| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ocfs2.h * * Defines macros and structures used in OCFS2 * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #ifndef OCFS2_H #define OCFS2_H #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/rbtree.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/mutex.h> #include <linux/lockdep.h> #include <linux/jbd2.h> /* For union ocfs2_dlm_lksb */ #include "stackglue.h" #include "ocfs2_fs.h" #include "ocfs2_lockid.h" #include "ocfs2_ioctl.h" /* For struct ocfs2_blockcheck_stats */ #include "blockcheck.h" #include "reservations.h" #include "filecheck.h" /* Caching of metadata buffers */ /* Most user visible OCFS2 inodes will have very few pieces of * metadata, but larger files (including bitmaps, etc) must be taken * into account when designing an access scheme. We allow a small * amount of inlined blocks to be stored on an array and grow the * structure into a rb tree when necessary. */ #define OCFS2_CACHE_INFO_MAX_ARRAY 2 /* Flags for ocfs2_caching_info */ enum ocfs2_caching_info_flags { /* Indicates that the metadata cache is using the inline array */ OCFS2_CACHE_FL_INLINE = 1<<1, }; struct ocfs2_caching_operations; struct ocfs2_caching_info { /* * The parent structure provides the locks, but because the * parent structure can differ, it provides locking operations * to struct ocfs2_caching_info. */ const struct ocfs2_caching_operations *ci_ops; /* next two are protected by trans_inc_lock */ /* which transaction were we created on? Zero if none. */ unsigned long ci_created_trans; /* last transaction we were a part of. */ unsigned long ci_last_trans; /* Cache structures */ unsigned int ci_flags; unsigned int ci_num_cached; union { sector_t ci_array[OCFS2_CACHE_INFO_MAX_ARRAY]; struct rb_root ci_tree; } ci_cache; }; /* * Need this prototype here instead of in uptodate.h because journal.h * uses it. */ struct super_block *ocfs2_metadata_cache_get_super(struct ocfs2_caching_info *ci); /* this limits us to 256 nodes * if we need more, we can do a kmalloc for the map */ #define OCFS2_NODE_MAP_MAX_NODES 256 struct ocfs2_node_map { u16 num_nodes; unsigned long map[BITS_TO_LONGS(OCFS2_NODE_MAP_MAX_NODES)]; }; enum ocfs2_ast_action { OCFS2_AST_INVALID = 0, OCFS2_AST_ATTACH, OCFS2_AST_CONVERT, OCFS2_AST_DOWNCONVERT, }; /* actions for an unlockast function to take. */ enum ocfs2_unlock_action { OCFS2_UNLOCK_INVALID = 0, OCFS2_UNLOCK_CANCEL_CONVERT, OCFS2_UNLOCK_DROP_LOCK, }; /* ocfs2_lock_res->l_flags flags. */ #define OCFS2_LOCK_ATTACHED (0x00000001) /* we have initialized * the lvb */ #define OCFS2_LOCK_BUSY (0x00000002) /* we are currently in * dlm_lock */ #define OCFS2_LOCK_BLOCKED (0x00000004) /* blocked waiting to * downconvert*/ #define OCFS2_LOCK_LOCAL (0x00000008) /* newly created inode */ #define OCFS2_LOCK_NEEDS_REFRESH (0x00000010) #define OCFS2_LOCK_REFRESHING (0x00000020) #define OCFS2_LOCK_INITIALIZED (0x00000040) /* track initialization * for shutdown paths */ #define OCFS2_LOCK_FREEING (0x00000080) /* help dlmglue track * when to skip queueing * a lock because it's * about to be * dropped. */ #define OCFS2_LOCK_QUEUED (0x00000100) /* queued for downconvert */ #define OCFS2_LOCK_NOCACHE (0x00000200) /* don't use a holder count */ #define OCFS2_LOCK_PENDING (0x00000400) /* This lockres is pending a call to dlm_lock. Only exists with BUSY set. */ #define OCFS2_LOCK_UPCONVERT_FINISHING (0x00000800) /* blocks the dc thread * from downconverting * before the upconvert * has completed */ #define OCFS2_LOCK_NONBLOCK_FINISHED (0x00001000) /* NONBLOCK cluster * lock has already * returned, do not block * dc thread from * downconverting */ struct ocfs2_lock_res_ops; typedef void (*ocfs2_lock_callback)(int status, unsigned long data); #ifdef CONFIG_OCFS2_FS_STATS struct ocfs2_lock_stats { u64 ls_total; /* Total wait in NSEC */ u32 ls_gets; /* Num acquires */ u32 ls_fail; /* Num failed acquires */ /* Storing max wait in usecs saves 24 bytes per inode */ u32 ls_max; /* Max wait in USEC */ u64 ls_last; /* Last unlock time in USEC */ }; #endif struct ocfs2_lock_res { void *l_priv; const struct ocfs2_lock_res_ops *l_ops; struct list_head l_blocked_list; struct list_head l_mask_waiters; struct list_head l_holders; unsigned long l_flags; char l_name[OCFS2_LOCK_ID_MAX_LEN]; unsigned int l_ro_holders; unsigned int l_ex_holders; signed char l_level; signed char l_requested; signed char l_blocking; /* Data packed - type enum ocfs2_lock_type */ unsigned char l_type; /* used from AST/BAST funcs. */ /* Data packed - enum type ocfs2_ast_action */ unsigned char l_action; /* Data packed - enum type ocfs2_unlock_action */ unsigned char l_unlock_action; unsigned int l_pending_gen; spinlock_t l_lock; struct ocfs2_dlm_lksb l_lksb; wait_queue_head_t l_event; struct list_head l_debug_list; #ifdef CONFIG_OCFS2_FS_STATS struct ocfs2_lock_stats l_lock_prmode; /* PR mode stats */ u32 l_lock_refresh; /* Disk refreshes */ u64 l_lock_wait; /* First lock wait time */ struct ocfs2_lock_stats l_lock_exmode; /* EX mode stats */ #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map l_lockdep_map; #endif }; enum ocfs2_orphan_reco_type { ORPHAN_NO_NEED_TRUNCATE = 0, ORPHAN_NEED_TRUNCATE, }; enum ocfs2_orphan_scan_state { ORPHAN_SCAN_ACTIVE, ORPHAN_SCAN_INACTIVE }; struct ocfs2_orphan_scan { struct mutex os_lock; struct ocfs2_super *os_osb; struct ocfs2_lock_res os_lockres; /* lock to synchronize scans */ struct delayed_work os_orphan_scan_work; time64_t os_scantime; /* time this node ran the scan */ u32 os_count; /* tracks node specific scans */ u32 os_seqno; /* tracks cluster wide scans */ atomic_t os_state; /* ACTIVE or INACTIVE */ }; struct ocfs2_dlm_debug { struct kref d_refcnt; u32 d_filter_secs; struct list_head d_lockres_tracking; }; enum ocfs2_vol_state { VOLUME_INIT = 0, VOLUME_MOUNTED, VOLUME_MOUNTED_QUOTAS, VOLUME_DISMOUNTED, VOLUME_DISABLED }; struct ocfs2_alloc_stats { atomic_t moves; atomic_t local_data; atomic_t bitmap_data; atomic_t bg_allocs; atomic_t bg_extends; }; enum ocfs2_local_alloc_state { OCFS2_LA_UNUSED = 0, /* Local alloc will never be used for * this mountpoint. */ OCFS2_LA_ENABLED, /* Local alloc is in use. */ OCFS2_LA_THROTTLED, /* Local alloc is in use, but number * of bits has been reduced. */ OCFS2_LA_DISABLED /* Local alloc has temporarily been * disabled. */ }; enum ocfs2_mount_options { OCFS2_MOUNT_HB_LOCAL = 1 << 0, /* Local heartbeat */ OCFS2_MOUNT_BARRIER = 1 << 1, /* Use block barriers */ OCFS2_MOUNT_NOINTR = 1 << 2, /* Don't catch signals */ OCFS2_MOUNT_ERRORS_PANIC = 1 << 3, /* Panic on errors */ OCFS2_MOUNT_DATA_WRITEBACK = 1 << 4, /* No data ordering */ OCFS2_MOUNT_LOCALFLOCKS = 1 << 5, /* No cluster aware user file locks */ OCFS2_MOUNT_NOUSERXATTR = 1 << 6, /* No user xattr */ OCFS2_MOUNT_INODE64 = 1 << 7, /* Allow inode numbers > 2^32 */ OCFS2_MOUNT_POSIX_ACL = 1 << 8, /* Force POSIX access control lists */ OCFS2_MOUNT_NO_POSIX_ACL = 1 << 9, /* Disable POSIX access control lists */ OCFS2_MOUNT_USRQUOTA = 1 << 10, /* We support user quotas */ OCFS2_MOUNT_GRPQUOTA = 1 << 11, /* We support group quotas */ OCFS2_MOUNT_COHERENCY_BUFFERED = 1 << 12, /* Allow concurrent O_DIRECT writes */ OCFS2_MOUNT_HB_NONE = 1 << 13, /* No heartbeat */ OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */ OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */ OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */ OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */ }; #define OCFS2_OSB_SOFT_RO 0x0001 #define OCFS2_OSB_HARD_RO 0x0002 #define OCFS2_OSB_ERROR_FS 0x0004 #define OCFS2_DEFAULT_ATIME_QUANTUM 60 struct ocfs2_triggers { struct jbd2_buffer_trigger_type ot_triggers; int ot_offset; struct super_block *sb; }; enum ocfs2_journal_trigger_type { OCFS2_JTR_DI, OCFS2_JTR_EB, OCFS2_JTR_RB, OCFS2_JTR_GD, OCFS2_JTR_DB, OCFS2_JTR_XB, OCFS2_JTR_DQ, OCFS2_JTR_DR, OCFS2_JTR_DL, OCFS2_JTR_NONE /* This must be the last entry */ }; #define OCFS2_JOURNAL_TRIGGER_COUNT OCFS2_JTR_NONE void ocfs2_initialize_journal_triggers(struct super_block *sb, struct ocfs2_triggers triggers[]); enum ocfs2_recovery_state { OCFS2_REC_ENABLED = 0, OCFS2_REC_QUOTA_WANT_DISABLE, /* * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for * ocfs2_recovery_disable_quota() to work. */ OCFS2_REC_QUOTA_DISABLED, OCFS2_REC_WANT_DISABLE, /* * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work */ OCFS2_REC_DISABLED, }; struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; struct ocfs2_replay_map; struct ocfs2_quota_recovery; struct ocfs2_super { struct task_struct *commit_task; struct super_block *sb; struct inode *root_inode; struct inode *sys_root_inode; struct inode *global_system_inodes[NUM_GLOBAL_SYSTEM_INODES]; struct inode **local_system_inodes; struct ocfs2_slot_info *slot_info; u32 *slot_recovery_generations; spinlock_t node_map_lock; u64 root_blkno; u64 system_dir_blkno; u64 bitmap_blkno; u32 bitmap_cpg; char *uuid_str; u32 uuid_hash; u8 *vol_label; u64 first_cluster_group_blkno; u32 fs_generation; u32 s_feature_compat; u32 s_feature_incompat; u32 s_feature_ro_compat; /* Protects s_next_generation, osb_flags and s_inode_steal_slot. * Could protect more on osb as it's very short lived. */ spinlock_t osb_lock; u32 s_next_generation; unsigned long osb_flags; u16 s_inode_steal_slot; u16 s_meta_steal_slot; atomic_t s_num_inodes_stolen; atomic_t s_num_meta_stolen; unsigned long s_mount_opt; unsigned int s_atime_quantum; unsigned int max_slots; unsigned int node_num; int slot_num; int preferred_slot; int s_sectsize_bits; int s_clustersize; int s_clustersize_bits; unsigned int s_xattr_inline_size; atomic_t vol_state; struct mutex recovery_lock; struct ocfs2_recovery_map *recovery_map; struct ocfs2_replay_map *replay_map; struct task_struct *recovery_thread_task; enum ocfs2_recovery_state recovery_state; wait_queue_head_t checkpoint_event; struct ocfs2_journal *journal; unsigned long osb_commit_interval; /* Journal triggers for checksum */ struct ocfs2_triggers s_journal_triggers[OCFS2_JOURNAL_TRIGGER_COUNT]; struct delayed_work la_enable_wq; /* * Must hold local alloc i_rwsem and osb->osb_lock to change * local_alloc_bits. Reads can be done under either lock. */ unsigned int local_alloc_bits; unsigned int local_alloc_default_bits; /* osb_clusters_at_boot can become stale! Do not trust it to * be up to date. */ unsigned int osb_clusters_at_boot; enum ocfs2_local_alloc_state local_alloc_state; /* protected * by osb_lock */ struct buffer_head *local_alloc_bh; u64 la_last_gd; struct ocfs2_reservation_map osb_la_resmap; unsigned int osb_resv_level; unsigned int osb_dir_resv_level; /* Next two fields are for local node slot recovery during * mount. */ struct ocfs2_dinode *local_alloc_copy; struct ocfs2_quota_recovery *quota_rec; struct ocfs2_blockcheck_stats osb_ecc_stats; struct ocfs2_alloc_stats alloc_stats; char dev_str[20]; /* "major,minor" of the device */ u8 osb_stackflags; char osb_cluster_stack[OCFS2_STACK_LABEL_LEN + 1]; char osb_cluster_name[OCFS2_CLUSTER_NAME_LEN + 1]; struct ocfs2_cluster_connection *cconn; struct ocfs2_lock_res osb_super_lockres; struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; struct rw_semaphore nfs_sync_rwlock; struct ocfs2_lock_res osb_trim_fs_lockres; struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; struct dentry *osb_debug_root; wait_queue_head_t recovery_event; spinlock_t dc_task_lock; struct task_struct *dc_task; wait_queue_head_t dc_event; unsigned long dc_wake_sequence; unsigned long dc_work_sequence; /* * Any thread can add locks to the list, but the downconvert * thread is the only one allowed to remove locks. Any change * to this rule requires updating * ocfs2_downconvert_thread_do_work(). */ struct list_head blocked_lock_list; unsigned long blocked_lock_count; /* List of dquot structures to drop last reference to */ struct llist_head dquot_drop_list; struct work_struct dquot_drop_work; wait_queue_head_t osb_mount_event; /* Truncate log info */ struct inode *osb_tl_inode; struct buffer_head *osb_tl_bh; struct delayed_work osb_truncate_log_wq; atomic_t osb_tl_disable; /* * How many clusters in our truncate log. * It must be protected by osb_tl_inode->i_rwsem. */ unsigned int truncated_clusters; struct ocfs2_node_map osb_recovering_orphan_dirs; unsigned int *osb_orphan_wipes; wait_queue_head_t osb_wipe_event; struct ocfs2_orphan_scan osb_orphan_scan; /* used to protect metaecc calculation check of xattr. */ spinlock_t osb_xattr_lock; unsigned int osb_dx_mask; u32 osb_dx_seed[4]; /* the group we used to allocate inodes. */ u64 osb_inode_alloc_group; /* rb tree root for refcount lock. */ struct rb_root osb_rf_lock_tree; struct ocfs2_refcount_tree *osb_ref_tree_lru; /* * OCFS2 needs to schedule several different types of work which * require cluster locking, disk I/O, recovery waits, etc. Since these * types of work tend to be heavy we avoid using the kernel events * workqueue and schedule on our own. */ struct workqueue_struct *ocfs2_wq; /* sysfs directory per partition */ struct kset *osb_dev_kset; /* file check related stuff */ struct ocfs2_filecheck_sysfs_entry osb_fc_ent; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) /* Useful typedef for passing around journal access functions */ typedef int (*ocfs2_journal_access_func)(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type); static inline int ocfs2_should_order_data(struct inode *inode) { if (!S_ISREG(inode->i_mode)) return 0; if (OCFS2_SB(inode->i_sb)->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK) return 0; return 1; } static inline int ocfs2_sparse_alloc(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC) return 1; return 0; } static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb) { /* * Support for sparse files is a pre-requisite */ if (!ocfs2_sparse_alloc(osb)) return 0; if (osb->s_feature_ro_compat & OCFS2_FEATURE_RO_COMPAT_UNWRITTEN) return 1; return 0; } static inline int ocfs2_supports_append_dio(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_APPEND_DIO) return 1; return 0; } static inline int ocfs2_supports_inline_data(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INLINE_DATA) return 1; return 0; } static inline int ocfs2_supports_xattr(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_XATTR) return 1; return 0; } static inline int ocfs2_meta_ecc(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_META_ECC) return 1; return 0; } static inline int ocfs2_supports_indexed_dirs(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS) return 1; return 0; } static inline int ocfs2_supports_discontig_bg(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG) return 1; return 0; } static inline unsigned int ocfs2_link_max(struct ocfs2_super *osb) { if (ocfs2_supports_indexed_dirs(osb)) return OCFS2_DX_LINK_MAX; return OCFS2_LINK_MAX; } static inline unsigned int ocfs2_read_links_count(struct ocfs2_dinode *di) { u32 nlink = le16_to_cpu(di->i_links_count); u32 hi = le16_to_cpu(di->i_links_count_hi); nlink |= (hi << OCFS2_LINKS_HI_SHIFT); return nlink; } static inline void ocfs2_set_links_count(struct ocfs2_dinode *di, u32 nlink) { u16 lo, hi; lo = nlink; hi = nlink >> OCFS2_LINKS_HI_SHIFT; di->i_links_count = cpu_to_le16(lo); di->i_links_count_hi = cpu_to_le16(hi); } static inline void ocfs2_add_links_count(struct ocfs2_dinode *di, int n) { u32 links = ocfs2_read_links_count(di); links += n; ocfs2_set_links_count(di, links); } static inline int ocfs2_refcount_tree(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE) return 1; return 0; } /* set / clear functions because cluster events can make these happen * in parallel so we want the transitions to be atomic. this also * means that any future flags osb_flags must be protected by spinlock * too! */ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb, unsigned long flag) { spin_lock(&osb->osb_lock); osb->osb_flags |= flag; spin_unlock(&osb->osb_lock); } static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb, int hard) { spin_lock(&osb->osb_lock); osb->osb_flags &= ~(OCFS2_OSB_SOFT_RO|OCFS2_OSB_HARD_RO); if (hard) osb->osb_flags |= OCFS2_OSB_HARD_RO; else osb->osb_flags |= OCFS2_OSB_SOFT_RO; spin_unlock(&osb->osb_lock); } static inline int ocfs2_is_hard_readonly(struct ocfs2_super *osb) { int ret; spin_lock(&osb->osb_lock); ret = osb->osb_flags & OCFS2_OSB_HARD_RO; spin_unlock(&osb->osb_lock); return ret; } static inline int ocfs2_is_soft_readonly(struct ocfs2_super *osb) { int ret; spin_lock(&osb->osb_lock); ret = osb->osb_flags & OCFS2_OSB_SOFT_RO; spin_unlock(&osb->osb_lock); return ret; } static inline int ocfs2_is_readonly(struct ocfs2_super *osb) { int ret; spin_lock(&osb->osb_lock); ret = osb->osb_flags & (OCFS2_OSB_SOFT_RO | OCFS2_OSB_HARD_RO); spin_unlock(&osb->osb_lock); return ret; } static inline int ocfs2_emergency_state(struct ocfs2_super *osb) { if (ocfs2_is_readonly(osb)) return -EROFS; return 0; } static inline int ocfs2_clusterinfo_valid(struct ocfs2_super *osb) { return (osb->s_feature_incompat & (OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO)); } static inline int ocfs2_userspace_stack(struct ocfs2_super *osb) { if (ocfs2_clusterinfo_valid(osb) && memcmp(osb->osb_cluster_stack, OCFS2_CLASSIC_CLUSTER_STACK, OCFS2_STACK_LABEL_LEN)) return 1; return 0; } static inline int ocfs2_o2cb_stack(struct ocfs2_super *osb) { if (ocfs2_clusterinfo_valid(osb) && !memcmp(osb->osb_cluster_stack, OCFS2_CLASSIC_CLUSTER_STACK, OCFS2_STACK_LABEL_LEN)) return 1; return 0; } static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb) { return ocfs2_o2cb_stack(osb) && (osb->osb_stackflags & OCFS2_CLUSTER_O2CB_GLOBAL_HEARTBEAT); } static inline int ocfs2_mount_local(struct ocfs2_super *osb) { return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT); } static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb) { return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP); } #define OCFS2_IS_VALID_DINODE(ptr) \ (!strcmp((ptr)->i_signature, OCFS2_INODE_SIGNATURE)) #define OCFS2_IS_VALID_EXTENT_BLOCK(ptr) \ (!strcmp((ptr)->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE)) #define OCFS2_IS_VALID_GROUP_DESC(ptr) \ (!strcmp((ptr)->bg_signature, OCFS2_GROUP_DESC_SIGNATURE)) #define OCFS2_IS_VALID_XATTR_BLOCK(ptr) \ (!strcmp((ptr)->xb_signature, OCFS2_XATTR_BLOCK_SIGNATURE)) #define OCFS2_IS_VALID_DIR_TRAILER(ptr) \ (!strcmp((ptr)->db_signature, OCFS2_DIR_TRAILER_SIGNATURE)) #define OCFS2_IS_VALID_DX_ROOT(ptr) \ (!strcmp((ptr)->dr_signature, OCFS2_DX_ROOT_SIGNATURE)) #define OCFS2_IS_VALID_DX_LEAF(ptr) \ (!strcmp((ptr)->dl_signature, OCFS2_DX_LEAF_SIGNATURE)) #define OCFS2_IS_VALID_REFCOUNT_BLOCK(ptr) \ (!strcmp((ptr)->rf_signature, OCFS2_REFCOUNT_BLOCK_SIGNATURE)) static inline unsigned long ino_from_blkno(struct super_block *sb, u64 blkno) { return (unsigned long)(blkno & (u64)ULONG_MAX); } static inline u64 ocfs2_clusters_to_blocks(struct super_block *sb, u32 clusters) { int c_to_b_bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; return (u64)clusters << c_to_b_bits; } static inline u32 ocfs2_clusters_for_blocks(struct super_block *sb, u64 blocks) { int b_to_c_bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; blocks += (1 << b_to_c_bits) - 1; return (u32)(blocks >> b_to_c_bits); } static inline u32 ocfs2_blocks_to_clusters(struct super_block *sb, u64 blocks) { int b_to_c_bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; return (u32)(blocks >> b_to_c_bits); } static inline unsigned int ocfs2_clusters_for_bytes(struct super_block *sb, u64 bytes) { int cl_bits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int clusters; bytes += OCFS2_SB(sb)->s_clustersize - 1; /* OCFS2 just cannot have enough clusters to overflow this */ clusters = (unsigned int)(bytes >> cl_bits); return clusters; } static inline unsigned int ocfs2_bytes_to_clusters(struct super_block *sb, u64 bytes) { int cl_bits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int clusters; clusters = (unsigned int)(bytes >> cl_bits); return clusters; } static inline u64 ocfs2_blocks_for_bytes(struct super_block *sb, u64 bytes) { bytes += sb->s_blocksize - 1; return bytes >> sb->s_blocksize_bits; } static inline u64 ocfs2_clusters_to_bytes(struct super_block *sb, u32 clusters) { return (u64)clusters << OCFS2_SB(sb)->s_clustersize_bits; } static inline u64 ocfs2_block_to_cluster_start(struct super_block *sb, u64 blocks) { int bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; unsigned int clusters; clusters = ocfs2_blocks_to_clusters(sb, blocks); return (u64)clusters << bits; } static inline u64 ocfs2_align_bytes_to_clusters(struct super_block *sb, u64 bytes) { int cl_bits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int clusters; clusters = ocfs2_clusters_for_bytes(sb, bytes); return (u64)clusters << cl_bits; } static inline u64 ocfs2_align_bytes_to_blocks(struct super_block *sb, u64 bytes) { u64 blocks; blocks = ocfs2_blocks_for_bytes(sb, bytes); return blocks << sb->s_blocksize_bits; } static inline unsigned long ocfs2_align_bytes_to_sectors(u64 bytes) { return (unsigned long)((bytes + 511) >> 9); } static inline unsigned int ocfs2_page_index_to_clusters(struct super_block *sb, unsigned long pg_index) { u32 clusters = pg_index; unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; if (unlikely(PAGE_SHIFT > cbits)) clusters = pg_index << (PAGE_SHIFT - cbits); else if (PAGE_SHIFT < cbits) clusters = pg_index >> (cbits - PAGE_SHIFT); return clusters; } /* * Find the 1st page index which covers the given clusters. */ static inline pgoff_t ocfs2_align_clusters_to_page_index(struct super_block *sb, u32 clusters) { unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; pgoff_t index = clusters; if (PAGE_SHIFT > cbits) { index = (pgoff_t)clusters >> (PAGE_SHIFT - cbits); } else if (PAGE_SHIFT < cbits) { index = (pgoff_t)clusters << (cbits - PAGE_SHIFT); } return index; } static inline unsigned int ocfs2_pages_per_cluster(struct super_block *sb) { unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int pages_per_cluster = 1; if (PAGE_SHIFT < cbits) pages_per_cluster = 1 << (cbits - PAGE_SHIFT); return pages_per_cluster; } static inline unsigned int ocfs2_megabytes_to_clusters(struct super_block *sb, unsigned int megs) { BUILD_BUG_ON(OCFS2_MAX_CLUSTERSIZE > 1048576); return megs << (20 - OCFS2_SB(sb)->s_clustersize_bits); } static inline unsigned int ocfs2_clusters_to_megabytes(struct super_block *sb, unsigned int clusters) { return clusters >> (20 - OCFS2_SB(sb)->s_clustersize_bits); } static inline void _ocfs2_set_bit(unsigned int bit, unsigned long *bitmap) { __set_bit_le(bit, bitmap); } #define ocfs2_set_bit(bit, addr) _ocfs2_set_bit((bit), (unsigned long *)(addr)) static inline void _ocfs2_clear_bit(unsigned int bit, unsigned long *bitmap) { __clear_bit_le(bit, bitmap); } #define ocfs2_clear_bit(bit, addr) _ocfs2_clear_bit((bit), (unsigned long *)(addr)) #define ocfs2_test_bit test_bit_le #define ocfs2_find_next_zero_bit find_next_zero_bit_le #define ocfs2_find_next_bit find_next_bit_le static inline void *correct_addr_and_bit_unaligned(int *bit, void *addr) { #if BITS_PER_LONG == 64 *bit += ((unsigned long) addr & 7UL) << 3; addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 *bit += ((unsigned long) addr & 3UL) << 3; addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif return addr; } static inline void ocfs2_set_bit_unaligned(int bit, void *bitmap) { bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); ocfs2_set_bit(bit, bitmap); } static inline void ocfs2_clear_bit_unaligned(int bit, void *bitmap) { bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); ocfs2_clear_bit(bit, bitmap); } static inline int ocfs2_test_bit_unaligned(int bit, void *bitmap) { bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); return ocfs2_test_bit(bit, bitmap); } static inline int ocfs2_find_next_zero_bit_unaligned(void *bitmap, int max, int start) { int fix = 0, ret, tmpmax; bitmap = correct_addr_and_bit_unaligned(&fix, bitmap); tmpmax = max + fix; start += fix; ret = ocfs2_find_next_zero_bit(bitmap, tmpmax, start) - fix; if (ret > max) return max; return ret; } #endif /* OCFS2_H */ |
| 34 34 34 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | // SPDX-License-Identifier: LGPL-2.1 /* * Copyright IBM Corporation, 2010 * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> */ #include <linux/mm.h> #include <linux/module.h> #include "trans_common.h" /** * p9_release_pages - Release pages after the transaction. * @pages: array of pages to be put * @nr_pages: size of array */ void p9_release_pages(struct page **pages, int nr_pages) { int i; for (i = 0; i < nr_pages; i++) if (pages[i]) put_page(pages[i]); } EXPORT_SYMBOL(p9_release_pages); |
| 36 8 23 23 23 23 22 35 34 34 35 35 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 | /* * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/in.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/ipv6.h> #include "rds_single_path.h" #include "rds.h" #include "loop.h" static DEFINE_SPINLOCK(loop_conns_lock); static LIST_HEAD(loop_conns); static atomic_t rds_loop_unloading = ATOMIC_INIT(0); static void rds_loop_set_unloading(void) { atomic_set(&rds_loop_unloading, 1); } static bool rds_loop_is_unloading(struct rds_connection *conn) { return atomic_read(&rds_loop_unloading) != 0; } /* * This 'loopback' transport is a special case for flows that originate * and terminate on the same machine. * * Connection build-up notices if the destination address is thought of * as a local address by a transport. At that time it decides to use the * loopback transport instead of the bound transport of the sending socket. * * The loopback transport's sending path just hands the sent rds_message * straight to the receiving path via an embedded rds_incoming. */ /* * Usually a message transits both the sender and receiver's conns as it * flows to the receiver. In the loopback case, though, the receive path * is handed the sending conn so the sense of the addresses is reversed. */ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm, unsigned int hdr_off, unsigned int sg, unsigned int off) { struct scatterlist *sgp = &rm->data.op_sg[sg]; int ret = sizeof(struct rds_header) + be32_to_cpu(rm->m_inc.i_hdr.h_len); /* Do not send cong updates to loopback */ if (rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); ret = min_t(int, ret, sgp->length - conn->c_xmit_data_off); goto out; } BUG_ON(hdr_off || sg || off); rds_inc_init(&rm->m_inc, conn, &conn->c_laddr); /* For the embedded inc. Matching put is in loop_inc_free() */ rds_message_addref(rm); rds_recv_incoming(conn, &conn->c_laddr, &conn->c_faddr, &rm->m_inc, GFP_KERNEL); rds_send_drop_acked(conn, be64_to_cpu(rm->m_inc.i_hdr.h_sequence), NULL); rds_inc_put(&rm->m_inc); out: return ret; } /* * See rds_loop_xmit(). Since our inc is embedded in the rm, we * make sure the rm lives at least until the inc is done. */ static void rds_loop_inc_free(struct rds_incoming *inc) { struct rds_message *rm = container_of(inc, struct rds_message, m_inc); rds_message_put(rm); } /* we need to at least give the thread something to succeed */ static int rds_loop_recv_path(struct rds_conn_path *cp) { return 0; } struct rds_loop_connection { struct list_head loop_node; struct rds_connection *conn; }; /* * Even the loopback transport needs to keep track of its connections, * so it can call rds_conn_destroy() on them on exit. N.B. there are * 1+ loopback addresses (127.*.*.*) so it's not a bug to have * multiple loopback conns allocated, although rather useless. */ static int rds_loop_conn_alloc(struct rds_connection *conn, gfp_t gfp) { struct rds_loop_connection *lc; unsigned long flags; lc = kzalloc_obj(struct rds_loop_connection, gfp); if (!lc) return -ENOMEM; INIT_LIST_HEAD(&lc->loop_node); lc->conn = conn; conn->c_transport_data = lc; spin_lock_irqsave(&loop_conns_lock, flags); list_add_tail(&lc->loop_node, &loop_conns); spin_unlock_irqrestore(&loop_conns_lock, flags); return 0; } static void rds_loop_conn_free(void *arg) { struct rds_loop_connection *lc = arg; unsigned long flags; rdsdebug("lc %p\n", lc); spin_lock_irqsave(&loop_conns_lock, flags); list_del(&lc->loop_node); spin_unlock_irqrestore(&loop_conns_lock, flags); kfree(lc); } static int rds_loop_conn_path_connect(struct rds_conn_path *cp) { rds_connect_complete(cp->cp_conn); return 0; } static void rds_loop_conn_path_shutdown(struct rds_conn_path *cp) { } void rds_loop_exit(void) { struct rds_loop_connection *lc, *_lc; LIST_HEAD(tmp_list); rds_loop_set_unloading(); synchronize_rcu(); /* avoid calling conn_destroy with irqs off */ spin_lock_irq(&loop_conns_lock); list_splice(&loop_conns, &tmp_list); INIT_LIST_HEAD(&loop_conns); spin_unlock_irq(&loop_conns_lock); list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) { WARN_ON(lc->conn->c_passive); rds_conn_destroy(lc->conn); } } static void rds_loop_kill_conns(struct net *net) { struct rds_loop_connection *lc, *_lc; LIST_HEAD(tmp_list); spin_lock_irq(&loop_conns_lock); list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) { struct net *c_net = read_pnet(&lc->conn->c_net); if (net != c_net) continue; list_move_tail(&lc->loop_node, &tmp_list); } spin_unlock_irq(&loop_conns_lock); list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) { WARN_ON(lc->conn->c_passive); rds_conn_destroy(lc->conn); } } static void __net_exit rds_loop_exit_net(struct net *net) { rds_loop_kill_conns(net); } static struct pernet_operations rds_loop_net_ops = { .exit = rds_loop_exit_net, }; int rds_loop_net_init(void) { return register_pernet_device(&rds_loop_net_ops); } void rds_loop_net_exit(void) { unregister_pernet_device(&rds_loop_net_ops); } /* * This is missing .xmit_* because loop doesn't go through generic * rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and * .laddr_check are missing because transport.c doesn't iterate over * rds_loop_transport. */ struct rds_transport rds_loop_transport = { .xmit = rds_loop_xmit, .recv_path = rds_loop_recv_path, .conn_alloc = rds_loop_conn_alloc, .conn_free = rds_loop_conn_free, .conn_path_connect = rds_loop_conn_path_connect, .conn_path_shutdown = rds_loop_conn_path_shutdown, .inc_copy_to_user = rds_message_inc_copy_to_user, .inc_free = rds_loop_inc_free, .t_name = "loopback", .t_type = RDS_TRANS_LOOP, .t_unloading = rds_loop_is_unloading, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 1999-2002 Vojtech Pavlik */ #ifndef _SERIO_H #define _SERIO_H #include <linux/cleanup.h> #include <linux/types.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/device-id/serio.h> #include <uapi/linux/serio.h> extern const struct bus_type serio_bus; struct serio { void *port_data; char name[32]; char phys[32]; char firmware_id[128]; bool manual_bind; struct serio_device_id id; /* Protects critical sections from port's interrupt handler */ spinlock_t lock; int (*write)(struct serio *, unsigned char); int (*open)(struct serio *); void (*close)(struct serio *); int (*start)(struct serio *); void (*stop)(struct serio *); struct serio *parent; /* Entry in parent->children list */ struct list_head child_node; struct list_head children; /* Level of nesting in serio hierarchy */ unsigned int depth; /* * serio->drv is accessed from interrupt handlers; when modifying * caller should acquire serio->drv_mutex and serio->lock. */ struct serio_driver *drv; /* Protects serio->drv so attributes can pin current driver */ struct mutex drv_mutex; struct device dev; struct list_head node; /* * For use by PS/2 layer when several ports share hardware and * may get indigestion when exposed to concurrent access (i8042). */ struct mutex *ps2_cmd_mutex; }; #define to_serio_port(d) container_of(d, struct serio, dev) struct serio_driver { const char *description; const struct serio_device_id *id_table; bool manual_bind; void (*write_wakeup)(struct serio *); irqreturn_t (*interrupt)(struct serio *, unsigned char, unsigned int); int (*connect)(struct serio *, struct serio_driver *drv); int (*reconnect)(struct serio *); int (*fast_reconnect)(struct serio *); void (*disconnect)(struct serio *); void (*cleanup)(struct serio *); struct device_driver driver; }; #define to_serio_driver(d) container_of_const(d, struct serio_driver, driver) int serio_open(struct serio *serio, struct serio_driver *drv); void serio_close(struct serio *serio); void serio_rescan(struct serio *serio); void serio_reconnect(struct serio *serio); irqreturn_t serio_interrupt(struct serio *serio, unsigned char data, unsigned int flags); void __serio_register_port(struct serio *serio, struct module *owner); /* use a define to avoid include chaining to get THIS_MODULE */ #define serio_register_port(serio) \ __serio_register_port(serio, THIS_MODULE) void serio_unregister_port(struct serio *serio); void serio_unregister_child_port(struct serio *serio); int __must_check __serio_register_driver(struct serio_driver *drv, struct module *owner, const char *mod_name); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define serio_register_driver(drv) \ __serio_register_driver(drv, THIS_MODULE, KBUILD_MODNAME) void serio_unregister_driver(struct serio_driver *drv); /** * module_serio_driver() - Helper macro for registering a serio driver * @__serio_driver: serio_driver struct * * Helper macro for serio drivers which do not do anything special in * module init/exit. This eliminates a lot of boilerplate. Each module * may only use this macro once, and calling it replaces module_init() * and module_exit(). */ #define module_serio_driver(__serio_driver) \ module_driver(__serio_driver, serio_register_driver, \ serio_unregister_driver) static inline int serio_write(struct serio *serio, unsigned char data) { if (serio->write) return serio->write(serio, data); else return -1; } static inline void serio_drv_write_wakeup(struct serio *serio) { if (serio->drv && serio->drv->write_wakeup) serio->drv->write_wakeup(serio); } /* * Use the following functions to manipulate serio's per-port * driver-specific data. */ static inline void *serio_get_drvdata(struct serio *serio) { return dev_get_drvdata(&serio->dev); } static inline void serio_set_drvdata(struct serio *serio, void *data) { dev_set_drvdata(&serio->dev, data); } /* * Use the following functions to protect critical sections in * driver code from port's interrupt handler */ static inline void serio_pause_rx(struct serio *serio) { spin_lock_irq(&serio->lock); } static inline void serio_continue_rx(struct serio *serio) { spin_unlock_irq(&serio->lock); } DEFINE_GUARD(serio_pause_rx, struct serio *, serio_pause_rx(_T), serio_continue_rx(_T)) #endif |
| 1 1 1 1 3 1 1 1 1 1 3 3 5 5 1 1 1 1 1 1 1 1 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007-2012 Siemens AG * * Written by: * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <net/netlink.h> #include <net/nl802154.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include <net/route.h> #include <net/cfg802154.h> #include "ieee802154_i.h" #include "cfg.h" static void ieee802154_tasklet_handler(struct tasklet_struct *t) { struct ieee802154_local *local = from_tasklet(local, t, tasklet); struct sk_buff *skb; while ((skb = skb_dequeue(&local->skb_queue))) { switch (skb->pkt_type) { case IEEE802154_RX_MSG: /* Clear skb->pkt_type in order to not confuse kernel * netstack. */ skb->pkt_type = 0; ieee802154_rx(local, skb); break; default: WARN(1, "mac802154: Packet is of unknown type %d\n", skb->pkt_type); kfree_skb(skb); break; } } } struct ieee802154_hw * ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) { struct wpan_phy *phy; struct ieee802154_local *local; size_t priv_size; if (WARN_ON(!ops || !(ops->xmit_async || ops->xmit_sync) || !ops->ed || !ops->start || !ops->stop || !ops->set_channel)) return NULL; /* Ensure 32-byte alignment of our private data and hw private data. * We use the wpan_phy priv data for both our ieee802154_local and for * the driver's private data * * in memory it'll be like this: * * +-------------------------+ * | struct wpan_phy | * +-------------------------+ * | struct ieee802154_local | * +-------------------------+ * | driver's private data | * +-------------------------+ * * Due to ieee802154 layer isn't aware of driver and MAC structures, * so lets align them here. */ priv_size = ALIGN(sizeof(*local), NETDEV_ALIGN) + priv_data_len; phy = wpan_phy_new(&mac802154_config_ops, priv_size); if (!phy) { pr_err("failure to allocate master IEEE802.15.4 device\n"); return NULL; } phy->privid = mac802154_wpan_phy_privid; local = wpan_phy_priv(phy); local->phy = phy; local->hw.phy = local->phy; local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN); local->ops = ops; INIT_LIST_HEAD(&local->interfaces); INIT_LIST_HEAD(&local->rx_beacon_list); INIT_LIST_HEAD(&local->rx_mac_cmd_list); mutex_init(&local->iflist_mtx); tasklet_setup(&local->tasklet, ieee802154_tasklet_handler); skb_queue_head_init(&local->skb_queue); INIT_WORK(&local->sync_tx_work, ieee802154_xmit_sync_worker); INIT_DELAYED_WORK(&local->scan_work, mac802154_scan_worker); INIT_WORK(&local->rx_beacon_work, mac802154_rx_beacon_worker); INIT_DELAYED_WORK(&local->beacon_work, mac802154_beacon_worker); INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker); init_completion(&local->assoc_done); /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; phy->supported.min_maxbe = 3; phy->supported.max_maxbe = 8; phy->supported.min_frame_retries = 0; phy->supported.max_frame_retries = 7; phy->supported.max_csma_backoffs = 5; phy->supported.lbt = NL802154_SUPPORTED_BOOL_FALSE; /* always supported */ phy->supported.iftypes = BIT(NL802154_IFTYPE_NODE) | BIT(NL802154_IFTYPE_COORD); return &local->hw; } EXPORT_SYMBOL(ieee802154_alloc_hw); void ieee802154_configure_durations(struct wpan_phy *phy, unsigned int page, unsigned int channel) { u32 duration = 0; switch (page) { case 0: if (BIT(channel) & 0x1) /* 868 MHz BPSK 802.15.4-2003: 20 ksym/s */ duration = 50 * NSEC_PER_USEC; else if (BIT(channel) & 0x7FE) /* 915 MHz BPSK 802.15.4-2003: 40 ksym/s */ duration = 25 * NSEC_PER_USEC; else if (BIT(channel) & 0x7FFF800) /* 2400 MHz O-QPSK 802.15.4-2006: 62.5 ksym/s */ duration = 16 * NSEC_PER_USEC; break; case 2: if (BIT(channel) & 0x1) /* 868 MHz O-QPSK 802.15.4-2006: 25 ksym/s */ duration = 40 * NSEC_PER_USEC; else if (BIT(channel) & 0x7FE) /* 915 MHz O-QPSK 802.15.4-2006: 62.5 ksym/s */ duration = 16 * NSEC_PER_USEC; break; case 3: if (BIT(channel) & 0x3FFF) /* 2.4 GHz CSS 802.15.4a-2007: 1/6 Msym/s */ duration = 6 * NSEC_PER_USEC; break; default: break; } if (!duration) { pr_debug("Unknown PHY symbol duration\n"); return; } phy->symbol_duration = duration; phy->lifs_period = (IEEE802154_LIFS_PERIOD * phy->symbol_duration) / NSEC_PER_USEC; phy->sifs_period = (IEEE802154_SIFS_PERIOD * phy->symbol_duration) / NSEC_PER_USEC; } EXPORT_SYMBOL(ieee802154_configure_durations); void ieee802154_free_hw(struct ieee802154_hw *hw) { struct ieee802154_local *local = hw_to_local(hw); BUG_ON(!list_empty(&local->interfaces)); mutex_destroy(&local->iflist_mtx); wpan_phy_free(local->phy); } EXPORT_SYMBOL(ieee802154_free_hw); static void ieee802154_setup_wpan_phy_pib(struct wpan_phy *wpan_phy) { /* TODO warn on empty symbol_duration * Should be done when all drivers sets this value. */ wpan_phy->lifs_period = (IEEE802154_LIFS_PERIOD * wpan_phy->symbol_duration) / NSEC_PER_USEC; wpan_phy->sifs_period = (IEEE802154_SIFS_PERIOD * wpan_phy->symbol_duration) / NSEC_PER_USEC; } int ieee802154_register_hw(struct ieee802154_hw *hw) { struct ieee802154_local *local = hw_to_local(hw); char mac_wq_name[IFNAMSIZ + 10] = {}; struct net_device *dev; int rc = -ENOSYS; local->workqueue = create_singlethread_workqueue(wpan_phy_name(local->phy)); if (!local->workqueue) { rc = -ENOMEM; goto out; } snprintf(mac_wq_name, IFNAMSIZ + 10, "%s-mac-cmds", wpan_phy_name(local->phy)); local->mac_wq = create_singlethread_workqueue(mac_wq_name); if (!local->mac_wq) { rc = -ENOMEM; goto out_wq; } hrtimer_setup(&local->ifs_timer, ieee802154_xmit_ifs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); wpan_phy_set_dev(local->phy, local->hw.parent); ieee802154_setup_wpan_phy_pib(local->phy); ieee802154_configure_durations(local->phy, local->phy->current_page, local->phy->current_channel); if (!(hw->flags & IEEE802154_HW_CSMA_PARAMS)) { local->phy->supported.min_csma_backoffs = 4; local->phy->supported.max_csma_backoffs = 4; local->phy->supported.min_maxbe = 5; local->phy->supported.max_maxbe = 5; local->phy->supported.min_minbe = 3; local->phy->supported.max_minbe = 3; } if (!(hw->flags & IEEE802154_HW_FRAME_RETRIES)) { local->phy->supported.min_frame_retries = 3; local->phy->supported.max_frame_retries = 3; } if (hw->flags & IEEE802154_HW_PROMISCUOUS) local->phy->supported.iftypes |= BIT(NL802154_IFTYPE_MONITOR); rc = wpan_phy_register(local->phy); if (rc < 0) goto out_mac_wq; rtnl_lock(); dev = ieee802154_if_add(local, "wpan%d", NET_NAME_ENUM, NL802154_IFTYPE_NODE, cpu_to_le64(0x0000000000000000ULL)); if (IS_ERR(dev)) { rtnl_unlock(); rc = PTR_ERR(dev); goto out_phy; } rtnl_unlock(); return 0; out_phy: wpan_phy_unregister(local->phy); out_mac_wq: destroy_workqueue(local->mac_wq); out_wq: destroy_workqueue(local->workqueue); out: return rc; } EXPORT_SYMBOL(ieee802154_register_hw); void ieee802154_unregister_hw(struct ieee802154_hw *hw) { struct ieee802154_local *local = hw_to_local(hw); tasklet_kill(&local->tasklet); flush_workqueue(local->workqueue); rtnl_lock(); ieee802154_remove_interfaces(local); rtnl_unlock(); destroy_workqueue(local->mac_wq); destroy_workqueue(local->workqueue); wpan_phy_unregister(local->phy); } EXPORT_SYMBOL(ieee802154_unregister_hw); static int __init ieee802154_init(void) { return ieee802154_iface_init(); } static void __exit ieee802154_exit(void) { ieee802154_iface_exit(); rcu_barrier(); } subsys_initcall(ieee802154_init); module_exit(ieee802154_exit); MODULE_DESCRIPTION("IEEE 802.15.4 subsystem"); MODULE_LICENSE("GPL v2"); |
