolume_unlink_hook, h); struct bch_fs *c = trans->c; int ret = 0; mutex_lock(&c->snapshots_unlinked_lock); if (!snapshot_list_has_id(&c->snapshots_unlinked, h->subvol)) ret = snapshot_list_add(c, &c->snapshots_unlinked, h->subvol); mutex_unlock(&c->snapshots_unlinked_lock); if (ret) return ret; if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_snapshot_delete_pagecache)) return -EROFS; if (!queue_work(c->write_ref_wq, &c->snapshot_wait_for_pagecache_and_delete_work)) bch2_write_ref_put(c, BCH_WRITE_REF_snapshot_delete_pagecache); return 0; } int bch2_subvolume_unlink(struct btree_trans *trans, u32 subvolid) { struct btree_iter iter; struct bkey_i_subvolume *n; struct subvolume_unlink_hook *h; int ret = 0; h = bch2_trans_kmalloc(trans, sizeof(*h)); ret = PTR_ERR_OR_ZERO(h); if (ret) return ret; h->h.fn = bch2_subvolume_wait_for_pagecache_and_delete_hook; h->subvol = subvolid; bch2_trans_commit_hook(trans, &h->h); n = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_subvolumes, POS(0, subvolid), BTREE_ITER_cached, subvolume); ret = PTR_ERR_OR_ZERO(n); if (unlikely(ret)) { bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing subvolume %u", subvolid); return ret; } SET_BCH_SUBVOLUME_UNLINKED(&n->v, true); bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_subvolume_create(struct btree_trans *trans, u64 inode, u32 parent_subvolid, u32 src_subvolid, u32 *new_subvolid, u32 *new_snapshotid, bool ro) { struct bch_fs *c = trans->c; struct btree_iter dst_iter, src_iter = (struct btree_iter) { NULL }; struct bkey_i_subvolume *new_subvol = NULL; struct bkey_i_subvolume *src_subvol = NULL; u32 parent = 0, new_nodes[2], snapshot_subvols[2]; int ret = 0; ret = bch2_bkey_get_empty_slot(trans, &dst_iter, BTREE_ID_subvolumes, POS(0, U32_MAX)); if (ret == -BCH_ERR_ENOSPC_btree_slot) ret = -BCH_ERR_ENOSPC_subvolume_create; if (ret) return ret; snapshot_subvols[0] = dst_iter.pos.offset; snapshot_subvols[1] = src_subvolid; if (src_subvolid) { /* Creating a snapshot: */ src_subvol = bch2_bkey_get_mut_typed(trans, &src_iter, BTREE_ID_subvolumes, POS(0, src_subvolid), BTREE_ITER_cached, subvolume); ret = PTR_ERR_OR_ZERO(src_subvol); if (unlikely(ret)) { bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), c, "subvolume %u not found", src_subvolid); goto err; } parent = le32_to_cpu(src_subvol->v.snapshot); } ret = bch2_snapshot_node_create(trans, parent, new_nodes, snapshot_subvols, src_subvolid ? 2 : 1); if (ret) goto err; if (src_subvolid) { src_subvol->v.snapshot = cpu_to_le32(new_nodes[1]); ret = bch2_trans_update(trans, &src_iter, &src_subvol->k_i, 0); if (ret) goto err; } new_subvol = bch2_bkey_alloc(trans, &dst_iter, 0, subvolume); ret = PTR_ERR_OR_ZERO(new_subvol); if (ret) goto err; new_subvol->v.flags = 0; new_subvol->v.snapshot = cpu_to_le32(new_nodes[0]); new_subvol->v.inode = cpu_to_le64(inode); new_subvol->v.creation_parent = cpu_to_le32(src_subvolid); new_subvol->v.fs_path_parent = cpu_to_le32(parent_subvolid); new_subvol->v.otime.lo = cpu_to_le64(bch2_current_time(c)); new_subvol->v.otime.hi = 0; SET_BCH_SUBVOLUME_RO(&new_subvol->v, ro); SET_BCH_SUBVOLUME_SNAP(&new_subvol->v, src_subvolid != 0); *new_subvolid = new_subvol->k.p.offset; *new_snapshotid = new_nodes[0]; err: bch2_trans_iter_exit(trans, &src_iter); bch2_trans_iter_exit(trans, &dst_iter); return ret; } int bch2_initialize_subvolumes(struct bch_fs *c) { struct bkey_i_snapshot_tree root_tree; struct bkey_i_snapshot root_snapshot; struct bkey_i_subvolume root_volume; int ret; bkey_snapshot_tree_init(&root_tree.k_i); root_tree.k.p.offset = 1; root_tree.v.master_subvol = cpu_to_le32(1); root_tree.v.root_snapshot = cpu_to_le32(U32_MAX); bkey_snapshot_init(&root_snapshot.k_i); root_snapshot.k.p.offset = U32_MAX; root_snapshot.v.flags = 0; root_snapshot.v.parent = 0; root_snapshot.v.subvol = cpu_to_le32(BCACHEFS_ROOT_SUBVOL); root_snapshot.v.tree = cpu_to_le32(1); SET_BCH_SNAPSHOT_SUBVOL(&root_snapshot.v, true); bkey_subvolume_init(&root_volume.k_i); root_volume.k.p.offset = BCACHEFS_ROOT_SUBVOL; root_volume.v.flags = 0; root_volume.v.snapshot = cpu_to_le32(U32_MAX); root_volume.v.inode = cpu_to_le64(BCACHEFS_ROOT_INO); ret = bch2_btree_insert(c, BTREE_ID_snapshot_trees, &root_tree.k_i, NULL, 0, 0) ?: bch2_btree_insert(c, BTREE_ID_snapshots, &root_snapshot.k_i, NULL, 0, 0) ?: bch2_btree_insert(c, BTREE_ID_subvolumes, &root_volume.k_i, NULL, 0, 0); bch_err_fn(c, ret); return ret; } static int __bch2_fs_upgrade_for_subvolumes(struct btree_trans *trans) { struct btree_iter iter; struct bkey_s_c k; struct bch_inode_unpacked inode; int ret; k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, SPOS(0, BCACHEFS_ROOT_INO, U32_MAX), 0); ret = bkey_err(k); if (ret) return ret; if (!bkey_is_inode(k.k)) { bch_err(trans->c, "root inode not found"); ret = -BCH_ERR_ENOENT_inode; goto err; } ret = bch2_inode_unpack(k, &inode); BUG_ON(ret); inode.bi_subvol = BCACHEFS_ROOT_SUBVOL; ret = bch2_inode_write(trans, &iter, &inode); err: bch2_trans_iter_exit(trans, &iter); return ret; } /* set bi_subvol on root inode */ int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c) { int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, __bch2_fs_upgrade_for_subvolumes(trans)); bch_err_fn(c, ret); return ret; } int bch2_fs_subvolumes_init(struct bch_fs *c) { INIT_WORK(&c->snapshot_delete_work, bch2_delete_dead_snapshots_work); INIT_WORK(&c->snapshot_wait_for_pagecache_and_delete_work, bch2_subvolume_wait_for_pagecache_and_delete); mutex_init(&c->snapshots_unlinked_lock); return 0; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Common interrupt code for 32 and 64 bit */ #include <linux/cpu.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/of.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/ftrace.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/irq.h> #include <asm/irq_stack.h> #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/irq.h> #include <asm/mce.h> #include <asm/hw_irq.h> #include <asm/desc.h> #include <asm/traps.h> #include <asm/thermal.h> #include <asm/posted_intr.h> #include <asm/irq_remapping.h> #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); atomic_t irq_err_count; /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. */ void ack_bad_irq(unsigned int irq) { if (printk_ratelimit()) pr_err("unexpected IRQ trap at vector %02x\n", irq); /* * Currently unexpected vectors happen only on SMP and APIC. * We _must_ ack these because every local APIC has only N * irq slots per priority level, and a 'hanging, unacked' IRQ * holds up an irq slot - in excessive cases (when multiple * unexpected vectors occur) that might lock up the APIC * completely. * But only ack when the APIC is enabled -AK */ apic_eoi(); } #define irq_stats(x) (&per_cpu(irq_stat, x)) /* * /proc/interrupts printing for arch specific interrupts */ int arch_show_interrupts(struct seq_file *p, int prec) { int j; seq_printf(p, "%*s: ", prec, "NMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->__nmi_count); seq_puts(p, " Non-maskable interrupts\n"); #ifdef CONFIG_X86_LOCAL_APIC seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs); seq_puts(p, " Local timer interrupts\n"); seq_printf(p, "%*s: ", prec, "SPU"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count); seq_puts(p, " Spurious interrupts\n"); seq_printf(p, "%*s: ", prec, "PMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs); seq_puts(p, " Performance monitoring interrupts\n"); seq_printf(p, "%*s: ", prec, "IWI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs); seq_puts(p, " IRQ work interrupts\n"); seq_printf(p, "%*s: ", prec, "RTR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count); seq_puts(p, " APIC ICR read retries\n"); if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); seq_puts(p, " Platform interrupts\n"); } #endif #ifdef CONFIG_SMP seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count); seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count); seq_puts(p, " TLB shootdowns\n"); #endif #ifdef CONFIG_X86_THERMAL_VECTOR seq_printf(p, "%*s: ", prec, "TRM"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count); seq_puts(p, " Thermal event interrupts\n"); #endif #ifdef CONFIG_X86_MCE_THRESHOLD seq_printf(p, "%*s: ", prec, "THR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); seq_puts(p, " Threshold APIC interrupts\n"); #endif #ifdef CONFIG_X86_MCE_AMD seq_printf(p, "%*s: ", prec, "DFR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count); seq_puts(p, " Deferred Error APIC interrupts\n"); #endif #ifdef CONFIG_X86_MCE seq_printf(p, "%*s: ", prec, "MCE"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(mce_exception_count, j)); seq_puts(p, " Machine check exceptions\n"); seq_printf(p, "%*s: ", prec, "MCP"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(mce_poll_count, j)); seq_puts(p, " Machine check polls\n"); #endif #ifdef CONFIG_X86_HV_CALLBACK_VECTOR if (test_bit(HYPERVISOR_CALLBACK_VECTOR, system_vectors)) { seq_printf(p, "%*s: ", prec, "HYP"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count); seq_puts(p, " Hypervisor callback interrupts\n"); } #endif #if IS_ENABLED(CONFIG_HYPERV) if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) { seq_printf(p, "%*s: ", prec, "HRE"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_hv_reenlightenment_count); seq_puts(p, " Hyper-V reenlightenment interrupts\n"); } if (test_bit(HYPERV_STIMER0_VECTOR, system_vectors)) { seq_printf(p, "%*s: ", prec, "HVS"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->hyperv_stimer0_count); seq_puts(p, " Hyper-V stimer0 interrupts\n"); } #endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); #endif #if IS_ENABLED(CONFIG_KVM) seq_printf(p, "%*s: ", prec, "PIN"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); seq_puts(p, " Posted-interrupt notification event\n"); seq_printf(p, "%*s: ", prec, "NPI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_nested_ipis); seq_puts(p, " Nested posted-interrupt event\n"); seq_printf(p, "%*s: ", prec, "PIW"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_wakeup_ipis); seq_puts(p, " Posted-interrupt wakeup event\n"); #endif #ifdef CONFIG_X86_POSTED_MSI seq_printf(p, "%*s: ", prec, "PMN"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->posted_msi_notification_count); seq_puts(p, " Posted MSI notification event\n"); #endif return 0; } /* * /proc/stat helpers */ u64 arch_irq_stat_cpu(unsigned int cpu) { u64 sum = irq_stats(cpu)->__nmi_count; #ifdef CONFIG_X86_LOCAL_APIC sum += irq_stats(cpu)->apic_timer_irqs; sum += irq_stats(cpu)->irq_spurious_count; sum += irq_stats(cpu)->apic_perf_irqs; sum += irq_stats(cpu)->apic_irq_work_irqs; sum += irq_stats(cpu)->icr_read_retry_count; if (x86_platform_ipi_callback) sum += irq_stats(cpu)->x86_platform_ipis; #endif #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR sum += irq_stats(cpu)->irq_thermal_count; #endif #ifdef CONFIG_X86_MCE_THRESHOLD sum += irq_stats(cpu)->irq_threshold_count; #endif #ifdef CONFIG_X86_HV_CALLBACK_VECTOR sum += irq_stats(cpu)->irq_hv_callback_count; #endif #if IS_ENABLED(CONFIG_HYPERV) sum += irq_stats(cpu)->irq_hv_reenlightenment_count; sum += irq_stats(cpu)->hyperv_stimer0_count; #endif #ifdef CONFIG_X86_MCE sum += per_cpu(mce_exception_count, cpu); sum += per_cpu(mce_poll_count, cpu); #endif return sum; } u64 arch_irq_stat(void) { u64 sum = atomic_read(&irq_err_count); return sum; } static __always_inline void handle_irq(struct irq_desc *desc, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_X86_64)) generic_handle_irq_desc(desc); else __handle_irq(desc, regs); } static __always_inline int call_irq_handler(int vector, struct pt_regs *regs) { struct irq_desc *desc; int ret = 0; desc = __this_cpu_read(vector_irq[vector]); if (likely(!IS_ERR_OR_NULL(desc))) { handle_irq(desc, regs); } else { ret = -EINVAL; if (desc == VECTOR_UNUSED) { pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n", __func__, smp_processor_id(), vector); } else { __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); } } return ret; } /* * common_interrupt() handles all normal device IRQ's (the special SMP * cross-CPU interrupts have their own entry points). */ DEFINE_IDTENTRY_IRQ(common_interrupt) { struct pt_regs *old_regs = set_irq_regs(regs); /* entry code tells RCU that we're not quiescent. Check it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); if (unlikely(call_irq_handler(vector, regs))) apic_eoi(); set_irq_regs(old_regs); } #ifdef CONFIG_X86_LOCAL_APIC /* Function pointer for generic interrupt vector handling */ void (*x86_platform_ipi_callback)(void) = NULL; /* * Handler for X86_PLATFORM_IPI_VECTOR. */ DEFINE_IDTENTRY_SYSVEC(sysvec_x86_platform_ipi) { struct pt_regs *old_regs = set_irq_regs(regs); apic_eoi(); trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); inc_irq_stat(x86_platform_ipis); if (x86_platform_ipi_callback) x86_platform_ipi_callback(); trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); set_irq_regs(old_regs); } #endif #if IS_ENABLED(CONFIG_KVM) static void dummy_handler(void) {} static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler; void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)) { if (handler) kvm_posted_intr_wakeup_handler = handler; else { kvm_posted_intr_wakeup_handler = dummy_handler; synchronize_rcu(); } } EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); /* * Handler for POSTED_INTERRUPT_VECTOR. */ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_ipi) { apic_eoi(); inc_irq_stat(kvm_posted_intr_ipis); } /* * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. */ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_posted_intr_wakeup_ipi) { apic_eoi(); inc_irq_stat(kvm_posted_intr_wakeup_ipis); kvm_posted_intr_wakeup_handler(); } /* * Handler for POSTED_INTERRUPT_NESTED_VECTOR. */ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi) { apic_eoi(); inc_irq_stat(kvm_posted_intr_nested_ipis); } #endif #ifdef CONFIG_X86_POSTED_MSI /* Posted Interrupt Descriptors for coalesced MSIs to be posted */ DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc); void intel_posted_msi_init(void) { u32 destination; u32 apic_id; this_cpu_write(posted_msi_pi_desc.nv, POSTED_MSI_NOTIFICATION_VECTOR); /* * APIC destination ID is stored in bit 8:15 while in XAPIC mode. * VT-d spec. CH 9.11 */ apic_id = this_cpu_read(x86_cpu_to_apicid); destination = x2apic_enabled() ? apic_id : apic_id << 8; this_cpu_write(posted_msi_pi_desc.ndst, destination); } /* * De-multiplexing posted interrupts is on the performance path, the code * below is written to optimize the cache performance based on the following * considerations: * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently * accessed by both CPU and IOMMU. * 2.During posted MSI processing, the CPU needs to do 64-bit read and xchg * for checking and clearing posted interrupt request (PIR), a 256 bit field * within the PID. * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache * line when posting interrupts and setting control bits. * 4.The CPU can access the cache line a magnitude faster than the IOMMU. * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID * cache line. The cache line states after each operation are as follows: * CPU IOMMU PID Cache line state * --------------------------------------------------------------- *...read64 exclusive *...lock xchg64 modified *... post/atomic swap invalid *...------------------------------------------------------------- * * To reduce L1 data cache miss, it is important to avoid contention with * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used * to dispatch interrupt handlers. * * In addition, the code is trying to keep the cache line state consistent * as much as possible. e.g. when making a copy and clearing the PIR * (assuming non-zero PIR bits are present in the entire PIR), it does: * read, read, read, read, xchg, xchg, xchg, xchg * instead of: * read, xchg, read, xchg, read, xchg, read, xchg */ static __always_inline bool handle_pending_pir(u64 *pir, struct pt_regs *regs) { int i, vec = FIRST_EXTERNAL_VECTOR; unsigned long pir_copy[4]; bool handled = false; for (i = 0; i < 4; i++) pir_copy[i] = pir[i]; for (i = 0; i < 4; i++) { if (!pir_copy[i]) continue; pir_copy[i] = arch_xchg(&pir[i], 0); handled = true; } if (handled) { for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR) call_irq_handler(vec, regs); } return handled; } /* * Performance data shows that 3 is good enough to harvest 90+% of the benefit * on high IRQ rate workload. */ #define MAX_POSTED_MSI_COALESCING_LOOP 3 /* * For MSIs that are delivered as posted interrupts, the CPU notifications * can be coalesced if the MSIs arrive in high frequency