| 5 5 7 7 7 7 7 7 7 5 5 5 5 5 5 5 4 4 4 4 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 7 5 5 5 5 4 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 2 2 2 5 5 5 2 5 5 5 5 4 4 2 2 2 1 1 6 5 5 4 3 6 5 5 5 5 5 4 4 4 5 5 5 5 4 4 4 4 4 4 7 5 2 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 | // SPDX-License-Identifier: GPL-2.0-only /* * Media entity * * Copyright (C) 2010 Nokia Corporation * * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com> * Sakari Ailus <sakari.ailus@iki.fi> */ #include <linux/bitmap.h> #include <linux/list.h> #include <linux/property.h> #include <linux/slab.h> #include <media/media-entity.h> #include <media/media-device.h> static inline const char *intf_type(struct media_interface *intf) { switch (intf->type) { case MEDIA_INTF_T_DVB_FE: return "dvb-frontend"; case MEDIA_INTF_T_DVB_DEMUX: return "dvb-demux"; case MEDIA_INTF_T_DVB_DVR: return "dvb-dvr"; case MEDIA_INTF_T_DVB_CA: return "dvb-ca"; case MEDIA_INTF_T_DVB_NET: return "dvb-net"; case MEDIA_INTF_T_V4L_VIDEO: return "v4l-video"; case MEDIA_INTF_T_V4L_VBI: return "v4l-vbi"; case MEDIA_INTF_T_V4L_RADIO: return "v4l-radio"; case MEDIA_INTF_T_V4L_SUBDEV: return "v4l-subdev"; case MEDIA_INTF_T_V4L_SWRADIO: return "v4l-swradio"; case MEDIA_INTF_T_V4L_TOUCH: return "v4l-touch"; default: return "unknown-intf"; } }; static inline const char *link_type_name(struct media_link *link) { switch (link->flags & MEDIA_LNK_FL_LINK_TYPE) { case MEDIA_LNK_FL_DATA_LINK: return "data"; case MEDIA_LNK_FL_INTERFACE_LINK: return "interface"; case MEDIA_LNK_FL_ANCILLARY_LINK: return "ancillary"; default: return "unknown"; } } __must_check int media_entity_enum_init(struct media_entity_enum *ent_enum, struct media_device *mdev) { int idx_max; idx_max = ALIGN(mdev->entity_internal_idx_max + 1, BITS_PER_LONG); ent_enum->bmap = bitmap_zalloc(idx_max, GFP_KERNEL); if (!ent_enum->bmap) return -ENOMEM; ent_enum->idx_max = idx_max; return 0; } EXPORT_SYMBOL_GPL(media_entity_enum_init); void media_entity_enum_cleanup(struct media_entity_enum *ent_enum) { bitmap_free(ent_enum->bmap); } EXPORT_SYMBOL_GPL(media_entity_enum_cleanup); /** * dev_dbg_obj - Prints in debug mode a change on some object * * @event_name: Name of the event to report. Could be __func__ * @gobj: Pointer to the object * * Enabled only if DEBUG or CONFIG_DYNAMIC_DEBUG. Otherwise, it * won't produce any code. */ static void dev_dbg_obj(const char *event_name, struct media_gobj *gobj) { #if defined(DEBUG) || defined (CONFIG_DYNAMIC_DEBUG) switch (media_type(gobj)) { case MEDIA_GRAPH_ENTITY: dev_dbg(gobj->mdev->dev, "%s id %u: entity '%s'\n", event_name, media_id(gobj), gobj_to_entity(gobj)->name); break; case MEDIA_GRAPH_LINK: { struct media_link *link = gobj_to_link(gobj); dev_dbg(gobj->mdev->dev, "%s id %u: %s link id %u ==> id %u\n", event_name, media_id(gobj), link_type_name(link), media_id(link->gobj0), media_id(link->gobj1)); break; } case MEDIA_GRAPH_PAD: { struct media_pad *pad = gobj_to_pad(gobj); dev_dbg(gobj->mdev->dev, "%s id %u: %s%spad '%s':%d\n", event_name, media_id(gobj), pad->flags & MEDIA_PAD_FL_SINK ? "sink " : "", pad->flags & MEDIA_PAD_FL_SOURCE ? "source " : "", pad->entity->name, pad->index); break; } case MEDIA_GRAPH_INTF_DEVNODE: { struct media_interface *intf = gobj_to_intf(gobj); struct media_intf_devnode *devnode = intf_to_devnode(intf); dev_dbg(gobj->mdev->dev, "%s id %u: intf_devnode %s - major: %d, minor: %d\n", event_name, media_id(gobj), intf_type(intf), devnode->major, devnode->minor); break; } } #endif } void media_gobj_create(struct media_device *mdev, enum media_gobj_type type, struct media_gobj *gobj) { BUG_ON(!mdev); gobj->mdev = mdev; /* Create a per-type unique object ID */ gobj->id = media_gobj_gen_id(type, ++mdev->id); switch (type) { case MEDIA_GRAPH_ENTITY: list_add_tail(&gobj->list, &mdev->entities); break; case MEDIA_GRAPH_PAD: list_add_tail(&gobj->list, &mdev->pads); break; case MEDIA_GRAPH_LINK: list_add_tail(&gobj->list, &mdev->links); break; case MEDIA_GRAPH_INTF_DEVNODE: list_add_tail(&gobj->list, &mdev->interfaces); break; } mdev->topology_version++; dev_dbg_obj(__func__, gobj); } void media_gobj_destroy(struct media_gobj *gobj) { /* Do nothing if the object is not linked. */ if (gobj->mdev == NULL) return; dev_dbg_obj(__func__, gobj); gobj->mdev->topology_version++; /* Remove the object from mdev list */ list_del(&gobj->list); gobj->mdev = NULL; } /* * TODO: Get rid of this. */ #define MEDIA_ENTITY_MAX_PADS 512 int media_entity_pads_init(struct media_entity *entity, u16 num_pads, struct media_pad *pads) { struct media_device *mdev = entity->graph_obj.mdev; struct media_pad *iter; unsigned int i = 0; int ret = 0; if (num_pads >= MEDIA_ENTITY_MAX_PADS) return -E2BIG; entity->num_pads = num_pads; entity->pads = pads; if (mdev) mutex_lock(&mdev->graph_mutex); media_entity_for_each_pad(entity, iter) { iter->entity = entity; iter->index = i++; if (hweight32(iter->flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) != 1) { ret = -EINVAL; break; } if (mdev) media_gobj_create(mdev, MEDIA_GRAPH_PAD, &iter->graph_obj); } if (ret && mdev) { media_entity_for_each_pad(entity, iter) media_gobj_destroy(&iter->graph_obj); } if (mdev) mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_entity_pads_init); /* ----------------------------------------------------------------------------- * Graph traversal */ /** * media_entity_has_pad_interdep - Check interdependency between two pads * * @entity: The entity * @pad0: The first pad index * @pad1: The second pad index * * This function checks the interdependency inside the entity between @pad0 * and @pad1. If two pads are interdependent they are part of the same pipeline * and enabling one of the pads means that the other pad will become "locked" * and doesn't allow configuration changes. * * This function uses the &media_entity_operations.has_pad_interdep() operation * to check the dependency inside the entity between @pad0 and @pad1. If the * has_pad_interdep operation is not implemented, all pads of the entity are * considered to be interdependent. * * One of @pad0 and @pad1 must be a sink pad and the other one a source pad. * The function returns false if both pads are sinks or sources. * * The caller must hold entity->graph_obj.mdev->mutex. * * Return: true if the pads are connected internally and false otherwise. */ static bool media_entity_has_pad_interdep(struct media_entity *entity, unsigned int pad0, unsigned int pad1) { if (pad0 >= entity->num_pads || pad1 >= entity->num_pads) return false; if (entity->pads[pad0].flags & entity->pads[pad1].flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) return false; if (!entity->ops || !entity->ops->has_pad_interdep) return true; return entity->ops->has_pad_interdep(entity, pad0, pad1); } static struct media_entity * media_entity_other(struct media_entity *entity, struct media_link *link) { if (link->source->entity == entity) return link->sink->entity; else return link->source->entity; } /* push an entity to traversal stack */ static void stack_push(struct media_graph *graph, struct media_entity *entity) { if (graph->top == MEDIA_ENTITY_ENUM_MAX_DEPTH - 1) { WARN_ON(1); return; } graph->top++; graph->stack[graph->top].link = entity->links.next; graph->stack[graph->top].entity = entity; } static struct media_entity *stack_pop(struct media_graph *graph) { struct media_entity *entity; entity = graph->stack[graph->top].entity; graph->top--; return entity; } #define link_top(en) ((en)->stack[(en)->top].link) #define stack_top(en) ((en)->stack[(en)->top].entity) /** * media_graph_walk_init - Allocate resources for graph walk * @graph: Media graph structure that will be used to walk the graph * @mdev: Media device * * Reserve resources for graph walk in media device's current * state. The memory must be released using * media_graph_walk_cleanup(). * * Returns error on failure, zero on success. */ __must_check int media_graph_walk_init( struct media_graph *graph, struct media_device *mdev) { return media_entity_enum_init(&graph->ent_enum, mdev); } EXPORT_SYMBOL_GPL(media_graph_walk_init); /** * media_graph_walk_cleanup - Release resources related to graph walking * @graph: Media graph structure that was used to walk the graph */ void media_graph_walk_cleanup(struct media_graph *graph) { media_entity_enum_cleanup(&graph->ent_enum); } EXPORT_SYMBOL_GPL(media_graph_walk_cleanup); void media_graph_walk_start(struct media_graph *graph, struct media_entity *entity) { media_entity_enum_zero(&graph->ent_enum); media_entity_enum_set(&graph->ent_enum, entity); graph->top = 0; graph->stack[graph->top].entity = NULL; stack_push(graph, entity); dev_dbg(entity->graph_obj.mdev->dev, "begin graph walk at '%s'\n", entity->name); } EXPORT_SYMBOL_GPL(media_graph_walk_start); static void media_graph_walk_iter(struct media_graph *graph) { struct media_entity *entity = stack_top(graph); struct media_link *link; struct media_entity *next; link = list_entry(link_top(graph), typeof(*link), list); /* If the link is not a data link, don't follow it */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { link_top(graph) = link_top(graph)->next; return; } /* The link is not enabled so we do not follow. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { link_top(graph) = link_top(graph)->next; dev_dbg(entity->graph_obj.mdev->dev, "walk: skipping disabled link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); return; } /* Get the entity at the other end of the link. */ next = media_entity_other(entity, link); /* Has the entity already been visited? */ if (media_entity_enum_test_and_set(&graph->ent_enum, next)) { link_top(graph) = link_top(graph)->next; dev_dbg(entity->graph_obj.mdev->dev, "walk: skipping entity '%s' (already seen)\n", next->name); return; } /* Push the new entity to stack and start over. */ link_top(graph) = link_top(graph)->next; stack_push(graph, next); dev_dbg(entity->graph_obj.mdev->dev, "walk: pushing '%s' on stack\n", next->name); lockdep_assert_held(&entity->graph_obj.mdev->graph_mutex); } struct media_entity *media_graph_walk_next(struct media_graph *graph) { struct media_entity *entity; if (stack_top(graph) == NULL) return NULL; /* * Depth first search. Push entity to stack and continue from * top of the stack until no more entities on the level can be * found. */ while (link_top(graph) != &stack_top(graph)->links) media_graph_walk_iter(graph); entity = stack_pop(graph); dev_dbg(entity->graph_obj.mdev->dev, "walk: returning entity '%s'\n", entity->name); return entity; } EXPORT_SYMBOL_GPL(media_graph_walk_next); /* ----------------------------------------------------------------------------- * Pipeline management */ /* * The pipeline traversal stack stores pads that are reached during graph * traversal, with a list of links to be visited to continue the traversal. * When a new pad is reached, an entry is pushed on the top of the stack and * points to the incoming pad and the first link of the entity. * * To find further pads in the pipeline, the traversal algorithm follows * internal pad dependencies in the entity, and then links in the graph. It * does so by iterating over all links of the entity, and following enabled * links that originate from a pad that is internally connected to the incoming * pad, as reported by the media_entity_has_pad_interdep() function. */ /** * struct media_pipeline_walk_entry - Entry in the pipeline traversal stack * * @pad: The media pad being visited * @links: Links left to be visited */ struct media_pipeline_walk_entry { struct media_pad *pad; struct list_head *links; }; /** * struct media_pipeline_walk - State used by the media pipeline traversal * algorithm * * @mdev: The media device * @stack: Depth-first search stack * @stack.size: Number of allocated entries in @stack.entries * @stack.top: Index of the top stack entry (-1 if the stack is empty) * @stack.entries: Stack entries */ struct media_pipeline_walk { struct media_device *mdev; struct { unsigned int size; int top; struct media_pipeline_walk_entry *entries; } stack; }; #define MEDIA_PIPELINE_STACK_GROW_STEP 16 static struct media_pipeline_walk_entry * media_pipeline_walk_top(struct media_pipeline_walk *walk) { return &walk->stack.entries[walk->stack.top]; } static bool media_pipeline_walk_empty(struct media_pipeline_walk *walk) { return walk->stack.top == -1; } /* Increase the stack size by MEDIA_PIPELINE_STACK_GROW_STEP elements. */ static int media_pipeline_walk_resize(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entries; unsigned int new_size; /* Safety check, to avoid stack overflows in case of bugs. */ if (walk->stack.size >= 256) return -E2BIG; new_size = walk->stack.size + MEDIA_PIPELINE_STACK_GROW_STEP; entries = krealloc(walk->stack.entries, new_size * sizeof(*walk->stack.entries), GFP_KERNEL); if (!entries) return -ENOMEM; walk->stack.entries = entries; walk->stack.size = new_size; return 0; } /* Push a new entry on the stack. */ static int media_pipeline_walk_push(struct media_pipeline_walk *walk, struct media_pad *pad) { struct media_pipeline_walk_entry *entry; int ret; if (walk->stack.top + 1 >= walk->stack.size) { ret = media_pipeline_walk_resize(walk); if (ret) return ret; } walk->stack.top++; entry = media_pipeline_walk_top(walk); entry->pad = pad; entry->links = pad->entity->links.next; dev_dbg(walk->mdev->dev, "media pipeline: pushed entry %u: '%s':%u\n", walk->stack.top, pad->entity->name, pad->index); return 0; } /* * Move the top entry link cursor to the next link. If all links of the entry * have been visited, pop the entry itself. Return true if the entry has been * popped. */ static bool media_pipeline_walk_pop(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry; if (WARN_ON(walk->stack.top < 0)) return false; entry = media_pipeline_walk_top(walk); if (entry->links->next == &entry->pad->entity->links) { dev_dbg(walk->mdev->dev, "media pipeline: entry %u has no more links, popping\n", walk->stack.top); walk->stack.top--; return true; } entry->links = entry->links->next; dev_dbg(walk->mdev->dev, "media pipeline: moved entry %u to next link\n", walk->stack.top); return false; } /* Free all memory allocated while walking the pipeline. */ static void media_pipeline_walk_destroy(struct media_pipeline_walk *walk) { kfree(walk->stack.entries); } /* Add a pad to the pipeline and push it to the stack. */ static int media_pipeline_add_pad(struct media_pipeline *pipe, struct media_pipeline_walk *walk, struct media_pad *pad) { struct media_pipeline_pad *ppad; list_for_each_entry(ppad, &pipe->pads, list) { if (ppad->pad == pad) { dev_dbg(pad->graph_obj.mdev->dev, "media pipeline: already contains pad '%s':%u\n", pad->entity->name, pad->index); return 0; } } ppad = kzalloc_obj(*ppad); if (!ppad) return -ENOMEM; ppad->pipe = pipe; ppad->pad = pad; list_add_tail(&ppad->list, &pipe->pads); dev_dbg(pad->graph_obj.mdev->dev, "media pipeline: added pad '%s':%u\n", pad->entity->name, pad->index); return media_pipeline_walk_push(walk, pad); } /* Explore the next link of the entity at the top of the stack. */ static int media_pipeline_explore_next_link(struct media_pipeline *pipe, struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry = media_pipeline_walk_top(walk); struct media_pad *origin; struct media_link *link; struct media_pad *local; struct media_pad *remote; bool last_link; int ret; origin = entry->pad; link = list_entry(entry->links, typeof(*link), list); last_link = media_pipeline_walk_pop(walk); if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (not data-link)\n"); return 0; } dev_dbg(walk->mdev->dev, "media pipeline: exploring link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); /* Get the local pad and remote pad. */ if (link->source->entity == origin->entity) { local = link->source; remote = link->sink; } else { local = link->sink; remote = link->source; } /* * Skip links that originate from a different pad than the incoming pad * that is not connected internally in the entity to the incoming pad. */ if (origin != local && !media_entity_has_pad_interdep(origin->entity, origin->index, local->index)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (no route)\n"); goto done; } /* * Add the local pad of the link to the pipeline and push it to the * stack, if not already present. */ ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; /* Similarly, add the remote pad, but only if the link is enabled. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (disabled)\n"); goto done; } ret = media_pipeline_add_pad(pipe, walk, remote); if (ret) return ret; done: /* * If we're done iterating over links, iterate over pads of the entity. * This is necessary to discover pads that are not connected with any * link. Those are dead ends from a pipeline exploration point of view, * but are still part of the pipeline and need to be added to enable * proper validation. */ if (!last_link) return 0; dev_dbg(walk->mdev->dev, "media pipeline: adding unconnected pads of '%s' reachable from pad %u\n", origin->entity->name, origin->index); media_entity_for_each_pad(origin->entity, local) { /* * Skip the origin pad (already handled), pad that have links * (already discovered through iterating over links) and pads * not internally connected. */ if (origin == local || local->num_links || !media_entity_has_pad_interdep(origin->entity, origin->index, local->index)) continue; ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; } return 0; } static void media_pipeline_cleanup(struct media_pipeline *pipe) { while (!list_empty(&pipe->pads)) { struct media_pipeline_pad *ppad; ppad = list_first_entry(&pipe->pads, typeof(*ppad), list); list_del(&ppad->list); kfree(ppad); } } static int media_pipeline_populate(struct media_pipeline *pipe, struct media_pad *pad) { struct media_pipeline_walk walk = { }; struct media_pipeline_pad *ppad; int ret; /* * Populate the media pipeline by walking the media graph, starting * from @pad. */ INIT_LIST_HEAD(&pipe->pads); pipe->mdev = pad->graph_obj.mdev; walk.mdev = pipe->mdev; walk.stack.top = -1; ret = media_pipeline_add_pad(pipe, &walk, pad); if (ret) goto done; /* * Use a depth-first search algorithm: as long as the stack is not * empty, explore the next link of the top entry. The * media_pipeline_explore_next_link() function will either move to the * next link, pop the entry if fully visited, or add new entries on * top. */ while (!media_pipeline_walk_empty(&walk)) { ret = media_pipeline_explore_next_link(pipe, &walk); if (ret) goto done; } dev_dbg(pad->graph_obj.mdev->dev, "media pipeline populated, found pads:\n"); list_for_each_entry(ppad, &pipe->pads, list) dev_dbg(pad->graph_obj.mdev->dev, "- '%s':%u\n", ppad->pad->entity->name, ppad->pad->index); WARN_ON(walk.stack.top != -1); ret = 0; done: media_pipeline_walk_destroy(&walk); if (ret) media_pipeline_cleanup(pipe); return ret; } __must_check int __media_pipeline_start(struct media_pad *origin, struct media_pipeline *pipe) { struct media_device *mdev = origin->graph_obj.mdev; struct media_pipeline_pad *err_ppad; struct media_pipeline_pad *ppad; int ret; lockdep_assert_held(&mdev->graph_mutex); /* * If the pad is already part of a pipeline, that pipeline must be the * same as the pipe given to media_pipeline_start(). */ if (WARN_ON(origin->pipe && origin->pipe != pipe)) return -EINVAL; /* * If the pipeline has already been started, it is guaranteed to be * valid, so just increase the start count. */ if (pipe->start_count) { pipe->start_count++; return 0; } /* * Populate the pipeline. This populates the media_pipeline pads list * with media_pipeline_pad instances for each pad found during graph * walk. */ ret = media_pipeline_populate(pipe, origin); if (ret) return ret; /* * Now that all the pads in the pipeline have been gathered, perform * the validation steps. */ list_for_each_entry(ppad, &pipe->pads, list) { struct media_pad *pad = ppad->pad; struct media_entity *entity = pad->entity; bool has_enabled_link = false; struct media_link *link; dev_dbg(mdev->dev, "Validating pad '%s':%u\n", pad->entity->name, pad->index); /* * 1. Ensure that the pad doesn't already belong to a different * pipeline. */ if (pad->pipe) { dev_dbg(mdev->dev, "Failed to start pipeline: pad '%s':%u busy\n", pad->entity->name, pad->index); ret = -EBUSY; goto error; } /* * 2. Validate all active links whose sink is the current pad. * Validation of the source pads is performed in the context of * the connected sink pad to avoid duplicating checks. */ for_each_media_entity_data_link(entity, link) { /* Skip links unrelated to the current pad. */ if (link->sink != pad && link->source != pad) continue; /* Record if the pad has links and enabled links. */ if (link->flags & MEDIA_LNK_FL_ENABLED) has_enabled_link = true; /* * Validate the link if it's enabled and has the * current pad as its sink. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->sink != pad) continue; if (!entity->ops || !entity->ops->link_validate) continue; ret = entity->ops->link_validate(link); if (ret) { dev_dbg(mdev->dev, "Link '%s':%u -> '%s':%u failed validation: %d\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index, ret); goto error; } dev_dbg(mdev->dev, "Link '%s':%u -> '%s':%u is valid\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); } /* * 3. If the pad has the MEDIA_PAD_FL_MUST_CONNECT flag set, * ensure that it has either no link or an enabled link. */ if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && !has_enabled_link) { dev_dbg(mdev->dev, "Pad '%s':%u must be connected by an enabled link\n", pad->entity->name, pad->index); ret = -ENOLINK; goto error; } /* Validation passed, store the pipe pointer in the pad. */ pad->pipe = pipe; } pipe->start_count++; return 0; error: /* * Link validation on graph failed. We revert what we did and * return the error. */ list_for_each_entry(err_ppad, &pipe->pads, list) { if (err_ppad == ppad) break; err_ppad->pad->pipe = NULL; } media_pipeline_cleanup(pipe); return ret; } EXPORT_SYMBOL_GPL(__media_pipeline_start); __must_check int media_pipeline_start(struct media_pad *origin, struct media_pipeline *pipe) { struct media_device *mdev = origin->graph_obj.mdev; int ret; mutex_lock(&mdev->graph_mutex); ret = __media_pipeline_start(origin, pipe); mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_pipeline_start); void __media_pipeline_stop(struct media_pad *pad) { struct media_pipeline *pipe = pad->pipe; struct media_pipeline_pad *ppad; /* * If the following check fails, the driver has performed an * unbalanced call to media_pipeline_stop() */ if (WARN_ON(!pipe)) return; if (--pipe->start_count) return; list_for_each_entry(ppad, &pipe->pads, list) ppad->pad->pipe = NULL; media_pipeline_cleanup(pipe); if (pipe->allocated) kfree(pipe); } EXPORT_SYMBOL_GPL(__media_pipeline_stop); void media_pipeline_stop(struct media_pad *pad) { struct media_device *mdev = pad->graph_obj.mdev; mutex_lock(&mdev->graph_mutex); __media_pipeline_stop(pad); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_pipeline_stop); __must_check int media_pipeline_alloc_start(struct media_pad *pad) { struct media_device *mdev = pad->graph_obj.mdev; struct media_pipeline *new_pipe = NULL; struct media_pipeline *pipe; int ret; mutex_lock(&mdev->graph_mutex); /* * Is the pad already part of a pipeline? If not, we need to allocate * a pipe. */ pipe = media_pad_pipeline(pad); if (!pipe) { new_pipe = kzalloc_obj(*new_pipe); if (!new_pipe) { ret = -ENOMEM; goto out; } pipe = new_pipe; pipe->allocated = true; } ret = __media_pipeline_start(pad, pipe); if (ret) kfree(new_pipe); out: mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_pipeline_alloc_start); struct media_pad * __media_pipeline_pad_iter_next(struct media_pipeline *pipe, struct media_pipeline_pad_iter *iter, struct media_pad *pad) { if (!pad) iter->cursor = pipe->pads.next; if (iter->cursor == &pipe->pads) return NULL; pad = list_entry(iter->cursor, struct media_pipeline_pad, list)->pad; iter->cursor = iter->cursor->next; return pad; } EXPORT_SYMBOL_GPL(__media_pipeline_pad_iter_next); int media_pipeline_entity_iter_init(struct media_pipeline *pipe, struct media_pipeline_entity_iter *iter) { return media_entity_enum_init(&iter->ent_enum, pipe->mdev); } EXPORT_SYMBOL_GPL(media_pipeline_entity_iter_init); void media_pipeline_entity_iter_cleanup(struct media_pipeline_entity_iter *iter) { media_entity_enum_cleanup(&iter->ent_enum); } EXPORT_SYMBOL_GPL(media_pipeline_entity_iter_cleanup); struct media_entity * __media_pipeline_entity_iter_next(struct media_pipeline *pipe, struct media_pipeline_entity_iter *iter, struct media_entity *entity) { if (!entity) iter->cursor = pipe->pads.next; while (iter->cursor != &pipe->pads) { struct media_pipeline_pad *ppad; struct media_entity *entity; ppad = list_entry(iter->cursor, struct media_pipeline_pad, list); entity = ppad->pad->entity; iter->cursor = iter->cursor->next; if (!media_entity_enum_test_and_set(&iter->ent_enum, entity)) return entity; } return NULL; } EXPORT_SYMBOL_GPL(__media_pipeline_entity_iter_next); /* ----------------------------------------------------------------------------- * Links management */ static struct media_link *media_add_link(struct list_head *head) { struct media_link *link; link = kzalloc_obj(*link); if (link == NULL) return NULL; list_add_tail(&link->list, head); return link; } static void __media_entity_remove_link(struct media_entity *entity, struct media_link *link) { struct media_link *rlink, *tmp; struct media_entity *remote; /* Remove the reverse links for a data link. */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == MEDIA_LNK_FL_DATA_LINK) { link->source->num_links--; link->sink->num_links--; if (link->source->entity == entity) remote = link->sink->entity; else remote = link->source->entity; list_for_each_entry_safe(rlink, tmp, &remote->links, list) { if (rlink != link->reverse) continue; if (link->source->entity == entity) remote->num_backlinks--; /* Remove the remote link */ list_del(&rlink->list); media_gobj_destroy(&rlink->graph_obj); kfree(rlink); if (--remote->num_links == 0) break; } } list_del(&link->list); media_gobj_destroy(&link->graph_obj); kfree(link); } int media_get_pad_index(struct media_entity *entity, u32 pad_type, enum media_pad_signal_type sig_type) { unsigned int i; if (!entity) return -EINVAL; for (i = 0; i < entity->num_pads; i++) { if ((entity->pads[i].flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) != pad_type) continue; if (entity->pads[i].sig_type == sig_type) return i; } return -EINVAL; } EXPORT_SYMBOL_GPL(media_get_pad_index); int media_create_pad_link(struct media_entity *source, u16 source_pad, struct media_entity *sink, u16 sink_pad, u32 flags) { struct media_link *link; struct media_link *backlink; if (flags & MEDIA_LNK_FL_LINK_TYPE) return -EINVAL; flags |= MEDIA_LNK_FL_DATA_LINK; if (WARN_ON(!source || !sink) || WARN_ON(source_pad >= source->num_pads) || WARN_ON(sink_pad >= sink->num_pads)) return -EINVAL; if (WARN_ON(!(source->pads[source_pad].flags & MEDIA_PAD_FL_SOURCE))) return -EINVAL; if (WARN_ON(!(sink->pads[sink_pad].flags & MEDIA_PAD_FL_SINK))) return -EINVAL; link = media_add_link(&source->links); if (link == NULL) return -ENOMEM; link->source = &source->pads[source_pad]; link->sink = &sink->pads[sink_pad]; link->flags = flags; /* Initialize graph object embedded at the new link */ media_gobj_create(source->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); /* Create the backlink. Backlinks are used to help graph traversal and * are not reported to userspace. */ backlink = media_add_link(&sink->links); if (backlink == NULL) { __media_entity_remove_link(source, link); return -ENOMEM; } backlink->source = &source->pads[source_pad]; backlink->sink = &sink->pads[sink_pad]; backlink->flags = flags; backlink->is_backlink = true; /* Initialize graph object embedded at the new link */ media_gobj_create(sink->graph_obj.mdev, MEDIA_GRAPH_LINK, &backlink->graph_obj); link->reverse = backlink; backlink->reverse = link; sink->num_backlinks++; sink->num_links++; source->num_links++; link->source->num_links++; link->sink->num_links++; return 0; } EXPORT_SYMBOL_GPL(media_create_pad_link); int media_create_pad_links(const struct media_device *mdev, const u32 source_function, struct media_entity *source, const u16 source_pad, const u32 sink_function, struct media_entity *sink, const u16 sink_pad, u32 flags, const bool allow_both_undefined) { struct media_entity *entity; unsigned function; int ret; /* Trivial case: 1:1 relation */ if (source && sink) return media_create_pad_link(source, source_pad, sink, sink_pad, flags); /* Worse case scenario: n:n relation */ if (!source && !sink) { if (!allow_both_undefined) return 0; media_device_for_each_entity(source, mdev) { if (source->function != source_function) continue; media_device_for_each_entity(sink, mdev) { if (sink->function != sink_function) continue; ret = media_create_pad_link(source, source_pad, sink, sink_pad, flags); if (ret) return ret; flags &= ~(MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); } } return 0; } /* Handle 1:n and n:1 cases */ if (source) function = sink_function; else function = source_function; media_device_for_each_entity(entity, mdev) { if (entity->function != function) continue; if (source) ret = media_create_pad_link(source, source_pad, entity, sink_pad, flags); else ret = media_create_pad_link(entity, source_pad, sink, sink_pad, flags); if (ret) return ret; flags &= ~(MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); } return 0; } EXPORT_SYMBOL_GPL(media_create_pad_links); void __media_entity_remove_links(struct media_entity *entity) { struct media_link *link, *tmp; list_for_each_entry_safe(link, tmp, &entity->links, list) __media_entity_remove_link(entity, link); entity->num_links = 0; entity->num_backlinks = 0; } EXPORT_SYMBOL_GPL(__media_entity_remove_links); void media_entity_remove_links(struct media_entity *entity) { struct media_device *mdev = entity->graph_obj.mdev; /* Do nothing if the entity is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_entity_remove_links(entity); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_entity_remove_links); static int __media_entity_setup_link_notify(struct media_link *link, u32 flags) { int ret; /* Notify both entities. */ ret = media_entity_call(link->source->entity, link_setup, link->source, link->sink, flags); if (ret < 0 && ret != -ENOIOCTLCMD) return ret; ret = media_entity_call(link->sink->entity, link_setup, link->sink, link->source, flags); if (ret < 0 && ret != -ENOIOCTLCMD) { media_entity_call(link->source->entity, link_setup, link->source, link->sink, link->flags); return ret; } link->flags = flags; link->reverse->flags = link->flags; return 0; } int __media_entity_setup_link(struct media_link *link, u32 flags) { const u32 mask = MEDIA_LNK_FL_ENABLED; struct media_device *mdev; struct media_pad *source, *sink; int ret = -EBUSY; if (link == NULL) return -EINVAL; /* The non-modifiable link flags must not be modified. */ if ((link->flags & ~mask) != (flags & ~mask)) return -EINVAL; if (link->flags & MEDIA_LNK_FL_IMMUTABLE) return link->flags == flags ? 0 : -EINVAL; if (link->flags == flags) return 0; source = link->source; sink = link->sink; if (!(link->flags & MEDIA_LNK_FL_DYNAMIC) && (media_pad_is_streaming(source) || media_pad_is_streaming(sink))) return -EBUSY; mdev = source->graph_obj.mdev; if (mdev->ops && mdev->ops->link_notify) { ret = mdev->ops->link_notify(link, flags, MEDIA_DEV_NOTIFY_PRE_LINK_CH); if (ret < 0) return ret; } ret = __media_entity_setup_link_notify(link, flags); if (mdev->ops && mdev->ops->link_notify) mdev->ops->link_notify(link, flags, MEDIA_DEV_NOTIFY_POST_LINK_CH); return ret; } EXPORT_SYMBOL_GPL(__media_entity_setup_link); int media_entity_setup_link(struct media_link *link, u32 flags) { int ret; mutex_lock(&link->graph_obj.mdev->graph_mutex); ret = __media_entity_setup_link(link, flags); mutex_unlock(&link->graph_obj.mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_entity_setup_link); struct media_link * media_entity_find_link(struct media_pad *source, struct media_pad *sink) { struct media_link *link; for_each_media_entity_data_link(source->entity, link) { if (link->source->entity == source->entity && link->source->index == source->index && link->sink->entity == sink->entity && link->sink->index == sink->index) return link; } return NULL; } EXPORT_SYMBOL_GPL(media_entity_find_link); struct media_pad *media_pad_remote_pad_first(const struct media_pad *pad) { struct media_link *link; for_each_media_entity_data_link(pad->entity, link) { if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->source == pad) return link->sink; if (link->sink == pad) return link->source; } return NULL; } EXPORT_SYMBOL_GPL(media_pad_remote_pad_first); struct media_pad * media_entity_remote_pad_unique(const struct media_entity *entity, unsigned int type) { struct media_pad *pad = NULL; struct media_link *link; list_for_each_entry(link, &entity->links, list) { struct media_pad *local_pad; struct media_pad *remote_pad; if (((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) || !(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (type == MEDIA_PAD_FL_SOURCE) { local_pad = link->sink; remote_pad = link->source; } else { local_pad = link->source; remote_pad = link->sink; } if (local_pad->entity == entity) { if (pad) return ERR_PTR(-ENOTUNIQ); pad = remote_pad; } } if (!pad) return ERR_PTR(-ENOLINK); return pad; } EXPORT_SYMBOL_GPL(media_entity_remote_pad_unique); struct media_pad *media_pad_remote_pad_unique(const struct media_pad *pad) { struct media_pad *found_pad = NULL; struct media_link *link; list_for_each_entry(link, &pad->entity->links, list) { struct media_pad *remote_pad; if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->sink == pad) remote_pad = link->source; else if (link->source == pad) remote_pad = link->sink; else continue; if (found_pad) return ERR_PTR(-ENOTUNIQ); found_pad = remote_pad; } if (!found_pad) return ERR_PTR(-ENOLINK); return found_pad; } EXPORT_SYMBOL_GPL(media_pad_remote_pad_unique); int media_entity_get_fwnode_pad(struct media_entity *entity, const struct fwnode_handle *fwnode, unsigned long direction_flags) { struct fwnode_endpoint endpoint; unsigned int i; int ret; if (!entity->ops || !entity->ops->get_fwnode_pad) { for (i = 0; i < entity->num_pads; i++) { if (entity->pads[i].flags & direction_flags) return i; } return -ENXIO; } ret = fwnode_graph_parse_endpoint(fwnode, &endpoint); if (ret) return ret; ret = entity->ops->get_fwnode_pad(entity, &endpoint); if (ret < 0) return ret; if (ret >= entity->num_pads) return -ENXIO; if (!(entity->pads[ret].flags & direction_flags)) return -ENXIO; return ret; } EXPORT_SYMBOL_GPL(media_entity_get_fwnode_pad); struct media_pipeline *media_entity_pipeline(struct media_entity *entity) { struct media_pad *pad; media_entity_for_each_pad(entity, pad) { if (pad->pipe) return pad->pipe; } return NULL; } EXPORT_SYMBOL_GPL(media_entity_pipeline); struct media_pipeline *media_pad_pipeline(struct media_pad *pad) { return pad->pipe; } EXPORT_SYMBOL_GPL(media_pad_pipeline); static void media_interface_init(struct media_device *mdev, struct media_interface *intf, u32 gobj_type, u32 intf_type, u32 flags) { intf->type = intf_type; intf->flags = flags; INIT_LIST_HEAD(&intf->links); media_gobj_create(mdev, gobj_type, &intf->graph_obj); } /* Functions related to the media interface via device nodes */ struct media_intf_devnode *media_devnode_create(struct media_device *mdev, u32 type, u32 flags, u32 major, u32 minor) { struct media_intf_devnode *devnode; devnode = kzalloc_obj(*devnode); if (!devnode) return NULL; devnode->major = major; devnode->minor = minor; media_interface_init(mdev, &devnode->intf, MEDIA_GRAPH_INTF_DEVNODE, type, flags); return devnode; } EXPORT_SYMBOL_GPL(media_devnode_create); void media_devnode_remove(struct media_intf_devnode *devnode) { media_remove_intf_links(&devnode->intf); media_gobj_destroy(&devnode->intf.graph_obj); kfree(devnode); } EXPORT_SYMBOL_GPL(media_devnode_remove); struct media_link *media_create_intf_link(struct media_entity *entity, struct media_interface *intf, u32 flags) { struct media_link *link; link = media_add_link(&intf->links); if (link == NULL) return NULL; link->intf = intf; link->entity = entity; link->flags = flags | MEDIA_LNK_FL_INTERFACE_LINK; /* Initialize graph object embedded at the new link */ media_gobj_create(intf->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); return link; } EXPORT_SYMBOL_GPL(media_create_intf_link); void __media_remove_intf_link(struct media_link *link) { list_del(&link->list); media_gobj_destroy(&link->graph_obj); kfree(link); } EXPORT_SYMBOL_GPL(__media_remove_intf_link); void media_remove_intf_link(struct media_link *link) { struct media_device *mdev = link->graph_obj.mdev; /* Do nothing if the intf is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_remove_intf_link(link); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_remove_intf_link); void __media_remove_intf_links(struct media_interface *intf) { struct media_link *link, *tmp; list_for_each_entry_safe(link, tmp, &intf->links, list) __media_remove_intf_link(link); } EXPORT_SYMBOL_GPL(__media_remove_intf_links); void media_remove_intf_links(struct media_interface *intf) { struct media_device *mdev = intf->graph_obj.mdev; /* Do nothing if the intf is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_remove_intf_links(intf); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_remove_intf_links); struct media_link *media_create_ancillary_link(struct media_entity *primary, struct media_entity *ancillary) { struct media_link *link; link = media_add_link(&primary->links); if (!link) return ERR_PTR(-ENOMEM); link->gobj0 = &primary->graph_obj; link->gobj1 = &ancillary->graph_obj; link->flags = MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_ANCILLARY_LINK; /* Initialize graph object embedded in the new link */ media_gobj_create(primary->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); return link; } EXPORT_SYMBOL_GPL(media_create_ancillary_link); struct media_link *__media_entity_next_link(struct media_entity *entity, struct media_link *link, unsigned long link_type) { link = link ? list_next_entry(link, list) : list_first_entry(&entity->links, typeof(*link), list); list_for_each_entry_from(link, &entity->links, list) if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == link_type) return link; return NULL; } EXPORT_SYMBOL_GPL(__media_entity_next_link); |
| 4 4 4 4 5 4 4 4 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 | /* * Copyright (c) 2006 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/percpu.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/export.h> #include "rds.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); EXPORT_PER_CPU_SYMBOL_GPL(rds_stats); /* :.,$s/unsigned long\>.*\<s_\(.*\);/"\1",/g */ static const char *const rds_stat_names[] = { "conn_reset", "recv_drop_bad_checksum", "recv_drop_old_seq", "recv_drop_no_sock", "recv_drop_dead_sock", "recv_deliver_raced", "recv_delivered", "recv_queued", "recv_immediate_retry", "recv_delayed_retry", "recv_ack_required", "recv_rdma_bytes", "recv_ping", "send_queue_empty", "send_queue_full", "send_lock_contention", "send_lock_queue_raced", "send_immediate_retry", "send_delayed_retry", "send_drop_acked", "send_ack_required", "send_queued", "send_rdma", "send_rdma_bytes", "send_pong", "page_remainder_hit", "page_remainder_miss", "copy_to_user", "copy_from_user", "cong_update_queued", "cong_update_received", "cong_send_error", "cong_send_blocked", "recv_bytes_added_to_sock", "recv_bytes_freed_fromsock", "send_stuck_rm", "mprds_catchup_tx0_retries", }; void rds_stats_info_copy(struct rds_info_iterator *iter, uint64_t *values, const char *const *names, size_t nr) { struct rds_info_counter ctr; size_t i; for (i = 0; i < nr; i++) { BUG_ON(strlen(names[i]) >= sizeof(ctr.name)); strscpy_pad(ctr.name, names[i]); ctr.value = values[i]; rds_info_copy(iter, &ctr, sizeof(ctr)); } } EXPORT_SYMBOL_GPL(rds_stats_info_copy); /* * This gives global counters across all the transports. The strings * are copied in so that the tool doesn't need knowledge of the specific * stats that we're exporting. Some are pretty implementation dependent * and may change over time. That doesn't stop them from being useful. * * This is the only function in the chain that knows about the byte granular * length in userspace. It converts it to number of stat entries that the * rest of the functions operate in. */ static void rds_stats_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds_statistics stats = {0, }; uint64_t *src; uint64_t *sum; size_t i; int cpu; unsigned int avail; avail = len / sizeof(struct rds_info_counter); if (avail < ARRAY_SIZE(rds_stat_names)) { avail = 0; goto trans; } for_each_online_cpu(cpu) { src = (uint64_t *)&(per_cpu(rds_stats, cpu)); sum = (uint64_t *)&stats; for (i = 0; i < sizeof(stats) / sizeof(uint64_t); i++) *(sum++) += *(src++); } rds_stats_info_copy(iter, (uint64_t *)&stats, rds_stat_names, ARRAY_SIZE(rds_stat_names)); avail -= ARRAY_SIZE(rds_stat_names); trans: lens->each = sizeof(struct rds_info_counter); lens->nr = rds_trans_stats_info_copy(iter, avail) + ARRAY_SIZE(rds_stat_names); } void rds_stats_exit(void) { rds_info_deregister_func(RDS_INFO_COUNTERS, rds_stats_info); } int rds_stats_init(void) { rds_info_register_func(RDS_INFO_COUNTERS, rds_stats_info); return 0; } |
| 12 11 12 11 11 11 11 11 11 11 244 24 24 1623 1620 1621 70 15 45 45 39 1696 1696 36 36 1701 3 1 1 5 4 3 2 2 1 2 1 6 14 40 20 8 1 8 14 14 14 14 14 14 14 14 114 96 96 57 11 1584 1584 1577 31 1583 70 69 70 46 70 70 20 20 20 20 70 12 70 40 1 70 177 23 23 20 20 20 20 20 14 14 14 14 12 14 12 14 14 14 9 14 14 14 14 11 11 11 11 6 6 21 21 10 21 21 10 21 21 21 21 21 18 21 7 7 6 20 20 20 42 42 42 21 13 13 42 205 203 205 194 24 204 205 23 3 2 2 3 10 10 10 6 10 27 27 27 9 24 6 18 7 1620 1622 1614 1622 1602 15 14 1600 1584 1575 1601 1517 4 1 1 1514 1511 9 1605 1618 8 1617 1 1619 168 169 168 28 142 169 169 175 7 7 5 5 177 177 11 11 11 11 11 11 11 11 11 22 11 11 11 11 76 75 76 76 76 4 4 177 21 20 164 160 160 177 173 177 176 177 177 177 177 21 177 176 2 177 21 177 21 177 177 177 177 177 72 175 177 177 177 61 61 61 2 61 177 11 11 6 4 5 4 11 8 7 7 7 2 7 8 185 31 31 24 23 24 31 16 2 2 14 2 12 9 9 33 2 34 29 31 31 2 34 34 38 4 41 34 1518 1521 34 2 14 36 30 45 45 33 33 45 44 34 22 38 36 36 36 36 36 36 15 36 36 35 25 23 17 23 22 1 22 11 12 3 3 3 9 22 22 22 1 22 5 22 5 22 22 22 22 23 23 11 11 23 28 27 27 12 16 15 202 84 21 192 192 192 179 175 23 23 22 22 21 191 205 22 203 205 202 205 196 34 33 30 194 194 193 192 8 176 177 2 1 13 12 11 185 192 205 203 203 202 207 204 207 2 47 46 2 2 50 47 45 45 11 11 39 35 36 30 30 3 3 1 2 6 4 3 3 2 4 12 14 4 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/signal.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/rbtree.h> #include <linux/wait.h> #include <linux/eventpoll.h> #include <linux/mount.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> #include <linux/capability.h> #include <linux/seqlock.h> #include <net/busy_poll.h> /* * fs/eventpoll.c - Efficient event polling ("epoll") kernel implementation. * * * Overview * -------- * * Each epoll_create(2) returns an anonymous [eventpoll] file whose * ->private_data is a struct eventpoll. Each EPOLL_CTL_ADD installs * a struct epitem linking one (watched file, fd) pair back to that * eventpoll via the watched file's f_op->poll() wait queue(s). When * the watched file signals readiness, ep_poll_callback() fires and * marks the epitem ready. epoll_wait(2) drains the ready list under * ep->mtx, re-queueing items in level-triggered mode. * * epoll instances can watch other epoll instances up to EP_MAX_NESTS * deep; cycles are forbidden and detected at EPOLL_CTL_ADD time. * * * Locking * ------- * * Three levels, acquired from outer to inner: * * epnested_mutex (global; rare; taken only for EPOLL_CTL_ADD * loop / path checks) * > ep->mtx (per-eventpoll; sleepable; serializes most ops) * > ep->lock (per-eventpoll; IRQ-safe spinlock) * * file->f_lock (per-file; NOT IRQ-safe; guards f_ep hlist ops; * nested inside ep->mtx, outside ep->lock) * * Rationale: * - ep->lock is a spinlock because ep_poll_callback() is called from * wake_up() which may run in hard-IRQ context. All ep->lock * critical sections use spin_lock_irqsave(). * - ep->mtx is a sleepable mutex because the event delivery loop * calls copy_to_user(), and ep_insert() may sleep in * kmem_cache_alloc() and f_op->poll(). * - epnested_mutex is global because cycle detection needs a global * view of the epoll topology; a per-object scheme would let two * concurrent inserts (A into B, B into A) construct a cycle * without either observer seeing it. * - Per-ep ep->mtx is preferred for scalability elsewhere. Events * that require epnested_mutex are rare. * * When EPOLL_CTL_ADD nests one eventpoll inside another we acquire * ep->mtx on both: outer first, target second. Since cycles are * forbidden the set of live ep->mtx holds is always a strict chain, * communicated to lockdep via mutex_lock_nested() subclasses derived * from the current recursion depth. * * * Field protection * ---------------- * * struct eventpoll: * mtx - self * rbr - ep->mtx * ovflist, rdllist - ep->lock (IRQ-safe) * wq - ep->lock for queue mutation * poll_wait - internal waitqueue spinlock * refs - file->f_lock for adds; ep->mtx for removes; * RCU for readers (hlist_del_rcu + kfree_rcu(ep)) * ws - ep->mtx * gen, loop_check_depth - epnested_mutex * file, user - immutable after setup * refcount - atomic (refcount_t) * napi_* - READ_ONCE / WRITE_ONCE * * struct epitem: * rbn / rcu union - rbn: ep->mtx (while epi is linked in ep->rbr). * rcu: written only by kfree_rcu(epi) on the free * path; otherwise untouched by epoll code. * rdllink, next - ep->lock * ffd, ep - immutable after ep_insert() * pwqlist - ep->mtx for writes; POLLFREE clears pwq->whead * via smp_store_release(), see below * fllink - file->f_lock for mutation; hlist_del_rcu + * kfree_rcu(epi) for safe RCU readers * ws - RCU (rcu_assign_pointer / * rcu_dereference_check(mtx)) * event - ep->mtx for writes; lockless read in * ep_poll_callback pairs with smp_mb() in * ep_modify() * * * Ready-list state machine * ------------------------ * * Readiness is tracked in two lists under ep->lock: * * rdllist - doubly-linked FIFO; the "current" ready list. * ovflist - singly-linked LIFO; used during a scan to catch * events that arrive while rdllist is being iterated * without ep->lock. * * Encoded in ep->ovflist: * EP_UNACTIVE_PTR - no scan active; callback appends to rdllist. * NULL - scan active, no spill yet. * pointer to epi - scan active with spilled items (LIFO). * * Encoded in epi->ovflist_next: * EP_UNACTIVE_PTR - epi is not on ovflist. * otherwise - next epi on ovflist (NULL at tail). * * ep_start_scan() flips "not scanning" to "scanning" and splices * rdllist into a caller-local scan_batch. ep_done_scan() drains ovflist * back to rdllist (list_add head-insert reverses LIFO to FIFO), * flips back to "not scanning", and re-splices any items the caller * left in scan_batch (e.g., level-triggered re-queues). * * * Removal paths * ------------- * * Three paths dispose of epitems and/or eventpolls: * * A. ep_remove() - EPOLL_CTL_DEL and ep_insert() * rollback. Caller holds ep->mtx. * B. ep_clear_and_put() - close of the epoll fd itself * (ep_eventpoll_release). * C. eventpoll_release_file() - close of a watched file, invoked * from __fput(). * * Coordination: * A and C exclude each other via the watched file's refcount. * A pins the file with epi_fget() before touching file->f_ep or * file->f_lock; if the pin fails, __fput() is in flight and C * will clean this epi up. See the epi_fget() block comment. * A and B both hold ep->mtx serially. B walks the rbtree with * rb_next() captured before ep_remove() erases the current node. * B and C both take ep->mtx; the loser sees fewer entries or an * empty file->f_ep. * * Within every path the internal order is strict: * ep_unregister_pollwait() - drain pwqlist; synchronizes with any * in-flight ep_poll_callback via the * watched wait-queue head's lock. * ep_remove_file() - hlist_del_rcu of epi->fllink and, * if last watcher, clear file->f_ep, * under file->f_lock. * ep_remove_epi() - rb_erase, rdllist unlink (ep->lock), * wakeup_source_unregister, * kfree_rcu(epi). * * kfree_rcu(epi) defers the free past RCU readers in * reverse_path_check_proc(); kfree_rcu(ep) defers past readers in * ep_get_upwards_depth_proc(). * * * POLLFREE handshake * ------------------ * * When a subsystem tears down a wait-queue head that an epitem is * registered on (binder, signalfd, ...), it wakes the callback with * POLLFREE and must RCU-defer the head's free. The store/load pair: * * ep_poll_callback() POLLFREE branch: * smp_store_release(&pwq->whead, NULL) * * ep_remove_wait_queue(): * smp_load_acquire(&pwq->whead) * * See those sites for the full argument. */ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry)) /* Wait structure used by the poll hooks */ struct eppoll_entry { /* List header used to link this structure to the "struct epitem" */ struct eppoll_entry *next; /* The "base" pointer is set to the container "struct epitem" */ struct epitem *base; /* * Wait queue item that will be linked to the target file wait * queue head. */ wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; }; /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. * Avoid increasing the size of this struct, there can be many thousands * of these on a server and we do not want this to take another cache line. */ struct epitem { union { /* RB tree node links this structure to the eventpoll RB tree */ struct rb_node rbn; /* Used to free the struct epitem */ struct rcu_head rcu; }; /* Link on the owning eventpoll's ready list (ep->rdllist). */ struct list_head rdllink; /* * Link on the owning eventpoll's scan-overflow list (ep->ovflist), * EP_UNACTIVE_PTR when not linked. See epi_on_ovflist() / * epi_clear_ovflist() and the "Ready-list state machine" section * in the top-of-file banner. */ struct epitem *ovflist_next; /* The file descriptor information this item refers to */ struct epoll_key ffd; /* List containing poll wait queues */ struct eppoll_entry *pwqlist; /* The "container" of this item */ struct eventpoll *ep; /* List header used to link this item to the "struct file" items list */ struct hlist_node fllink; /* wakeup_source used when EPOLLWAKEUP is set */ struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; /* * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. */ struct eventpoll { /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event * collection loop, the file cleanup path, the epoll file exit * code and the ctl operations. */ struct mutex mtx; /* Wait queue used by sys_epoll_wait() */ wait_queue_head_t wq; /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; /* List of ready file descriptors */ struct list_head rdllist; /* Lock which protects rdllist and ovflist */ spinlock_t lock; /* Protect switching between rdllist and ovflist */ seqcount_spinlock_t seq; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out * holding ->lock. */ struct epitem *ovflist; /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ struct user_struct *user; struct file *file; /* used to optimize loop detection check */ u64 gen; struct hlist_head refs; u8 loop_check_depth; /* usage count, orchestrates "struct eventpoll" disposal */ refcount_t refcount; /* used to defer freeing past ep_get_upwards_depth_proc() RCU walk */ struct rcu_head rcu; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; /* busy poll timeout */ u32 busy_poll_usecs; /* busy poll packet budget */ u16 busy_poll_budget; bool prefer_busy_poll; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC /* tracks wakeup nests for lockdep validation */ u8 nests; #endif }; /* Wrapper struct used by poll queueing */ struct ep_pqueue { poll_table pt; struct epitem *epi; }; /* * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; /* * Cycle and path-length checks at EPOLL_CTL_ADD * --------------------------------------------- * * When EPOLL_CTL_ADD creates a link that either targets an eventpoll * file or extends an existing chain of eventpolls, two checks run: * * 1. no cycle is being formed -- ep_loop_check() walks downward * from the candidate target, and ep_get_upwards_depth_proc() * walks upward from the outer ep, both bounded by EP_MAX_NESTS. * 2. no file accumulates more than path_limits[depth] wakeup paths * of a given length -- reverse_path_check(). * * Both need a global view of the epoll topology and must be atomic * with the insertion, so the check is serialized by epnested_mutex * and carries its scratch state on a stack-allocated struct * ep_ctl_ctx scoped to one do_epoll_ctl() call. Non-nested inserts * skip this machinery entirely and take only ep->mtx. * * epnested_mutex Serializes the whole check. * loop_check_gen Global monotonic stamp, bumped at the start of * a check and again at the end. ep->gen caches * the value under which ep was last visited by * ep_loop_check_proc() or * ep_get_upwards_depth_proc(); the post-check * bump ensures those cached stamps can no longer * equal loop_check_gen, so the * "ep->gen == loop_check_gen" trigger in * ep_ctl_lock() only fires while another check * is in flight. * * struct ep_ctl_ctx carries the rest (inserting_into, tfile_check_list, * path_count[]) through the walk; see its declaration below. * * Commits fdcfce93073d ("eventpoll: Fix integer overflow in * ep_loop_check_proc()") and f2e467a48287 ("eventpoll: Fix * semi-unbounded recursion") hardened the walk; any refactor must * preserve both bail-outs. */ static DEFINE_MUTEX(epnested_mutex); static u64 loop_check_gen = 0; #define PATH_ARR_SIZE 5 /* * Per-do_epoll_ctl() scratch for the loop / path checks. Allocated on * the caller's stack; populated by ep_ctl_lock() and the downward * walk; consumed by reverse_path_check(); released by ep_ctl_unlock(). * Only valid while the caller holds epnested_mutex. */ struct ep_ctl_ctx { /* * Outer eventpoll for one ep_loop_check(); if the downward walk * reaches it the insert would form a cycle. */ struct eventpoll *inserting_into; /* * Singly-linked list of epitems_head objects collected during * ep_loop_check_proc(), then walked by reverse_path_check(). * Terminated by EP_UNACTIVE_PTR, not NULL: epitems_head->next * doubles as a membership flag (a NULL ->next means "not on this * list", see ep_remove_file()), so the list uses a non-NULL * sentinel to keep the tail head distinguishable from an unlisted * one. */ struct epitems_head *tfile_check_list; /* * Per-depth wakeup-path tally used by reverse_path_check_proc(); * reinitialized to zero at the start of each reverse_path_check() * iteration. */ int path_count[PATH_ARR_SIZE]; }; /* Slab cache used to allocate "struct epitem" */ static struct kmem_cache *epi_cache __ro_after_init; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __ro_after_init; /* * Wrapper anchor for file->f_ep when the watched file is not itself an * eventpoll; for the epoll-watches-epoll case, file->f_ep points at * &watched_ep->refs directly. The ->next field threads * ctx->tfile_check_list during one EPOLL_CTL_ADD path check. */ struct epitems_head { struct hlist_head epitems; struct epitems_head *next; }; static struct kmem_cache *ephead_cache __ro_after_init; static inline void free_ephead(struct epitems_head *head) { if (head) kmem_cache_free(ephead_cache, head); } static void list_file(struct file *file, struct ep_ctl_ctx *ctx) { struct epitems_head *head; head = container_of(file->f_ep, struct epitems_head, epitems); if (!head->next) { head->next = ctx->tfile_check_list; ctx->tfile_check_list = head; } } static void unlist_file(struct epitems_head *head) { struct epitems_head *to_free = head; struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems)); if (p) { struct epitem *epi= container_of(p, struct epitem, fllink); spin_lock(&epi->ffd.file->f_lock); if (!hlist_empty(&head->epitems)) to_free = NULL; head->next = NULL; spin_unlock(&epi->ffd.file->f_lock); } free_ephead(to_free); } #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long long_zero; static long long_max = LONG_MAX; static const struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &long_zero, .extra2 = &long_max, }, }; static void __init epoll_sysctls_init(void) { register_sysctl("fs/epoll", epoll_table); } #else #define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; bool is_file_epoll(struct file *f) { return f->f_op == &eventpoll_fops; } /* Compare RB tree keys */ static inline int ep_cmp_ffd(struct epoll_key *p1, struct epoll_key *p2) { return (p1->file > p2->file ? +1: (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } /* True iff @epi is on its owning ep's ready list. */ static inline bool ep_is_linked(struct epitem *epi) { return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } /* * Ready-list / ovflist state (see "Ready-list state machine" in the * top-of-file banner for the full state machine). EP_UNACTIVE_PTR is * the sentinel; these wrappers name each transition and each test so * call sites do not need to know the sentinel's value. */ /* True iff @ep is between ep_enter_scan() and ep_exit_scan(). */ static inline bool ep_is_scanning(struct eventpoll *ep) { return READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } /* Called by ep_start_scan(): divert ep_poll_callback() to ovflist. */ static inline void ep_enter_scan(struct eventpoll *ep) { WRITE_ONCE(ep->ovflist, NULL); } /* Called by ep_done_scan(): redirect ep_poll_callback() back to rdllist. */ static inline void ep_exit_scan(struct eventpoll *ep) { WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); } /* True iff @epi is currently linked on its ep's ovflist. */ static inline bool epi_on_ovflist(const struct epitem *epi) { return epi->ovflist_next != EP_UNACTIVE_PTR; } /* Mark @epi as not on any ovflist (init and post-drain). */ static inline void epi_clear_ovflist(struct epitem *epi) { epi->ovflist_next = EP_UNACTIVE_PTR; } /* True iff @ep has ready events that epoll_wait() might harvest. */ static inline bool ep_events_available(struct eventpoll *ep) { unsigned int seq = read_seqcount_begin(&ep->seq); return !list_empty_careful(&ep->rdllist) || ep_is_scanning(ep) || read_seqcount_retry(&ep->seq, seq); } #ifdef CONFIG_NET_RX_BUSY_POLL /** * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value * from the epoll instance ep is preferred, but if it is not set fallback to * the system-wide global via busy_loop_timeout. * * @start_time: The start time used to compute the remaining time until timeout. * @ep: Pointer to the eventpoll context. * * Return: true if the timeout has expired, false otherwise. */ static bool busy_loop_ep_timeout(unsigned long start_time, struct eventpoll *ep) { unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } else { return busy_loop_timeout(start_time); } } static bool ep_busy_loop_on(struct eventpoll *ep) { return !!READ_ONCE(ep->busy_poll_usecs) || READ_ONCE(ep->prefer_busy_poll) || net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep = p; return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep); } /* * Busy poll if globally on and supporting sockets found && no events, * busy loop will return if need_resched or ep_events_available. * * we must do our busy polling with irqs enabled */ static bool ep_busy_loop(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); u16 budget = READ_ONCE(ep->busy_poll_budget); bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (!budget) budget = BUSY_POLL_BUDGET; if (napi_id_valid(napi_id) && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, ep_busy_loop_end, ep, prefer_busy_poll, budget); if (ep_events_available(ep)) return true; /* * Busy poll timed out. Drop NAPI ID for now, we can add * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ if (prefer_busy_poll) napi_resume_irqs(napi_id); ep->napi_id = 0; return false; } return false; } /* * Set epoll busy poll NAPI ID from sk. */ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { struct eventpoll *ep = epi->ep; unsigned int napi_id; struct socket *sock; struct sock *sk; if (!ep_busy_loop_on(ep)) return; sock = sock_from_file(epi->ffd.file); if (!sock) return; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); /* Non-NAPI IDs can be rejected * or * Nothing to do if we already have this ID */ if (!napi_id_valid(napi_id) || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ ep->napi_id = napi_id; } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct eventpoll *ep = file->private_data; void __user *uarg = (void __user *)arg; struct epoll_params epoll_params; switch (cmd) { case EPIOCSPARAMS: if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) return -EFAULT; /* pad byte must be zero */ if (epoll_params.__pad) return -EINVAL; if (epoll_params.busy_poll_usecs > S32_MAX) return -EINVAL; if (epoll_params.prefer_busy_poll > 1) return -EINVAL; if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT && !capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs); WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget); WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll); return 0; case EPIOCGPARAMS: memset(&epoll_params, 0, sizeof(epoll_params)); epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs); epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget); epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) return -EFAULT; return 0; default: return -ENOIOCTLCMD; } } static void ep_suspend_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_suspend_irqs(napi_id); } static void ep_resume_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_resume_irqs(napi_id); } #else static inline bool ep_busy_loop(struct eventpoll *ep) { return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } static void ep_suspend_napi_irqs(struct eventpoll *ep) { } static void ep_resume_napi_irqs(struct eventpoll *ep) { } #endif /* CONFIG_NET_RX_BUSY_POLL */ /* * As described in commit 0ccf831cb lockdep: annotate epoll * the use of wait queues used by epoll is done in a very controlled * manner. Wake ups can nest inside each other, but are never done * with the same locking. For example: * * dfd = socket(...); * efd1 = epoll_create(); * efd2 = epoll_create(); * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); * * When a packet arrives to the device underneath "dfd", the net code will * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a * callback wakeup entry on that queue, and the wake_up() performed by the * "dfd" net code will end up in ep_poll_callback(). At this point epoll * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid * stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; u8 nests = 0; /* * To set the subclass or nesting level for spin_lock_irqsave_nested() * it might be natural to create a per-cpu nest count. However, since * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can * schedule() in the -rt kernel, the per-cpu variable are no longer * protected. Thus, we are introducing a per eventpoll nest field. * If we are not being call from ep_poll_callback(), epi is NULL and * we are at the first level of nesting, 0. Otherwise, we are being * called from ep_poll_callback() and if a previous wakeup source is * not an epoll file itself, we are at depth 1 since the wakeup source * is depth 0. If the wakeup source is a previous epoll file in the * wakeup chain then we use its nests value and record ours as * nests + 1. The previous epoll file nests value is stable since its * already holding its own poll_wait.lock. */ if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data; nests = ep_src->nests; } else { nests = 1; } } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif static void ep_remove_wait_queue(struct eppoll_entry *pwq) { wait_queue_head_t *whead; rcu_read_lock(); /* * POLLFREE handshake, acquire side; see "POLLFREE handshake" * at the top of this file. * * A NULL load is paired with the smp_store_release(&whead, NULL) * in ep_poll_callback()'s POLLFREE branch: the teardown is * complete and we must not touch whead again. On a non-NULL load * rcu_read_lock() keeps the waitqueue memory alive (POLLFREE * firers RCU-defer the free) and whead->lock inside * remove_wait_queue() serializes us against the store side. */ whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); } /* * This function unregisters poll callbacks from the associated file * descriptor. Must be called with "mtx" held. */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { struct eppoll_entry **p = &epi->pwqlist; struct eppoll_entry *pwq; while ((pwq = *p) != NULL) { *p = pwq->next; ep_remove_wait_queue(pwq); kmem_cache_free(pwq_cache, pwq); } } /* call only when ep->mtx is held */ static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) { return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); } /* call only when ep->mtx is held */ static inline void ep_pm_stay_awake(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); if (ws) __pm_stay_awake(ws); } static inline bool ep_has_wakeup_source(struct epitem *epi) { return rcu_access_pointer(epi->ws) ? true : false; } /* call when ep->mtx cannot be held (ep_poll_callback) */ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) { struct wakeup_source *ws; rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock(); } /* * ep->mutex needs to be held because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ static void ep_start_scan(struct eventpoll *ep, struct list_head *scan_batch) { /* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events * happening while looping w/out locks, are not lost. We cannot * have the poll callback to queue directly on ep->rdllist, * because we want the "sproc" callback to be able to do it * in a lockless way. */ lockdep_assert_irqs_enabled(); spin_lock_irq(&ep->lock); write_seqcount_begin(&ep->seq); list_splice_init(&ep->rdllist, scan_batch); ep_enter_scan(ep); write_seqcount_end(&ep->seq); spin_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, struct list_head *scan_batch) { struct epitem *epi, *nepi; spin_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; ) { nepi = epi->ovflist_next; epi_clear_ovflist(epi); /* * Skip items that the caller already returned via @scan_batch * -- the list_splice() below takes care of those. */ if (!ep_is_linked(epi)) { /* * ovflist is LIFO; list_add() head-insert here * reverses the iteration order into FIFO. */ list_add(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } write_seqcount_begin(&ep->seq); /* Back out of scan mode; callbacks target ep->rdllist again. */ ep_exit_scan(ep); /* * Quickly re-inject items left on "scan_batch". */ list_splice(scan_batch, &ep->rdllist); write_seqcount_end(&ep->seq); __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); } spin_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); } /* * Drop a reference to @ep; returns true iff it was the last, in which * case the caller is responsible for ep_free(). */ static bool ep_put(struct eventpoll *ep) { if (!refcount_dec_and_test(&ep->refcount)) return false; WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root)); return true; } static void ep_free(struct eventpoll *ep) { ep_resume_napi_irqs(ep); mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); /* ep_get_upwards_depth_proc() may still hold epi->ep under RCU */ kfree_rcu(ep, rcu); } /* * Pin @epi->ffd.file for operations that require both safe dereference * and exclusion from __fput(). * * struct file uses SLAB_TYPESAFE_BY_RCU, so a freed slot can be * reassigned at any time. The bare load of epi->ffd.file is safe here * because the caller holds ep->mtx and eventpoll_release_file() blocks * on that mutex while tearing down the epi, so the backing file * allocation cannot be freed and reused under us. An rcu_read_lock() * is therefore unnecessary for the load. * * A successful file_ref_get() additionally blocks __fput() from * starting on this file: once the refcount has reached zero it cannot * come back. ep_remove() relies on that to touch file->f_lock and * file->f_ep without racing eventpoll_release_file() (see commit * a6dc643c6931). A NULL return means __fput() is already in flight; * the caller must bail without touching the file, and * eventpoll_release_file() will clean the epi up from its side. */ static struct file *epi_fget(const struct epitem *epi) { struct file *file; file = epi->ffd.file; if (!file_ref_get(&file->f_ref)) file = NULL; return file; } /* * Takes &file->f_lock; returns with it released. */ static void ep_remove_file(struct eventpoll *ep, struct epitem *epi, struct file *file) { struct epitems_head *to_free = NULL; struct hlist_head *head; lockdep_assert_held(&ep->mtx); spin_lock(&file->f_lock); head = file->f_ep; if (hlist_is_singular_node(&epi->fllink, head)) { /* * Last watcher: publish NULL so the eventpoll_release() * fastpath in include/linux/eventpoll.h can skip the slow * path on a future __fput(). Safe because every f_ep writer * either holds a pin on @file via epi_fget() or is __fput() * itself -- see the comment in eventpoll_release(). */ WRITE_ONCE(file->f_ep, NULL); if (!is_file_epoll(file)) { struct epitems_head *v; v = container_of(head, struct epitems_head, epitems); if (!smp_load_acquire(&v->next)) to_free = v; } } hlist_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); free_ephead(to_free); } static void ep_remove_epi(struct eventpoll *ep, struct epitem *epi) { lockdep_assert_held(&ep->mtx); rb_erase_cached(&epi->rbn, &ep->rbr); spin_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); spin_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* * At this point it is safe to free the eventpoll item. Use the union * field epi->rcu, since we are trying to minimize the size of * 'struct epitem'. The 'rbn' field is no longer in use. Protected by * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); } /* * ep_remove variant for callers owing an additional reference to the ep */ static void ep_remove(struct eventpoll *ep, struct epitem *epi) { struct file *file __free(fput) = NULL; lockdep_assert_irqs_enabled(); lockdep_assert_held(&ep->mtx); ep_unregister_pollwait(ep, epi); /* * If we manage to grab a reference it means we're not in * eventpoll_release_file() and aren't going to be: once @file's * refcount has reached zero, file_ref_get() cannot bring it back. */ file = epi_fget(epi); if (!file) return; ep_remove_file(ep, epi, file); ep_remove_epi(ep, epi); WARN_ON_ONCE(ep_put(ep)); } /* * Pass 1 of ep_clear_and_put(): drain every epi's pwqlist. * ep_unregister_pollwait() takes each watched wait-queue head's lock, * which synchronizes with any in-flight ep_poll_callback(); after * this returns no callback can still be about to dereference an epi * on this ep. Must strictly precede ep_drain_tree() -- fusing the * two walks would let a callback queued on epi_i still fire after * epi_{i+k} had already been freed. */ static void ep_drain_pollwaits(struct eventpoll *ep) { struct rb_node *rbp; struct epitem *epi; lockdep_assert_held(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); cond_resched(); } } /* * Pass 2 of ep_clear_and_put(): ep_remove() every epi. The per-epi * pwqlist is already empty (ep_drain_pollwaits ran), but the rest of * ep_remove() still runs: epi_fget() pin, f_ep clear under f_lock, * rbtree erase, rdllist unlink, kfree_rcu(epi). rb_next() is captured * before each erase so the iteration is stable. * * A concurrent eventpoll_release_file() (removal path C) on a watched * file serializes with us via ep->mtx; ep_remove() transparently * hands off any epi whose file is in __fput() by bailing when * epi_fget() returns NULL, and path C will clean that epi up. */ static void ep_drain_tree(struct eventpoll *ep) { struct rb_node *rbp, *next; struct epitem *epi; lockdep_assert_held(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) { next = rb_next(rbp); epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); cond_resched(); } } /* * Removal path B (see "Removal paths" in the top-of-file banner): * close of the epoll fd itself, reached via ep_eventpoll_release(). * * Two passes under ep->mtx: first ep_drain_pollwaits() quiesces * in-flight callbacks, then ep_drain_tree() frees the epis. The * ep->refcount is kept > 0 across the walk by the ep file's own * share, which we drop below; ep_free() runs iff we were the last * holder after the tree drained. */ static void ep_clear_and_put(struct eventpoll *ep) { /* Release any threads blocked in poll-on-ep. */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); mutex_lock(&ep->mtx); ep_drain_pollwaits(ep); ep_drain_tree(ep); mutex_unlock(&ep->mtx); if (ep_put(ep)) ep_free(ep); } static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; if (!is_file_epoll(file)) return -EINVAL; switch (cmd) { case EPIOCSPARAMS: case EPIOCGPARAMS: ret = ep_eventpoll_bp_ioctl(file, cmd, arg); break; default: ret = -EINVAL; break; } return ret; } static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; if (ep) ep_clear_and_put(ep); return 0; } static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth); static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; LIST_HEAD(scan_batch); struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; init_poll_funcptr(&pt, NULL); /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); /* * Proceed to find out if wanted events are really available inside * the ready list. */ mutex_lock_nested(&ep->mtx, depth); ep_start_scan(ep, &scan_batch); list_for_each_entry_safe(epi, tmp, &scan_batch, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; break; } else { /* * Item has been dropped into the ready list by the poll * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } ep_done_scan(ep, &scan_batch); mutex_unlock(&ep->mtx); return res; } /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct file *file = epi_fget(epi); __poll_t res; /* * We could return EPOLLERR | EPOLLHUP or something, but let's * treat this more as "file doesn't exist, poll didn't happen". */ if (!file) return 0; pt->_key = epi->event.events; if (!is_file_epoll(file)) res = vfs_poll(file, pt); else res = __ep_eventpoll_poll(file, pt, depth); fput(file); return res & epi->event.events; } static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait) { return __ep_eventpoll_poll(file, wait, 0); } #ifdef CONFIG_PROC_FS static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; mutex_lock(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); struct inode *inode = file_inode(epi->ffd.file); seq_printf(m, "tfd: %8d events: %8x data: %16llx " " pos:%lli ino:%llx sdev:%x\n", epi->ffd.fd, epi->event.events, (long long)epi->event.data, (long long)epi->ffd.file->f_pos, inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); } #endif /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = ep_show_fdinfo, #endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, .unlocked_ioctl = ep_eventpoll_ioctl, .compat_ioctl = compat_ptr_ioctl, }; /* * This is called from eventpoll_release() to unlink files from the eventpoll * interface. We need to have this facility to cleanup correctly files that are * closed without being removed from the eventpoll interface. */ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi; /* * A concurrent ep_remove() cannot outrace us: it pins @file via * epi_fget(), which fails once __fput() has dropped the refcount * to zero -- the path we're on. So any racing ep_remove() bails * and leaves the epi for us to clean up here. */ again: spin_lock(&file->f_lock); if (file->f_ep && file->f_ep->first) { epi = hlist_entry(file->f_ep->first, struct epitem, fllink); spin_unlock(&file->f_lock); /* * ep access is safe as we still own a reference to the ep * struct */ ep = epi->ep; mutex_lock(&ep->mtx); ep_unregister_pollwait(ep, epi); ep_remove_file(ep, epi, file); ep_remove_epi(ep, epi); mutex_unlock(&ep->mtx); if (ep_put(ep)) ep_free(ep); goto again; } spin_unlock(&file->f_lock); } static int ep_alloc(struct eventpoll **pep) { struct eventpoll *ep; ep = kzalloc_obj(*ep); if (unlikely(!ep)) return -ENOMEM; mutex_init(&ep->mtx); spin_lock_init(&ep->lock); seqcount_spinlock_init(&ep->seq, &ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; /* not scanning */ ep->user = get_current_user(); refcount_set(&ep->refcount, 1); *pep = ep; return 0; } /* * Search the file inside the eventpoll tree. The RB tree operations * are protected by the "mtx" mutex, and ep_find() must be called with * "mtx" held. */ static struct epitem *ep_find(struct eventpoll *ep, struct epoll_key *tf) { int kcmp; struct rb_node *rbp; struct epitem *epi, *epir = NULL; for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(tf, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) rbp = rbp->rb_left; else { epir = epi; break; } } return epir; } /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); unsigned long flags; int ewake = 0; spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the * EPOLLONESHOT bit that disables the descriptor when an event is received, * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) goto out_unlock; /* * Check the events coming with the callback. At this stage, not * every device reports the events in the "key" parameter of the * callback. We need to be able to handle both cases here, hence the * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) goto out_unlock; /* * If we are transferring events to userspace, we can hold no locks * (because we're accessing user memory, and because of linux f_op->poll() * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ if (ep_is_scanning(ep)) { if (!epi_on_ovflist(epi)) { epi->ovflist_next = READ_ONCE(ep->ovflist); WRITE_ONCE(ep->ovflist, epi); ep_pm_stay_awake_rcu(epi); } } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake_rcu(epi); } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() * wait list. */ if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { case EPOLLIN: if (epi->event.events & EPOLLIN) ewake = 1; break; case EPOLLOUT: if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: ewake = 1; break; } } if (sync) wake_up_sync(&ep->wq); else wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; out_unlock: spin_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; if (pollflags & POLLFREE) { /* * POLLFREE handshake, release side; see "POLLFREE handshake" * at the top of this file. * * Unlink our wait entry with list_del_init rather than * __remove_wait_queue: a concurrent ep_remove_wait_queue() * that already loaded a non-NULL whead may still call * remove_wait_queue() after us, and list_del_init() tolerates * the second delete. * * smp_store_release(&whead, NULL) publishes the teardown to * ep_remove_wait_queue()'s smp_load_acquire(). Before this * store, a racing ep_clear_and_put() / ep_remove() reaches * ep_remove_wait_queue() which sees whead != NULL and takes * whead->lock -- the same lock held by our caller, so it * serializes behind us. Once whead is zeroed, nothing else * protects ep / epi / wait. */ list_del_init(&wait->entry); smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } return ewake; } /* * This is the callback that is used to add our wait queue to the * target file wakeup lists. */ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt); struct epitem *epi = epq->epi; struct eppoll_entry *pwq; if (unlikely(!epi)) // an earlier allocation has failed return; pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL); if (unlikely(!pwq)) { epq->epi = NULL; return; } init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; if (epi->event.events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(whead, &pwq->wait); else add_wait_queue(whead, &pwq->wait); pwq->next = epi->pwqlist; epi->pwqlist = pwq; } static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) { p = &parent->rb_right; leftmost = false; } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } /* * Upper bound on wakeup paths emanating from any one watched file, * indexed by path depth (1..PATH_ARR_SIZE). For example, we allow * 1000 paths of length 1 from each watched file. These caps limit * the wakeup amplification that can be built from epoll-watches- * epoll topologies without rejecting reasonable usage. * * Enforced at EPOLL_CTL_ADD; CTL_MOD and CTL_DEL cannot add paths. * The running tallies live in ctx->path_count[] and are protected by * epnested_mutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count_inc(struct ep_ctl_ctx *ctx, int nests) { /* Allow an arbitrary number of depth 1 paths */ if (nests == 0) return 0; if (++ctx->path_count[nests] > path_limits[nests]) return -1; return 0; } static void path_count_init(struct ep_ctl_ctx *ctx) { int i; for (i = 0; i < PATH_ARR_SIZE; i++) ctx->path_count[i] = 0; } static int reverse_path_check_proc(struct ep_ctl_ctx *ctx, struct hlist_head *refs, int depth) { int error = 0; struct epitem *epi; if (depth > EP_MAX_NESTS) /* too deep nesting */ return -1; /* CTL_DEL can remove links here, but that can't increase our count */ hlist_for_each_entry_rcu(epi, refs, fllink) { struct hlist_head *refs = &epi->ep->refs; if (hlist_empty(refs)) error = path_count_inc(ctx, depth); else error = reverse_path_check_proc(ctx, refs, depth + 1); if (error != 0) break; } return error; } /** * reverse_path_check - ctx->tfile_check_list is a list of epitems_head * anchoring files with newly proposed links; make * sure those links don't push any path-length bucket * over its limit in path_limits[]. * @ctx: Per-do_epoll_ctl() scratch for the loop / path checks. * * Return: %zero if the proposed links don't create too many paths, * %-1 otherwise. */ static int reverse_path_check(struct ep_ctl_ctx *ctx) { struct epitems_head *p; for (p = ctx->tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) { int error; path_count_init(ctx); rcu_read_lock(); error = reverse_path_check_proc(ctx, &p->epitems, 0); rcu_read_unlock(); if (error) return error; } return 0; } static int ep_create_wakeup_source(struct epitem *epi) { struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register(NULL, "eventpoll"); if (!epi->ep->ws) return -ENOMEM; } take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); ws = wakeup_source_register(NULL, n.name.name); release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; rcu_assign_pointer(epi->ws, ws); return 0; } /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ static noinline void ep_destroy_wakeup_source(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); RCU_INIT_POINTER(epi->ws, NULL); /* * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is * used internally by wakeup_source_remove, too (called by * wakeup_source_unregister), so we cannot use call_rcu */ synchronize_rcu(); wakeup_source_unregister(ws); } static int ep_attach_file(struct file *file, struct epitem *epi) { struct epitems_head *to_free = NULL; struct hlist_head *head = NULL; struct eventpoll *ep = NULL; if (is_file_epoll(file)) ep = file->private_data; if (ep) { head = &ep->refs; } else if (!READ_ONCE(file->f_ep)) { allocate: to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL); if (!to_free) return -ENOMEM; head = &to_free->epitems; } spin_lock(&file->f_lock); if (!file->f_ep) { if (unlikely(!head)) { spin_unlock(&file->f_lock); goto allocate; } /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, head); to_free = NULL; } hlist_add_head_rcu(&epi->fllink, file->f_ep); spin_unlock(&file->f_lock); free_ephead(to_free); return 0; } /* * Charge the user's epoll_watches quota, allocate a fresh epitem for * @tf, and initialize its fields. The returned item is not yet linked * into any data structure; the caller must install it via * ep_register_epitem() (which takes over on success) or kmem_cache_free() * it and decrement epoll_watches on its own. * * Returns ERR_PTR(-ENOSPC) if the quota is exceeded, ERR_PTR(-ENOMEM) * if the slab allocation fails. */ static struct epitem *ep_alloc_epitem(struct eventpoll *ep, const struct epoll_event *event, struct epoll_key *tf) { struct epitem *epi; if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return ERR_PTR(-ENOSPC); percpu_counter_inc(&ep->user->epoll_watches); epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL); if (unlikely(!epi)) { percpu_counter_dec(&ep->user->epoll_watches); return ERR_PTR(-ENOMEM); } INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; epi->ffd = *tf; epi->event = *event; epi_clear_ovflist(epi); return epi; } /* * Install @epi into its target file's f_ep hlist and into @ep's rbtree, * taking one additional reference on @ep for the lifetime of the item. * * If @tep is non-NULL, the target file is itself an eventpoll; we hold * tep->mtx at subclass 1 across the attach + rbtree insert to serialize * with the target side. RB tree ops are protected by @ep->mtx, which * the caller already holds. * * On failure the epi is freed and the epoll_watches counter decremented, * matching ep_alloc_epitem()'s allocation. After this returns * successfully, ep_insert()'s later error paths use ep_remove() for * unwind; that cannot drop @ep's refcount to zero because the ep file * itself still holds the original reference. */ static int ep_register_epitem(struct ep_ctl_ctx *ctx, struct eventpoll *ep, struct epitem *epi, struct eventpoll *tep, int full_check) { struct file *tfile = epi->ffd.file; int error; if (tep) mutex_lock_nested(&tep->mtx, 1); error = ep_attach_file(tfile, epi); if (unlikely(error)) { if (tep) mutex_unlock(&tep->mtx); kmem_cache_free(epi_cache, epi); percpu_counter_dec(&ep->user->epoll_watches); return error; } if (full_check && !tep) list_file(tfile, ctx); ep_rbtree_insert(ep, epi); if (tep) mutex_unlock(&tep->mtx); ep_get(ep); return 0; } /* * Must be called with "mtx" held. */ static int ep_insert(struct ep_ctl_ctx *ctx, struct eventpoll *ep, const struct epoll_event *event, struct epoll_key *tf, int full_check) { int error, pwake = 0; __poll_t revents; struct epitem *epi; struct ep_pqueue epq; struct eventpoll *tep = NULL; if (is_file_epoll(tf->file)) tep = tf->file->private_data; lockdep_assert_irqs_enabled(); epi = ep_alloc_epitem(ep, event, tf); if (IS_ERR(epi)) return PTR_ERR(epi); error = ep_register_epitem(ctx, ep, epi, tep, full_check); if (error) return error; /* Reject the insert if the new link would create too many back-paths. */ if (unlikely(full_check && reverse_path_check(ctx))) { ep_remove(ep, epi); return -EINVAL; } if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) { ep_remove(ep, epi); return error; } } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); /* * Attach the item to the poll hooks and get current event bits. * We can safely use the file* here because its usage count has * been increased by the caller of this function. Note that after * this operation completes, the poll callback can start hitting * the new item. */ revents = ep_item_poll(epi, &epq.pt, 1); /* ep_ptable_queue_proc() signals allocation failure by clearing epq.epi. */ if (unlikely(!epq.epi)) { ep_remove(ep, epi); return -ENOMEM; } /* Drop the new item onto the ready list if it is already ready. */ spin_lock_irq(&ep->lock); ep_set_busy_poll_napi_id(epi); if (revents && !ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } spin_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Modify the interest event mask by dropping an event if the new mask * has a match in the current file status. Must be called with "mtx" held. */ static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { int pwake = 0; poll_table pt; lockdep_assert_irqs_enabled(); init_poll_funcptr(&pt, NULL); /* * Set the new event interest mask before calling f_op->poll(); * otherwise we might miss an event that happens between the * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } /* * The following barrier has two effects: * * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). * We need this because we did not take ep->lock while * changing epi above (but ep_poll_callback does take * ep->lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also * pairs with the barrier in wq_has_sleeper (see * comments for wq_has_sleeper). * * This barrier will now guarantee ep_poll_callback or f_op->poll * (or both) will notice the readiness of an item. */ smp_mb(); /* * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. * If the item is "hot" and it is not registered inside the ready * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { spin_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } spin_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Attempt to deliver one event for @epi into @*uevents. * * Returns 1 if an event was delivered (with *uevents advanced to the * next slot), 0 if the re-poll reported no caller-requested events * (@epi drops out of the ready list; a future callback will re-add * it), or -EFAULT if copy_to_user() faulted (in which case @epi is * re-inserted at the head of @scan_batch so ep_done_scan() merges it * back to rdllist for the next attempt). * * PM bookkeeping and level-triggered re-queue are handled here. * Caller holds ep->mtx and the scan is active. */ static int ep_deliver_event(struct eventpoll *ep, struct epitem *epi, poll_table *pt, struct epoll_event __user **uevents, struct list_head *scan_batch) { struct epoll_event __user *next; struct wakeup_source *ws; __poll_t revents; /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactivate epi->ws * below). Rearranging to delay the deactivation would let * epi->ws drift out of sync with ep_is_linked(). */ ws = ep_wakeup_source(epi); if (ws) { if (ws->active) __pm_stay_awake(ep->ws); __pm_relax(ws); } list_del_init(&epi->rdllink); /* * Re-poll under ep->mtx so userspace cannot change the item * out from under us. If no caller-requested events remain, * @epi stays off the ready list; the poll callback will * re-queue it when events next appear. */ revents = ep_item_poll(epi, pt, 1); if (!revents) return 0; next = epoll_put_uevent(revents, epi->event.data, *uevents); if (!next) { /* * copy_to_user() faulted: put the item back so * ep_done_scan() splices it onto rdllist for the next * attempt. */ list_add(&epi->rdllink, scan_batch); ep_pm_stay_awake(epi); return -EFAULT; } *uevents = next; if (epi->event.events & EPOLLONESHOT) { epi->event.events &= EP_PRIVATE_BITS; } else if (!(epi->event.events & EPOLLET)) { /* * Level-triggered: re-queue so the next epoll_wait() * rechecks availability. We are the sole writer to * rdllist here -- epoll_ctl() callers are locked out * by ep->mtx, and the poll callback queues to ovflist * during scans. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } return 1; } static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; LIST_HEAD(scan_batch); poll_table pt; int res = 0; /* * Always short-circuit for fatal signals to allow threads to make a * timely exit without the chance of finding more events available and * fetching repeatedly. */ if (fatal_signal_pending(current)) return -EINTR; init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); ep_start_scan(ep, &scan_batch); /* * We can loop without lock because we are passed a task-private * scan_batch; items cannot vanish while we hold ep->mtx. */ list_for_each_entry_safe(epi, tmp, &scan_batch, rdllink) { int delivered; if (res >= maxevents) break; delivered = ep_deliver_event(ep, epi, &pt, &events, &scan_batch); if (delivered < 0) { if (!res) res = delivered; break; } res += delivered; } ep_done_scan(ep, &scan_batch); mutex_unlock(&ep->mtx); return res; } static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { struct timespec64 now; if (ms < 0) return NULL; if (!ms) { to->tv_sec = 0; to->tv_nsec = 0; return to; } to->tv_sec = ms / MSEC_PER_SEC; to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); *to = timespec64_add_safe(now, *to); return to; } /* * autoremove_wake_function, but remove even on failure to wake up, because we * know that default_wake_function/ttwu will only fail if the thread is already * woken, and in that case the ep_poll loop will remove the entry anyways, not * try to reuse it. */ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wq_entry, mode, sync, key); /* * Pairs with list_empty_careful in ep_poll, and ensures future loop * iterations see the cause of this wakeup. */ list_del_init_careful(&wq_entry->entry); return ret; } static int ep_try_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { int res; /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of * more luck. */ res = ep_send_events(ep, events, maxevents); if (res > 0) ep_suspend_napi_irqs(ep); return res; } static int ep_schedule_timeout(ktime_t *to) { if (to) return ktime_after(*to, ktime_get()); else return 1; } /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. * * @ep: Pointer to the eventpoll context. * @events: Pointer to the userspace buffer where the ready events should be * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in * timespec. If the timeout is zero, the function will not block, * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * * Return: the number of ready events which have been fetched, or an * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout) { int res, timed_out = 0; bool eavail; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; *to = timespec64_to_ktime(*timeout); } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the * caller specified a non blocking operation. */ timed_out = 1; } /* * This call is racy: We may or may not see events that are being added * to the ready list under the lock (e.g., in IRQ callbacks). For cases * with a non-zero timeout, this thread will check the ready list under * lock and will add to the wait queue. For cases with a zero * timeout, the user by definition should not care and will have to * recheck again. */ eavail = ep_events_available(ep); while (1) { if (eavail) { res = ep_try_send_events(ep, events, maxevents); if (res) return res; } if (timed_out) return 0; eavail = ep_busy_loop(ep); if (eavail) continue; if (signal_pending(current)) return -EINTR; /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each * wakeup. Why it is important? In case of several waiters * each new wakeup will hit the next waiter, giving it the * chance to harvest new event. Otherwise wakeup can be * lost. This is also good performance-wise, because on * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. * * In fact, we now use an even more aggressive function that * unconditionally removes, because we don't reuse the wait * entry between loop iterations. This lets us also avoid the * performance issue if a process is killed, causing all of its * threads to wake up without being removed normally. */ init_wait(&wait); wait.func = ep_autoremove_wake_function; spin_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it * is safe to avoid an explicit barrier. */ __set_current_state(TASK_INTERRUPTIBLE); /* * Do the final check under the lock. ep_start/done_scan() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is * important. */ eavail = ep_events_available(ep); if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); spin_unlock_irq(&ep->lock); if (!eavail) timed_out = !ep_schedule_timeout(to) || !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * We were woken up, thus go and try to harvest some events. * If timed out and still on the wait queue, recheck eavail * carefully under lock, below. */ eavail = true; if (!list_empty_careful(&wait.entry)) { spin_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its * timeout expired before it could reacquire the lock. * Thus, when wait.entry is empty, it needs to harvest * events. */ if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); spin_unlock_irq(&ep->lock); } } } /** * ep_loop_check_proc - verify that adding an epoll file @ep inside another * epoll file does not create closed loops, and * determine the depth of the subtree starting at @ep * * @ctx: Per-do_epoll_ctl() scratch for the loop / path checks. * @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * * Return: depth of the subtree, or a value bigger than EP_MAX_NESTS if we found * a loop or went too deep. */ static int ep_loop_check_proc(struct ep_ctl_ctx *ctx, struct eventpoll *ep, int depth) { int result = 0; struct rb_node *rbp; struct epitem *epi; if (ep->gen == loop_check_gen) return ep->loop_check_depth; mutex_lock_nested(&ep->mtx, depth + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { struct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit == ctx->inserting_into || depth > EP_MAX_NESTS) result = EP_MAX_NESTS+1; else result = max(result, ep_loop_check_proc(ctx, ep_tovisit, depth + 1) + 1); if (result > EP_MAX_NESTS) break; } else { /* * A non-epoll leaf. Queue it for the companion * reverse_path_check() that runs after this walk so * any new links we propose don't add too many wakeup * paths. */ list_file(epi->ffd.file, ctx); } } ep->loop_check_depth = result; mutex_unlock(&ep->mtx); return result; } /* ep_get_upwards_depth_proc - determine depth of @ep when traversed upwards */ static int ep_get_upwards_depth_proc(struct eventpoll *ep, int depth) { int result = 0; struct epitem *epi; if (ep->gen == loop_check_gen) return ep->loop_check_depth; hlist_for_each_entry_rcu(epi, &ep->refs, fllink) result = max(result, ep_get_upwards_depth_proc(epi->ep, depth + 1) + 1); ep->gen = loop_check_gen; ep->loop_check_depth = result; return result; } /** * ep_loop_check - Performs a check to verify that adding an epoll file (@to) * into another epoll file (represented by @ep) does not create * closed loops or too deep chains. * * @ctx: Per-CTL_ADD scratch context. * @ep: Pointer to the epoll we are inserting into. * @to: Pointer to the epoll to be inserted. * * Return: %zero if adding the epoll @to inside the epoll @from * does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check(struct ep_ctl_ctx *ctx, struct eventpoll *ep, struct eventpoll *to) { int depth, upwards_depth; ctx->inserting_into = ep; /* * Check how deep down we can get from @to, and whether it is possible * to loop up to @ep. */ depth = ep_loop_check_proc(ctx, to, 0); if (depth > EP_MAX_NESTS) return -1; /* Check how far up we can go from @ep. */ rcu_read_lock(); upwards_depth = ep_get_upwards_depth_proc(ep, 0); rcu_read_unlock(); return (depth+1+upwards_depth > EP_MAX_NESTS) ? -1 : 0; } static void clear_tfile_check_list(struct ep_ctl_ctx *ctx) { rcu_read_lock(); while (ctx->tfile_check_list != EP_UNACTIVE_PTR) { struct epitems_head *head = ctx->tfile_check_list; ctx->tfile_check_list = head->next; unlist_file(head); } rcu_read_unlock(); } /* * Open an eventpoll file descriptor. */ static int do_epoll_create(int flags) { int error; struct eventpoll *ep; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); if (flags & ~EPOLL_CLOEXEC) return -EINVAL; /* * Create the internal data structure ("struct eventpoll"). */ error = ep_alloc(&ep); if (error < 0) return error; /* * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ FD_PREPARE(fdf, O_RDWR | (flags & O_CLOEXEC), anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, O_RDWR | (flags & O_CLOEXEC))); if (fdf.err) { ep_clear_and_put(ep); return fdf.err; } ep->file = fd_prepare_file(fdf); return fd_publish(fdf); } SYSCALL_DEFINE1(epoll_create1, int, flags) { return do_epoll_create(flags); } SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; return do_epoll_create(0); } #ifdef CONFIG_PM_SLEEP static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epev->events &= ~EPOLLWAKEUP; } #else static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { epev->events &= ~EPOLLWAKEUP; } #endif static inline int epoll_mutex_lock(struct mutex *mutex, bool nonblock) { if (!nonblock) { mutex_lock(mutex); return 0; } return mutex_trylock(mutex) ? 0 : -EAGAIN; } /* * Acquire the locks required for do_epoll_ctl() on @ep for @op. * * Always takes ep->mtx. For EPOLL_CTL_ADD, additionally runs the * loop / path check under epnested_mutex when the topology can * change: @ep is already watched (epfile->f_ep non-NULL), @ep was * recently loop-checked (ep->gen == loop_check_gen), or @tfile is * itself an eventpoll. * * Return value encodes both outcome and lock state: * * 0 success; ep->mtx held. * 1 success; ep->mtx held AND the full check ran under * epnested_mutex (which is also still held). The value * doubles as the @full_check argument to ep_insert(). * -errno failure; no locks held. * * The caller releases what was taken with ep_ctl_unlock(ep, ret). * * Holding epnested_mutex on add is what prevents two racing * EPOLL_CTL_ADDs on different eps from building a cycle without * either walker observing it. */ static int ep_ctl_lock(struct ep_ctl_ctx *ctx, struct eventpoll *ep, int op, struct file *epfile, struct file *tfile, bool nonblock) { struct eventpoll *tep; int error; error = epoll_mutex_lock(&ep->mtx, nonblock); if (error) return error; if (op != EPOLL_CTL_ADD) return 0; if (!READ_ONCE(epfile->f_ep) && ep->gen != loop_check_gen && !is_file_epoll(tfile)) return 0; /* Full check needed: drop ep->mtx so we can take epnested_mutex. */ mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epnested_mutex, nonblock); if (error) return error; loop_check_gen++; if (is_file_epoll(tfile)) { tep = tfile->private_data; if (ep_loop_check(ctx, ep, tep) != 0) { error = -ELOOP; goto err_unlock_nested; } } error = epoll_mutex_lock(&ep->mtx, nonblock); if (error) goto err_unlock_nested; return 1; err_unlock_nested: clear_tfile_check_list(ctx); loop_check_gen++; mutex_unlock(&epnested_mutex); return error; } static void ep_ctl_unlock(struct ep_ctl_ctx *ctx, struct eventpoll *ep, int full_check) { mutex_unlock(&ep->mtx); if (full_check) { clear_tfile_check_list(ctx); loop_check_gen++; mutex_unlock(&epnested_mutex); } } int do_epoll_ctl_file(struct file *f, int op, struct epoll_key *tf, struct epoll_event *epds, bool nonblock) { int error; int full_check; struct eventpoll *ep; struct epitem *epi; struct ep_ctl_ctx ctx = { .tfile_check_list = EP_UNACTIVE_PTR, }; /* The target file descriptor must support poll */ if (!file_can_poll(tf->file)) return -EPERM; /* Check if EPOLLWAKEUP is allowed */ if (ep_op_has_event(op)) ep_take_care_of_epollwakeup(epds); /* * The @f file must itself be an eventpoll, and we do not permit * adding an epoll file descriptor inside itself. */ if (f == tf->file || !is_file_epoll(f)) return -EINVAL; /* * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, nested exclusive wakeups are not supported. */ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) return -EINVAL; if (op == EPOLL_CTL_ADD && (is_file_epoll(tf->file) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) return -EINVAL; } ep = f->private_data; full_check = ep_ctl_lock(&ctx, ep, op, f, tf->file, nonblock); if (full_check < 0) return full_check; /* * Look the target up in ep's RB tree. We hold ep->mtx, so the * item stays valid until we release. */ epi = ep_find(ep, tf); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_insert(&ctx, ep, epds, tf, full_check); } else error = -EEXIST; break; case EPOLL_CTL_DEL: if (epi) { /* * The eventpoll itself is still alive: the refcount * can't go to zero here. */ ep_remove(ep, epi); error = 0; } else { error = -ENOENT; } break; case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, epds); } } else error = -ENOENT; break; } ep_ctl_unlock(&ctx, ep, full_check); return error; } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock) { struct epoll_key efd; CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; /* Get the "struct file *" for the target file */ CLASS(fd, tf)(fd); if (fd_empty(tf)) return -EBADF; efd.file = fd_file(tf); efd.fd = fd; return do_epoll_ctl_file(fd_file(f), op, &efd, epds, nonblock); } /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { struct epoll_event epds; if (ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) return -EFAULT; return do_epoll_ctl(epfd, op, fd, &epds, false); } static int ep_check_params(struct file *file, struct epoll_event __user *evs, int maxevents) { /* The maximum number of event must be greater than zero */ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ if (!access_ok(evs, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* * We have to check that the file structure underneath the fd * the user passed to us _is_ an eventpoll file. */ if (!is_file_epoll(file)) return -EINVAL; return 0; } int epoll_sendevents(struct file *file, struct epoll_event __user *events, int maxevents) { struct eventpoll *ep; int ret; ret = ep_check_params(file, events, maxevents); if (unlikely(ret)) return ret; ep = file->private_data; /* * Racy call, but that's ok - it should get retried based on * poll readiness anyway. */ if (ep_events_available(ep)) return ep_try_send_events(ep, events, maxevents); return 0; } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to) { struct eventpoll *ep; int ret; /* Get the "struct file *" for the eventpoll file */ CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; ret = ep_check_params(fd_file(f), events, maxevents); if (unlikely(ret)) return ret; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* Time to fish for events ... */ return ep_poll(ep, events, maxevents, to); } SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { struct timespec64 to; return do_epoll_wait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ static int do_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to, const sigset_t __user *sigmask, size_t sigsetsize) { int error; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ error = set_user_sigmask(sigmask, sigsetsize); if (error) return error; error = do_epoll_wait(epfd, events, maxevents, to); restore_saved_sigmask_unless(error == -EINTR); return error; } SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 to; return do_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; struct epitem *epi; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (epi->ffd.fd == tfd) { if (toff == 0) return epi; else toff--; } cond_resched(); } return NULL; } struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff) { struct file *file_raw; struct eventpoll *ep; struct epitem *epi; if (!is_file_epoll(file)) return ERR_PTR(-EINVAL); ep = file->private_data; mutex_lock(&ep->mtx); epi = ep_find_tfd(ep, tfd, toff); if (epi) file_raw = epi->ffd.file; else file_raw = ERR_PTR(-ENOENT); mutex_unlock(&ep->mtx); return file_raw; } #endif /* CONFIG_KCMP */ #ifdef CONFIG_COMPAT static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { long err; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ err = set_compat_user_sigmask(sigmask, sigsetsize); if (err) return err; err = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(err == -EINTR); return err; } COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 to; return do_compat_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_compat_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #endif static int __init eventpoll_init(void) { struct sysinfo si; si_meminfo(&si); /* * Allows top 4% of lomem to be allocated for epoll watches (per user). */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; BUG_ON(max_user_watches < 0); /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs */ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); return 0; } fs_initcall(eventpoll_init); |