bursts. */ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification) { struct pt_regs *old_regs = set_irq_regs(regs); struct pi_desc *pid; int i = 0; pid = this_cpu_ptr(&posted_msi_pi_desc); inc_irq_stat(posted_msi_notification_count); irq_enter(); /* * Max coalescing count includes the extra round of handle_pending_pir * after clearing the outstanding notification bit. Hence, at most * MAX_POSTED_MSI_COALESCING_LOOP - 1 loops are executed here. */ while (++i < MAX_POSTED_MSI_COALESCING_LOOP) { if (!handle_pending_pir(pid->pir64, regs)) break; } /* * Clear outstanding notification bit to allow new IRQ notifications, * do this last to maximize the window of interrupt coalescing. */ pi_clear_on(pid); /* * There could be a race of PI notification and the clearing of ON bit, * process PIR bits one last time such that handling the new interrupts * are not delayed until the next IRQ. */ handle_pending_pir(pid->pir64, regs); apic_eoi(); irq_exit(); set_irq_regs(old_regs); } #endif /* X86_POSTED_MSI */ #ifdef CONFIG_HOTPLUG_CPU /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { unsigned int vector; struct irq_desc *desc; struct irq_data *data; struct irq_chip *chip; irq_migrate_all_off_this_cpu(); /* * We can remove mdelay() and then send spurious interrupts to * new cpu targets for all the irqs that were handled previously by * this cpu. While it works, I have seen spurious interrupt messages * (nothing wrong but still...). * * So for now, retain mdelay(1) and check the IRR and then send those * interrupts to new targets as this cpu is already offlined... */ mdelay(1); /* * We can walk the vector array of this cpu without holding * vector_lock because the cpu is already marked !online, so * nothing else will touch it. */ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector]))) continue; if (is_vector_pending(vector)) { desc = __this_cpu_read(vector_irq[vector]); raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); chip = irq_data_get_irq_chip(data); if (chip->irq_retrigger) { chip->irq_retrigger(data); __this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED); } raw_spin_unlock(&desc->lock); } if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED) __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); } } #endif #ifdef CONFIG_X86_THERMAL_VECTOR static void smp_thermal_vector(void) { if (x86_thermal_enabled()) intel_thermal_interrupt(); else pr_err("CPU%d: Unexpected LVT thermal interrupt!\n", smp_processor_id()); } DEFINE_IDTENTRY_SYSVEC(sysvec_thermal) { trace_thermal_apic_entry(THERMAL_APIC_VECTOR); inc_irq_stat(irq_thermal_count); smp_thermal_vector(); trace_thermal_apic_exit(THERMAL_APIC_VECTOR); apic_eoi(); } #endif |
| 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 | /* * linux/drivers/video/console/bitblit.c -- BitBlitting Operation * * Originally from the 'accel_*' routines in drivers/video/console/fbcon.c * * Copyright (C) 2004 Antonino Daplas <adaplas @pol.net> * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive for * more details. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/fb.h> #include <linux/vt_kern.h> #include <linux/console.h> #include <asm/types.h> #include "fbcon.h" /* * Accelerated handlers. */ static void update_attr(u8 *dst, u8 *src, int attribute, struct vc_data *vc) { int i, offset = (vc->vc_font.height < 10) ? 1 : 2; int width = DIV_ROUND_UP(vc->vc_font.width, 8); unsigned int cellsize = vc->vc_font.height * width; u8 c; offset = cellsize - (offset * width); for (i = 0; i < cellsize; i++) { c = src[i]; if (attribute & FBCON_ATTRIBUTE_UNDERLINE && i >= offset) c = 0xff; if (attribute & FBCON_ATTRIBUTE_BOLD) c |= c >> 1; if (attribute & FBCON_ATTRIBUTE_REVERSE) c = ~c; dst[i] = c; } } static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy, int sx, int dy, int dx, int height, int width) { struct fb_copyarea area; area.sx = sx * vc->vc_font.width; area.sy = sy * vc->vc_font.height; area.dx = dx * vc->vc_font.width; area.dy = dy * vc->vc_font.height; area.height = height * vc->vc_font.height; area.width = width * vc->vc_font.width; info->fbops->fb_copyarea(info, &area); } static void bit_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; struct fb_fillrect region; region.color = attr_bgcol_ec(bgshift, vc, info); region.dx = sx * vc->vc_font.width; region.dy = sy * vc->vc_font.height; region.width = width * vc->vc_font.width; region.height = height * vc->vc_font.height; region.rop = ROP_COPY; info->fbops->fb_fillrect(info, ®ion); } static inline void bit_putcs_aligned(struct vc_data *vc, struct fb_info *info, const u16 *s, u32 attr, u32 cnt, u32 d_pitch, u32 s_pitch, u32 cellsize, struct fb_image *image, u8 *buf, u8 *dst) { u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; u32 idx = vc->vc_font.width >> 3; u8 *src; while (cnt--) { src = vc->vc_font.data + (scr_readw(s++)& charmask)*cellsize; if (attr) { update_attr(buf, src, attr, vc); src = buf; } if (likely(idx == 1)) __fb_pad_aligned_buffer(dst, d_pitch, src, idx, image->height); else fb_pad_aligned_buffer(dst, d_pitch, src, idx, image->height); dst += s_pitch; } info->fbops->fb_imageblit(info, image); } static inline void bit_putcs_unaligned(struct vc_data *vc, struct fb_info *info, const u16 *s, u32 attr, u32 cnt, u32 d_pitch, u32 s_pitch, u32 cellsize, struct fb_image *image, u8 *buf, u8 *dst) { u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; u32 shift_low = 0, mod = vc->vc_font.width % 8; u32 shift_high = 8; u32 idx = vc->vc_font.width >> 3; u8 *src; while (cnt--) { src = vc->vc_font.data + (scr_readw(s++)& charmask)*cellsize; if (attr) { update_attr(buf, src, attr, vc); src = buf; } fb_pad_unaligned_buffer(dst, d_pitch, src, idx, image->height, shift_high, shift_low, mod); shift_low += mod; dst += (shift_low >= 8) ? s_pitch : s_pitch - 1; shift_low &= 7; shift_high = 8 - shift_low; } info->fbops->fb_imageblit(info, image); } static void bit_putcs(struct vc_data *vc, struct fb_info *info, const unsigned short *s, int count, int yy, int xx, int fg, int bg) { struct fb_image image; u32 width = DIV_ROUND_UP(vc->vc_font.width, 8); u32 cellsize = width * vc->vc_font.height; u32 maxcnt = info->pixmap.size/cellsize; u32 scan_align = info->pixmap.scan_align - 1; u32 buf_align = info->pixmap.buf_align - 1; u32 mod = vc->vc_font.width % 8, cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; image.fg_color = fg; image.bg_color = bg; image.dx = xx * vc->vc_font.width; image.dy = yy * vc->vc_font.height; image.height = vc->vc_font.height; image.depth = 1; if (attribute) { buf = kmalloc(cellsize, GFP_ATOMIC); if (!buf) return; } while (count) { if (count > maxcnt) cnt = maxcnt; else cnt = count; image.width = vc->vc_font.width * cnt; pitch = DIV_ROUND_UP(image.width, 8) + scan_align; pitch &= ~scan_align; size = pitch * image.height + buf_align; size &= ~buf_align; dst = fb_get_buffer_offset(info, &info->pixmap, size); image.data = dst; if (!mod) bit_putcs_aligned(vc, info, s, attribute, cnt, pitch, width, cellsize, &image, buf, dst); else bit_putcs_unaligned(vc, info, s, attribute, cnt, pitch, width, cellsize, &image, buf, dst); image.dx += cnt * vc->vc_font.width; count -= cnt; s += cnt; } /* buf is always NULL except when in monochrome mode, so in this case it's a gain to check buf against NULL even though kfree() handles NULL pointers just fine */ if (unlikely(buf)) kfree(buf); } static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, int color, int bottom_only) { unsigned int cw = vc->vc_font.width; unsigned int ch = vc->vc_font.height; unsigned int rw = info->var.xres - (vc->vc_cols*cw); unsigned int bh = info->var.yres - (vc->vc_rows*ch); unsigned int rs = info->var.xres - rw; unsigned int bs = info->var.yres - bh; struct fb_fillrect region; region.color = color; region.rop = ROP_COPY; if ((int) rw > 0 && !bottom_only) { region.dx = info->var.xoffset + rs; region.dy = 0; region.width = rw; region.height = info->var.yres_virtual; info->fbops->fb_fillrect(info, ®ion); } if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset + bs; region.width = rs; region.height = bh; info->fbops->fb_fillrect(info, ®ion); } } static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, int fg, int bg) { struct fb_cursor cursor; struct fbcon_ops *ops = info->fbcon_par; unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; int w = DIV_ROUND_UP(vc->vc_font.width, 8), c; int y = real_y(ops->p, vc->state.y); int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1; char *src; cursor.set = 0; if (!vc->vc_font.data) return; c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height)); if (ops->cursor_state.image.data != src || ops->cursor_reset) { ops->cursor_state.image.data = src; cursor.set |= FB_CUR_SETIMAGE; } if (attribute) { u8 *dst; dst = kmalloc_array(w, vc->vc_font.height, GFP_ATOMIC); if (!dst) return; kfree(ops->cursor_data); ops->cursor_data = dst; update_attr(dst, src, attribute, vc); src = dst; } if (ops->cursor_state.image.fg_color != fg || ops->cursor_state.image.bg_color != bg || ops->cursor_reset) { ops->cursor_state.image.fg_color = fg; ops->cursor_state.image.bg_color = bg; cursor.set |= FB_CUR_SETCMAP; } if ((ops->cursor_state.image.dx != (vc->vc_font.width * vc->state.x)) || (ops->cursor_state.image.dy != (vc->vc_font.height * y)) || ops->cursor_reset) { ops->cursor_state.image.dx = vc->vc_font.width * vc->state.x; ops->cursor_state.image.dy = vc->vc_font.height * y; cursor.set |= FB_CUR_SETPOS; } if (ops->cursor_state.image.height != vc->vc_font.height || ops->cursor_state.image.width != vc->vc_font.width || ops->cursor_reset) { ops->cursor_state.image.height = vc->vc_font.height; ops->cursor_state.image.width = vc->vc_font.width; cursor.set |= FB_CUR_SETSIZE; } if (ops->cursor_state.hot.x || ops->cursor_state.hot.y || ops->cursor_reset) { ops->cursor_state.hot.x = cursor.hot.y = 0; cursor.set |= FB_CUR_SETHOT; } if (cursor.set & FB_CUR_SETSIZE || vc->vc_cursor_type != ops->p->cursor_shape || ops->cursor_state.mask == NULL || ops->cursor_reset) { char *mask = kmalloc_array(w, vc->vc_font.height, GFP_ATOMIC); int cur_height, size, i = 0; u8 msk = 0xff; if (!mask) return; kfree(ops->cursor_state.mask); ops->cursor_state.mask = mask; ops->p->cursor_shape = vc->vc_cursor_type; cursor.set |= FB_CUR_SETSHAPE; switch (CUR_SIZE(ops->p->cursor_shape)) { case CUR_NONE: cur_height = 0; break; case CUR_UNDERLINE: cur_height = (vc->vc_font.height < 10) ? 1 : 2; break; case CUR_LOWER_THIRD: cur_height = vc->vc_font.height/3; break; case CUR_LOWER_HALF: cur_height = vc->vc_font.height >> 1; break; case CUR_TWO_THIRDS: cur_height = (vc->vc_font.height << 1)/3; break; case CUR_BLOCK: default: cur_height = vc->vc_font.height; break; } size = (vc->vc_font.height - cur_height) * w; while (size--) mask[i++] = ~msk; size = cur_height * w; while (size--) mask[i++] = msk; } ops->cursor_state.enable = enable && !use_sw; cursor.image.data = src; cursor.image.fg_color = ops->cursor_state.image.fg_color; cursor.image.bg_color = ops->cursor_state.image.bg_color; cursor.image.dx = ops->cursor_state.image.dx; cursor.image.dy = ops->cursor_state.image.dy; cursor.image.height = ops->cursor_state.image.height; cursor.image.width = ops->cursor_state.image.width; cursor.hot.x = ops->cursor_state.hot.x; cursor.hot.y = ops->cursor_state.hot.y; cursor.mask = ops->cursor_state.mask; cursor.enable = ops->cursor_state.enable; cursor.image.depth = 1; cursor.rop = ROP_XOR; if (info->fbops->fb_cursor) err = info->fbops->fb_cursor(info, &cursor); if (err) soft_cursor(info, &cursor); ops->cursor_reset = 0; } static int bit_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; int err; err = fb_pan_display(info, &ops->var); ops->var.xoffset = info->var.xoffset; ops->var.yoffset = info->var.yoffset; ops->var.vmode = info->var.vmode; return err; } void fbcon_set_bitops(struct fbcon_ops *ops) { ops->bmove = bit_bmove; ops->clear = bit_clear; ops->putcs = bit_putcs; ops->clear_margins = bit_clear_margins; ops->cursor = bit_cursor; ops->update_start = bit_update_start; ops->rotate_font = NULL; if (ops->rotate) fbcon_set_rotate(ops); } |
| 4826 4846 4859 4827 4638 4639 4636 4639 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 | // SPDX-License-Identifier: GPL-2.0 /* * Workingset detection * * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner */ #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/writeback.h> #include <linux/shmem_fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/swap.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/mm.h> #include "internal.h" /* * Double CLOCK lists * * Per node, two clock lists are maintained for file pages: the * inactive and the active list. Freshly faulted pages start out at * the head of the inactive list and page reclaim scans pages from the * tail. Pages that are accessed multiple times on the inactive list * are promoted to the active list, to protect them from reclaim, * whereas active pages are demoted to the inactive list when the * active list grows too big. * * fault ------------------------+ * | * +--------------+ | +-------------+ * reclaim <- | inactive | <-+-- demotion | active | <--+ * +--------------+ +-------------+ | * | | * +-------------- promotion ------------------+ * * * Access frequency and refault distance * * A workload is thrashing when its pages are frequently used but they * are evicted from the inactive list every time before another access * would have promoted them to the active list. * * In cases where the average access distance between thrashing pages * is bigger than the size of memory there is nothing that can be * done - the thrashing set could never fit into memory under any * circumstance. * * However, the average access distance could be bigger than the * inactive list, yet smaller than the size of memory. In this case, * the set could fit into memory if it weren't for the currently * active pages - which may be used more, hopefully less frequently: * * +-memory available to cache-+ * | | * +-inactive------+-active----+ * a b | c d e f g h i | J K L M N | * +---------------+-----------+ * * It is prohibitively expensive to accurately track access frequency * of pages. But a reasonable approximation can be made to measure * thrashing on the inactive list, after which refaulting pages can be * activated optimistically to compete with the existing active pages. * * Approximating inactive page access frequency - Observations: * * 1. When a page is accessed for the first time, it is added to the * head of the inactive list, slides every existing inactive page * towards the tail by one slot, and pushes the current tail page * out of memory. * * 2. When a page is accessed for the second time, it is promoted to * the active list, shrinking the inactive list by one slot. This * also slides all inactive pages that were faulted into the cache * more recently than the activated page towards the tail of the * inactive list. * * Thus: * * 1. The sum of evictions and activations between any two points in * time indicate the minimum number of inactive pages accessed in * between. * * 2. Moving one inactive page N page slots towards the tail of the * list requires at least N inactive page accesses. * * Combining these: * * 1. When a page is finally evicted from memory, the number of * inactive pages accessed while the page was in cache is at least * the number of page slots on the inactive list. * * 2. In addition, measuring the sum of evictions and activations (E) * at the time of a page's eviction, and comparing it to another * reading (R) at the time the page faults back into memory tells * the minimum number of accesses while the page was not cached. * This is called the refault distance. * * Because the first access of the page was the fault and the second * access the refault, we combine the in-cache distance with the * out-of-cache distance to get the complete minimum access distance * of this page: * * NR_inactive + (R - E) * * And knowing the minimum access distance of a page, we can easily * tell if the page would be able to stay in cache assuming all page * slots in the cache were available: * * NR_inactive + (R - E) <= NR_inactive + NR_active * * If we have swap we should consider about NR_inactive_anon and * NR_active_anon, so for page cache and anonymous respectively: * * NR_inactive_file + (R - E) <= NR_inactive_file + NR_active_file * + NR_inactive_anon + NR_active_anon * * NR_inactive_anon + (R - E) <= NR_inactive_anon + NR_active_anon * + NR_inactive_file + NR_active_file * * Which can be further simplified to: * * (R - E) <= NR_active_file + NR_inactive_anon + NR_active_anon * * (R - E) <= NR_active_anon + NR_inactive_file + NR_active_file * * Put