| 4 4 1 1 5 1 1 4 4 3 1 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * virtio-fs: Virtio Filesystem * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/fs.h> #include <linux/dax.h> #include <linux/pci.h> #include <linux/interrupt.h> #include <linux/group_cpus.h> #include <linux/memremap.h> #include <linux/module.h> #include <linux/virtio.h> #include <linux/virtio_fs.h> #include <linux/delay.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/highmem.h> #include <linux/cleanup.h> #include <linux/uio.h> #include "dev.h" #include "fuse_i.h" #include "fuse_dev_i.h" /* Used to help calculate the FUSE connection's max_pages limit for a request's * size. Parts of the struct fuse_req are sliced into scattergather lists in * addition to the pages used, so this can help account for that overhead. */ #define FUSE_HEADER_OVERHEAD 4 /* List of virtio-fs device instances and a lock for the list. Also provides * mutual exclusion in device removal and mounting path */ static DEFINE_MUTEX(virtio_fs_mutex); static LIST_HEAD(virtio_fs_instances); /* The /sys/fs/virtio_fs/ kset */ static struct kset *virtio_fs_kset; enum { VQ_HIPRIO, VQ_REQUEST }; #define VQ_NAME_LEN 24 /* Per-virtqueue state */ struct virtio_fs_vq { spinlock_t lock; struct virtqueue *vq; /* protected by ->lock */ struct work_struct done_work; struct list_head queued_reqs; struct list_head end_reqs; /* End these requests */ struct work_struct dispatch_work; struct fuse_dev *fud; bool connected; long in_flight; struct completion in_flight_zero; /* No inflight requests */ struct kobject *kobj; char name[VQ_NAME_LEN]; } ____cacheline_aligned_in_smp; /* A virtio-fs device instance */ struct virtio_fs { struct kobject kobj; struct kobject *mqs_kobj; struct list_head list; /* on virtio_fs_instances */ char *tag; struct virtio_fs_vq *vqs; unsigned int nvqs; /* number of virtqueues */ unsigned int num_request_queues; /* number of request queues */ struct dax_device *dax_dev; unsigned int *mq_map; /* index = cpu id, value = request vq id */ /* DAX memory window where file contents are mapped */ void *window_kaddr; phys_addr_t window_phys_addr; size_t window_len; }; struct virtio_fs_forget_req { struct fuse_in_header ih; struct fuse_forget_in arg; }; struct virtio_fs_forget { /* This request can be temporarily queued on virt queue */ struct list_head list; struct virtio_fs_forget_req req; }; struct virtio_fs_req_work { struct fuse_req *req; struct virtio_fs_vq *fsvq; struct work_struct done_work; }; static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, struct fuse_req *req, bool in_flight, gfp_t gfp); static const struct constant_table dax_param_enums[] = { {"always", FUSE_DAX_ALWAYS }, {"never", FUSE_DAX_NEVER }, {"inode", FUSE_DAX_INODE_USER }, {} }; enum { OPT_DAX, OPT_DAX_ENUM, }; static const struct fs_parameter_spec virtio_fs_parameters[] = { fsparam_flag("dax", OPT_DAX), fsparam_enum("dax", OPT_DAX_ENUM, dax_param_enums), {} }; static int virtio_fs_parse_param(struct fs_context *fsc, struct fs_parameter *param) { struct fs_parse_result result; struct fuse_fs_context *ctx = fsc->fs_private; int opt; opt = fs_parse(fsc, virtio_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case OPT_DAX: ctx->dax_mode = FUSE_DAX_ALWAYS; break; case OPT_DAX_ENUM: ctx->dax_mode = result.uint_32; break; default: return -EINVAL; } return 0; } static void virtio_fs_free_fsc(struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; kfree(ctx); } static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq) { struct virtio_fs *fs = vq->vdev->priv; return &fs->vqs[vq->index]; } /* Should be called with fsvq->lock held. */ static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq) { fsvq->in_flight++; } /* Should be called with fsvq->lock held. */ static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq) { WARN_ON(fsvq->in_flight <= 0); fsvq->in_flight--; if (!fsvq->in_flight) complete(&fsvq->in_flight_zero); } static ssize_t tag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj); return sysfs_emit(buf, "%s\n", fs->tag); } static struct kobj_attribute virtio_fs_tag_attr = __ATTR_RO(tag); static struct attribute *virtio_fs_attrs[] = { &virtio_fs_tag_attr.attr, NULL }; ATTRIBUTE_GROUPS(virtio_fs); static void virtio_fs_ktype_release(struct kobject *kobj) { struct virtio_fs *vfs = container_of(kobj, struct virtio_fs, kobj); kfree(vfs->mq_map); kfree(vfs->vqs); kfree(vfs); } static const struct kobj_type virtio_fs_ktype = { .release = virtio_fs_ktype_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = virtio_fs_groups, }; static struct virtio_fs_vq *virtio_fs_kobj_to_vq(struct virtio_fs *fs, struct kobject *kobj) { int i; for (i = 0; i < fs->nvqs; i++) { if (kobj == fs->vqs[i].kobj) return &fs->vqs[i]; } return NULL; } static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct virtio_fs *fs = container_of(kobj->parent->parent, struct virtio_fs, kobj); struct virtio_fs_vq *fsvq = virtio_fs_kobj_to_vq(fs, kobj); if (!fsvq) return -EINVAL; return sysfs_emit(buf, "%s\n", fsvq->name); } static struct kobj_attribute virtio_fs_vq_name_attr = __ATTR_RO(name); static ssize_t cpu_list_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct virtio_fs *fs = container_of(kobj->parent->parent, struct virtio_fs, kobj); struct virtio_fs_vq *fsvq = virtio_fs_kobj_to_vq(fs, kobj); unsigned int cpu, qid; const size_t size = PAGE_SIZE - 1; bool first = true; int ret = 0, pos = 0; if (!fsvq) return -EINVAL; qid = fsvq->vq->index; for (cpu = 0; cpu < nr_cpu_ids; cpu++) { if (qid < VQ_REQUEST || (fs->mq_map[cpu] == qid)) { if (first) ret = snprintf(buf + pos, size - pos, "%u", cpu); else ret = snprintf(buf + pos, size - pos, ", %u", cpu); if (ret >= size - pos) break; first = false; pos += ret; } } ret = snprintf(buf + pos, size + 1 - pos, "\n"); return pos + ret; } static struct kobj_attribute virtio_fs_vq_cpu_list_attr = __ATTR_RO(cpu_list); static struct attribute *virtio_fs_vq_attrs[] = { &virtio_fs_vq_name_attr.attr, &virtio_fs_vq_cpu_list_attr.attr, NULL }; static struct attribute_group virtio_fs_vq_attr_group = { .attrs = virtio_fs_vq_attrs, }; /* Make sure virtiofs_mutex is held */ static void virtio_fs_put_locked(struct virtio_fs *fs) { lockdep_assert_held(&virtio_fs_mutex); kobject_put(&fs->kobj); } static void virtio_fs_put(struct virtio_fs *fs) { mutex_lock(&virtio_fs_mutex); virtio_fs_put_locked(fs); mutex_unlock(&virtio_fs_mutex); } static void virtio_fs_fiq_release(struct fuse_iqueue *fiq) { struct virtio_fs *vfs = fiq->priv; virtio_fs_put(vfs); } static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq) { WARN_ON(fsvq->in_flight < 0); /* Wait for in flight requests to finish.*/ spin_lock(&fsvq->lock); if (fsvq->in_flight) { /* We are holding virtio_fs_mutex. There should not be any * waiters waiting for completion. */ reinit_completion(&fsvq->in_flight_zero); spin_unlock(&fsvq->lock); wait_for_completion(&fsvq->in_flight_zero); } else { spin_unlock(&fsvq->lock); } flush_work(&fsvq->done_work); flush_work(&fsvq->dispatch_work); } static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; virtio_fs_drain_queue(fsvq); } } static void virtio_fs_drain_all_queues(struct virtio_fs *fs) { /* Provides mutual exclusion between ->remove and ->kill_sb * paths. We don't want both of these draining queue at the * same time. Current completion logic reinits completion * and that means there should not be any other thread * doing reinit or waiting for completion already. */ mutex_lock(&virtio_fs_mutex); virtio_fs_drain_all_queues_locked(fs); mutex_unlock(&virtio_fs_mutex); } static void virtio_fs_start_all_queues(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; spin_lock(&fsvq->lock); fsvq->connected = true; spin_unlock(&fsvq->lock); } } static void virtio_fs_delete_queues_sysfs(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; kobject_put(fsvq->kobj); } } static int virtio_fs_add_queues_sysfs(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; char buff[12]; int i, j, ret; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; sprintf(buff, "%d", i); fsvq->kobj = kobject_create_and_add(buff, fs->mqs_kobj); if (!fsvq->kobj) { ret = -ENOMEM; goto out_del; } ret = sysfs_create_group(fsvq->kobj, &virtio_fs_vq_attr_group); if (ret) { kobject_put(fsvq->kobj); goto out_del; } } return 0; out_del: for (j = 0; j < i; j++) { fsvq = &fs->vqs[j]; kobject_put(fsvq->kobj); } return ret; } /* Add a new instance to the list or return -EEXIST if tag name exists*/ static int virtio_fs_add_instance(struct virtio_device *vdev, struct virtio_fs *fs) { struct virtio_fs *fs2; int ret; mutex_lock(&virtio_fs_mutex); list_for_each_entry(fs2, &virtio_fs_instances, list) { if (strcmp(fs->tag, fs2->tag) == 0) { mutex_unlock(&virtio_fs_mutex); return -EEXIST; } } /* Use the virtio_device's index as a unique identifier, there is no * need to allocate our own identifiers because the virtio_fs instance * is only visible to userspace as long as the underlying virtio_device * exists. */ fs->kobj.kset = virtio_fs_kset; ret = kobject_add(&fs->kobj, NULL, "%d", vdev->index); if (ret < 0) goto out_unlock; fs->mqs_kobj = kobject_create_and_add("mqs", &fs->kobj); if (!fs->mqs_kobj) { ret = -ENOMEM; goto out_del; } ret = sysfs_create_link(&fs->kobj, &vdev->dev.kobj, "device"); if (ret < 0) goto out_put; ret = virtio_fs_add_queues_sysfs(fs); if (ret) goto out_remove; list_add_tail(&fs->list, &virtio_fs_instances); mutex_unlock(&virtio_fs_mutex); kobject_uevent(&fs->kobj, KOBJ_ADD); return 0; out_remove: sysfs_remove_link(&fs->kobj, "device"); out_put: kobject_put(fs->mqs_kobj); out_del: kobject_del(&fs->kobj); out_unlock: mutex_unlock(&virtio_fs_mutex); return ret; } /* Return the virtio_fs with a given tag, or NULL */ static struct virtio_fs *virtio_fs_find_instance(const char *tag) { struct virtio_fs *fs; mutex_lock(&virtio_fs_mutex); list_for_each_entry(fs, &virtio_fs_instances, list) { if (strcmp(fs->tag, tag) == 0) { kobject_get(&fs->kobj); goto found; } } fs = NULL; /* not found */ found: mutex_unlock(&virtio_fs_mutex); return fs; } static void virtio_fs_free_devs(struct virtio_fs *fs) { unsigned int i; for (i = 0; i < fs->nvqs; i++) { struct virtio_fs_vq *fsvq = &fs->vqs[i]; if (!fsvq->fud) continue; fuse_dev_put(fsvq->fud); fsvq->fud = NULL; } } /* Read filesystem name from virtio config into fs->tag (must kfree()). */ static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs) { char tag_buf[sizeof_field(struct virtio_fs_config, tag)]; char *end; size_t len; virtio_cread_bytes(vdev, offsetof(struct virtio_fs_config, tag), &tag_buf, sizeof(tag_buf)); end = memchr(tag_buf, '\0', sizeof(tag_buf)); if (end == tag_buf) return -EINVAL; /* empty tag */ if (!end) end = &tag_buf[sizeof(tag_buf)]; len = end - tag_buf; fs->tag = devm_kmalloc(&vdev->dev, len + 1, GFP_KERNEL); if (!fs->tag) return -ENOMEM; memcpy(fs->tag, tag_buf, len); fs->tag[len] = '\0'; /* While the VIRTIO specification allows any character, newlines are * awkward on mount(8) command-lines and cause problems in the sysfs * "tag" attr and uevent TAG= properties. Forbid them. */ if (strchr(fs->tag, '\n')) { dev_dbg(&vdev->dev, "refusing virtiofs tag with newline character\n"); return -EINVAL; } dev_info(&vdev->dev, "discovered new tag: %s\n", fs->tag); return 0; } /* Work function for hiprio completion */ static void virtio_fs_hiprio_done_work(struct work_struct *work) { struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, done_work); struct virtqueue *vq = fsvq->vq; /* Free completed FUSE_FORGET requests */ spin_lock(&fsvq->lock); do { unsigned int len; void *req; virtqueue_disable_cb(vq); while ((req = virtqueue_get_buf(vq, &len)) != NULL) { kfree(req); dec_in_flight_req(fsvq); } } while (!virtqueue_enable_cb(vq)); if (!list_empty(&fsvq->queued_reqs)) schedule_work(&fsvq->dispatch_work); spin_unlock(&fsvq->lock); } static void virtio_fs_request_dispatch_work(struct work_struct *work) { struct fuse_req *req; struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, dispatch_work); int ret; pr_debug("virtio-fs: worker %s called.\n", __func__); while (1) { spin_lock(&fsvq->lock); req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req, list); if (!req) { spin_unlock(&fsvq->lock); break; } list_del_init(&req->list); spin_unlock(&fsvq->lock); fuse_request_end(req); } /* Dispatch pending requests */ while (1) { unsigned int flags; spin_lock(&fsvq->lock); req = list_first_entry_or_null(&fsvq->queued_reqs, struct fuse_req, list); if (!req) { spin_unlock(&fsvq->lock); return; } list_del_init(&req->list); spin_unlock(&fsvq->lock); flags = memalloc_nofs_save(); ret = virtio_fs_enqueue_req(fsvq, req, true, GFP_KERNEL); memalloc_nofs_restore(flags); if (ret < 0) { if (ret == -ENOSPC) { spin_lock(&fsvq->lock); list_add_tail(&req->list, &fsvq->queued_reqs); spin_unlock(&fsvq->lock); return; } req->out.h.error = ret; spin_lock(&fsvq->lock); dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret); fuse_request_end(req); } } } /* * Returns 1 if queue is full and sender should wait a bit before sending * next request, 0 otherwise. */ static int send_forget_request(struct virtio_fs_vq *fsvq, struct virtio_fs_forget *forget, bool in_flight) { struct scatterlist sg; struct virtqueue *vq; int ret = 0; bool notify; struct virtio_fs_forget_req *req = &forget->req; spin_lock(&fsvq->lock); if (!fsvq->connected) { if (in_flight) dec_in_flight_req(fsvq); kfree(forget); goto out; } sg_init_one(&sg, req, sizeof(*req)); vq = fsvq->vq; dev_dbg(&vq->vdev->dev, "%s\n", __func__); ret = virtqueue_add_outbuf(vq, &sg, 1, forget, GFP_ATOMIC); if (ret < 0) { if (ret == -ENOSPC) { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n", ret); list_add_tail(&forget->list, &fsvq->queued_reqs); if (!in_flight) inc_in_flight_req(fsvq); /* Queue is full */ ret = 1; } else { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n", ret); kfree(forget); if (in_flight) dec_in_flight_req(fsvq); } goto out; } if (!in_flight) inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); if (notify) virtqueue_notify(vq); return ret; out: spin_unlock(&fsvq->lock); return ret; } static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) { struct virtio_fs_forget *forget; struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, dispatch_work); pr_debug("virtio-fs: worker %s called.\n", __func__); while (1) { spin_lock(&fsvq->lock); forget = list_first_entry_or_null(&fsvq->queued_reqs, struct virtio_fs_forget, list); if (!forget) { spin_unlock(&fsvq->lock); return; } list_del(&forget->list); spin_unlock(&fsvq->lock); if (send_forget_request(fsvq, forget, true)) return; } } /* Allocate and copy args into req->argbuf */ static int copy_args_to_argbuf(struct fuse_req *req, gfp_t gfp) { struct fuse_args *args = req->args; unsigned int offset = 0; unsigned int num_in; unsigned int num_out; unsigned int len; unsigned int i; num_in = args->in_numargs - args->in_pages; num_out = args->out_numargs - args->out_pages; len = fuse_len_args(num_in, (struct fuse_arg *) args->in_args) + fuse_len_args(num_out, args->out_args); req->argbuf = kmalloc(len, gfp); if (!req->argbuf) return -ENOMEM; for (i = 0; i < num_in; i++) { memcpy(req->argbuf + offset, args->in_args[i].value, args->in_args[i].size); offset += args->in_args[i].size; } return 0; } /* Copy args out of and free req->argbuf */ static void copy_args_from_argbuf(struct fuse_args *args, struct fuse_req *req) { unsigned int remaining; unsigned int offset; unsigned int num_in; unsigned int num_out; unsigned int i; remaining = req->out.h.len - sizeof(req->out.h); num_in = args->in_numargs - args->in_pages; num_out = args->out_numargs - args->out_pages; offset = fuse_len_args(num_in, (struct fuse_arg *)args->in_args); for (i = 0; i < num_out; i++) { unsigned int argsize = args->out_args[i].size; if (args->out_argvar && i == args->out_numargs - 1 && argsize > remaining) { argsize = remaining; } memcpy(args->out_args[i].value, req->argbuf + offset, argsize); offset += argsize; if (i != args->out_numargs - 1) remaining -= argsize; } /* Store the actual size of the variable-length arg */ if (args->out_argvar) args->out_args[args->out_numargs - 1].size = remaining; kfree(req->argbuf); req->argbuf = NULL; } /* Verify that the server properly follows the FUSE protocol */ static bool virtio_fs_verify_response(struct fuse_req *req, unsigned int len) { struct fuse_out_header *oh = &req->out.h; if (len < sizeof(*oh)) { pr_warn("virtio-fs: response too short (%u)\n", len); return false; } if (oh->len != len) { pr_warn("virtio-fs: oh.len mismatch (%u != %u)\n", oh->len, len); return false; } if (oh->unique != req->in.h.unique) { pr_warn("virtio-fs: oh.unique mismatch (%llu != %llu)\n", oh->unique, req->in.h.unique); return false; } return true; } /* Work function for request completion */ static void virtio_fs_request_complete(struct fuse_req *req, struct virtio_fs_vq *fsvq) { struct fuse_args *args; struct fuse_args_pages *ap; unsigned int len, i, thislen; struct folio *folio; args = req->args; copy_args_from_argbuf(args, req); if (args->out_pages && args->page_zeroing) { len = args->out_args[args->out_numargs - 1].size; ap = container_of(args, typeof(*ap), args); for (i = 0; i < ap->num_folios; i++) { thislen = ap->descs[i].length; if (len < thislen) { WARN_ON(ap->descs[i].offset); folio = ap->folios[i]; folio_zero_segment(folio, len, thislen); len = 0; } else { len -= thislen; } } } clear_bit(FR_SENT, &req->flags); fuse_request_end(req); spin_lock(&fsvq->lock); dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); } static void virtio_fs_complete_req_work(struct work_struct *work) { struct virtio_fs_req_work *w = container_of(work, typeof(*w), done_work); virtio_fs_request_complete(w->req, w->fsvq); kfree(w); } static void virtio_fs_requests_done_work(struct work_struct *work) { struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, done_work); struct fuse_pqueue *fpq = &fsvq->fud->pq; struct virtqueue *vq = fsvq->vq; struct fuse_req *req; struct fuse_req *next; unsigned int len; LIST_HEAD(reqs); /* Collect completed requests off the virtqueue */ spin_lock(&fsvq->lock); do { virtqueue_disable_cb(vq); while ((req = virtqueue_get_buf(vq, &len)) != NULL) { if (!virtio_fs_verify_response(req, len)) { req->out.h.error = -EIO; req->out.h.len = sizeof(struct fuse_out_header); } spin_lock(&fpq->lock); list_move_tail(&req->list, &reqs); spin_unlock(&fpq->lock); } } while (!virtqueue_enable_cb(vq)); spin_unlock(&fsvq->lock); /* End requests */ list_for_each_entry_safe(req, next, &reqs, list) { list_del_init(&req->list); /* blocking async request completes in a worker context */ if (req->args->may_block) { struct virtio_fs_req_work *w; w = kzalloc_obj(*w, GFP_NOFS | __GFP_NOFAIL); INIT_WORK(&w->done_work, virtio_fs_complete_req_work); w->fsvq = fsvq; w->req = req; schedule_work(&w->done_work); } else { virtio_fs_request_complete(req, fsvq); } } /* Try to push previously queued requests, as the queue might no longer be full */ spin_lock(&fsvq->lock); if (!list_empty(&fsvq->queued_reqs)) schedule_work(&fsvq->dispatch_work); spin_unlock(&fsvq->lock); } static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *fs) { const struct cpumask *mask, *masks; unsigned int q, cpu, nr_masks; /* First attempt to map using existing transport layer affinities * e.g. PCIe MSI-X */ if (!vdev->config->get_vq_affinity) goto fallback; for (q = 0; q < fs->num_request_queues; q++) { mask = vdev->config->get_vq_affinity(vdev, VQ_REQUEST + q); if (!mask) goto fallback; for_each_cpu(cpu, mask) fs->mq_map[cpu] = q + VQ_REQUEST; } return; fallback: /* Attempt to map evenly in groups over the CPUs */ masks = group_cpus_evenly(fs->num_request_queues, &nr_masks); /* If even this fails we default to all CPUs use first request queue */ if (!masks) { for_each_possible_cpu(cpu) fs->mq_map[cpu] = VQ_REQUEST; return; } for (q = 0; q < fs->num_request_queues; q++) { for_each_cpu(cpu, &masks[q % nr_masks]) fs->mq_map[cpu] = q + VQ_REQUEST; } kfree(masks); } /* Virtqueue interrupt handler */ static void virtio_fs_vq_done(struct virtqueue *vq) { struct virtio_fs_vq *fsvq = vq_to_fsvq(vq); dev_dbg(&vq->vdev->dev, "%s %s\n", __func__, fsvq->name); schedule_work(&fsvq->done_work); } static void virtio_fs_init_vq(struct virtio_fs_vq *fsvq, char *name, int vq_type) { strscpy(fsvq->name, name, VQ_NAME_LEN); spin_lock_init(&fsvq->lock); INIT_LIST_HEAD(&fsvq->queued_reqs); INIT_LIST_HEAD(&fsvq->end_reqs); init_completion(&fsvq->in_flight_zero); if (vq_type == VQ_REQUEST) { INIT_WORK(&fsvq->done_work, virtio_fs_requests_done_work); INIT_WORK(&fsvq->dispatch_work, virtio_fs_request_dispatch_work); } else { INIT_WORK(&fsvq->done_work, virtio_fs_hiprio_done_work); INIT_WORK(&fsvq->dispatch_work, virtio_fs_hiprio_dispatch_work); } } /* Initialize virtqueues */ static int virtio_fs_setup_vqs(struct virtio_device *vdev, struct virtio_fs *fs) { struct virtqueue_info *vqs_info; struct virtqueue **vqs; /* Specify pre_vectors to ensure that the queues before the * request queues (e.g. hiprio) don't claim any of the CPUs in * the multi-queue mapping and interrupt affinities */ struct irq_affinity desc = { .pre_vectors = VQ_REQUEST }; unsigned int i; int ret = 0; virtio_cread_le(vdev, struct virtio_fs_config, num_request_queues, &fs->num_request_queues); if (fs->num_request_queues == 0) return -EINVAL; /* Truncate nr of request queues to nr_cpu_id */ fs->num_request_queues = min_t(unsigned int, fs->num_request_queues, nr_cpu_ids); fs->nvqs = VQ_REQUEST + fs->num_request_queues; fs->vqs = kzalloc_objs(fs->vqs[VQ_HIPRIO], fs->nvqs); if (!fs->vqs) return -ENOMEM; vqs = kmalloc_objs(vqs[VQ_HIPRIO], fs->nvqs); fs->mq_map = kcalloc_node(nr_cpu_ids, sizeof(*fs->mq_map), GFP_KERNEL, dev_to_node(&vdev->dev)); vqs_info = kzalloc_objs(*vqs_info, fs->nvqs); if (!vqs || !vqs_info || !fs->mq_map) { ret = -ENOMEM; goto out; } /* Initialize the hiprio/forget request virtqueue */ vqs_info[VQ_HIPRIO].callback = virtio_fs_vq_done; virtio_fs_init_vq(&fs->vqs[VQ_HIPRIO], "hiprio", VQ_HIPRIO); vqs_info[VQ_HIPRIO].name = fs->vqs[VQ_HIPRIO].name; /* Initialize the requests virtqueues */ for (i = VQ_REQUEST; i < fs->nvqs; i++) { char vq_name[VQ_NAME_LEN]; snprintf(vq_name, VQ_NAME_LEN, "requests.%u", i - VQ_REQUEST); virtio_fs_init_vq(&fs->vqs[i], vq_name, VQ_REQUEST); vqs_info[i].callback = virtio_fs_vq_done; vqs_info[i].name = fs->vqs[i].name; } ret = virtio_find_vqs(vdev, fs->nvqs, vqs, vqs_info, &desc); if (ret < 0) goto out; for (i = 0; i < fs->nvqs; i++) fs->vqs[i].vq = vqs[i]; virtio_fs_start_all_queues(fs); out: kfree(vqs_info); kfree(vqs); if (ret) { kfree(fs->vqs); fs->vqs = NULL; kfree(fs->mq_map); fs->mq_map = NULL; } return ret; } /* Free virtqueues (device must already be reset) */ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev) { vdev->config->del_vqs(vdev); } /* Map a window offset to a page frame number. The window offset will have * been produced by .iomap_begin(), which maps a file offset to a window * offset. */ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, unsigned long *pfn) { struct virtio_fs *fs = dax_get_private(dax_dev); phys_addr_t offset = PFN_PHYS(pgoff); size_t max_nr_pages = fs->window_len / PAGE_SIZE - pgoff; if (kaddr) *kaddr = fs->window_kaddr + offset; if (pfn) *pfn = PHYS_PFN(fs->window_phys_addr + offset); return nr_pages > max_nr_pages ? max_nr_pages : nr_pages; } static int virtio_fs_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { long rc; void *kaddr; rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS, &kaddr, NULL); if (rc < 0) return dax_mem2blk_err(rc); memset(kaddr, 0, nr_pages << PAGE_SHIFT); dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT); return 0; } static const struct dax_operations virtio_fs_dax_ops = { .direct_access = virtio_fs_direct_access, .zero_page_range = virtio_fs_zero_page_range, }; static void virtio_fs_cleanup_dax(void *data) { struct dax_device *dax_dev = data; kill_dax(dax_dev); put_dax(dax_dev); } DEFINE_FREE(cleanup_dax, struct dax_dev *, if (!IS_ERR_OR_NULL(_T)) virtio_fs_cleanup_dax(_T)) static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) { struct dax_device *dax_dev __free(cleanup_dax) = NULL; struct virtio_shm_region cache_reg; struct dev_pagemap *pgmap; bool have_cache; if (!IS_ENABLED(CONFIG_FUSE_DAX)) return 0; dax_dev = alloc_dax(fs, &virtio_fs_dax_ops); if (IS_ERR(dax_dev)) { int rc = PTR_ERR(dax_dev); return rc == -EOPNOTSUPP ? 0 : rc; } /* Get cache region */ have_cache = virtio_get_shm_region(vdev, &cache_reg, (u8)VIRTIO_FS_SHMCAP_ID_CACHE); if (!have_cache) { dev_notice(&vdev->dev, "%s: No cache capability\n", __func__); return 0; } if (!devm_request_mem_region(&vdev->dev, cache_reg.addr, cache_reg.len, dev_name(&vdev->dev))) { dev_warn(&vdev->dev, "could not reserve region addr=0x%llx len=0x%llx\n", cache_reg.addr, cache_reg.len); return -EBUSY; } dev_notice(&vdev->dev, "Cache len: 0x%llx @ 0x%llx\n", cache_reg.len, cache_reg.addr); pgmap = devm_kzalloc(&vdev->dev, sizeof(*pgmap), GFP_KERNEL); if (!pgmap) return -ENOMEM; pgmap->type = MEMORY_DEVICE_FS_DAX; /* Ideally we would directly use the PCI BAR resource but * devm_memremap_pages() wants its own copy in pgmap. So * initialize a struct resource from scratch (only the start * and end fields will be used). */ pgmap->range = (struct range) { .start = (phys_addr_t) cache_reg.addr, .end = (phys_addr_t) cache_reg.addr + cache_reg.len - 1, }; pgmap->nr_range = 1; fs->window_kaddr = devm_memremap_pages(&vdev->dev, pgmap); if (IS_ERR(fs->window_kaddr)) return PTR_ERR(fs->window_kaddr); fs->window_phys_addr = (phys_addr_t) cache_reg.addr; fs->window_len = (phys_addr_t) cache_reg.len; dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr, cache_reg.len); fs->dax_dev = no_free_ptr(dax_dev); return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax, fs->dax_dev); } static int virtio_fs_probe(struct virtio_device *vdev) { struct virtio_fs *fs; int ret; fs = kzalloc_obj(*fs); if (!fs) return -ENOMEM; kobject_init(&fs->kobj, &virtio_fs_ktype); vdev->priv = fs; ret = virtio_fs_read_tag(vdev, fs); if (ret < 0) goto out; ret = virtio_fs_setup_vqs(vdev, fs); if (ret < 0) goto out; virtio_fs_map_queues(vdev, fs); ret = virtio_fs_setup_dax(vdev, fs); if (ret < 0) goto out_vqs; /* Bring the device online in case the filesystem is mounted and * requests need to be sent before we return. */ virtio_device_ready(vdev); ret = virtio_fs_add_instance(vdev, fs); if (ret < 0) goto out_vqs; return 0; out_vqs: virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev); out: vdev->priv = NULL; kobject_put(&fs->kobj); return ret; } static void virtio_fs_stop_all_queues(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; spin_lock(&fsvq->lock); fsvq->connected = false; spin_unlock(&fsvq->lock); } } static void virtio_fs_remove(struct virtio_device *vdev) { struct virtio_fs *fs = vdev->priv; mutex_lock(&virtio_fs_mutex); /* This device is going away. No one should get new reference */ list_del_init(&fs->list); virtio_fs_delete_queues_sysfs(fs); sysfs_remove_link(&fs->kobj, "device"); kobject_put(fs->mqs_kobj); kobject_del(&fs->kobj); virtio_fs_stop_all_queues(fs); virtio_fs_drain_all_queues_locked(fs); virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev); vdev->priv = NULL; /* Put device reference on virtio_fs object */ virtio_fs_put_locked(fs); mutex_unlock(&virtio_fs_mutex); } #ifdef CONFIG_PM_SLEEP static int virtio_fs_freeze(struct virtio_device *vdev) { /* TODO need to save state here */ pr_warn("virtio-fs: suspend/resume not yet supported\n"); return -EOPNOTSUPP; } static int virtio_fs_restore(struct virtio_device *vdev) { /* TODO need to restore state here */ return 0; } #endif /* CONFIG_PM_SLEEP */ static const struct virtio_device_id id_table[] = { { VIRTIO_ID_FS, VIRTIO_DEV_ANY_ID }, {}, }; static const unsigned int feature_table[] = {}; static struct virtio_driver virtio_fs_driver = { .driver.name = KBUILD_MODNAME, .id_table = id_table, .feature_table = feature_table, .feature_table_size = ARRAY_SIZE(feature_table), .probe = virtio_fs_probe, .remove = virtio_fs_remove, #ifdef CONFIG_PM_SLEEP .freeze = virtio_fs_freeze, .restore = virtio_fs_restore, #endif }; static void virtio_fs_send_forget(struct fuse_iqueue *fiq, struct fuse_forget_link *link) { struct virtio_fs_forget *forget; struct virtio_fs_forget_req *req; struct virtio_fs *fs = fiq->priv; struct virtio_fs_vq *fsvq = &fs->vqs[VQ_HIPRIO]; u64 unique = fuse_get_unique(fiq); /* Allocate a buffer for the request */ forget = kmalloc_obj(*forget, GFP_NOFS | __GFP_NOFAIL); req = &forget->req; req->ih = (struct fuse_in_header){ .opcode = FUSE_FORGET, .nodeid = link->forget_one.nodeid, .unique = unique, .len = sizeof(*req), }; req->arg = (struct fuse_forget_in){ .nlookup = link->forget_one.nlookup, }; send_forget_request(fsvq, forget, false); kfree(link); } static void virtio_fs_send_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { /* * TODO interrupts. * * Normal fs operations on a local filesystems aren't interruptible. * Exceptions are blocking lock operations; for example fcntl(F_SETLKW) * with shared lock between host and guest. */ } /* Count number of scatter-gather elements required */ static unsigned int sg_count_fuse_folios(struct fuse_folio_desc *folio_descs, unsigned int num_folios, unsigned int total_len) { unsigned int i; unsigned int this_len; for (i = 0; i < num_folios && total_len; i++) { this_len = min(folio_descs[i].length, total_len); total_len -= this_len; } return i; } /* Return the number of scatter-gather list elements required */ static unsigned int sg_count_fuse_req(struct fuse_req *req) { struct fuse_args *args = req->args; struct fuse_args_pages *ap = container_of(args, typeof(*ap), args); unsigned int size, total_sgs = 1 /* fuse_in_header */; if (args->in_numargs - args->in_pages) total_sgs += 1; if (args->in_pages) { size = args->in_args[args->in_numargs - 1].size; total_sgs += sg_count_fuse_folios(ap->descs, ap->num_folios, size); } if (!test_bit(FR_ISREPLY, &req->flags)) return total_sgs; total_sgs += 1 /* fuse_out_header */; if (args->out_numargs - args->out_pages) total_sgs += 1; if (args->out_pages) { size = args->out_args[args->out_numargs - 1].size; total_sgs += sg_count_fuse_folios(ap->descs, ap->num_folios, size); } return total_sgs; } /* Add folios to scatter-gather list and return number of elements used */ static unsigned int sg_init_fuse_folios(struct scatterlist *sg, struct folio **folios, struct fuse_folio_desc *folio_descs, unsigned int num_folios, unsigned int total_len) { unsigned int i; unsigned int this_len; for (i = 0; i < num_folios && total_len; i++) { sg_init_table(&sg[i], 1); this_len = min(folio_descs[i].length, total_len); sg_set_folio(&sg[i], folios[i], this_len, folio_descs[i].offset); total_len -= this_len; } return i; } /* Add args to scatter-gather list and return number of elements used */ static unsigned int sg_init_fuse_args(struct scatterlist *sg, struct fuse_req *req, struct fuse_arg *args, unsigned int numargs, bool argpages, void *argbuf, unsigned int *len_used) { struct fuse_args_pages *ap = container_of(req->args, typeof(*ap), args); unsigned int total_sgs = 0; unsigned int len; len = fuse_len_args(numargs - argpages, args); if (len) sg_init_one(&sg[total_sgs++], argbuf, len); if (argpages) total_sgs += sg_init_fuse_folios(&sg[total_sgs], ap->folios, ap->descs, ap->num_folios, args[numargs - 1].size); if (len_used) *len_used = len; return total_sgs; } /* Add a request to a virtqueue and kick the device */ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, struct fuse_req *req, bool in_flight, gfp_t gfp) { /* requests need at least 4 elements */ struct scatterlist *stack_sgs[6]; struct scatterlist stack_sg[ARRAY_SIZE(stack_sgs)]; struct scatterlist **sgs = stack_sgs; struct scatterlist *sg = stack_sg; struct virtqueue *vq; struct fuse_args *args = req->args; unsigned int argbuf_used = 0; unsigned int out_sgs = 0; unsigned int in_sgs = 0; unsigned int total_sgs; unsigned int i, hash; int ret; bool notify; struct fuse_pqueue *fpq; /* Does the sglist fit on the stack? */ total_sgs = sg_count_fuse_req(req); if (total_sgs > ARRAY_SIZE(stack_sgs)) { sgs = kmalloc_objs(sgs[0], total_sgs, gfp); sg = kmalloc_objs(sg[0], total_sgs, gfp); if (!sgs || !sg) { ret = -ENOMEM; goto out; } } /* Use a bounce buffer since stack args cannot be mapped */ ret = copy_args_to_argbuf(req, gfp); if (ret < 0) goto out; /* Request elements */ sg_init_one(&sg[out_sgs++], &req->in.h, sizeof(req->in.h)); out_sgs += sg_init_fuse_args(&sg[out_sgs], req, (struct fuse_arg *)args->in_args, args->in_numargs, args->in_pages, req->argbuf, &argbuf_used); /* Reply elements */ if (test_bit(FR_ISREPLY, &req->flags)) { sg_init_one(&sg[out_sgs + in_sgs++], &req->out.h, sizeof(req->out.h)); in_sgs += sg_init_fuse_args(&sg[out_sgs + in_sgs], req, args->out_args, args->out_numargs, args->out_pages, req->argbuf + argbuf_used, NULL); } WARN_ON(out_sgs + in_sgs != total_sgs); for (i = 0; i < total_sgs; i++) sgs[i] = &sg[i]; spin_lock(&fsvq->lock); if (!fsvq->connected) { spin_unlock(&fsvq->lock); ret = -ENOTCONN; goto out; } vq = fsvq->vq; ret = virtqueue_add_sgs(vq, sgs, out_sgs, in_sgs, req, GFP_ATOMIC); if (ret < 0) { spin_unlock(&fsvq->lock); goto out; } /* Request successfully sent. */ fpq = &fsvq->fud->pq; hash = fuse_req_hash(req->in.h.unique); spin_lock(&fpq->lock); list_add_tail(&req->list, &fpq->processing[hash]); spin_unlock(&fpq->lock); set_bit(FR_SENT, &req->flags); /* matches barrier in request_wait_answer() */ smp_mb__after_atomic(); if (!in_flight) inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); if (notify) virtqueue_notify(vq); out: if (ret < 0 && req->argbuf) { kfree(req->argbuf); req->argbuf = NULL; } if (sgs != stack_sgs) { kfree(sgs); kfree(sg); } return ret; } static void virtio_fs_send_req(struct fuse_iqueue *fiq, struct fuse_req *req) { unsigned int queue_id; struct virtio_fs *fs; struct virtio_fs_vq *fsvq; int ret; fuse_request_assign_unique(fiq, req); clear_bit(FR_PENDING, &req->flags); fs = fiq->priv; queue_id = fs->mq_map[raw_smp_processor_id()]; pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u queue_id %u\n", __func__, req->in.h.opcode, req->in.h.unique, req->in.h.nodeid, req->in.h.len, fuse_len_args(req->args->out_numargs, req->args->out_args), queue_id); fsvq = &fs->vqs[queue_id]; ret = virtio_fs_enqueue_req(fsvq, req, false, GFP_ATOMIC); if (ret < 0) { if (ret == -ENOSPC) { /* * Virtqueue full. Retry submission from worker * context as we might be holding fc->chan->bg_lock. */ spin_lock(&fsvq->lock); list_add_tail(&req->list, &fsvq->queued_reqs); inc_in_flight_req(fsvq); spin_unlock(&fsvq->lock); return; } req->out.h.error = ret; pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret); /* Can't end request in submission context. Use a worker */ spin_lock(&fsvq->lock); list_add_tail(&req->list, &fsvq->end_reqs); schedule_work(&fsvq->dispatch_work); spin_unlock(&fsvq->lock); return; } } static const struct fuse_iqueue_ops virtio_fs_fiq_ops = { .send_forget = virtio_fs_send_forget, .send_interrupt = virtio_fs_send_interrupt, .send_req = virtio_fs_send_req, .release = virtio_fs_fiq_release, }; static inline void virtio_fs_ctx_set_defaults(struct fuse_fs_context *ctx) { ctx->rootmode = S_IFDIR; ctx->default_permissions = 1; ctx->allow_other = 1; ctx->max_read = UINT_MAX; ctx->blksize = 512; ctx->destroy = true; ctx->no_control = true; ctx->no_force_umount = true; } static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc) { struct fuse_mount *fm = get_fuse_mount_super(sb); struct fuse_conn *fc = fm->fc; struct virtio_fs *fs = fc->chan->iq.priv; struct fuse_fs_context *ctx = fsc->fs_private; unsigned int i; int err; virtio_fs_ctx_set_defaults(ctx); mutex_lock(&virtio_fs_mutex); /* After holding mutex, make sure virtiofs device is still there. * Though we are holding a reference to it, drive ->remove might * still have cleaned up virtual queues. In that case bail out. */ err = -EINVAL; if (list_empty(&fs->list)) { pr_info("virtio-fs: tag <%s> not found\n", fs->tag); goto err; } err = -ENOMEM; /* Allocate fuse_dev for hiprio and notification queues */ for (i = 0; i < fs->nvqs; i++) { struct virtio_fs_vq *fsvq = &fs->vqs[i]; fsvq->fud = fuse_dev_alloc(); if (!fsvq->fud) goto err_free_fuse_devs; } if (ctx->dax_mode != FUSE_DAX_NEVER) { if (ctx->dax_mode == FUSE_DAX_ALWAYS && !fs->dax_dev) { err = -EINVAL; pr_err("virtio-fs: dax can't be enabled as filesystem" " device does not support it.\n"); goto err_free_fuse_devs; } ctx->dax_dev = fs->dax_dev; } err = fuse_fill_super_common(sb, ctx); if (err < 0) goto err_free_fuse_devs; for (i = 0; i < fs->nvqs; i++) { struct virtio_fs_vq *fsvq = &fs->vqs[i]; fuse_dev_install(fsvq->fud, fc->chan); } /* Previous unmount will stop all queues. Start these again */ virtio_fs_start_all_queues(fs); fuse_send_init(fm); mutex_unlock(&virtio_fs_mutex); return 0; err_free_fuse_devs: virtio_fs_free_devs(fs); err: mutex_unlock(&virtio_fs_mutex); return err; } static void virtio_fs_conn_destroy(struct fuse_mount *fm) { struct fuse_conn *fc = fm->fc; struct virtio_fs *vfs = fc->chan->iq.priv; struct virtio_fs_vq *fsvq = &vfs->vqs[VQ_HIPRIO]; /* Stop dax worker. Soon evict_inodes() will be called which * will free all memory ranges belonging to all inodes. */ if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_cancel_work(fc); /* Stop forget queue. Soon destroy will be sent */ spin_lock(&fsvq->lock); fsvq->connected = false; spin_unlock(&fsvq->lock); virtio_fs_drain_all_queues(vfs); fuse_conn_destroy(fm); /* fuse_conn_destroy() must have sent destroy. Stop all queues * and drain one more time and free fuse devices. Freeing fuse * devices will drop their reference on fuse_conn and that in * turn will drop its reference on virtio_fs object. */ virtio_fs_stop_all_queues(vfs); virtio_fs_drain_all_queues(vfs); virtio_fs_free_devs(vfs); } static void virtio_kill_sb(struct super_block *sb) { struct fuse_mount *fm = get_fuse_mount_super(sb); bool last; /* If mount failed, we can still be called without any fc */ if (sb->s_root) { last = fuse_mount_remove(fm); if (last) virtio_fs_conn_destroy(fm); } kill_anon_super(sb); fuse_mount_destroy(fm); } static int virtio_fs_test_super(struct super_block *sb, struct fs_context *fsc) { struct fuse_mount *fsc_fm = fsc->s_fs_info; struct fuse_mount *sb_fm = get_fuse_mount_super(sb); return fsc_fm->fc->chan->iq.priv == sb_fm->fc->chan->iq.priv; } static int virtio_fs_get_tree(struct fs_context *fsc) { struct virtio_fs *fs; struct super_block *sb; struct fuse_conn *fc = NULL; struct fuse_mount *fm; unsigned int virtqueue_size; struct fuse_chan *fch __free(fuse_chan_free) = fuse_chan_new(); int err = -EIO; if (!fch) return -ENOMEM; if (!fsc->source) return invalf(fsc, "No source specified"); /* This gets a reference on virtio_fs object. This ptr gets installed * in chan->iq->priv. Once fuse_conn is going away, it calls ->put() * to drop the reference to this object. */ fs = virtio_fs_find_instance(fsc->source); if (!fs) { pr_info("virtio-fs: tag <%s> not found\n", fsc->source); return -EINVAL; } virtqueue_size = virtqueue_get_vring_size(fs->vqs[VQ_REQUEST].vq); if (WARN_ON(virtqueue_size <= FUSE_HEADER_OVERHEAD)) goto out_err; err = -ENOMEM; fc = kzalloc_obj(struct fuse_conn); if (!fc) goto out_err; fm = kzalloc_obj(struct fuse_mount); if (!fm) goto out_err; fuse_iqueue_init(&fch->iq, &virtio_fs_fiq_ops, fs); fuse_conn_init(fc, fm, fsc->user_ns, no_free_ptr(fch)); fc->release = fuse_free_conn; fc->delete_stale = true; fc->auto_submounts = true; fc->sync_fs = true; fc->use_pages_for_kvec_io = true; /* Tell FUSE to split requests that exceed the virtqueue's size */ fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit, virtqueue_size - FUSE_HEADER_OVERHEAD); fsc->s_fs_info = fm; sb = sget_fc(fsc, virtio_fs_test_super, set_anon_super_fc); if (fsc->s_fs_info) fuse_mount_destroy(fm); if (IS_ERR(sb)) return PTR_ERR(sb); if (!sb->s_root) { err = virtio_fs_fill_super(sb, fsc); if (err) { deactivate_locked_super(sb); return err; } sb->s_flags |= SB_ACTIVE; } WARN_ON(fsc->root); fsc->root = dget(sb->s_root); return 0; out_err: kfree(fc); virtio_fs_put(fs); return err; } static const struct fs_context_operations virtio_fs_context_ops = { .free = virtio_fs_free_fsc, .parse_param = virtio_fs_parse_param, .get_tree = virtio_fs_get_tree, }; static int virtio_fs_init_fs_context(struct fs_context *fsc) { struct fuse_fs_context *ctx; if (fsc->purpose == FS_CONTEXT_FOR_SUBMOUNT) return fuse_init_fs_context_submount(fsc); ctx = kzalloc_obj(struct fuse_fs_context); if (!ctx) return -ENOMEM; fsc->fs_private = ctx; fsc->ops = &virtio_fs_context_ops; return 0; } static struct file_system_type virtio_fs_type = { .owner = THIS_MODULE, .name = "virtiofs", .init_fs_context = virtio_fs_init_fs_context, .kill_sb = virtio_kill_sb, .fs_flags = FS_ALLOW_IDMAP, }; static int virtio_fs_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj); add_uevent_var(env, "TAG=%s", fs->tag); return 0; } static const struct kset_uevent_ops virtio_fs_uevent_ops = { .uevent = virtio_fs_uevent, }; static int __init virtio_fs_sysfs_init(void) { virtio_fs_kset = kset_create_and_add("virtiofs", &virtio_fs_uevent_ops, fs_kobj); if (!virtio_fs_kset) return -ENOMEM; return 0; } static void virtio_fs_sysfs_exit(void) { kset_unregister(virtio_fs_kset); virtio_fs_kset = NULL; } static int __init virtio_fs_init(void) { int ret; ret = virtio_fs_sysfs_init(); if (ret < 0) return ret; ret = register_virtio_driver(&virtio_fs_driver); if (ret < 0) goto sysfs_exit; ret = register_filesystem(&virtio_fs_type); if (ret < 0) goto unregister_virtio_driver; return 0; unregister_virtio_driver: unregister_virtio_driver(&virtio_fs_driver); sysfs_exit: virtio_fs_sysfs_exit(); return ret; } module_init(virtio_fs_init); static void __exit virtio_fs_exit(void) { unregister_filesystem(&virtio_fs_type); unregister_virtio_driver(&virtio_fs_driver); virtio_fs_sysfs_exit(); } module_exit(virtio_fs_exit); MODULE_AUTHOR("Stefan Hajnoczi <stefanha@redhat.com>"); MODULE_DESCRIPTION("Virtio Filesystem"); MODULE_LICENSE("GPL"); MODULE_ALIAS_FS(KBUILD_MODNAME); MODULE_DEVICE_TABLE(virtio, id_table); |
| 4 2 4 2 2 2 30 30 30 21 31 84 14 1 85 5 5 5 9 1 1 2 1 2 1 1 2 2 1 1 1 1 1 1 4 31 2 4 2 2 1 2 1 1 1 1 2 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 | // 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; snd_use_lock_t *lock __free(seq_oss_use_lock) = NULL; if (!snd_seq_oss_process_event(dp, (union evrec *)ev, &tmpev, &lock)) 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; } |
| 59 95 86 86 130 130 126 190 12 190 19 81 69 156 5 20 56 66 128 83 59 64 130 73 6 19 124 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XFRM_HASH_H #define _XFRM_HASH_H #include <linux/xfrm.h> #include <linux/socket.h> #include <linux/jhash.h> static inline unsigned int __xfrm4_addr_hash(const xfrm_address_t *addr) { return ntohl(addr->a4); } static inline unsigned int __xfrm6_addr_hash(const xfrm_address_t *addr) { return jhash2((__force u32 *)addr->a6, 4, 0); } static inline unsigned int __xfrm4_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4; return ntohl((__force __be32)sum); } static inline unsigned int __xfrm6_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { return __xfrm6_addr_hash(daddr) ^ __xfrm6_addr_hash(saddr); } static inline u32 __bits2mask32(__u8 bits) { u32 mask32 = 0xffffffff; if (bits == 0) mask32 = 0; else if (bits < 32) mask32 <<= (32 - bits); return mask32; } static inline unsigned int __xfrm4_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return jhash_2words(ntohl(daddr->a4) & __bits2mask32(dbits), ntohl(saddr->a4) & __bits2mask32(sbits), 0); } static inline unsigned int __xfrm6_pref_hash(const xfrm_address_t *addr, __u8 prefixlen) { unsigned int pdw; unsigned int pbi; u32 initval = 0; pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pbi) { __be32 mask; mask = htonl((0xffffffff) << (32 - pbi)); initval = (__force u32)(addr->a6[pdw] & mask); } return jhash2((__force u32 *)addr->a6, pdw, initval); } static inline unsigned int __xfrm6_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return __xfrm6_pref_hash(daddr, dbits) ^ __xfrm6_pref_hash(saddr, sbits); } static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family, unsigned int hmask) { unsigned int h = family ^ reqid; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_src_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask) { unsigned int h = family; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, unsigned int hmask) { unsigned int h = (__force u32)spi ^ proto; switch (family) { case AF_INET: h ^= __xfrm4_addr_hash(daddr); break; case AF_INET6: h ^= __xfrm6_addr_hash(daddr); break; } return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } static inline unsigned int __xfrm_seq_hash(u32 seq, unsigned int hmask) { unsigned int h = seq; return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } static inline unsigned int __idx_hash(u32 index, unsigned int hmask) { return (index ^ (index >> 8)) & hmask; } static inline unsigned int __sel_hash(const struct xfrm_selector *sel, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { const xfrm_address_t *daddr = &sel->daddr; const xfrm_address_t *saddr = &sel->saddr; unsigned int h = 0; switch (family) { case AF_INET: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } static inline unsigned int __addr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { unsigned int h = 0; switch (family) { case AF_INET: h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } struct hlist_head *xfrm_hash_alloc(unsigned int sz); void xfrm_hash_free(struct hlist_head *n, unsigned int sz); #endif /* _XFRM_HASH_H */ |
| 2 2 2 2 73 73 73 73 73 73 3 2 2 3 1 2 1 1 34 34 34 4 4 34 34 34 34 34 34 31 4 31 31 31 31 31 74 74 74 74 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/seq_file.h> #include <net/protocol.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" /* Internal logging interface, which relies on the real LOG target modules */ #define NFLOGGER_NAME_LEN 64 int sysctl_nf_log_all_netns __read_mostly; EXPORT_SYMBOL(sysctl_nf_log_all_netns); static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; static DEFINE_MUTEX(nf_log_mutex); #define nft_log_dereference(logger) \ rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex)) static struct nf_logger *__find_logger(int pf, const char *str_logger) { struct nf_logger *log; int i; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { log = nft_log_dereference(loggers[pf][i]); if (!log) continue; if (!strncasecmp(str_logger, log->name, strlen(log->name))) return log; } return NULL; } int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) { const struct nf_logger *log; if (pf == NFPROTO_UNSPEC || pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EOPNOTSUPP; mutex_lock(&nf_log_mutex); log = nft_log_dereference(net->nf.nf_loggers[pf]); if (log == NULL) rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_set); void nf_log_unset(struct net *net, const struct nf_logger *logger) { int i; const struct nf_logger *log; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(net->nf.nf_loggers[i]); if (log == logger) RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL); } mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unset); /* return EEXIST if the same logger is registered, 0 on success. */ int nf_log_register(u_int8_t pf, struct nf_logger *logger) { int i; int ret = 0; if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { if (rcu_access_pointer(loggers[i][logger->type])) { ret = -EBUSY; goto unlock; } } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(loggers[i][logger->type], logger); } else { if (rcu_access_pointer(loggers[pf][logger->type])) { ret = -EBUSY; goto unlock; } rcu_assign_pointer(loggers[pf][logger->type], logger); } unlock: mutex_unlock(&nf_log_mutex); return ret; } EXPORT_SYMBOL(nf_log_register); void nf_log_unregister(struct nf_logger *logger) { const struct nf_logger *log; int i; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(loggers[i][logger->type]); if (log == logger) RCU_INIT_POINTER(loggers[i][logger->type], NULL); } mutex_unlock(&nf_log_mutex); synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister); /** * nf_log_is_registered - Check if any logger is registered for a given * protocol family. * * @pf: Protocol family * * Returns: true if at least one logger is active for @pf, false otherwise. */ bool nf_log_is_registered(u_int8_t pf) { int i; if (pf >= NFPROTO_NUMPROTO) { WARN_ON_ONCE(1); return false; } for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (rcu_access_pointer(loggers[pf][i])) return true; } return false; } EXPORT_SYMBOL(nf_log_is_registered); int nf_log_bind_pf(struct net *net, u_int8_t pf, const struct nf_logger *logger) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (__find_logger(pf, logger->name) == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_bind_pf); void nf_log_unbind_pf(struct net *net, u_int8_t pf) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return; mutex_lock(&nf_log_mutex); RCU_INIT_POINTER(net->nf.nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unbind_pf); int nf_logger_find_get(int pf, enum nf_log_type type) { struct nf_logger *logger; int ret = -ENOENT; if (pf >= ARRAY_SIZE(loggers)) return -EINVAL; if (type >= NF_LOG_TYPE_MAX) return -EINVAL; if (pf == NFPROTO_INET) { ret = nf_logger_find_get(NFPROTO_IPV4, type); if (ret < 0) return ret; ret = nf_logger_find_get(NFPROTO_IPV6, type); if (ret < 0) { nf_logger_put(NFPROTO_IPV4, type); return ret; } return 0; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (logger == NULL) goto out; if (try_module_get(logger->me)) ret = 0; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_logger_find_get); void nf_logger_put(int pf, enum nf_log_type type) { struct nf_logger *logger; if (pf == NFPROTO_INET) { nf_logger_put(NFPROTO_IPV4, type); nf_logger_put(NFPROTO_IPV6, type); return; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (!logger) WARN_ON_ONCE(1); else module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); void nf_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); if (loginfo != NULL) logger = rcu_dereference(loggers[pf][loginfo->type]); else logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_packet); void nf_log_trace(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_trace); #define S_SIZE (1024 - (sizeof(unsigned int) + 1)) struct nf_log_buf { unsigned int count; char buf[S_SIZE + 1]; }; static struct nf_log_buf emergency, *emergency_ptr = &emergency; __printf(2, 3) int nf_log_buf_add(struct nf_log_buf *m, const char *f, ...) { va_list args; int len; if (likely(m->count < S_SIZE)) { va_start(args, f); len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args); va_end(args); if (likely(m->count + len < S_SIZE)) { m->count += len; return 0; } } m->count = S_SIZE; printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n"); return -1; } EXPORT_SYMBOL_GPL(nf_log_buf_add); struct nf_log_buf *nf_log_buf_open(void) { struct nf_log_buf *m = kmalloc_obj(*m, GFP_ATOMIC); if (unlikely(!m)) { local_bh_disable(); do { m = xchg(&emergency_ptr, NULL); } while (!m); } m->count = 0; return m; } EXPORT_SYMBOL_GPL(nf_log_buf_open); void nf_log_buf_close(struct nf_log_buf *m) { m->buf[m->count] = 0; printk("%s\n", m->buf); if (likely(m != &emergency)) kfree(m); else { emergency_ptr = m; local_bh_enable(); } } EXPORT_SYMBOL_GPL(nf_log_buf_close); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { struct net *net = seq_file_net(s); (*pos)++; if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void seq_stop(struct seq_file *s, void *v) { mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) { loff_t *pos = v; const struct nf_logger *logger; int i; struct net *net = seq_file_net(s); logger = nft_log_dereference(net->nf.nf_loggers[*pos]); if (!logger) seq_printf(s, "%2lld NONE (", *pos); else seq_printf(s, "%2lld %s (", *pos, logger->name); if (seq_has_overflowed(s)) return -ENOSPC; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[*pos][i] == NULL) continue; logger = nft_log_dereference(loggers[*pos][i]); seq_puts(s, logger->name); if (i == 0 && loggers[*pos][i + 1] != NULL) seq_puts(s, ","); if (seq_has_overflowed(s)) return -ENOSPC; } seq_puts(s, ")\n"); if (seq_has_overflowed(s)) return -ENOSPC; return 0; } static const struct seq_operations nflog_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO]; static struct ctl_table_header *nf_log_sysctl_fhdr; static struct ctl_table nf_log_sysctl_ftable[] = { { .procname = "nf_log_all_netns", .data = &sysctl_nf_log_all_netns, .maxlen = sizeof(sysctl_nf_log_all_netns), .mode = 0644, .proc_handler = proc_dointvec, }, }; static int nf_log_proc_dostring(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; /* proc_dostring() can append to existing strings, so we need to * initialize it as an empty string. */ buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) return r; if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(net, tindex); return 0; } mutex_lock(&nf_log_mutex); logger = __find_logger(tindex, buf); if (logger == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { struct ctl_table tmp = *table; tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) strscpy(buf, "NONE", sizeof(buf)); else strscpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; } static int netfilter_log_sysctl_init(struct net *net) { int i; struct ctl_table *table; table = nf_log_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(nf_log_sysctl_table, sizeof(nf_log_sysctl_table), GFP_KERNEL); if (!table) goto err_alloc; } else { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { snprintf(nf_log_sysctl_fnames[i], 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = nf_log_proc_dostring; nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i; } nf_log_sysctl_fhdr = register_net_sysctl(net, "net/netfilter", nf_log_sysctl_ftable); if (!nf_log_sysctl_fhdr) goto err_freg; } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) table[i].extra2 = net; net->nf.nf_log_dir_header = register_net_sysctl_sz(net, "net/netfilter/nf_log", table, ARRAY_SIZE(nf_log_sysctl_table)); if (!net->nf.nf_log_dir_header) goto err_reg; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); err_freg: err_alloc: return -ENOMEM; } static void netfilter_log_sysctl_exit(struct net *net) { const struct ctl_table *table; table = net->nf.nf_log_dir_header->ctl_table_arg; unregister_net_sysctl_table(net->nf.nf_log_dir_header); if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); } #else static int netfilter_log_sysctl_init(struct net *net) { return 0; } static void netfilter_log_sysctl_exit(struct net *net) { } #endif /* CONFIG_SYSCTL */ static int __net_init nf_log_net_init(struct net *net) { int ret = -ENOMEM; #ifdef CONFIG_PROC_FS if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter, &nflog_seq_ops, sizeof(struct seq_net_private))) return ret; #endif ret = netfilter_log_sysctl_init(net); if (ret < 0) goto out_sysctl; return 0; out_sysctl: #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif return ret; } static void __net_exit nf_log_net_exit(struct net *net) { netfilter_log_sysctl_exit(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif } static struct pernet_operations nf_log_net_ops = { .init = nf_log_net_init, .exit = nf_log_net_exit, }; int __init netfilter_log_init(void) { return register_pernet_subsys(&nf_log_net_ops); } |
| 3 1 1 1 1 7 7 7 3 3 3 3 2 2 6 6 7 87 87 87 2 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 3 3 3 3 3 3 3 3 4 86 87 86 87 86 87 87 87 6 5 6 6 5 6 4 4 87 87 14 14 14 14 14 14 14 14 14 14 14 14 14 946 154 805 173 172 174 29 174 176 15 14 15 13 15 31 31 31 31 19 19 4 19 972 972 971 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Helpers for formatting and printing strings * * Copyright 31 August 2008 James Bottomley * Copyright (C) 2013, Intel Corporation */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/hex.h> #include <linux/limits.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/string_helpers.h> #include <kunit/test.h> #include <kunit/test-bug.h> /** * string_get_size - get the size in the specified units * @size: The size to be converted in blocks * @blk_size: Size of the block (use 1 for size in bytes) * @units: Units to use (powers of 1000 or 1024), whether to include space separator * @buf: buffer to format to * @len: length of buffer * * This function returns a string formatted to 3 significant figures * giving the size in the required units. @buf should have room for * at least 9 bytes and will always be zero terminated. * * Return value: number of characters of output that would have been written * (which may be greater than len, if output was truncated). */ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units, char *buf, int len) { enum string_size_units units_base = units & STRING_UNITS_MASK; static const char *const units_10[] = { "", "k", "M", "G", "T", "P", "E", "Z", "Y", }; static const char *const units_2[] = { "", "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi", }; static const char *const *const units_str[] = { [STRING_UNITS_10] = units_10, [STRING_UNITS_2] = units_2, }; static const unsigned int divisor[] = { [STRING_UNITS_10] = 1000, [STRING_UNITS_2] = 1024, }; static const unsigned int rounding[] = { 500, 50, 5 }; int i = 0, j; u32 remainder = 0, sf_cap; char tmp[12]; const char *unit; tmp[0] = '\0'; if (blk_size == 0) size = 0; if (size == 0) goto out; /* This is Napier's algorithm. Reduce the original block size to * * coefficient * divisor[units_base]^i * * we do the reduction so both coefficients are just under 32 bits so * that multiplying them together won't overflow 64 bits and we keep * as much precision as possible in the numbers. * * Note: it's safe to throw away the remainders here because all the * precision is in the coefficients. */ while (blk_size >> 32) { do_div(blk_size, divisor[units_base]); i++; } while (size >> 32) { do_div(size, divisor[units_base]); i++; } /* now perform the actual multiplication keeping i as the sum of the * two logarithms */ size *= blk_size; /* and logarithmically reduce it until it's just under the divisor */ while (size >= divisor[units_base]) { remainder = do_div(size, divisor[units_base]); i++; } /* work out in j how many digits of precision we need from the * remainder */ sf_cap = size; for (j = 0; sf_cap*10 < 1000; j++) sf_cap *= 10; if (units_base == STRING_UNITS_2) { /* express the remainder as a decimal. It's currently the * numerator of a fraction whose denominator is * divisor[units_base], which is 1 << 10 for STRING_UNITS_2 */ remainder *= 1000; remainder >>= 10; } /* add a 5 to the digit below what will be printed to ensure * an arithmetical round up and carry it through to size */ remainder += rounding[j]; if (remainder >= 1000) { remainder -= 1000; size += 1; } if (j) { snprintf(tmp, sizeof(tmp), ".%03u", remainder); tmp[j+1] = '\0'; } out: if (i >= ARRAY_SIZE(units_2)) unit = "UNK"; else unit = units_str[units_base][i]; return snprintf(buf, len, "%u%s%s%s%s", (u32)size, tmp, (units & STRING_UNITS_NO_SPACE) ? "" : " ", unit, (units & STRING_UNITS_NO_BYTES) ? "" : "B"); } EXPORT_SYMBOL(string_get_size); int parse_int_array(const char *buf, size_t count, int **array) { int *ints, nints; get_options(buf, 0, &nints); if (!nints) return -ENOENT; ints = kzalloc_objs(*ints, nints + 1); if (!ints) return -ENOMEM; get_options(buf, nints + 1, ints); *array = ints; return 0; } EXPORT_SYMBOL(parse_int_array); /** * parse_int_array_user - Split string into a sequence of integers * @from: The user space buffer to read from * @count: The maximum number of bytes to read * @array: Returned pointer to sequence of integers * * On success @array is allocated and initialized with a sequence of * integers extracted from the @from plus an additional element that * begins the sequence and specifies the integers count. * * Caller takes responsibility for freeing @array when it is no longer * needed. */ int parse_int_array_user(const char __user *from, size_t count, int **array) { char *buf; int ret; buf = memdup_user_nul(from, count); if (IS_ERR(buf)) return PTR_ERR(buf); ret = parse_int_array(buf, count, array); kfree(buf); return ret; } EXPORT_SYMBOL(parse_int_array_user); static bool unescape_space(char **src, char **dst) { char *p = *dst, *q = *src; switch (*q) { case 'n': *p = '\n'; break; case 'r': *p = '\r'; break; case 't': *p = '\t'; break; case 'v': *p = '\v'; break; case 'f': *p = '\f'; break; default: return false; } *dst += 1; *src += 1; return true; } static bool unescape_octal(char **src, char **dst) { char *p = *dst, *q = *src; u8 num; if (isodigit(*q) == 0) return false; num = (*q++) & 7; while (num < 32 && isodigit(*q) && (q - *src < 3)) { num <<= 3; num += (*q++) & 7; } *p = num; *dst += 1; *src = q; return true; } static bool unescape_hex(char **src, char **dst) { char *p = *dst, *q = *src; int digit; u8 num; if (*q++ != 'x') return false; num = digit = hex_to_bin(*q++); if (digit < 0) return false; digit = hex_to_bin(*q); if (digit >= 0) { q++; num = (num << 4) | digit; } *p = num; *dst += 1; *src = q; return true; } static bool unescape_special(char **src, char **dst) { char *p = *dst, *q = *src; switch (*q) { case '\"': *p = '\"'; break; case '\\': *p = '\\'; break; case 'a': *p = '\a'; break; case 'e': *p = '\e'; break; default: return false; } *dst += 1; *src += 1; return true; } /** * string_unescape - unquote characters in the given string * @src: source buffer (escaped) * @dst: destination buffer (unescaped) * @size: size of the destination buffer (0 to unlimit) * @flags: combination of the flags. * * Description: * The function unquotes characters in the given string. * * Because the size of the output will be the same as or less than the size of * the input, the transformation may be performed in place. * * Caller must provide valid source and destination pointers. Be aware that * destination buffer will always be NULL-terminated. Source string must be * NULL-terminated as well. The supported flags are:: * * UNESCAPE_SPACE: * '\f' - form feed * '\n' - new line * '\r' - carriage return * '\t' - horizontal tab * '\v' - vertical tab * UNESCAPE_OCTAL: * '\NNN' - byte with octal value NNN (1 to 3 digits) * UNESCAPE_HEX: * '\xHH' - byte with hexadecimal value HH (1 to 2 digits) * UNESCAPE_SPECIAL: * '\"' - double quote * '\\' - backslash * '\a' - alert (BEL) * '\e' - escape * UNESCAPE_ANY: * all previous together * * Return: * The amount of the characters processed to the destination buffer excluding * trailing '\0' is returned. */ int string_unescape(char *src, char *dst, size_t size, unsigned int flags) { char *out = dst; if (!size) size = SIZE_MAX; while (*src && --size) { if (src[0] == '\\' && src[1] != '\0' && size > 1) { src++; size--; if (flags & UNESCAPE_SPACE && unescape_space(&src, &out)) continue; if (flags & UNESCAPE_OCTAL && unescape_octal(&src, &out)) continue; if (flags & UNESCAPE_HEX && unescape_hex(&src, &out)) continue; if (flags & UNESCAPE_SPECIAL && unescape_special(&src, &out)) continue; *out++ = '\\'; } *out++ = *src++; } *out = '\0'; return out - dst; } EXPORT_SYMBOL(string_unescape); static bool escape_passthrough(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = c; *dst = out + 1; return true; } static bool escape_space(unsigned char c, char **dst, char *end) { char *out = *dst; unsigned char to; switch (c) { case '\n': to = 'n'; break; case '\r': to = 'r'; break; case '\t': to = 't'; break; case '\v': to = 'v'; break; case '\f': to = 'f'; break; default: return false; } if (out < end) *out = '\\'; ++out; if (out < end) *out = to; ++out; *dst = out; return true; } static bool escape_special(unsigned char c, char **dst, char *end) { char *out = *dst; unsigned char to; switch (c) { case '\\': to = '\\'; break; case '\a': to = 'a'; break; case '\e': to = 'e'; break; case '"': to = '"'; break; default: return false; } if (out < end) *out = '\\'; ++out; if (out < end) *out = to; ++out; *dst = out; return true; } static bool escape_null(unsigned char c, char **dst, char *end) { char *out = *dst; if (c) return false; if (out < end) *out = '\\'; ++out; if (out < end) *out = '0'; ++out; *dst = out; return true; } static bool escape_octal(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = '\\'; ++out; if (out < end) *out = ((c >> 6) & 0x07) + '0'; ++out; if (out < end) *out = ((c >> 3) & 0x07) + '0'; ++out; if (out < end) *out = ((c >> 0) & 0x07) + '0'; ++out; *dst = out; return true; } static bool escape_hex(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = '\\'; ++out; if (out < end) *out = 'x'; ++out; if (out < end) *out = hex_asc_hi(c); ++out; if (out < end) *out = hex_asc_lo(c); ++out; *dst = out; return true; } /** * string_escape_mem - quote characters in the given memory buffer * @src: source buffer (unescaped) * @isz: source buffer size * @dst: destination buffer (escaped) * @osz: destination buffer size * @flags: combination of the flags * @only: NULL-terminated string containing characters used to limit * the selected escape class. If characters are included in @only * that would not normally be escaped by the classes selected * in @flags, they will be copied to @dst unescaped. * * Description: * The process of escaping byte buffer includes several parts. They are applied * in the following sequence. * * 1. The character is not matched to the one from @only string and thus * must go as-is to the output. * 2. The character is matched to the printable and ASCII classes, if asked, * and in case of match it passes through to the output. * 3. The character is matched to the printable or ASCII class, if asked, * and in case of match it passes through to the output. * 4. The character is checked if it falls into the class given by @flags. * %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any * character. Note that they actually can't go together, otherwise * %ESCAPE_HEX will be ignored. * * Caller must provide valid source and destination pointers. Be aware that * destination buffer will not be NULL-terminated, thus caller have to append * it if needs. The supported flags are:: * * %ESCAPE_SPACE: (special white space, not space itself) * '\f' - form feed * '\n' - new line * '\r' - carriage return * '\t' - horizontal tab * '\v' - vertical tab * %ESCAPE_SPECIAL: * '\"' - double quote * '\\' - backslash * '\a' - alert (BEL) * '\e' - escape * %ESCAPE_NULL: * '\0' - null * %ESCAPE_OCTAL: * '\NNN' - byte with octal value NNN (3 digits) * %ESCAPE_ANY: * all previous together * %ESCAPE_NP: * escape only non-printable characters, checked by isprint() * %ESCAPE_ANY_NP: * all previous together * %ESCAPE_HEX: * '\xHH' - byte with hexadecimal value HH (2 digits) * %ESCAPE_NA: * escape only non-ascii characters, checked by isascii() * %ESCAPE_NAP: * escape only non-printable or non-ascii characters * %ESCAPE_APPEND: * append characters from @only to be escaped by the given classes * * %ESCAPE_APPEND would help to pass additional characters to the escaped, when * one of %ESCAPE_NP, %ESCAPE_NA, or %ESCAPE_NAP is provided. * * One notable caveat, the %ESCAPE_NAP, %ESCAPE_NP and %ESCAPE_NA have the * higher priority than the rest of the flags (%ESCAPE_NAP is the highest). * It doesn't make much sense to use either of them without %ESCAPE_OCTAL * or %ESCAPE_HEX, because they cover most of the other character classes. * %ESCAPE_NAP can utilize %ESCAPE_SPACE or %ESCAPE_SPECIAL in addition to * the above. * * Return: * The total size of the escaped output that would be generated for * the given input and flags. To check whether the output was * truncated, compare the return value to osz. There is room left in * dst for a '\0' terminator if and only if ret < osz. */ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only) { char *p = dst; char *end = p + osz; bool is_dict = only && *only; bool is_append = flags & ESCAPE_APPEND; while (isz--) { unsigned char c = *src++; bool in_dict = is_dict && strchr(only, c); /* * Apply rules in the following sequence: * - the @only string is supplied and does not contain a * character under question * - the character is printable and ASCII, when @flags has * %ESCAPE_NAP bit set * - the character is printable, when @flags has * %ESCAPE_NP bit set * - the character is ASCII, when @flags has * %ESCAPE_NA bit set * - the character doesn't fall into a class of symbols * defined by given @flags * In these cases we just pass through a character to the * output buffer. * * When %ESCAPE_APPEND is passed, the characters from @only * have been excluded from the %ESCAPE_NAP, %ESCAPE_NP, and * %ESCAPE_NA cases. */ if (!(is_append || in_dict) && is_dict && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isascii(c) && isprint(c) && flags & ESCAPE_NAP && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isprint(c) && flags & ESCAPE_NP && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isascii(c) && flags & ESCAPE_NA && escape_passthrough(c, &p, end)) continue; if (flags & ESCAPE_SPACE && escape_space(c, &p, end)) continue; if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end)) continue; if (flags & ESCAPE_NULL && escape_null(c, &p, end)) continue; /* ESCAPE_OCTAL and ESCAPE_HEX always go last */ if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end)) continue; if (flags & ESCAPE_HEX && escape_hex(c, &p, end)) continue; escape_passthrough(c, &p, end); } return p - dst; } EXPORT_SYMBOL(string_escape_mem); /* * Return an allocated string that has been escaped of special characters * and double quotes, making it safe to log in quotes. */ char *kstrdup_quotable(const char *src, gfp_t gfp) { size_t slen, dlen; char *dst; const int flags = ESCAPE_HEX; const char esc[] = "\f\n\r\t\v\a\e\\\""; if (!src) return NULL; slen = strlen(src); dlen = string_escape_mem(src, slen, NULL, 0, flags, esc); dst = kmalloc(dlen + 1, gfp); if (!dst) return NULL; WARN_ON(string_escape_mem(src, slen, dst, dlen, flags, esc) != dlen); dst[dlen] = '\0'; return dst; } EXPORT_SYMBOL_GPL(kstrdup_quotable); /* * Returns allocated NULL-terminated string containing process * command line, with inter-argument NULLs replaced with spaces, * and other special characters escaped. */ char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp) { char *buffer, *quoted; int i, res; buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!buffer) return NULL; res = get_cmdline(task, buffer, PAGE_SIZE - 1); buffer[res] = '\0'; /* Collapse trailing NULLs, leave res pointing to last non-NULL. */ while (--res >= 0 && buffer[res] == '\0') ; /* Replace inter-argument NULLs. */ for (i = 0; i <= res; i++) if (buffer[i] == '\0') buffer[i] = ' '; /* Make sure result is printable. */ quoted = kstrdup_quotable(buffer, gfp); kfree(buffer); return quoted; } EXPORT_SYMBOL_GPL(kstrdup_quotable_cmdline); /* * Returns allocated NULL-terminated string containing pathname, * with special characters escaped, able to be safely logged. If * there is an error, the leading character will be "<". */ char *kstrdup_quotable_file(struct file *file, gfp_t gfp) { char *temp, *pathname; if (!file) return kstrdup("<unknown>", gfp); /* We add 11 spaces for ' (deleted)' to be appended */ temp = kmalloc(PATH_MAX + 11, GFP_KERNEL); if (!temp) return kstrdup("<no_memory>", gfp); pathname = file_path(file, temp, PATH_MAX + 11); if (IS_ERR(pathname)) pathname = kstrdup("<too_long>", gfp); else pathname = kstrdup_quotable(pathname, gfp); kfree(temp); return pathname; } EXPORT_SYMBOL_GPL(kstrdup_quotable_file); /* * Returns duplicate string in which the @old characters are replaced by @new. */ char *kstrdup_and_replace(const char *src, char old, char new, gfp_t gfp) { char *dst; dst = kstrdup(src, gfp); if (!dst) return NULL; return strreplace(dst, old, new); } EXPORT_SYMBOL_GPL(kstrdup_and_replace); /** * kasprintf_strarray - allocate and fill array of sequential strings * @gfp: flags for the slab allocator * @prefix: prefix to be used * @n: number of strings to be allocated and filled * * Allocates and fills @n strings using pattern "%s-%zu", where prefix * is provided by caller. The caller is responsible to free them with * kfree_strarray() after use. * * Returns array of strings or NULL when memory can't be allocated. */ char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n) { char **names; size_t i; names = kcalloc(n, sizeof(char *), gfp); if (!names) return NULL; for (i = 0; i < n; i++) { names[i] = kasprintf(gfp, "%s-%zu", prefix, i); if (!names[i]) { kfree_strarray(names, i); return NULL; } } return names; } EXPORT_SYMBOL_GPL(kasprintf_strarray); /** * kfree_strarray - free a number of dynamically allocated strings contained * in an array and the array itself * * @array: Dynamically allocated array of strings to free. * @n: Number of strings (starting from the beginning of the array) to free. * * Passing a non-NULL @array and @n == 0 as well as NULL @array are valid * use-cases. If @array is NULL, the function does nothing. */ void kfree_strarray(char **array, size_t n) { unsigned int i; if (!array) return; for (i = 0; i < n; i++) kfree(array[i]); kfree(array); } EXPORT_SYMBOL_GPL(kfree_strarray); struct strarray { char **array __counted_by_ptr(n); size_t n; }; static void devm_kfree_strarray(struct device *dev, void *res) { struct strarray *array = res; kfree_strarray(array->array, array->n); } char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n) { struct strarray *ptr; ptr = devres_alloc(devm_kfree_strarray, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); ptr->n = n; ptr->array = kasprintf_strarray(GFP_KERNEL, prefix, n); if (!ptr->array) { devres_free(ptr); return ERR_PTR(-ENOMEM); } devres_add(dev, ptr); return ptr->array; } EXPORT_SYMBOL_GPL(devm_kasprintf_strarray); /** * skip_spaces - Removes leading whitespace from @str. * @str: The string to be stripped. * * Returns a pointer to the first non-whitespace character in @str. */ char *skip_spaces(const char *str) { while (isspace(*str)) ++str; return (char *)str; } EXPORT_SYMBOL(skip_spaces); /** * strim - Removes leading and trailing whitespace from @s. * @s: The string to be stripped. * * Note that the first trailing whitespace is replaced with a %NUL-terminator * in the given string @s. Returns a pointer to the first non-whitespace * character in @s. */ char *strim(char *s) { size_t size; char *end; size = strlen(s); if (!size) return s; end = s + size - 1; while (end >= s && isspace(*end)) end--; *(end + 1) = '\0'; return skip_spaces(s); } EXPORT_SYMBOL(strim); /** * sysfs_streq - return true if strings are equal, modulo trailing newline * @s1: one string * @s2: another string * * This routine returns true iff two strings are equal, treating both * NUL and newline-then-NUL as equivalent string terminations. It's * geared for use with sysfs input strings, which generally terminate * with newlines but are compared against values without newlines. */ bool sysfs_streq(const char *s1, const char *s2) { while (*s1 && *s1 == *s2) { s1++; s2++; } if (*s1 == *s2) return true; if (!*s1 && *s2 == '\n' && !s2[1]) return true; if (*s1 == '\n' && !s1[1] && !*s2) return true; return false; } EXPORT_SYMBOL(sysfs_streq); /** * match_string - matches given string in an array * @array: array of strings * @n: number of strings in the array or -1 for NULL terminated arrays * @string: string to match with * * This routine will look for a string in an array of strings up to the * n-th element in the array or until the first NULL element. * * Historically the value of -1 for @n, was used to search in arrays that * are NULL terminated. However, the function does not make a distinction * when finishing the search: either @n elements have been compared OR * the first NULL element was found. * * Return: * index of a @string in the @array if matches, or %-EINVAL otherwise. */ int match_string(const char * const *array, size_t n, const char *string) { int index; const char *item; for (index = 0; index < n; index++) { item = array[index]; if (!item) break; if (!strcmp(item, string)) return index; } return -EINVAL; } EXPORT_SYMBOL(match_string); /** * __sysfs_match_string - matches given string in an array * @array: array of strings * @n: number of strings in the array or -1 for NULL terminated arrays * @str: string to match with * * Returns index of @str in the @array or -EINVAL, just like match_string(). * Uses sysfs_streq instead of strcmp for matching. * * This routine will look for a string in an array of strings up to the * n-th element in the array or until the first NULL element. * * Historically the value of -1 for @n, was used to search in arrays that * are NULL terminated. However, the function does not make a distinction * when finishing the search: either @n elements have been compared OR * the first NULL element was found. */ int __sysfs_match_string(const char * const *array, size_t n, const char *str) { const char *item; int index; for (index = 0; index < n; index++) { item = array[index]; if (!item) break; if (sysfs_streq(item, str)) return index; } return -EINVAL; } EXPORT_SYMBOL(__sysfs_match_string); /** * strreplace - Replace all occurrences of character in string. * @str: The string to operate on. * @old: The character being replaced. * @new: The character @old is replaced with. * * Replaces the each @old character with a @new one in the given string @str. * * Return: pointer to the string @str itself. */ char *strreplace(char *str, char old, char new) { char *s = str; for (; *s; ++s) if (*s == old) *s = new; return str; } EXPORT_SYMBOL(strreplace); /** * memcpy_and_pad - Copy one buffer to another with padding * @dest: Where to copy to * @dest_len: The destination buffer size * @src: Where to copy from * @count: The number of bytes to copy * @pad: Character to use for padding if space is left in destination. */ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad) { if (dest_len > count) { memcpy(dest, src, count); memset(dest + count, pad, dest_len - count); } else { memcpy(dest, src, dest_len); } } EXPORT_SYMBOL(memcpy_and_pad); #ifdef CONFIG_FORTIFY_SOURCE /* These are placeholders for fortify compile-time warnings. */ void __read_overflow2_field(size_t avail, size_t wanted) { } EXPORT_SYMBOL(__read_overflow2_field); void __write_overflow_field(size_t avail, size_t wanted) { } EXPORT_SYMBOL(__write_overflow_field); static const char * const fortify_func_name[] = { #define MAKE_FORTIFY_FUNC_NAME(func) [MAKE_FORTIFY_FUNC(func)] = #func EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC_NAME) #undef MAKE_FORTIFY_FUNC_NAME }; void __fortify_report(const u8 reason, const size_t avail, const size_t size) { const u8 func = FORTIFY_REASON_FUNC(reason); const bool write = FORTIFY_REASON_DIR(reason); const char *name; name = fortify_func_name[umin(func, FORTIFY_FUNC_UNKNOWN)]; WARN(1, "%s: detected buffer overflow: %zu byte %s of buffer size %zu\n", name, size, str_read_write(!write), avail); } EXPORT_SYMBOL(__fortify_report); void __fortify_panic(const u8 reason, const size_t avail, const size_t size) { __fortify_report(reason, avail, size); BUG(); } EXPORT_SYMBOL(__fortify_panic); #endif /* CONFIG_FORTIFY_SOURCE */ |