into words, the refault distance (out-of-cache) can be seen as * a deficit in inactive list space (in-cache). If the inactive list * had (R - E) more page slots, the page would not have been evicted * in between accesses, but activated instead. And on a full system, * the only thing eating into inactive list space is active pages. * * * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given * time there is actually a good chance that pages on the active list * are no longer in active use. * * So when a refault distance of (R - E) is observed and there are at * least (R - E) pages in the userspace workingset, the refaulting page * is activated optimistically in the hope that (R - E) pages are actually * used less frequently than the refaulting page - or even not used at * all anymore. * * That means if inactive cache is refaulting with a suitable refault * distance, we assume the cache workingset is transitioning and put * pressure on the current workingset. * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. * * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * * Refaulting active pages * * If on the other hand the refaulting pages have recently been * deactivated, it means that the active list is no longer protecting * actively used cache from reclaim. The cache is NOT transitioning to * a different workingset; the existing workingset is thrashing in the * space allocated to the page cache. * * * Implementation * * For each node's LRU lists, a counter for inactive evictions and * activations is maintained (node->nonresident_age). * * On eviction, a snapshot of this counter (along with some bits to * identify the node) is stored in the now empty page cache * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible * refault distance will immediately activate the refaulting page. */ #define WORKINGSET_SHIFT 1 #define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ WORKINGSET_SHIFT + NODES_SHIFT + \ MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* * Eviction timestamps need to be able to cover the full range of * actionable refaults. However, bits are tight in the xarray * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group * evictions into coarser buckets by shaving off lower timestamp bits. */ static unsigned int bucket_order __read_mostly; static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, bool workingset) { eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; eviction = (eviction << WORKINGSET_SHIFT) | workingset; return xa_mk_value(eviction); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, unsigned long *evictionp, bool *workingsetp) { unsigned long entry = xa_to_value(shadow); int memcgid, nid; bool workingset; workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1); entry >>= WORKINGSET_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); entry >>= MEM_CGROUP_ID_SHIFT; *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry; *workingsetp = workingset; } #ifdef CONFIG_LRU_GEN static void *lru_gen_eviction(struct folio *folio) { int hist; unsigned long token; unsigned long min_seq; struct lruvec *lruvec; struct lru_gen_folio *lrugen; int type = folio_is_file_lru(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); int tier = lru_tier_from_refs(refs, workingset); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT); lruvec = mem_cgroup_lruvec(memcg, pgdat); lrugen = &lruvec->lrugen; min_seq = READ_ONCE(lrugen->min_seq[type]); token = (min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0); hist = lru_hist_from_seq(min_seq); atomic_long_add(delta, &lrugen->evicted[hist][type][tier]); return pack_shadow(mem_cgroup_id(memcg), pgdat, token, workingset); } /* * Tests if the shadow entry is for a folio that was recently evicted. * Fills in @lruvec, @token, @workingset with the values unpacked from shadow. */ static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec, unsigned long *token, bool *workingset) { int memcg_id; unsigned long max_seq; struct mem_cgroup *memcg; struct pglist_data *pgdat; unpack_shadow(shadow, &memcg_id, &pgdat, token, workingset); memcg = mem_cgroup_from_id(memcg_id); *lruvec = mem_cgroup_lruvec(memcg, pgdat); max_seq = READ_ONCE((*lruvec)->lrugen.max_seq); max_seq &= EVICTION_MASK >> LRU_REFS_WIDTH; return abs_diff(max_seq, *token >> LRU_REFS_WIDTH) < MAX_NR_GENS; } static void lru_gen_refault(struct folio *folio, void *shadow) { bool recent; int hist, tier, refs; bool workingset; unsigned long token; struct lruvec *lruvec; struct lru_gen_folio *lrugen; int type = folio_is_file_lru(folio); int delta = folio_nr_pages(folio); rcu_read_lock(); recent = lru_gen_test_recent(shadow, &lruvec, &token, &workingset); if (lruvec != folio_lruvec(folio)) goto unlock; mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta); if (!recent) goto unlock; lrugen = &lruvec->lrugen; hist = lru_hist_from_seq(READ_ONCE(lrugen->min_seq[type])); refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + 1; tier = lru_tier_from_refs(refs, workingset); atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]); /* see folio_add_lru() where folio_set_active() will be called */ if (lru_gen_in_fault()) mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta); if (workingset) { folio_set_workingset(folio); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); } else set_mask_bits(&folio->flags, LRU_REFS_MASK, (refs - 1UL) << LRU_REFS_PGOFF); unlock: rcu_read_unlock(); } #else /* !CONFIG_LRU_GEN */ static void *lru_gen_eviction(struct folio *folio) { return NULL; } static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec, unsigned long *token, bool *workingset) { return false; } static void lru_gen_refault(struct folio *folio, void *shadow) { } #endif /* CONFIG_LRU_GEN */ /** * workingset_age_nonresident - age non-resident entries as LRU ages * @lruvec: the lruvec that was aged * @nr_pages: the number of pages to count * * As in-memory pages are aged, non-resident pages need to be aged as * well, in order for the refault distances later on to be comparable * to the in-memory dimensions. This function allows reclaim and LRU * operations to drive the non-resident aging along in parallel. */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) { /* * Reclaiming a cgroup means reclaiming all its children in a * round-robin fashion. That means that each cgroup has an LRU * order that is composed of the LRU orders of its child * cgroups; and every page has an LRU position not just in the * cgroup that owns it, but in all of that group's ancestors. * * So when the physical inactive list of a leaf cgroup ages, * the virtual inactive lists of all its parents, including * the root cgroup's, age as well. */ do { atomic_long_add(nr_pages, &lruvec->nonresident_age); } while ((lruvec = parent_lruvec(lruvec))); } /** * workingset_eviction - note the eviction of a folio from memory * @target_memcg: the cgroup that is causing the reclaim * @folio: the folio being evicted * * Return: a shadow entry to be stored in @folio->mapping->i_pages in place * of the evicted @folio so that a later refault can be detected. */ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg) { struct pglist_data *pgdat = folio_pgdat(folio); unsigned long eviction; struct lruvec *lruvec; int memcgid; /* Folio is fully exclusive and pins folio's memory cgroup pointer */ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (lru_gen_enabled()) return lru_gen_eviction(folio); lruvec = mem_cgroup_lruvec(target_memcg, pgdat); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); eviction = atomic_long_read(&lruvec->nonresident_age); eviction >>= bucket_order; workingset_age_nonresident(lruvec, folio_nr_pages(folio)); return pack_shadow(memcgid, pgdat, eviction, folio_test_workingset(folio)); } /** * workingset_test_recent - tests if the shadow entry is for a folio that was * recently evicted. Also fills in @workingset with the value unpacked from * shadow. * @shadow: the shadow entry to be tested. * @file: whether the corresponding folio is from the file lru. * @workingset: where the workingset value unpacked from shadow should * be stored. * @flush: whether to flush cgroup rstat. * * Return: true if the shadow is for a recently evicted folio; false otherwise. */ bool workingset_test_recent(void *shadow, bool file, bool *workingset, bool flush) { struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; unsigned long refault_distance; unsigned long workingset_size; unsigned long refault; int memcgid; struct pglist_data *pgdat; unsigned long eviction; if (lru_gen_enabled()) { bool recent; rcu_read_lock(); recent = lru_gen_test_recent(shadow, &eviction_lruvec, &eviction, workingset); rcu_read_unlock(); return recent; } rcu_read_lock(); unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset); eviction <<= bucket_order; /* * Look up the memcg associated with the stored ID. It might * have been deleted since the folio's eviction. * * Note that in rare events the ID could have been recycled * for a new cgroup that refaults a shared folio. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging * algorithm's job to shake out the minimum access frequency * for the active cache. * * XXX: On !CONFIG_MEMCG, this will always return NULL; it * would be better if the root_mem_cgroup existed in all * configurations instead. */ eviction_memcg = mem_cgroup_from_id(memcgid); if (!mem_cgroup_tryget(eviction_memcg)) eviction_memcg = NULL; rcu_read_unlock(); if (!mem_cgroup_disabled() && !eviction_memcg) return false; /* * Flush stats (and potentially sleep) outside the RCU read section. * * Note that workingset_test_recent() itself might be called in RCU read * section (for e.g, in cachestat) - these callers need to skip flushing * stats (via the flush argument). * * XXX: With per-memcg flushing and thresholding, is ratelimiting * still needed here? */ if (flush) mem_cgroup_flush_stats_ratelimited(eviction_memcg); eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); refault = atomic_long_read(&eviction_lruvec->nonresident_age); /* * Calculate the refault distance * * The unsigned subtraction here gives an accurate distance * across nonresident_age overflows in most cases. There is a * special case: usually, shadow entries have a short lifetime * and are either refaulted or reclaimed along with the inode * before they get too old. But it is not impossible for the * nonresident_age to lap a shadow entry in the field, which * can then result in a false small refault distance, leading * to a false activation should this old entry actually * refault again. However, earlier kernels used to deactivate * unconditionally with *every* reclaim invocation for the * longest time, so the occasional inappropriate activation * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if * all the memory was available to the workingset. Whether * workingset competition needs to consider anon or not depends * on having free swap space. */ workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); if (!file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_FILE); } if (mem_cgroup_get_nr_swap_pages(eviction_memcg) > 0) { workingset_size += lruvec_page_state(eviction_lruvec, NR_ACTIVE_ANON); if (file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_ANON); } } mem_cgroup_put(eviction_memcg); return refault_distance <= workingset_size; } /** * workingset_refault - Evaluate the refault of a previously evicted folio. * @folio: The freshly allocated replacement folio. * @shadow: Shadow entry of the evicted folio. * * Calculates and evaluates the refault distance of the previously * evicted folio in the context of the node and the memcg whose memory * pressure caused the eviction. */ void workingset_refault(struct folio *folio, void *shadow) { bool file = folio_is_file_lru(folio); struct pglist_data *pgdat; struct mem_cgroup *memcg; struct lruvec *lruvec; bool workingset; long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (lru_gen_enabled()) { lru_gen_refault(folio, shadow); return; } /* * The activation decision for this folio is made at the level * where the eviction occurred, as that is where the LRU order * during folio reclaim is being determined. * * However, the cgroup that will own the folio is the one that * is actually experiencing the refault event. Make sure the folio is * locked to guarantee folio_memcg() stability throughout. */ nr = folio_nr_pages(folio); memcg = folio_memcg(folio); pgdat = folio_pgdat(folio); lruvec = mem_cgroup_lruvec(memcg, pgdat); mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); if (!workingset_test_recent(shadow, file, &workingset, true)) return; folio_set_active(folio); workingset_age_nonresident(lruvec, nr); mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr); /* Folio was active prior to eviction */ if (workingset) { folio_set_workingset(folio); /* * XXX: Move to folio_add_lru() when it supports new vs * putback */ lru_note_cost_refault(folio); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr); } } /** * workingset_activation - note a page activation * @folio: Folio that is being activated. */ void workingset_activation(struct folio *folio) { /* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. */ if (mem_cgroup_disabled() || folio_memcg_charged(folio)) workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio)); } /* * Shadow entries reflect the share of the working set that does not * fit into memory, so their number depends on the access pattern of * the workload. In most cases, they will refault or get reclaimed * along with the inode, but a (malicious) workload that streams * through files with a total size several times that of available * memory, while preventing the inodes from being reclaimed, can * create excessive amounts of shadow nodes. To keep a lid on this, * track shadow nodes and reclaim them when they grow way past the * point where they would still be useful. */ struct list_lru shadow_nodes; void workingset_update_node(struct xa_node *node) { struct address_space *mapping; struct page *page = virt_to_page(node); /* * Track non-empty nodes that contain only shadow entries; * unlink those that contain pages or are being freed. * * Avoid acquiring the list_lru lock when the nodes are * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ mapping = container_of(node->array, struct address_space, i_pages); lockdep_assert_held(&mapping->i_pages.xa_lock); if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add_obj(&shadow_nodes, &node->private_list); __inc_node_page_state(page, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { list_lru_del_obj(&shadow_nodes, &node->private_list); __dec_node_page_state(page, WORKINGSET_NODES); } } } static unsigned long count_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long max_nodes; unsigned long nodes; unsigned long pages; nodes = list_lru_shrink_count(&shadow_nodes, sc); if (!nodes) return SHRINK_EMPTY; /* * Approximate a reasonable limit for the nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. * * The size of the active list converges toward 100% of * overall page cache as memory grows, with only a tiny * inactive list. Assume the total cache size for that. * * Nodes might be sparsely populated, with only one shadow * entry in the extreme case. Obviously, we cannot keep one * node for every eligible shadow entry, so compromise on a * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. * * On 64-bit with 7 xa_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume * ~1.8% of available memory: * * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE */ #ifdef CONFIG_MEMCG if (sc->memcg) { struct lruvec *lruvec; int i; mem_cgroup_flush_stats_ratelimited(sc->memcg); lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) pages += lruvec_page_state_local(lruvec, NR_LRU_BASE + i); pages += lruvec_page_state_local( lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT; pages += lruvec_page_state_local( lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT; } else #endif pages = node_present_pages(sc->nid); max_nodes = pages >> (XA_CHUNK_SHIFT - 3); if (nodes <= max_nodes) return 0; return nodes - max_nodes; } static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) __must_hold(lru->lock) { struct xa_node *node = container_of(item, struct xa_node, private_list); struct address_space *mapping; int ret; /* * Page cache insertions and deletions synchronously maintain * the shadow node LRU under the i_pages lock and the * &lru->lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the &lru->lock pins any * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the &lru->lock. */ mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { spin_unlock_irq(&lru->lock); ret = LRU_RETRY; goto out; } /* For page cache we need to hold i_lock */ if (mapping->host != NULL) { if (!spin_trylock(&mapping->host->i_lock)) { xa_unlock(&mapping->i_pages); spin_unlock_irq(&lru->lock); ret = LRU_RETRY; goto out; } } list_lru_isolate(lru, item); __dec_node_page_state(virt_to_page(node), WORKINGSET_NODES); spin_unlock(&lru->lock); /* * The nodes should only contain one or more shadow entries, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; xa_delete_node(node, workingset_update_node); __inc_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM); out_invalid: xa_unlock_irq(&mapping->i_pages); if (mapping->host != NULL) { if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } ret = LRU_REMOVED_RETRY; out: cond_resched(); return ret; } static unsigned long scan_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { /* list_lru lock nests inside the IRQ-safe i_pages lock */ return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate, NULL); } /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * i_pages lock. */ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { struct shrinker *workingset_shadow_shrinker; unsigned int timestamp_bits; unsigned int max_order; int ret = -ENOMEM; BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* * Calculate the eviction bucket size to cover the longest * actionable refault distance, which is currently half of * memory (totalram_pages/2). However, memory hotplug may add * some more pages at runtime, so keep working with up to * double the initial memory by using totalram_pages as-is. */ timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT; max_order = fls_long(totalram_pages() - 1); if (max_order > timestamp_bits) bucket_order = max_order - timestamp_bits; pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); workingset_shadow_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-shadow"); if (!workingset_shadow_shrinker) goto err; ret = list_lru_init_memcg_key(&shadow_nodes, workingset_shadow_shrinker, &shadow_nodes_key); if (ret) goto err_list_lru; workingset_shadow_shrinker->count_objects = count_shadow_nodes; workingset_shadow_shrinker->scan_objects = scan_shadow_nodes; /* ->count reports only fully expendable nodes */ workingset_shadow_shrinker->seeks = 0; shrinker_register(workingset_shadow_shrinker); return 0; err_list_lru: shrinker_free(workingset_shadow_shrinker); err: return ret; } module_init(workingset_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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kernfs.h - pseudo filesystem decoupled from vfs locking */ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/idr.h> #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/types.h> #include <linux/uidgid.h> #include <linux/wait.h> #include <linux/rwsem.h> #include <linux/cache.h> struct file; struct dentry; struct iattr; struct seq_file; struct vm_area_struct; struct vm_operations_struct; struct super_block; struct file_system_type; struct poll_table_struct; struct fs_context; struct kernfs_fs_context; struct kernfs_open_node; struct kernfs_iattrs; /* * NR_KERNFS_LOCK_BITS determines size (NR_KERNFS_LOCKS) of hash * table of locks. * Having a small hash table would impact scalability, since * more and more kernfs_node objects will end up using same lock * and having a very large hash table would waste memory. * * At the moment size of hash table of locks is being set based on * the number of CPUs as follows: * * NR_CPU NR_KERNFS_LOCK_BITS NR_KERNFS_LOCKS * 1 1 2 * 2-3 2 4 * 4-7 4 16 * 8-15 6 64 * 16-31 8 256 * 32 and more 10 1024 * * The above relation between NR_CPU and number of locks is based * on some internal experimentation which involved booting qemu * with different values of smp, performing some sysfs operations * on all CPUs and observing how increase in number of locks impacts * completion time of these sysfs operations on each CPU. */ #ifdef CONFIG_SMP #define NR_KERNFS_LOCK_BITS (2 * (ilog2(NR_CPUS < 32 ? NR_CPUS : 32))) #else #define NR_KERNFS_LOCK_BITS 1 #endif #define NR_KERNFS_LOCKS (1 << NR_KERNFS_LOCK_BITS) /* * There's one kernfs_open_file for each open file and one kernfs_open_node * for each kernfs_node with one or more open files. * * filp->private_data points to seq_file whose ->private points to * kernfs_open_file. * * kernfs_open_files are chained at kernfs_open_node->files, which is * protected by kernfs_global_locks.open_file_mutex[i]. * * To reduce possible contention in sysfs access, arising due to single * locks, use an array of locks (e.g. open_file_mutex) and use kernfs_node * object address as hash keys to get the index of these locks. * * Hashed mutexes are safe to use here because operations using these don't * rely on global exclusion. * * In future we intend to replace other global locks with hashed ones as well. * kernfs_global_locks acts as a holder for all such hash tables. */ struct kernfs_global_locks { struct mutex open_file_mutex[NR_KERNFS_LOCKS]; }; enum kernfs_node_type { KERNFS_DIR = 0x0001, KERNFS_FILE = 0x0002, KERNFS_LINK = 0x0004, }; #define KERNFS_TYPE_MASK 0x000f #define KERNFS_FLAG_MASK ~KERNFS_TYPE_MASK #define KERNFS_MAX_USER_XATTRS 128 #define KERNFS_USER_XATTR_SIZE_LIMIT (128 << 10) enum kernfs_node_flag { KERNFS_ACTIVATED = 0x0010, KERNFS_NS = 0x0020, KERNFS_HAS_SEQ_SHOW = 0x0040, KERNFS_HAS_MMAP = 0x0080, KERNFS_LOCKDEP = 0x0100, KERNFS_HIDDEN = 0x0200, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, KERNFS_HAS_RELEASE = 0x2000, KERNFS_REMOVING = 0x4000, }; /* @flags for kernfs_create_root() */ enum kernfs_root_flag { /* * kernfs_nodes are created in the deactivated state and invisible. * They require explicit kernfs_activate() to become visible. This * can be used to make related nodes become visible atomically * after all nodes are created successfully. */ KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, /* * For regular files, if the opener has CAP_DAC_OVERRIDE, open(2) * succeeds regardless of the RW permissions. sysfs had an extra * layer of enforcement where open(2) fails with -EACCES regardless * of CAP_DAC_OVERRIDE if the permission doesn't have the * respective read or write access at all (none of S_IRUGO or * S_IWUGO) or the respective operation isn't implemented. The * following flag enables that behavior. */ KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, /* * The filesystem supports exportfs operation, so userspace can use * fhandle to access nodes of the fs. */ KERNFS_ROOT_SUPPORT_EXPORTOP = 0x0004, /* * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, }; /* type-specific structures for kernfs_node union members */ struct kernfs_elem_dir { unsigned long subdirs; /* children rbtree starts here and goes through kn->rb */ struct rb_root children; /* * The kernfs hierarchy this directory belongs to. This fits * better directly in kernfs_node but is here to save space. */ struct kernfs_root *root; /* * Monotonic revision counter, used to identify if a directory * node has changed during negative dentry revalidation. */ unsigned long rev; }; struct kernfs_elem_symlink { struct kernfs_node *target_kn; }; struct kernfs_elem_attr { const struct kernfs_ops *ops; struct kernfs_open_node __rcu *open; loff_t size; struct kernfs_node *notify_next; /* for kernfs_notify() */ }; /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are * private to kernfs and shouldn't be accessed directly by kernfs users. * * As long as count reference is held, the kernfs_node itself is * accessible. Dereferencing elem or any other outer entity requires * active reference. */ struct kernfs_node { atomic_t count; atomic_t active; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* * Use kernfs_get_parent() and kernfs_name/path() instead of * accessing the following two fields directly. If the node is * never moved to a different parent, it is safe to access the * parent directly. */ struct kernfs_node *parent; const char *name; struct rb_node rb; const void *ns; /* namespace tag */ unsigned int hash; /* ns + name hash */ unsigned short flags; umode_t mode; union { struct kernfs_elem_dir dir; struct kernfs_elem_symlink symlink; struct kernfs_elem_attr attr; }; /* * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, * the low 32bits are ino and upper generation. */ u64 id; void *priv; struct