| 20 19 40 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 | /* * * dvb_ringbuffer.c: ring buffer implementation for the dvb driver * * Copyright (C) 2003 Oliver Endriss * Copyright (C) 2004 Andrew de Quincey * * based on code originally found in av7110.c & dvb_ci.c: * Copyright (C) 1999-2003 Ralph Metzler * & Marcus Metzler for convergence integrated media GmbH * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public License * as published by the Free Software Foundation; either version 2.1 * 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 Lesser General Public License for more details. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/uaccess.h> #include <media/dvb_ringbuffer.h> #define PKT_READY 0 #define PKT_DISPOSED 1 void dvb_ringbuffer_init(struct dvb_ringbuffer *rbuf, void *data, size_t len) { rbuf->pread = 0; rbuf->pwrite = 0; rbuf->data = data; rbuf->size = len; rbuf->error = 0; init_waitqueue_head(&rbuf->queue); spin_lock_init(&(rbuf->lock)); } int dvb_ringbuffer_empty(struct dvb_ringbuffer *rbuf) { /* smp_load_acquire() to load write pointer on reader side * this pairs with smp_store_release() in dvb_ringbuffer_write(), * dvb_ringbuffer_write_user(), or dvb_ringbuffer_reset() * * for memory barriers also see Documentation/core-api/circular-buffers.rst */ return (rbuf->pread == smp_load_acquire(&rbuf->pwrite)); } ssize_t dvb_ringbuffer_free(struct dvb_ringbuffer *rbuf) { ssize_t free; /* READ_ONCE() to load read pointer on writer side * this pairs with smp_store_release() in dvb_ringbuffer_read(), * dvb_ringbuffer_read_user(), dvb_ringbuffer_flush(), * or dvb_ringbuffer_reset() */ free = READ_ONCE(rbuf->pread) - rbuf->pwrite; if (free <= 0) free += rbuf->size; return free-1; } ssize_t dvb_ringbuffer_avail(struct dvb_ringbuffer *rbuf) { ssize_t avail; /* smp_load_acquire() to load write pointer on reader side * this pairs with smp_store_release() in dvb_ringbuffer_write(), * dvb_ringbuffer_write_user(), or dvb_ringbuffer_reset() */ avail = smp_load_acquire(&rbuf->pwrite) - rbuf->pread; if (avail < 0) avail += rbuf->size; return avail; } void dvb_ringbuffer_flush(struct dvb_ringbuffer *rbuf) { /* dvb_ringbuffer_flush() counts as read operation * smp_load_acquire() to load write pointer * smp_store_release() to update read pointer, this ensures that the * correct pointer is visible for subsequent dvb_ringbuffer_free() * calls on other cpu cores */ smp_store_release(&rbuf->pread, smp_load_acquire(&rbuf->pwrite)); rbuf->error = 0; } EXPORT_SYMBOL(dvb_ringbuffer_flush); void dvb_ringbuffer_reset(struct dvb_ringbuffer *rbuf) { /* dvb_ringbuffer_reset() counts as read and write operation * smp_store_release() to update read pointer */ smp_store_release(&rbuf->pread, 0); /* smp_store_release() to update write pointer */ smp_store_release(&rbuf->pwrite, 0); rbuf->error = 0; } void dvb_ringbuffer_flush_spinlock_wakeup(struct dvb_ringbuffer *rbuf) { unsigned long flags; spin_lock_irqsave(&rbuf->lock, flags); dvb_ringbuffer_flush(rbuf); spin_unlock_irqrestore(&rbuf->lock, flags); wake_up(&rbuf->queue); } ssize_t dvb_ringbuffer_read_user(struct dvb_ringbuffer *rbuf, u8 __user *buf, size_t len) { size_t todo = len; size_t split; split = (rbuf->pread + len > rbuf->size) ? rbuf->size - rbuf->pread : 0; if (split > 0) { if (copy_to_user(buf, rbuf->data+rbuf->pread, split)) return -EFAULT; buf += split; todo -= split; /* smp_store_release() for read pointer update to ensure * that buf is not overwritten until read is complete, * this pairs with READ_ONCE() in dvb_ringbuffer_free() */ smp_store_release(&rbuf->pread, 0); } if (copy_to_user(buf, rbuf->data+rbuf->pread, todo)) return -EFAULT; /* smp_store_release() to update read pointer, see above */ smp_store_release(&rbuf->pread, (rbuf->pread + todo) % rbuf->size); return len; } void dvb_ringbuffer_read(struct dvb_ringbuffer *rbuf, u8 *buf, size_t len) { size_t todo = len; size_t split; split = (rbuf->pread + len > rbuf->size) ? rbuf->size - rbuf->pread : 0; if (split > 0) { memcpy(buf, rbuf->data+rbuf->pread, split); buf += split; todo -= split; /* smp_store_release() for read pointer update to ensure * that buf is not overwritten until read is complete, * this pairs with READ_ONCE() in dvb_ringbuffer_free() */ smp_store_release(&rbuf->pread, 0); } memcpy(buf, rbuf->data+rbuf->pread, todo); /* smp_store_release() to update read pointer, see above */ smp_store_release(&rbuf->pread, (rbuf->pread + todo) % rbuf->size); } ssize_t dvb_ringbuffer_write(struct dvb_ringbuffer *rbuf, const u8 *buf, size_t len) { size_t todo = len; size_t split; split = (rbuf->pwrite + len > rbuf->size) ? rbuf->size - rbuf->pwrite : 0; if (split > 0) { memcpy(rbuf->data+rbuf->pwrite, buf, split); buf += split; todo -= split; /* smp_store_release() for write pointer update to ensure that * written data is visible on other cpu cores before the pointer * update, this pairs with smp_load_acquire() in * dvb_ringbuffer_empty() or dvb_ringbuffer_avail() */ smp_store_release(&rbuf->pwrite, 0); } memcpy(rbuf->data+rbuf->pwrite, buf, todo); /* smp_store_release() for write pointer update, see above */ smp_store_release(&rbuf->pwrite, (rbuf->pwrite + todo) % rbuf->size); return len; } ssize_t dvb_ringbuffer_write_user(struct dvb_ringbuffer *rbuf, const u8 __user *buf, size_t len) { int status; size_t todo = len; size_t split; split = (rbuf->pwrite + len > rbuf->size) ? rbuf->size - rbuf->pwrite : 0; if (split > 0) { status = copy_from_user(rbuf->data+rbuf->pwrite, buf, split); if (status) return len - todo; buf += split; todo -= split; /* smp_store_release() for write pointer update to ensure that * written data is visible on other cpu cores before the pointer * update, this pairs with smp_load_acquire() in * dvb_ringbuffer_empty() or dvb_ringbuffer_avail() */ smp_store_release(&rbuf->pwrite, 0); } status = copy_from_user(rbuf->data+rbuf->pwrite, buf, todo); if (status) return len - todo; /* smp_store_release() for write pointer update, see above */ smp_store_release(&rbuf->pwrite, (rbuf->pwrite + todo) % rbuf->size); return len; } ssize_t dvb_ringbuffer_pkt_write(struct dvb_ringbuffer *rbuf, u8 *buf, size_t len) { int status; ssize_t oldpwrite = rbuf->pwrite; DVB_RINGBUFFER_WRITE_BYTE(rbuf, len >> 8); DVB_RINGBUFFER_WRITE_BYTE(rbuf, len & 0xff); DVB_RINGBUFFER_WRITE_BYTE(rbuf, PKT_READY); status = dvb_ringbuffer_write(rbuf, buf, len); if (status < 0) rbuf->pwrite = oldpwrite; return status; } ssize_t dvb_ringbuffer_pkt_read_user(struct dvb_ringbuffer *rbuf, size_t idx, int offset, u8 __user *buf, size_t len) { size_t todo; size_t split; size_t pktlen; pktlen = rbuf->data[idx] << 8; pktlen |= rbuf->data[(idx + 1) % rbuf->size]; if (offset > pktlen) return -EINVAL; if ((offset + len) > pktlen) len = pktlen - offset; idx = (idx + DVB_RINGBUFFER_PKTHDRSIZE + offset) % rbuf->size; todo = len; split = ((idx + len) > rbuf->size) ? rbuf->size - idx : 0; if (split > 0) { if (copy_to_user(buf, rbuf->data+idx, split)) return -EFAULT; buf += split; todo -= split; idx = 0; } if (copy_to_user(buf, rbuf->data+idx, todo)) return -EFAULT; return len; } ssize_t dvb_ringbuffer_pkt_read(struct dvb_ringbuffer *rbuf, size_t idx, int offset, u8 *buf, size_t len) { size_t todo; size_t split; size_t pktlen; pktlen = rbuf->data[idx] << 8; pktlen |= rbuf->data[(idx + 1) % rbuf->size]; if (offset > pktlen) return -EINVAL; if ((offset + len) > pktlen) len = pktlen - offset; idx = (idx + DVB_RINGBUFFER_PKTHDRSIZE + offset) % rbuf->size; todo = len; split = ((idx + len) > rbuf->size) ? rbuf->size - idx : 0; if (split > 0) { memcpy(buf, rbuf->data+idx, split); buf += split; todo -= split; idx = 0; } memcpy(buf, rbuf->data+idx, todo); return len; } void dvb_ringbuffer_pkt_dispose(struct dvb_ringbuffer *rbuf, size_t idx) { size_t pktlen; rbuf->data[(idx + 2) % rbuf->size] = PKT_DISPOSED; // clean up disposed packets while (dvb_ringbuffer_avail(rbuf) > DVB_RINGBUFFER_PKTHDRSIZE) { if (DVB_RINGBUFFER_PEEK(rbuf, 2) == PKT_DISPOSED) { pktlen = DVB_RINGBUFFER_PEEK(rbuf, 0) << 8; pktlen |= DVB_RINGBUFFER_PEEK(rbuf, 1); DVB_RINGBUFFER_SKIP(rbuf, pktlen + DVB_RINGBUFFER_PKTHDRSIZE); } else { // first packet is not disposed, so we stop cleaning now break; } } } ssize_t dvb_ringbuffer_pkt_next(struct dvb_ringbuffer *rbuf, size_t idx, size_t *pktlen) { int consumed; int curpktlen; int curpktstatus; if (idx == -1) { idx = rbuf->pread; } else { curpktlen = rbuf->data[idx] << 8; curpktlen |= rbuf->data[(idx + 1) % rbuf->size]; idx = (idx + curpktlen + DVB_RINGBUFFER_PKTHDRSIZE) % rbuf->size; } consumed = (idx - rbuf->pread); if (consumed < 0) consumed += rbuf->size; while ((dvb_ringbuffer_avail(rbuf) - consumed) > DVB_RINGBUFFER_PKTHDRSIZE) { curpktlen = rbuf->data[idx] << 8; curpktlen |= rbuf->data[(idx + 1) % rbuf->size]; curpktstatus = rbuf->data[(idx + 2) % rbuf->size]; if (curpktstatus == PKT_READY) { *pktlen = curpktlen; return idx; } consumed += curpktlen + DVB_RINGBUFFER_PKTHDRSIZE; idx = (idx + curpktlen + DVB_RINGBUFFER_PKTHDRSIZE) % rbuf->size; } // no packets available return -1; } EXPORT_SYMBOL(dvb_ringbuffer_init); EXPORT_SYMBOL(dvb_ringbuffer_empty); EXPORT_SYMBOL(dvb_ringbuffer_free); EXPORT_SYMBOL(dvb_ringbuffer_avail); EXPORT_SYMBOL(dvb_ringbuffer_flush_spinlock_wakeup); EXPORT_SYMBOL(dvb_ringbuffer_read_user); EXPORT_SYMBOL(dvb_ringbuffer_read); EXPORT_SYMBOL(dvb_ringbuffer_write); EXPORT_SYMBOL(dvb_ringbuffer_write_user); |
| 14 9 9 8 8 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 | // SPDX-License-Identifier: GPL-2.0 /* * Coherent per-device memory handling. * Borrowed from i386 */ #include <linux/io.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> struct dma_coherent_mem { void *virt_base; dma_addr_t device_base; unsigned long pfn_base; int size; unsigned long *bitmap; spinlock_t spinlock; bool use_dev_dma_pfn_offset; }; static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev) { if (dev && dev->dma_mem) return dev->dma_mem; return NULL; } static inline dma_addr_t dma_get_device_base(struct device *dev, struct dma_coherent_mem * mem) { if (mem->use_dev_dma_pfn_offset) return phys_to_dma(dev, PFN_PHYS(mem->pfn_base)); return mem->device_base; } static struct dma_coherent_mem *dma_init_coherent_memory(phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, bool use_dma_pfn_offset) { struct dma_coherent_mem *dma_mem; int pages = size >> PAGE_SHIFT; void *mem_base; if (!size) return ERR_PTR(-EINVAL); mem_base = memremap(phys_addr, size, MEMREMAP_WC); if (!mem_base) return ERR_PTR(-EINVAL); dma_mem = kzalloc_obj(struct dma_coherent_mem); if (!dma_mem) goto out_unmap_membase; dma_mem->bitmap = bitmap_zalloc(pages, GFP_KERNEL); if (!dma_mem->bitmap) goto out_free_dma_mem; dma_mem->virt_base = mem_base; dma_mem->device_base = device_addr; dma_mem->pfn_base = PFN_DOWN(phys_addr); dma_mem->size = pages; dma_mem->use_dev_dma_pfn_offset = use_dma_pfn_offset; spin_lock_init(&dma_mem->spinlock); return dma_mem; out_free_dma_mem: kfree(dma_mem); out_unmap_membase: memunmap(mem_base); pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %zd MiB\n", &phys_addr, size / SZ_1M); return ERR_PTR(-ENOMEM); } static void _dma_release_coherent_memory(struct dma_coherent_mem *mem) { if (!mem) return; memunmap(mem->virt_base); bitmap_free(mem->bitmap); kfree(mem); } static int dma_assign_coherent_memory(struct device *dev, struct dma_coherent_mem *mem) { if (!dev) return -ENODEV; if (dev->dma_mem) return -EBUSY; dev->dma_mem = mem; return 0; } /* * Declare a region of memory to be handed out by dma_alloc_coherent() when it * is asked for coherent memory for this device. This shall only be used * from platform code, usually based on the device tree description. * * phys_addr is the CPU physical address to which the memory is currently * assigned (this will be ioremapped so the CPU can access the region). * * device_addr is the DMA address the device needs to be programmed with to * actually address this memory (this will be handed out as the dma_addr_t in * dma_alloc_coherent()). * * size is the size of the area (must be a multiple of PAGE_SIZE). * * As a simplification for the platforms, only *one* such region of memory may * be declared per device. */ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size) { struct dma_coherent_mem *mem; int ret; mem = dma_init_coherent_memory(phys_addr, device_addr, size, false); if (IS_ERR(mem)) return PTR_ERR(mem); ret = dma_assign_coherent_memory(dev, mem); if (ret) _dma_release_coherent_memory(mem); return ret; } void dma_release_coherent_memory(struct device *dev) { if (dev) { _dma_release_coherent_memory(dev->dma_mem); dev->dma_mem = NULL; } } static void *__dma_alloc_from_coherent(struct device *dev, struct dma_coherent_mem *mem, ssize_t size, dma_addr_t *dma_handle) { int order = get_order(size); unsigned long flags; int pageno; void *ret; spin_lock_irqsave(&mem->spinlock, flags); if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT))) goto err; pageno = bitmap_find_free_region(mem->bitmap, mem->size, order); if (unlikely(pageno < 0)) goto err; /* * Memory was found in the coherent area. */ *dma_handle = dma_get_device_base(dev, mem) + ((dma_addr_t)pageno << PAGE_SHIFT); ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT); spin_unlock_irqrestore(&mem->spinlock, flags); memset(ret, 0, size); return ret; err: spin_unlock_irqrestore(&mem->spinlock, flags); return NULL; } /** * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool * @dev: device from which we allocate memory * @size: size of requested memory area * @dma_handle: This will be filled with the correct dma handle * @ret: This pointer will be filled with the virtual address * to allocated area. * * This function should be only called from per-arch dma_alloc_coherent() * to support allocation from per-device coherent memory pools. * * Returns 0 if dma_alloc_coherent should continue with allocating from * generic memory areas, or !0 if dma_alloc_coherent should return @ret. */ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle, void **ret) { struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); if (!mem) return 0; *ret = __dma_alloc_from_coherent(dev, mem, size, dma_handle); return 1; } static int __dma_release_from_coherent(struct dma_coherent_mem *mem, int order, void *vaddr) { if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; unsigned long flags; spin_lock_irqsave(&mem->spinlock, flags); bitmap_release_region(mem->bitmap, page, order); spin_unlock_irqrestore(&mem->spinlock, flags); return 1; } return 0; } /** * dma_release_from_dev_coherent() - free memory to device coherent memory pool * @dev: device from which the memory was allocated * @order: the order of pages allocated * @vaddr: virtual address of allocated pages * * This checks whether the memory was allocated from the per-device * coherent memory pool and if so, releases that memory. * * Returns 1 if we correctly released the memory, or 0 if the caller should * proceed with releasing memory from generic pools. */ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr) { struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); return __dma_release_from_coherent(mem, order, vaddr); } static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem, struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { if (mem && vaddr >= mem->virt_base && vaddr + size <= (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { unsigned long off = vma->vm_pgoff; int start = (vaddr - mem->virt_base) >> PAGE_SHIFT; unsigned long user_count = vma_pages(vma); int count = PAGE_ALIGN(size) >> PAGE_SHIFT; *ret = -ENXIO; if (off < count && user_count <= count - off) { unsigned long pfn = mem->pfn_base + start + off; *ret = remap_pfn_range(vma, vma->vm_start, pfn, user_count << PAGE_SHIFT, vma->vm_page_prot); } return 1; } return 0; } /** * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool * @dev: device from which the memory was allocated * @vma: vm_area for the userspace memory * @vaddr: cpu address returned by dma_alloc_from_dev_coherent * @size: size of the memory buffer allocated * @ret: result from remap_pfn_range() * * This checks whether the memory was allocated from the per-device * coherent memory pool and if so, maps that memory to the provided vma. * * Returns 1 if @vaddr belongs to the device coherent pool and the caller * should return @ret, or 0 if they should proceed with mapping memory from * generic areas. */ int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret); } #ifdef CONFIG_DMA_GLOBAL_POOL static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init; void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle) { if (!dma_coherent_default_memory) return NULL; return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size, dma_handle); } int dma_release_from_global_coherent(int order, void *vaddr) { if (!dma_coherent_default_memory) return 0; return __dma_release_from_coherent(dma_coherent_default_memory, order, vaddr); } int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { if (!dma_coherent_default_memory) return 0; return __dma_mmap_from_coherent(dma_coherent_default_memory, vma, vaddr, size, ret); } int dma_init_global_coherent(phys_addr_t phys_addr, size_t size) { struct dma_coherent_mem *mem; mem = dma_init_coherent_memory(phys_addr, phys_addr, size, true); if (IS_ERR(mem)) return PTR_ERR(mem); dma_coherent_default_memory = mem; pr_info("DMA: default coherent area is set\n"); return 0; } #endif /* CONFIG_DMA_GLOBAL_POOL */ /* * Support for reserved memory regions defined in device tree */ #ifdef CONFIG_OF_RESERVED_MEM #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/of_reserved_mem.h> #ifdef CONFIG_DMA_GLOBAL_POOL static phys_addr_t dma_reserved_default_memory_base __initdata; static phys_addr_t dma_reserved_default_memory_size __initdata; #endif static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev) { struct dma_coherent_mem *mem = rmem->priv; if (!mem) { mem = dma_init_coherent_memory(rmem->base, rmem->base, rmem->size, true); if (IS_ERR(mem)) return PTR_ERR(mem); rmem->priv = mem; } /* Warn if the device potentially can't use the reserved memory */ if (mem->device_base + rmem->size - 1 > min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit)) dev_warn(dev, "reserved memory is beyond device's set DMA address range\n"); dma_assign_coherent_memory(dev, mem); return 0; } static void rmem_dma_device_release(struct reserved_mem *rmem, struct device *dev) { if (dev) dev->dma_mem = NULL; } static int __init rmem_dma_setup(unsigned long node, struct reserved_mem *rmem) { if (of_get_flat_dt_prop(node, "reusable", NULL)) return -ENODEV; #ifdef CONFIG_ARM if (!of_get_flat_dt_prop(node, "no-map", NULL)) { pr_err("Reserved memory: regions without no-map are not yet supported\n"); return -EINVAL; } #endif #ifdef CONFIG_DMA_GLOBAL_POOL if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) { WARN(dma_reserved_default_memory_size, "Reserved memory: region for default DMA coherent area is redefined\n"); dma_reserved_default_memory_base = rmem->base; dma_reserved_default_memory_size = rmem->size; } #endif pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n", &rmem->base, (unsigned long)rmem->size / SZ_1M); return 0; } #ifdef CONFIG_DMA_GLOBAL_POOL static int __init dma_init_reserved_memory(void) { if (!dma_reserved_default_memory_size) return -ENOMEM; return dma_init_global_coherent(dma_reserved_default_memory_base, dma_reserved_default_memory_size); } core_initcall(dma_init_reserved_memory); #endif /* CONFIG_DMA_GLOBAL_POOL */ static const struct reserved_mem_ops rmem_dma_ops = { .node_init = rmem_dma_setup, .device_init = rmem_dma_device_init, .device_release = rmem_dma_device_release, }; RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", &rmem_dma_ops); #endif |
| 76 74 74 74 73 72 61 11 4 7 4 7 69 69 68 8 20 3 3 1 2 1 67 76 13 12 29 27 27 27 27 26 27 25 2 2 13 13 13 13 13 13 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * GRE over IPv4 demultiplexer driver * * Authors: Dmitry Kozlov (xeb@mail.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/if.h> #include <linux/icmp.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/skbuff.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/if_tunnel.h> #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> #include <net/erspan.h> #include <net/icmp.h> #include <net/route.h> #include <net/xfrm.h> static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; int gre_add_protocol(const struct gre_protocol *proto, u8 version) { if (version >= GREPROTO_MAX) return -EINVAL; return (cmpxchg((const struct gre_protocol **)&gre_proto[version], NULL, proto) == NULL) ? 0 : -EBUSY; } EXPORT_SYMBOL_GPL(gre_add_protocol); int gre_del_protocol(const struct gre_protocol *proto, u8 version) { int ret; if (version >= GREPROTO_MAX) return -EINVAL; ret = (cmpxchg((const struct gre_protocol **)&gre_proto[version], proto, NULL) == proto) ? 0 : -EBUSY; if (ret) return ret; synchronize_rcu(); return 0; } EXPORT_SYMBOL_GPL(gre_del_protocol); /* Fills in tpi and returns header length to be pulled. * Note that caller must use pskb_may_pull() before pulling GRE header. */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs) { const struct gre_base_hdr *greh; __be32 *options; int hdr_len; if (unlikely(!pskb_may_pull(skb, nhs + sizeof(struct gre_base_hdr)))) return -EINVAL; greh = (struct gre_base_hdr *)(skb->data + nhs); if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; gre_flags_to_tnl_flags(tpi->flags, greh->flags); hdr_len = gre_calc_hlen(tpi->flags); if (!pskb_may_pull(skb, nhs + hdr_len)) return -EINVAL; greh = (struct gre_base_hdr *)(skb->data + nhs); tpi->proto = greh->protocol; options = (__be32 *)(greh + 1); if (greh->flags & GRE_CSUM) { if (!skb_checksum_simple_validate(skb)) { skb_checksum_try_convert(skb, IPPROTO_GRE, null_compute_pseudo); } else if (csum_err) { *csum_err = true; return -EINVAL; } options++; } if (greh->flags & GRE_KEY) { tpi->key = *options; options++; } else { tpi->key = 0; } if (unlikely(greh->flags & GRE_SEQ)) { tpi->seq = *options; options++; } else { tpi->seq = 0; } /* WCCP version 1 and 2 protocol decoding. * - Change protocol to IPv4/IPv6 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { u8 _val, *val; val = skb_header_pointer(skb, nhs + hdr_len, sizeof(_val), &_val); if (!val) return -EINVAL; tpi->proto = proto; if ((*val & 0xF0) != 0x40) hdr_len += 4; } tpi->hdr_len = hdr_len; /* ERSPAN ver 1 and 2 protocol sets GRE key field * to 0 and sets the configured key in the * inner erspan header field */ if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) || greh->protocol == htons(ETH_P_ERSPAN2)) { struct erspan_base_hdr *ershdr; if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) return -EINVAL; ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len); tpi->key = cpu_to_be32(get_session_id(ershdr)); } return hdr_len; } EXPORT_SYMBOL(gre_parse_header); static int gre_rcv(struct sk_buff *skb) { const struct gre_protocol *proto; u8 ver; int ret; if (!pskb_may_pull(skb, 12)) goto drop; ver = skb->data[1]&0x7f; if (ver >= GREPROTO_MAX) goto drop; rcu_read_lock(); proto = rcu_dereference(gre_proto[ver]); if (!proto || !proto->handler) goto drop_nohandler; ret = proto->handler(skb); rcu_read_unlock(); return ret; drop_nohandler: rcu_read_unlock(); dev_core_stats_rx_nohandler_inc(skb->dev); kfree_skb(skb); return NET_RX_DROP; drop: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb(skb); return NET_RX_DROP; } static int gre_err(struct sk_buff *skb, u32 info) { const struct gre_protocol *proto; const struct iphdr *iph = (const struct iphdr *)skb->data; u8 ver = skb->data[(iph->ihl<<2) + 1]&0x7f; int err = 0; if (ver >= GREPROTO_MAX) return -EINVAL; rcu_read_lock(); proto = rcu_dereference(gre_proto[ver]); if (proto && proto->err_handler) proto->err_handler(skb, info); else err = -EPROTONOSUPPORT; rcu_read_unlock(); return err; } static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexer driver\n"); if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { pr_err("can't add protocol\n"); return -EAGAIN; } return 0; } static void __exit gre_exit(void) { inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } module_init(gre_init); module_exit(gre_exit); MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver"); MODULE_AUTHOR("D. Kozlov <xeb@mail.ru>"); MODULE_LICENSE("GPL"); |
| 2 2 2 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 | // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 TDLS handling code * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2014, Intel Corporation * Copyright 2014 Intel Mobile Communications GmbH * Copyright 2015 - 2016 Intel Deutschland GmbH * Copyright (C) 2019, 2021-2026 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/log2.h> #include <net/cfg80211.h> #include <linux/rtnetlink.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #include "wme.h" /* give usermode some time for retries in setting up the TDLS session */ #define TDLS_PEER_SETUP_TIMEOUT (15 * HZ) void ieee80211_tdls_peer_del_work(struct wiphy *wiphy, struct wiphy_work *wk) { struct ieee80211_sub_if_data *sdata; struct ieee80211_local *local; sdata = container_of(wk, struct ieee80211_sub_if_data, u.mgd.tdls_peer_del_work.work); local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); if (!is_zero_ether_addr(sdata->u.mgd.tdls_peer)) { tdls_dbg(sdata, "TDLS del peer %pM\n", sdata->u.mgd.tdls_peer); sta_info_destroy_addr(sdata, sdata->u.mgd.tdls_peer); eth_zero_addr(sdata->u.mgd.tdls_peer); } } static void ieee80211_tdls_add_ext_capab(struct ieee80211_link_data *link, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; bool chan_switch = local->hw.wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH; bool wider_band = ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) && !ifmgd->tdls_wider_bw_prohibited; bool buffer_sta = ieee80211_hw_check(&local->hw, SUPPORTS_TDLS_BUFFER_STA); struct ieee80211_supported_band *sband = ieee80211_get_link_sband(link); bool vht = sband && sband->vht_cap.vht_supported; u8 *pos = skb_put(skb, 10); *pos++ = WLAN_EID_EXT_CAPABILITY; *pos++ = 8; /* len */ *pos++ = 0x0; *pos++ = 0x0; *pos++ = 0x0; *pos++ = (chan_switch ? WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH : 0) | (buffer_sta ? WLAN_EXT_CAPA4_TDLS_BUFFER_STA : 0); *pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED; *pos++ = 0; *pos++ = 0; *pos++ = (vht && wider_band) ? WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED : 0; } static u8 ieee80211_tdls_add_subband(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u16 start, u16 end, u16 spacing) { u8 subband_cnt = 0, ch_cnt = 0; struct ieee80211_channel *ch; struct cfg80211_chan_def chandef; int i, subband_start; struct wiphy *wiphy = sdata->local->hw.wiphy; for (i = start; i <= end; i += spacing) { if (!ch_cnt) subband_start = i; ch = ieee80211_get_channel(sdata->local->hw.wiphy, i); if (ch) { /* we will be active on the channel */ cfg80211_chandef_create(&chandef, ch, NL80211_CHAN_NO_HT); if (cfg80211_reg_can_beacon_relax(wiphy, &chandef, sdata->wdev.iftype)) { ch_cnt++; /* * check if the next channel is also part of * this allowed range */ continue; } } /* * we've reached the end of a range, with allowed channels * found */ if (ch_cnt) { u8 *pos = skb_put(skb, 2); *pos++ = ieee80211_frequency_to_channel(subband_start); *pos++ = ch_cnt; subband_cnt++; ch_cnt = 0; } } /* all channels in the requested range are allowed - add them here */ if (ch_cnt) { u8 *pos = skb_put(skb, 2); *pos++ = ieee80211_frequency_to_channel(subband_start); *pos++ = ch_cnt; subband_cnt++; } return subband_cnt; } static void ieee80211_tdls_add_supp_channels(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { /* * Add possible channels for TDLS. These are channels that are allowed * to be active. */ u8 subband_cnt; u8 *pos = skb_put(skb, 2); *pos++ = WLAN_EID_SUPPORTED_CHANNELS; /* * 5GHz and 2GHz channels numbers can overlap. Ignore this for now, as * this doesn't happen in real world scenarios. */ /* 2GHz, with 5MHz spacing */ subband_cnt = ieee80211_tdls_add_subband(sdata, skb, 2412, 2472, 5); /* 5GHz, with 20MHz spacing */ subband_cnt += ieee80211_tdls_add_subband(sdata, skb, 5000, 5825, 20); /* length */ *pos = 2 * subband_cnt; } static void ieee80211_tdls_add_oper_classes(struct ieee80211_link_data *link, struct sk_buff *skb) { u8 *pos; u8 op_class; if (!ieee80211_chandef_to_operating_class(&link->conf->chanreq.oper, &op_class)) return; pos = skb_put(skb, 4); *pos++ = WLAN_EID_SUPPORTED_REGULATORY_CLASSES; *pos++ = 2; /* len */ *pos++ = op_class; *pos++ = op_class; /* give current operating class as alternate too */ } static void ieee80211_tdls_add_bss_coex_ie(struct sk_buff *skb) { u8 *pos = skb_put(skb, 3); *pos++ = WLAN_EID_BSS_COEX_2040; *pos++ = 1; /* len */ *pos++ = WLAN_BSS_COEX_INFORMATION_REQUEST; } static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_link_data *link, u16 status_code) { struct ieee80211_supported_band *sband; /* The capability will be 0 when sending a failure code */ if (status_code != 0) return 0; sband = ieee80211_get_link_sband(link); if (sband && sband->band == NL80211_BAND_2GHZ) { return WLAN_CAPABILITY_SHORT_SLOT_TIME | WLAN_CAPABILITY_SHORT_PREAMBLE; } return 0; } static void ieee80211_tdls_add_link_ie(struct ieee80211_link_data *link, struct sk_buff *skb, const u8 *peer, bool initiator) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_tdls_lnkie *lnkid; const u8 *init_addr, *rsp_addr; if (initiator) { init_addr = sdata->vif.addr; rsp_addr = peer; } else { init_addr = peer; rsp_addr = sdata->vif.addr; } lnkid = skb_put(skb, sizeof(struct ieee80211_tdls_lnkie)); lnkid->ie_type = WLAN_EID_LINK_ID; lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2; memcpy(lnkid->bssid, link->u.mgd.bssid, ETH_ALEN); memcpy(lnkid->init_sta, init_addr, ETH_ALEN); memcpy(lnkid->resp_sta, rsp_addr, ETH_ALEN); } static void ieee80211_tdls_add_aid(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { u8 *pos = skb_put(skb, 4); *pos++ = WLAN_EID_AID; *pos++ = 2; /* len */ put_unaligned_le16(sdata->vif.cfg.aid, pos); } /* translate numbering in the WMM parameter IE to the mac80211 notation */ static enum ieee80211_ac_numbers ieee80211_ac_from_wmm(int ac) { switch (ac) { default: WARN_ON_ONCE(1); fallthrough; case 0: return IEEE80211_AC_BE; case 1: return IEEE80211_AC_BK; case 2: return IEEE80211_AC_VI; case 3: return IEEE80211_AC_VO; } } static u8 ieee80211_wmm_aci_aifsn(int aifsn, bool acm, int aci) { u8 ret; ret = aifsn & 0x0f; if (acm) ret |= 0x10; ret |= (aci << 5) & 0x60; return ret; } static u8 ieee80211_wmm_ecw(u16 cw_min, u16 cw_max) { return ((ilog2(cw_min + 1) << 0x0) & 0x0f) | ((ilog2(cw_max + 1) << 0x4) & 0xf0); } static void ieee80211_tdls_add_wmm_param_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_wmm_param_ie *wmm; struct ieee80211_tx_queue_params *txq; int i; wmm = skb_put_zero(skb, sizeof(*wmm)); wmm->element_id = WLAN_EID_VENDOR_SPECIFIC; wmm->len = sizeof(*wmm) - 2; wmm->oui[0] = 0x00; /* Microsoft OUI 00:50:F2 */ wmm->oui[1] = 0x50; wmm->oui[2] = 0xf2; wmm->oui_type = 2; /* WME */ wmm->oui_subtype = 1; /* WME param */ wmm->version = 1; /* WME ver */ wmm->qos_info = 0; /* U-APSD not in use */ /* * Use the EDCA parameters defined for the BSS, or default if the AP * doesn't support it, as mandated by 802.11-2012 section 10.22.4 */ for (i = 0; i < IEEE80211_NUM_ACS; i++) { txq = &sdata->deflink.tx_conf[ieee80211_ac_from_wmm(i)]; wmm->ac[i].aci_aifsn = ieee80211_wmm_aci_aifsn(txq->aifs, txq->acm, i); wmm->ac[i].cw = ieee80211_wmm_ecw(txq->cw_min, txq->cw_max); wmm->ac[i].txop_limit = cpu_to_le16(txq->txop); } } static void ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { /* IEEE802.11ac-2013 Table E-4 */ static const u16 centers_80mhz[] = { 5210, 5290, 5530, 5610, 5690, 5775 }; struct cfg80211_chan_def uc = sta->tdls_chandef; enum nl80211_chan_width max_width; int i; switch (ieee80211_sta_current_bw(&sta->deflink, &uc, IEEE80211_STA_BW_RX_FROM_STA)) { case IEEE80211_STA_RX_BW_20: max_width = NL80211_CHAN_WIDTH_20; break; case IEEE80211_STA_RX_BW_40: max_width = NL80211_CHAN_WIDTH_40; break; default: /* 80 or higher, only support upgrade to 80 */ max_width = NL80211_CHAN_WIDTH_80; break; } if (uc.width >= max_width) return; /* * Channel usage constrains in the IEEE802.11ac-2013 specification only * allow expanding a 20MHz channel to 80MHz in a single way. In * addition, there are no 40MHz allowed channels that are not part of * the allowed 80MHz range in the 5GHz spectrum (the relevant one here). */ for (i = 0; i < ARRAY_SIZE(centers_80mhz); i++) if (abs(uc.chan->center_freq - centers_80mhz[i]) <= 30) { uc.center_freq1 = centers_80mhz[i]; uc.center_freq2 = 0; uc.width = NL80211_CHAN_WIDTH_80; break; } if (!uc.center_freq1) return; /* proceed to downgrade the chandef until usable or the same as AP BW */ while (uc.width > max_width || (uc.width > sta->tdls_chandef.width && !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc, sdata->wdev.iftype))) ieee80211_chandef_downgrade(&uc, NULL); if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) { tdls_dbg(sdata, "TDLS ch width upgraded %d -> %d\n", sta->tdls_chandef.width, uc.width); /* * the station is not yet authorized when BW upgrade is done, * locking is not required */ sta->tdls_chandef = uc; } } static void ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link, struct sk_buff *skb, const u8 *peer, u8 action_code, bool initiator, const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_supported_band *sband; struct ieee80211_local *local = sdata->local; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; const struct ieee80211_sta_he_cap *he_cap; const struct ieee80211_sta_eht_cap *eht_cap; struct sta_info *sta = NULL; size_t offset = 0, noffset; u8 *pos; sband = ieee80211_get_link_sband(link); if (WARN_ON_ONCE(!sband)) return; ieee80211_put_srates_elem(skb, sband, 0, 0, WLAN_EID_SUPP_RATES); ieee80211_put_srates_elem(skb, sband, 0, 0, WLAN_EID_EXT_SUPP_RATES); ieee80211_tdls_add_supp_channels(sdata, skb); /* add any custom IEs that go before Extended Capabilities */ if (extra_ies_len) { static const u8 before_ext_cap[] = { WLAN_EID_SUPP_RATES, WLAN_EID_COUNTRY, WLAN_EID_EXT_SUPP_RATES, WLAN_EID_SUPPORTED_CHANNELS, WLAN_EID_RSN, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_ext_cap, ARRAY_SIZE(before_ext_cap), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } ieee80211_tdls_add_ext_capab(link, skb); /* add the QoS element if we support it */ if (local->hw.queues >= IEEE80211_NUM_ACS && action_code != WLAN_PUB_ACTION_TDLS_DISCOVER_RES) ieee80211_add_wmm_info_ie(skb_put(skb, 9), 0); /* no U-APSD */ /* add any custom IEs that go before HT capabilities */ if (extra_ies_len) { static const u8 before_ht_cap[] = { WLAN_EID_SUPP_RATES, WLAN_EID_COUNTRY, WLAN_EID_EXT_SUPP_RATES, WLAN_EID_SUPPORTED_CHANNELS, WLAN_EID_RSN, WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_CAPA, WLAN_EID_FAST_BSS_TRANSITION, WLAN_EID_TIMEOUT_INTERVAL, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_ht_cap, ARRAY_SIZE(before_ht_cap), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } /* we should have the peer STA if we're already responding */ if (action_code == WLAN_TDLS_SETUP_RESPONSE) { sta = sta_info_get(sdata, peer); if (WARN_ON_ONCE(!sta)) return; sta->tdls_chandef = link->conf->chanreq.oper; } ieee80211_tdls_add_oper_classes(link, skb); /* * with TDLS we can switch channels, and HT-caps are not necessarily * the same on all bands. The specification limits the setup to a * single HT-cap, so use the current band for now. */ memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap)); if ((action_code == WLAN_TDLS_SETUP_REQUEST || action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) && ht_cap.ht_supported) { ieee80211_apply_htcap_overrides(sdata, &ht_cap); /* disable SMPS in TDLS initiator */ ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED << IEEE80211_HT_CAP_SM_PS_SHIFT; pos = skb_put(skb, sizeof(struct ieee80211_ht_cap) + 2); ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap); } else if (action_code == WLAN_TDLS_SETUP_RESPONSE && ht_cap.ht_supported && sta->sta.deflink.ht_cap.ht_supported) { /* the peer caps are already intersected with our own */ memcpy(&ht_cap, &sta->sta.deflink.ht_cap, sizeof(ht_cap)); pos = skb_put(skb, sizeof(struct ieee80211_ht_cap) + 2); ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap); } if (ht_cap.ht_supported && (ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40)) ieee80211_tdls_add_bss_coex_ie(skb); ieee80211_tdls_add_link_ie(link, skb, peer, initiator); /* add any custom IEs that go before VHT capabilities */ if (extra_ies_len) { static const u8 before_vht_cap[] = { WLAN_EID_SUPP_RATES, WLAN_EID_COUNTRY, WLAN_EID_EXT_SUPP_RATES, WLAN_EID_SUPPORTED_CHANNELS, WLAN_EID_RSN, WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_CAPA, WLAN_EID_FAST_BSS_TRANSITION, WLAN_EID_TIMEOUT_INTERVAL, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_MULTI_BAND, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_vht_cap, ARRAY_SIZE(before_vht_cap), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } /* add AID if VHT, HE or EHT capabilities supported */ memcpy(&vht_cap, &sband->vht_cap, sizeof(vht_cap)); he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); if ((vht_cap.vht_supported || he_cap || eht_cap) && (action_code == WLAN_TDLS_SETUP_REQUEST || action_code == WLAN_TDLS_SETUP_RESPONSE)) ieee80211_tdls_add_aid(sdata, skb); /* build the VHT-cap similarly to the HT-cap */ if ((action_code == WLAN_TDLS_SETUP_REQUEST || action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) && vht_cap.vht_supported) { ieee80211_apply_vhtcap_overrides(sdata, &vht_cap); pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap); } else if (action_code == WLAN_TDLS_SETUP_RESPONSE && vht_cap.vht_supported && sta->sta.deflink.vht_cap.vht_supported) { /* the peer caps are already intersected with our own */ memcpy(&vht_cap, &sta->sta.deflink.vht_cap, sizeof(vht_cap)); pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap); /* * if both peers support WIDER_BW, we can expand the chandef to * a wider compatible one, up to 80MHz */ if (test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) ieee80211_tdls_chandef_vht_upgrade(sdata, sta); } /* add any custom IEs that go before HE capabilities */ if (extra_ies_len) { static const u8 before_he_cap[] = { WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_REQ_PARAMS, WLAN_EID_AP_CSN, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_he_cap, ARRAY_SIZE(before_he_cap), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } /* build the HE-cap from sband */ if (action_code == WLAN_TDLS_SETUP_REQUEST || action_code == WLAN_TDLS_SETUP_RESPONSE || action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) { ieee80211_put_he_cap(skb, sdata, sband, NULL); /* Build HE 6Ghz capa IE from sband */ if (sband->band == NL80211_BAND_6GHZ) ieee80211_put_he_6ghz_cap(skb, sdata, link->smps_mode); } /* add any custom IEs that go before EHT capabilities */ if (extra_ies_len) { static const u8 