kernfs_iattrs *iattr; struct rcu_head rcu; }; /* * kernfs_syscall_ops may be specified on kernfs_create_root() to support * syscalls. These optional callbacks are invoked on the matching syscalls * and can perform any kernfs operations which don't necessarily have to be * the exact operation requested. An active reference is held for each * kernfs_node parameter. */ struct kernfs_syscall_ops { int (*show_options)(struct seq_file *sf, struct kernfs_root *root); int (*mkdir)(struct kernfs_node *parent, const char *name, umode_t mode); int (*rmdir)(struct kernfs_node *kn); int (*rename)(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name); int (*show_path)(struct seq_file *sf, struct kernfs_node *kn, struct kernfs_root *root); }; struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root); struct kernfs_open_file { /* published fields */ struct kernfs_node *kn; struct file *file; struct seq_file *seq_file; void *priv; /* private fields, do not use outside kernfs proper */ struct mutex mutex; struct mutex prealloc_mutex; int event; struct list_head list; char *prealloc_buf; size_t atomic_write_len; bool mmapped:1; bool released:1; const struct vm_operations_struct *vm_ops; }; struct kernfs_ops { /* * Optional open/release methods. Both are called with * @of->seq_file populated. */ int (*open)(struct kernfs_open_file *of); void (*release)(struct kernfs_open_file *of); /* * Read is handled by either seq_file or raw_read(). * * If seq_show() is present, seq_file path is active. Other seq * operations are optional and if not implemented, the behavior is * equivalent to single_open(). @sf->private points to the * associated kernfs_open_file. * * read() is bounced through kernel buffer and a read larger than * PAGE_SIZE results in partial operation of PAGE_SIZE. */ int (*seq_show)(struct seq_file *sf, void *v); void *(*seq_start)(struct seq_file *sf, loff_t *ppos); void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); void (*seq_stop)(struct seq_file *sf, void *v); ssize_t (*read)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); /* * write() is bounced through kernel buffer. If atomic_write_len * is not set, a write larger than PAGE_SIZE results in partial * operations of PAGE_SIZE chunks. If atomic_write_len is set, * writes upto the specified size are executed atomically but * larger ones are rejected with -E2BIG. */ size_t atomic_write_len; /* * "prealloc" causes a buffer to be allocated at open for * all read/write requests. As ->seq_show uses seq_read() * which does its own allocation, it is incompatible with * ->prealloc. Provide ->read and ->write with ->prealloc. */ bool prealloc; ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence); }; /* * The kernfs superblock creation/mount parameter context. */ struct kernfs_fs_context { struct kernfs_root *root; /* Root of the hierarchy being mounted */ void *ns_tag; /* Namespace tag of the mount (or NULL) */ unsigned long magic; /* File system specific magic number */ /* The following are set/used by kernfs_mount() */ bool new_sb_created; /* Set to T if we allocated a new sb */ }; #ifdef CONFIG_KERNFS static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return kn->flags & KERNFS_TYPE_MASK; } static inline ino_t kernfs_id_ino(u64 id) { /* id is ino if ino_t is 64bit; otherwise, low 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return id; else return (u32)id; } static inline u32 kernfs_id_gen(u64 id) { /* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return 1; else return id >> 32; } static inline ino_t kernfs_ino(struct kernfs_node *kn) { return kernfs_id_ino(kn->id); } static inline ino_t kernfs_gen(struct kernfs_node *kn) { return kernfs_id_gen(kn->id); } /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty * * This is to be called right after @kn is created to enable namespace * under it. All children of @kn must have non-NULL namespace tags and * only the ones which match the super_block's tag will be visible. */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); WARN_ON_ONCE(!RB_EMPTY_ROOT(&kn->dir.children)); kn->flags |= KERNFS_NS; } /** * kernfs_ns_enabled - test whether namespace is enabled * @kn: the node to test * * Test whether namespace filtering is enabled for the children of @ns. */ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return kn->flags & KERNFS_NS; } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn); struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns); struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns); void kernfs_get(struct kernfs_node *kn); void kernfs_put(struct kernfs_node *kn); struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct super_block *sb); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns); struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key); struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target); void kernfs_activate(struct kernfs_node *kn); void kernfs_show(struct kernfs_node *kn, bool show); void kernfs_remove(struct kernfs_node *kn); void kernfs_break_active_protection(struct kernfs_node *kn); void kernfs_unbreak_active_protection(struct kernfs_node *kn); bool kernfs_remove_self(struct kernfs_node *kn); int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns); int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); __poll_t kernfs_generic_poll(struct kernfs_open_file *of, struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size); int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags); const void *kernfs_super_ns(struct super_block *sb); int kernfs_get_tree(struct fs_context *fc); void kernfs_free_fs_context(struct fs_context *fc); void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return 0; } /* whatever */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { } static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return false; } static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { } static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { return NULL; } static inline struct kernfs_node * kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { return NULL; } static inline struct kernfs_node * kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { return NULL; } static inline void kernfs_get(struct kernfs_node *kn) { } static inline void kernfs_put(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { return NULL; } static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { return NULL; } static inline struct inode * kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) { return NULL; } static inline struct kernfs_root * kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target) { return ERR_PTR(-ENOSYS); } static inline void kernfs_activate(struct kernfs_node *kn) { } static inline void kernfs_remove(struct kernfs_node *kn) { } static inline bool kernfs_remove_self(struct kernfs_node *kn) { return false; } static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn, const char *name, const void *ns) { return -ENOSYS; } static inline int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { return -ENOSYS; } static inline int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { return -ENOSYS; } static inline __poll_t kernfs_generic_poll(struct kernfs_open_file *of, struct poll_table_struct *pt) { return -ENOSYS; } static inline void kernfs_notify(struct kernfs_node *kn) { } static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size) { return -ENOSYS; } static inline int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags) { return -ENOSYS; } static inline const void *kernfs_super_ns(struct super_block *sb) { return NULL; } static inline int kernfs_get_tree(struct fs_context *fc) { return -ENOSYS; } static inline void kernfs_free_fs_context(struct fs_context *fc) { } static inline void kernfs_kill_sb(struct super_block *sb) { } static inline void kernfs_init(void) { } #endif /* CONFIG_KERNFS */ /** * kernfs_path - build full path of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * If @kn is NULL result will be "(null)". * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { return kernfs_path_from_node(kn, NULL, buf, buflen); } static inline struct kernfs_node * kernfs_find_and_get(struct kernfs_node *kn, const char *name) { return kernfs_find_and_get_ns(kn, name, NULL); } static inline struct kernfs_node * kernfs_ |