before_he_cap[] = { WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_REQ_PARAMS, WLAN_EID_AP_CSN, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_he_cap, ARRAY_SIZE(before_he_cap), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } /* build the EHT-cap from sband */ if (action_code == WLAN_TDLS_SETUP_REQUEST || action_code == WLAN_TDLS_SETUP_RESPONSE || action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) ieee80211_put_eht_cap(skb, sdata, sband, NULL); /* add any remaining IEs */ if (extra_ies_len) { noffset = extra_ies_len; skb_put_data(skb, extra_ies + offset, noffset - offset); } } static void ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_link_data *link, struct sk_buff *skb, const u8 *peer, bool initiator, const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; size_t offset = 0, noffset; struct sta_info *sta, *ap_sta; struct ieee80211_supported_band *sband; u8 *pos; sband = ieee80211_get_link_sband(link); if (WARN_ON_ONCE(!sband)) return; sta = sta_info_get(sdata, peer); ap_sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr); if (WARN_ON_ONCE(!sta || !ap_sta)) return; sta->tdls_chandef = link->conf->chanreq.oper; /* add any custom IEs that go before the QoS IE */ if (extra_ies_len) { static const u8 before_qos[] = { WLAN_EID_RSN, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_qos, ARRAY_SIZE(before_qos), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } /* add the QoS param IE if both the peer and we support it */ if (local->hw.queues >= IEEE80211_NUM_ACS && sta->sta.wme) ieee80211_tdls_add_wmm_param_ie(sdata, skb); /* add any custom IEs that go before HT operation */ if (extra_ies_len) { static const u8 before_ht_op[] = { WLAN_EID_RSN, WLAN_EID_QOS_CAPA, WLAN_EID_FAST_BSS_TRANSITION, WLAN_EID_TIMEOUT_INTERVAL, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_ht_op, ARRAY_SIZE(before_ht_op), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } /* * if HT support is only added in TDLS, we need an HT-operation IE. * add the IE as required by IEEE802.11-2012 9.23.3.2. */ if (!ap_sta->sta.deflink.ht_cap.ht_supported && sta->sta.deflink.ht_cap.ht_supported) { u16 prot = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED | IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT | IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation)); ieee80211_ie_build_ht_oper(pos, &sta->sta.deflink.ht_cap, &link->conf->chanreq.oper, prot, true); } ieee80211_tdls_add_link_ie(link, skb, peer, initiator); /* only include VHT-operation if not on the 2.4GHz band */ if (sband->band != NL80211_BAND_2GHZ && sta->sta.deflink.vht_cap.vht_supported) { /* * if both peers support WIDER_BW, we can expand the chandef to * a wider compatible one, up to 80MHz */ if (test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) ieee80211_tdls_chandef_vht_upgrade(sdata, sta); pos = skb_put(skb, 2 + sizeof(struct ieee80211_vht_operation)); ieee80211_ie_build_vht_oper(pos, &sta->sta.deflink.vht_cap, &sta->tdls_chandef); } /* add any remaining IEs */ if (extra_ies_len) { noffset = extra_ies_len; skb_put_data(skb, extra_ies + offset, noffset - offset); } } static void ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_link_data *link, struct sk_buff *skb, const u8 *peer, bool initiator, const u8 *extra_ies, size_t extra_ies_len, u8 oper_class, struct cfg80211_chan_def *chandef) { struct ieee80211_tdls_data *tf; size_t offset = 0, noffset; if (WARN_ON_ONCE(!chandef)) return; tf = (void *)skb->data; tf->u.chan_switch_req.target_channel = ieee80211_frequency_to_channel(chandef->chan->center_freq); tf->u.chan_switch_req.oper_class = oper_class; if (extra_ies_len) { static const u8 before_lnkie[] = { WLAN_EID_SECONDARY_CHANNEL_OFFSET, }; noffset = ieee80211_ie_split(extra_ies, extra_ies_len, before_lnkie, ARRAY_SIZE(before_lnkie), offset); skb_put_data(skb, extra_ies + offset, noffset - offset); offset = noffset; } ieee80211_tdls_add_link_ie(link, skb, peer, initiator); /* add any remaining IEs */ if (extra_ies_len) { noffset = extra_ies_len; skb_put_data(skb, extra_ies + offset, noffset - offset); } } static void ieee80211_tdls_add_chan_switch_resp_ies(struct ieee80211_link_data *link, struct sk_buff *skb, const u8 *peer, u16 status_code, bool initiator, const u8 *extra_ies, size_t extra_ies_len) { if (status_code == 0) ieee80211_tdls_add_link_ie(link, skb, peer, initiator); if (extra_ies_len) skb_put_data(skb, extra_ies, extra_ies_len); } static void ieee80211_tdls_add_ies(struct ieee80211_link_data *link, struct sk_buff *skb, const u8 *peer, u8 action_code, u16 status_code, bool initiator, const u8 *extra_ies, size_t extra_ies_len, u8 oper_class, struct cfg80211_chan_def *chandef) { switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: case WLAN_TDLS_SETUP_RESPONSE: case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: if (status_code == 0) ieee80211_tdls_add_setup_start_ies(link, skb, peer, action_code, initiator, extra_ies, extra_ies_len); break; case WLAN_TDLS_SETUP_CONFIRM: if (status_code == 0) ieee80211_tdls_add_setup_cfm_ies(link, skb, peer, initiator, extra_ies, extra_ies_len); break; case WLAN_TDLS_TEARDOWN: case WLAN_TDLS_DISCOVERY_REQUEST: if (extra_ies_len) skb_put_data(skb, extra_ies, extra_ies_len); if (status_code == 0 || action_code == WLAN_TDLS_TEARDOWN) ieee80211_tdls_add_link_ie(link, skb, peer, initiator); break; case WLAN_TDLS_CHANNEL_SWITCH_REQUEST: ieee80211_tdls_add_chan_switch_req_ies(link, skb, peer, initiator, extra_ies, extra_ies_len, oper_class, chandef); break; case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE: ieee80211_tdls_add_chan_switch_resp_ies(link, skb, peer, status_code, initiator, extra_ies, extra_ies_len); break; } } static int ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_link_data *link, const u8 *peer, u8 action_code, u8 dialog_token, u16 status_code, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_tdls_data *tf; tf = skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); memcpy(tf->da, peer, ETH_ALEN); memcpy(tf->sa, sdata->vif.addr, ETH_ALEN); tf->ether_type = cpu_to_be16(ETH_P_TDLS); tf->payload_type = WLAN_TDLS_SNAP_RFTYPE; /* network header is after the ethernet header */ skb_set_network_header(skb, ETH_HLEN); switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: tf->category = WLAN_CATEGORY_TDLS; tf->action_code = WLAN_TDLS_SETUP_REQUEST; skb_put(skb, sizeof(tf->u.setup_req)); tf->u.setup_req.dialog_token = dialog_token; tf->u.setup_req.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(link, status_code)); break; case WLAN_TDLS_SETUP_RESPONSE: tf->category = WLAN_CATEGORY_TDLS; tf->action_code = WLAN_TDLS_SETUP_RESPONSE; skb_put(skb, sizeof(tf->u.setup_resp)); tf->u.setup_resp.status_code = cpu_to_le16(status_code); tf->u.setup_resp.dialog_token = dialog_token; tf->u.setup_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(link, status_code)); break; case WLAN_TDLS_SETUP_CONFIRM: tf->category = WLAN_CATEGORY_TDLS; tf->action_code = WLAN_TDLS_SETUP_CONFIRM; skb_put(skb, sizeof(tf->u.setup_cfm)); tf->u.setup_cfm.status_code = cpu_to_le16(status_code); tf->u.setup_cfm.dialog_token = dialog_token; break; case WLAN_TDLS_TEARDOWN: tf->category = WLAN_CATEGORY_TDLS; tf->action_code = WLAN_TDLS_TEARDOWN; skb_put(skb, sizeof(tf->u.teardown)); tf->u.teardown.reason_code = cpu_to_le16(status_code); break; case WLAN_TDLS_DISCOVERY_REQUEST: tf->category = WLAN_CATEGORY_TDLS; tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST; skb_put(skb, sizeof(tf->u.discover_req)); tf->u.discover_req.dialog_token = dialog_token; break; case WLAN_TDLS_CHANNEL_SWITCH_REQUEST: tf->category = WLAN_CATEGORY_TDLS; tf->action_code = WLAN_TDLS_CHANNEL_SWITCH_REQUEST; skb_put(skb, sizeof(tf->u.chan_switch_req)); break; case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE: tf->category = WLAN_CATEGORY_TDLS; tf->action_code = WLAN_TDLS_CHANNEL_SWITCH_RESPONSE; skb_put(skb, sizeof(tf->u.chan_switch_resp)); tf->u.chan_switch_resp.status_code = cpu_to_le16(status_code); break; default: return -EINVAL; } return 0; } static int ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, struct ieee80211_link_data *link, u8 action_code, u8 dialog_token, u16 status_code, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_mgmt *mgmt; if (action_code != WLAN_PUB_ACTION_TDLS_DISCOVER_RES) return -EINVAL; mgmt = skb_put_zero(skb, IEEE80211_MIN_ACTION_SIZE(tdls_discover_resp)); memcpy(mgmt->da, peer, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); memcpy(mgmt->bssid, link->u.mgd.bssid, ETH_ALEN); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); mgmt->u.action.category = WLAN_CATEGORY_PUBLIC; mgmt->u.action.action_code = WLAN_PUB_ACTION_TDLS_DISCOVER_RES; mgmt->u.action.tdls_discover_resp.dialog_token = dialog_token; mgmt->u.action.tdls_discover_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(link, status_code)); return 0; } static struct sk_buff * ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata, const u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, bool initiator, const u8 *extra_ies, size_t extra_ies_len, u8 oper_class, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; int ret; struct ieee80211_link_data *link; link_id = link_id >= 0 ? link_id : 0; rcu_read_lock(); link = rcu_dereference(sdata->link[link_id]); if (WARN_ON(!link)) goto unlock; skb = netdev_alloc_skb(sdata->dev, local->hw.extra_tx_headroom + max(sizeof(struct ieee80211_mgmt), sizeof(struct ieee80211_tdls_data)) + 50 + /* supported rates */ 10 + /* ext capab */ 26 + /* max(WMM-info, WMM-param) */ 2 + max(sizeof(struct ieee80211_ht_cap), sizeof(struct ieee80211_ht_operation)) + 2 + max(sizeof(struct ieee80211_vht_cap), sizeof(struct ieee80211_vht_operation)) + 2 + 1 + sizeof(struct ieee80211_he_cap_elem) + sizeof(struct ieee80211_he_mcs_nss_supp) + IEEE80211_HE_PPE_THRES_MAX_LEN + 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa) + 2 + 1 + sizeof(struct ieee80211_eht_cap_elem) + sizeof(struct ieee80211_eht_mcs_nss_supp) + IEEE80211_EHT_PPE_THRES_MAX_LEN + 50 + /* supported channels */ 3 + /* 40/20 BSS coex */ 4 + /* AID */ 4 + /* oper classes */ extra_ies_len + sizeof(struct ieee80211_tdls_lnkie)); if (!skb) goto unlock; skb_reserve(skb, local->hw.extra_tx_headroom); switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: case WLAN_TDLS_SETUP_RESPONSE: case WLAN_TDLS_SETUP_CONFIRM: case WLAN_TDLS_TEARDOWN: case WLAN_TDLS_DISCOVERY_REQUEST: case WLAN_TDLS_CHANNEL_SWITCH_REQUEST: case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE: ret = ieee80211_prep_tdls_encap_data(local->hw.wiphy, sdata->dev, link, peer, action_code, dialog_token, status_code, skb); break; case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: ret = ieee80211_prep_tdls_direct(local->hw.wiphy, sdata->dev, peer, link, action_code, dialog_token, status_code, skb); break; default: ret = -EOPNOTSUPP; break; } if (ret < 0) goto fail; ieee80211_tdls_add_ies(link, skb, peer, action_code, status_code, initiator, extra_ies, extra_ies_len, oper_class, chandef); rcu_read_unlock(); return skb; fail: dev_kfree_skb(skb); unlock: rcu_read_unlock(); return NULL; } static int ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *extra_ies, size_t extra_ies_len, u8 oper_class, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sk_buff *skb = NULL; struct sta_info *sta; u32 flags = 0; int ret = 0; rcu_read_lock(); sta = sta_info_get(sdata, peer); /* infer the initiator if we can, to support old userspace */ switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: if (sta) { set_sta_flag(sta, WLAN_STA_TDLS_INITIATOR); sta->sta.tdls_initiator = false; } fallthrough; case WLAN_TDLS_SETUP_CONFIRM: case WLAN_TDLS_DISCOVERY_REQUEST: initiator = true; break; case WLAN_TDLS_SETUP_RESPONSE: /* * In some testing scenarios, we send a request and response. * Make the last packet sent take effect for the initiator * value. */ if (sta) { clear_sta_flag(sta, WLAN_STA_TDLS_INITIATOR); sta->sta.tdls_initiator = true; } fallthrough; case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: initiator = false; break; case WLAN_TDLS_TEARDOWN: case WLAN_TDLS_CHANNEL_SWITCH_REQUEST: case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE: /* any value is ok */ break; default: ret = -EOPNOTSUPP; break; } if (sta && test_sta_flag(sta, WLAN_STA_TDLS_INITIATOR)) initiator = true; rcu_read_unlock(); if (ret < 0) goto fail; skb = ieee80211_tdls_build_mgmt_packet_data(sdata, peer, link_id, action_code, dialog_token, status_code, initiator, extra_ies, extra_ies_len, oper_class, chandef); if (!skb) { ret = -EINVAL; goto fail; } if (action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) { ieee80211_tx_skb_tid(sdata, skb, 7, link_id); return 0; } /* * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise * we should default to AC_VI. */ switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: case WLAN_TDLS_SETUP_RESPONSE: skb->priority = 256 + 2; break; default: skb->priority = 256 + 5; break; } /* * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress. * Later, if no ACK is returned from peer, we will re-send the teardown * packet through the AP. */ if ((action_code == WLAN_TDLS_TEARDOWN) && ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) { bool try_resend; /* Should we keep skb for possible resend */ /* If not sending directly to peer - no point in keeping skb */ rcu_read_lock(); sta = sta_info_get(sdata, peer); try_resend = sta && test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); rcu_read_unlock(); spin_lock_bh(&sdata->u.mgd.teardown_lock); if (try_resend && !sdata->u.mgd.teardown_skb) { /* Mark it as requiring TX status callback */ flags |= IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_INTFL_MLME_CONN_TX; /* * skb is copied since mac80211 will later set * properties that might not be the same as the AP, * such as encryption, QoS, addresses, etc. * * No problem if skb_copy() fails, so no need to check. */ sdata->u.mgd.teardown_skb = skb_copy(skb, GFP_ATOMIC); sdata->u.mgd.orig_teardown_skb = skb; } spin_unlock_bh(&sdata->u.mgd.teardown_lock); } /* disable bottom halves when entering the Tx path */ local_bh_disable(); __ieee80211_subif_start_xmit(skb, dev, flags, IEEE80211_TX_CTRL_MLO_LINK_UNSPEC, NULL); local_bh_enable(); return ret; fail: dev_kfree_skb(skb); return ret; } static int ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; enum ieee80211_smps_mode smps_mode = sdata->deflink.u.mgd.driver_smps_mode; int ret; /* don't support setup with forced SMPS mode that's not off */ if (smps_mode != IEEE80211_SMPS_AUTOMATIC && smps_mode != IEEE80211_SMPS_OFF) { tdls_dbg(sdata, "Aborting TDLS setup due to SMPS mode %d\n", smps_mode); return -EOPNOTSUPP; } lockdep_assert_wiphy(local->hw.wiphy); /* we don't support concurrent TDLS peer setups */ if (!is_zero_ether_addr(sdata->u.mgd.tdls_peer) && !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) { ret = -EBUSY; goto out_unlock; } /* * make sure we have a STA representing the peer so we drop or buffer * non-TDLS-setup frames to the peer. We can't send other packets * during setup through the AP path. * Allow error packets to be sent - sometimes we don't even add a STA * before failing the setup. */ if (status_code == 0) { rcu_read_lock(); if (!sta_info_get(sdata, peer)) { rcu_read_unlock(); ret = -ENOLINK; goto out_unlock; } rcu_read_unlock(); } ieee80211_flush_queues(local, sdata, false); memcpy(sdata->u.mgd.tdls_peer, peer, ETH_ALEN); /* we cannot take the mutex while preparing the setup packet */ ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, extra_ies, extra_ies_len, 0, NULL); if (ret < 0) { eth_zero_addr(sdata->u.mgd.tdls_peer); return ret; } wiphy_delayed_work_queue(sdata->local->hw.wiphy, &sdata->u.mgd.tdls_peer_del_work, TDLS_PEER_SETUP_TIMEOUT); return 0; out_unlock: return ret; } static int ieee80211_tdls_mgmt_teardown(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret; /* * No packets can be transmitted to the peer via the AP during setup - * the STA is set as a TDLS peer, but is not authorized. * During teardown, we prevent direct transmissions by stopping the * queues and flushing all direct packets. */ ieee80211_stop_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN); ieee80211_flush_queues(local, sdata, false); ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, extra_ies, extra_ies_len, 0, NULL); if (ret < 0) sdata_err(sdata, "Failed sending TDLS teardown packet %d\n", ret); /* * Remove the STA AUTH flag to force further traffic through the AP. If * the STA was unreachable, it was already removed. */ rcu_read_lock(); sta = sta_info_get(sdata, peer); if (sta) clear_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); rcu_read_unlock(); ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN); return 0; } int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); int ret; if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) return -EOPNOTSUPP; /* make sure we are in managed mode, and associated */ if (sdata->vif.type != NL80211_IFTYPE_STATION || !sdata->u.mgd.associated) return -EINVAL; switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: case WLAN_TDLS_SETUP_RESPONSE: ret = ieee80211_tdls_mgmt_setup(wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, extra_ies, extra_ies_len); break; case WLAN_TDLS_TEARDOWN: ret = ieee80211_tdls_mgmt_teardown(wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, extra_ies, extra_ies_len); break; case WLAN_TDLS_DISCOVERY_REQUEST: /* * Protect the discovery so we can hear the TDLS discovery * response frame. It is transmitted directly and not buffered * by the AP. */ drv_mgd_protect_tdls_discover(sdata->local, sdata, link_id); fallthrough; case WLAN_TDLS_SETUP_CONFIRM: case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: /* no special handling */ ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, extra_ies, extra_ies_len, 0, NULL); break; default: ret = -EOPNOTSUPP; break; } tdls_dbg(sdata, "TDLS mgmt action %d peer %pM link_id %d status %d\n", action_code, peer, link_id, ret); return ret; } static void iee80211_tdls_recalc_chanctx(struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *ctx; enum nl80211_chan_width width; struct ieee80211_supported_band *sband; lockdep_assert_wiphy(local->hw.wiphy); conf = rcu_dereference_protected(sdata->vif.bss_conf.chanctx_conf, lockdep_is_held(&local->hw.wiphy->mtx)); if (conf) { width = conf->def.width; sband = local->hw.wiphy->bands[conf->def.chan->band]; ctx = container_of(conf, struct ieee80211_chanctx, conf); ieee80211_recalc_chanctx_chantype(local, ctx); /* if width changed and a peer is given, update its BW */ if (width != conf->def.width && sta && test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) { enum ieee80211_sta_rx_bandwidth bw; bw = ieee80211_chan_width_to_rx_bw(conf->def.width); bw = min(bw, ieee80211_sta_current_bw(&sta->deflink, &conf->def, IEEE80211_STA_BW_RX_FROM_STA)); if (bw != sta->sta.deflink.bandwidth) { sta->sta.deflink.bandwidth = bw; rate_control_rate_update(local, sband, &sta->deflink, IEEE80211_RC_BW_CHANGED); /* * if a TDLS peer BW was updated, we need to * recalc the chandef width again, to get the * correct chanctx min_def */ ieee80211_recalc_chanctx_chantype(local, ctx); } } } } static int iee80211_tdls_have_ht_peers(struct ieee80211_sub_if_data *sdata) { struct sta_info *sta; bool result = false; rcu_read_lock(); list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH) || !sta->sta.deflink.ht_cap.ht_supported) continue; result = true; break; } rcu_read_unlock(); return result; } static void iee80211_tdls_recalc_ht_protection(struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { bool tdls_ht; u16 protection = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED | IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT | IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; u16 opmode; /* Nothing to do if the BSS connection uses (at least) HT */ if (sdata->deflink.u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT) return; tdls_ht = (sta && sta->sta.deflink.ht_cap.ht_supported) || iee80211_tdls_have_ht_peers(sdata); opmode = sdata->vif.bss_conf.ht_operation_mode; if (tdls_ht) opmode |= protection; else opmode &= ~protection; if (opmode == sdata->vif.bss_conf.ht_operation_mode) return; sdata->vif.bss_conf.ht_operation_mode = opmode; ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_HT); } int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper) { struct sta_info *sta; struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; int ret; lockdep_assert_wiphy(local->hw.wiphy); if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) return -EOPNOTSUPP; if (sdata->vif.type != NL80211_IFTYPE_STATION || !sdata->vif.cfg.assoc) return -EINVAL; switch (oper) { case NL80211_TDLS_ENABLE_LINK: case NL80211_TDLS_DISABLE_LINK: break; case NL80211_TDLS_TEARDOWN: case NL80211_TDLS_SETUP: case NL80211_TDLS_DISCOVERY_REQ: /* We don't support in-driver setup/teardown/discovery */ return -EOPNOTSUPP; } /* protect possible bss_conf changes and avoid concurrency in * ieee80211_bss_info_change_notify() */ tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer); switch (oper) { case NL80211_TDLS_ENABLE_LINK: if (sdata->vif.bss_conf.csa_active) { tdls_dbg(sdata, "TDLS: disallow link during CSA\n"); return -EBUSY; } sta = sta_info_get(sdata, peer); if (!sta || !sta->sta.tdls) return -ENOLINK; iee80211_tdls_recalc_chanctx(sdata, sta); iee80211_tdls_recalc_ht_protection(sdata, sta); set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); WARN_ON_ONCE(is_zero_ether_addr(sdata->u.mgd.tdls_peer) || !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)); break; case NL80211_TDLS_DISABLE_LINK: /* * The teardown message in ieee80211_tdls_mgmt_teardown() was * created while the queues were stopped, so it might still be * pending. Before flushing the queues we need to be sure the * message is handled by the tasklet handling pending messages, * otherwise we might start destroying the station before * sending the teardown packet. * Note that this only forces the tasklet to flush pendings - * not to stop the tasklet from rescheduling itself. */ tasklet_kill(&local->tx_pending_tasklet); /* flush a potentially queued teardown packet */ ieee80211_flush_queues(local, sdata, false); ret = sta_info_destroy_addr(sdata, peer); iee80211_tdls_recalc_ht_protection(sdata, NULL); iee80211_tdls_recalc_chanctx(sdata, NULL); if (ret) return ret; break; default: return -EOPNOTSUPP; } if (ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) { wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &sdata->u.mgd.tdls_peer_del_work); eth_zero_addr(sdata->u.mgd.tdls_peer); } wiphy_work_queue(sdata->local->hw.wiphy, &sdata->deflink.u.mgd.request_smps_work); return 0; } void ieee80211_tdls_oper_request(struct ieee80211_vif *vif, const u8 *peer, enum nl80211_tdls_operation oper, u16 reason_code, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (vif->type != NL80211_IFTYPE_STATION || !vif->cfg.assoc) { sdata_err(sdata, "Discarding TDLS oper %d - not STA or disconnected\n", oper); return; } cfg80211_tdls_oper_request(sdata->dev, peer, oper, reason_code, gfp); } EXPORT_SYMBOL(ieee80211_tdls_oper_request); static void iee80211_tdls_add_ch_switch_timing(u8 *buf, u16 switch_time, u16 switch_timeout) { struct ieee80211_ch_switch_timing *ch_sw; *buf++ = WLAN_EID_CHAN_SWITCH_TIMING; *buf++ = sizeof(struct ieee80211_ch_switch_timing); ch_sw = (void *)buf; ch_sw->switch_time = cpu_to_le16(switch_time); ch_sw->switch_timeout = cpu_to_le16(switch_timeout); } /* find switch timing IE in SKB ready for Tx */ static const u8 *ieee80211_tdls_find_sw_timing_ie(struct sk_buff *skb) { struct ieee80211_tdls_data *tf; const u8 *ie_start; /* * Get the offset for the new location of the switch timing IE. * The SKB network header will now point to the "payload_type" * element of the TDLS data frame struct. */ tf = container_of(skb->data + skb_network_offset(skb), struct ieee80211_tdls_data, payload_type); ie_start = tf->u.chan_switch_req.variable; return cfg80211_find_ie(WLAN_EID_CHAN_SWITCH_TIMING, ie_start, skb->len - (ie_start - skb->data)); } static struct sk_buff * ieee80211_tdls_ch_sw_tmpl_get(struct sta_info *sta, u8 oper_class, struct cfg80211_chan_def *chandef, u32 *ch_sw_tm_ie_offset) { struct ieee80211_sub_if_data *sdata = sta->sdata; u8 extra_ies[2 + sizeof(struct ieee80211_sec_chan_offs_ie) + 2 + sizeof(struct ieee80211_ch_switch_timing)]; int extra_ies_len = 2 + sizeof(struct ieee80211_ch_switch_timing); u8 *pos = extra_ies; struct sk_buff *skb; int link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0; /* * if chandef points to a wide channel add a Secondary-Channel * Offset information element */ if (chandef->width == NL80211_CHAN_WIDTH_40) { struct ieee80211_sec_chan_offs_ie *sec_chan_ie; bool ht40plus; *pos++ = WLAN_EID_SECONDARY_CHANNEL_OFFSET; *pos++ = sizeof(*sec_chan_ie); sec_chan_ie = (void *)pos; ht40plus = cfg80211_get_chandef_type(chandef) == NL80211_CHAN_HT40PLUS; sec_chan_ie->sec_chan_offs = ht40plus ? IEEE80211_HT_PARAM_CHA_SEC_ABOVE : IEEE80211_HT_PARAM_CHA_SEC_BELOW; pos += sizeof(*sec_chan_ie); extra_ies_len += 2 + sizeof(struct ieee80211_sec_chan_offs_ie); } /* just set the values to 0, this is a template */ iee80211_tdls_add_ch_switch_timing(pos, 0, 0); skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr, link_id, WLAN_TDLS_CHANNEL_SWITCH_REQUEST, 0, 0, !sta->sta.tdls_initiator, extra_ies, extra_ies_len, oper_class, chandef); if (!skb) return NULL; skb = ieee80211_build_data_template(sdata, skb, 0); if (IS_ERR(skb)) { tdls_dbg(sdata, "Failed building TDLS channel switch frame\n"); return NULL; } if (ch_sw_tm_ie_offset) { const u8 *tm_ie = ieee80211_tdls_find_sw_timing_ie(skb); if (!tm_ie) { tdls_dbg(sdata, "No switch timing IE in TDLS switch\n"); dev_kfree_skb_any(skb); return NULL; } *ch_sw_tm_ie_offset = tm_ie - skb->data; } tdls_dbg(sdata, "TDLS channel switch request template for %pM ch %d width %d\n", sta->sta.addr, chandef->chan->center_freq, chandef->width); return skb; } int ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev, const u8 *addr, u8 oper_class, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct sk_buff *skb = NULL; u32 ch_sw_tm_ie; int ret; lockdep_assert_wiphy(local->hw.wiphy); if (chandef->chan->freq_offset) /* this may work, but is untested */ return -EOPNOTSUPP; sta = sta_info_get(sdata, addr); if (!sta) { tdls_dbg(sdata, "Invalid TDLS peer %pM for channel switch request\n", addr); ret = -ENOENT; goto out; } if (!test_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH)) { tdls_dbg(sdata, "TDLS channel switch unsupported by %pM\n", addr); ret = -EOPNOTSUPP; goto out; } skb = ieee80211_tdls_ch_sw_tmpl_get(sta, oper_class, chandef, &ch_sw_tm_ie); if (!skb) { ret = -ENOENT; goto out; } ret = drv_tdls_channel_switch(local, sdata, &sta->sta, oper_class, chandef, skb, ch_sw_tm_ie); if (!ret) set_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL); out: dev_kfree_skb_any(skb); return ret; } void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy, struct net_device *dev, const u8 *addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get(sdata, addr); if (!sta) { tdls_dbg(sdata, "Invalid TDLS peer %pM for channel switch cancel\n", addr); return; } if (!test_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL)) { tdls_dbg(sdata, "TDLS channel switch not initiated by %pM\n", addr); return; } drv_tdls_cancel_channel_switch(local, sdata, &sta->sta); clear_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL); } static struct sk_buff * ieee80211_tdls_ch_sw_resp_tmpl_get(struct sta_info *sta, u32 *ch_sw_tm_ie_offset) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct sk_buff *skb; u8 extra_ies[2 + sizeof(struct ieee80211_ch_switch_timing)]; int link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0; /* initial timing are always zero in the template */ iee80211_tdls_add_ch_switch_timing(extra_ies, 0, 0); skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr, link_id, WLAN_TDLS_CHANNEL_SWITCH_RESPONSE, 0, 0, !sta->sta.tdls_initiator, extra_ies, sizeof(extra_ies), 0, NULL); if (!skb) return NULL; skb = ieee80211_build_data_template(sdata, skb, 0); if (IS_ERR(skb)) { tdls_dbg(sdata, "Failed building TDLS channel switch resp frame\n"); return NULL; } if (ch_sw_tm_ie_offset) { const u8 *tm_ie = ieee80211_tdls_find_sw_timing_ie(skb); if (!tm_ie) { tdls_dbg(sdata, "No switch timing IE in TDLS switch resp\n"); dev_kfree_skb_any(skb); return NULL; } *ch_sw_tm_ie_offset = tm_ie - skb->data; } tdls_dbg(sdata, "TDLS get channel switch response template for %pM\n", sta->sta.addr); return skb; } static int ieee80211_process_tdls_channel_switch_resp(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee802_11_elems *elems = NULL; struct sta_info *sta; struct ieee80211_tdls_data *tf = (void *)skb->data; bool local_initiator; struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); int baselen = offsetof(typeof(*tf), u.chan_switch_resp.variable); struct ieee80211_tdls_ch_sw_params params = {}; int ret; lockdep_assert_wiphy(local->hw.wiphy); params.action_code = WLAN_TDLS_CHANNEL_SWITCH_RESPONSE; params.timestamp = rx_status->device_timestamp; if (skb->len < baselen) { tdls_dbg(sdata, "TDLS channel switch resp too short: %d\n", skb->len); return -EINVAL; } sta = sta_info_get(sdata, tf->sa); if (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) { tdls_dbg(sdata, "TDLS chan switch from non-peer sta %pM\n", tf->sa); ret = -EINVAL; goto out; } params.sta = &sta->sta; params.status = le16_to_cpu(tf->u.chan_switch_resp.status_code); if (params.status != 0) { ret = 0; goto call_drv; } elems = ieee802_11_parse_elems(tf->u.chan_switch_resp.variable, skb->len - baselen, IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION, NULL); if (!elems) { ret = -ENOMEM; goto out; } if (elems->parse_error) { tdls_dbg(sdata, "Invalid IEs in TDLS channel switch resp\n"); ret = -EINVAL; goto out; } if (!elems->ch_sw_timing || !elems->lnk_id) { tdls_dbg(sdata, "TDLS channel switch resp - missing IEs\n"); ret = -EINVAL; goto out; } /* validate the initiator is set correctly */ local_initiator = !memcmp(elems->lnk_id->init_sta, sdata->vif.addr, ETH_ALEN); if (local_initiator == sta->sta.tdls_initiator) { tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n"); ret = -EINVAL; goto out; } params.switch_time = le16_to_cpu(elems->ch_sw_timing->switch_time); params.switch_timeout = le16_to_cpu(elems->ch_sw_timing->switch_timeout); params.tmpl_skb = ieee80211_tdls_ch_sw_resp_tmpl_get(sta, ¶ms.ch_sw_tm_ie); if (!params.tmpl_skb) { ret = -ENOENT; goto out; } ret = 0; call_drv: drv_tdls_recv_channel_switch(sdata->local, sdata, ¶ms); tdls_dbg(sdata, "TDLS channel switch response received from %pM status %d\n", tf->sa, params.status); out: dev_kfree_skb_any(params.tmpl_skb); kfree(elems); return ret; } static int ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee802_11_elems *elems; struct cfg80211_chan_def chandef; struct ieee80211_channel *chan; enum nl80211_channel_type chan_type; int freq; u8 target_channel, oper_class; bool local_initiator; struct sta_info *sta; enum nl80211_band band; struct ieee80211_tdls_data *tf = (void *)skb->data; struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); int baselen = offsetof(typeof(*tf), u.chan_switch_req.variable); struct ieee80211_tdls_ch_sw_params params = {}; int ret = 0; lockdep_assert_wiphy(local->hw.wiphy); params.action_code = WLAN_TDLS_CHANNEL_SWITCH_REQUEST; params.timestamp = rx_status->device_timestamp; if (skb->len < baselen) { tdls_dbg(sdata, "TDLS channel switch req too short: %d\n", skb->len); return -EINVAL; } target_channel = tf->u.chan_switch_req.target_channel; oper_class = tf->u.chan_switch_req.oper_class; /* * We can't easily infer the channel band. The operating class is * ambiguous - there are multiple tables (US/Europe/JP/Global). The * solution here is to treat channels with number >14 as 5GHz ones, * and specifically check for the (oper_class, channel) combinations * where this doesn't hold. These are thankfully unique according to * IEEE802.11-2012. * We consider only the 2GHz and 5GHz bands and 20MHz+ channels as * valid here. */ if ((oper_class == 112 || oper_class == 2 || oper_class == 3 || oper_class == 4 || oper_class == 5 || oper_class == 6) && target_channel < 14) band = NL80211_BAND_5GHZ; else band = target_channel < 14 ? NL80211_BAND_2GHZ : NL80211_BAND_5GHZ; freq = ieee80211_channel_to_frequency(target_channel, band); if (freq == 0) { tdls_dbg(sdata, "Invalid channel in TDLS chan switch: %d\n", target_channel); return -EINVAL; } chan = ieee80211_get_channel(sdata->local->hw.wiphy, freq); if (!chan) { tdls_dbg(sdata, "Unsupported channel for TDLS chan switch: %d\n", target_channel); return -EINVAL; } elems = ieee802_11_parse_elems(tf->u.chan_switch_req.variable, skb->len - baselen, IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION, NULL); if (!elems) return -ENOMEM; if (elems->parse_error) { tdls_dbg(sdata, "Invalid IEs in TDLS channel switch req\n"); ret = -EINVAL; goto free; } if (!elems->ch_sw_timing || !elems->lnk_id) { tdls_dbg(sdata, "TDLS channel switch req - missing IEs\n"); ret = -EINVAL; goto free; } if (!elems->sec_chan_offs) { chan_type = NL80211_CHAN_HT20; } else { switch (elems->sec_chan_offs->sec_chan_offs) { case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: chan_type = NL80211_CHAN_HT40PLUS; break; case IEEE80211_HT_PARAM_CHA_SEC_BELOW: chan_type = NL80211_CHAN_HT40MINUS; break; default: chan_type = NL80211_CHAN_HT20; break; } } cfg80211_chandef_create(&chandef, chan, chan_type); /* we will be active on the TDLS link */ if (!cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &chandef, sdata->wdev.iftype)) { tdls_dbg(sdata, "TDLS chan switch to forbidden channel\n"); ret = -EINVAL; goto free; } sta = sta_info_get(sdata, tf->sa); if (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) { tdls_dbg(sdata, "TDLS chan switch from non-peer sta %pM\n", tf->sa); ret = -EINVAL; goto out; } params.sta = &sta->sta; /* validate the initiator is set correctly */ local_initiator = !memcmp(elems->lnk_id->init_sta, sdata->vif.addr, ETH_ALEN); if (local_initiator == sta->sta.tdls_initiator) { tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n"); ret = -EINVAL; goto out; } /* peer should have known better */ if (!sta->sta.deflink.ht_cap.ht_supported && elems->sec_chan_offs && elems->sec_chan_offs->sec_chan_offs) { tdls_dbg(sdata, "TDLS chan switch - wide chan unsupported\n"); ret = -EOPNOTSUPP; goto out; } params.chandef = &chandef; params.switch_time = le16_to_cpu(elems->ch_sw_timing->switch_time); params.switch_timeout = le16_to_cpu(elems->ch_sw_timing->switch_timeout); params.tmpl_skb = ieee80211_tdls_ch_sw_resp_tmpl_get(sta, ¶ms.ch_sw_tm_ie); if (!params.tmpl_skb) { ret = -ENOENT; goto out; } drv_tdls_recv_channel_switch(sdata->local, sdata, ¶ms); tdls_dbg(sdata, "TDLS ch switch request received from %pM ch %d width %d\n", tf->sa, params.chandef->chan->center_freq, params.chandef->width); out: dev_kfree_skb_any(params.tmpl_skb); free: kfree(elems); return ret; } void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_tdls_data *tf = (void *)skb->data; struct wiphy *wiphy = sdata->local->hw.wiphy; lockdep_assert_wiphy(wiphy); /* make sure the driver supports it */ if (!(wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH)) return; /* we want to access the entire packet */ if (skb_linearize(skb)) return; /* * The packet/size was already validated by mac80211 Rx path, only look * at the action type. */ switch (tf->action_code) { case WLAN_TDLS_CHANNEL_SWITCH_REQUEST: ieee80211_process_tdls_channel_switch_req(sdata, skb); break; case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE: ieee80211_process_tdls_channel_switch_resp(sdata, skb); break; default: WARN_ON_ONCE(1); return; } } void ieee80211_teardown_tdls_peers(struct ieee80211_link_data *link) { struct ieee80211_sub_if_data *sdata = link->sdata; struct sta_info *sta; u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; rcu_read_lock(); list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) continue; if (sta->deflink.link_id != link->link_id) continue; ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr, NL80211_TDLS_TEARDOWN, reason, GFP_ATOMIC); } rcu_read_unlock(); } void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason) { struct ieee80211_sta *sta; rcu_read_lock(); sta = ieee80211_find_sta(&sdata->vif, peer); if (!sta || !sta->tdls) { rcu_read_unlock(); return; } rcu_read_unlock(); tdls_dbg(sdata, "disconnected from TDLS peer %pM (Reason: %u=%s)\n", peer, reason, ieee80211_get_reason_code_string(reason)); ieee80211_tdls_oper_request(&sdata->vif, peer, NL80211_TDLS_TEARDOWN, WLAN_REASON_TDLS_TEARDOWN_UNREACHABLE, GFP_ATOMIC); } |
| 6 5 5 4 3 6 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 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <net/ip.h> #include <net/ipv6.h> #include <linux/sctp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_sctp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Kiran Kumar Immidi"); MODULE_DESCRIPTION("Xtables: SCTP protocol packet match"); MODULE_ALIAS("ipt_sctp"); MODULE_ALIAS("ip6t_sctp"); #define SCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ || (!!((invflag) & (option)) ^ (cond))) static bool match_flags(const struct xt_sctp_flag_info *flag_info, const int flag_count, u_int8_t chunktype, u_int8_t chunkflags) { int i; for (i = 0; i < flag_count; i++) if (flag_info[i].chunktype == chunktype) return (chunkflags & flag_info[i].flag_mask) == flag_info[i].flag; return true; } static inline bool match_packet(const struct sk_buff *skb, unsigned int offset, const struct xt_sctp_info *info, bool *hotdrop) { u_int32_t chunkmapcopy[256 / sizeof (u_int32_t)]; const struct sctp_chunkhdr *sch; struct sctp_chunkhdr _sch; int chunk_match_type = info->chunk_match_type; const struct xt_sctp_flag_info *flag_info = info->flag_info; int flag_count = info->flag_count; #ifdef DEBUG int i = 0; #endif if (chunk_match_type == SCTP_CHUNK_MATCH_ALL) SCTP_CHUNKMAP_COPY(chunkmapcopy, info->chunkmap); do { sch = skb_header_pointer(skb, offset, sizeof(_sch), &_sch); if (sch == NULL || sch->length == 0) { pr_debug("Dropping invalid SCTP packet.\n"); *hotdrop = true; return false; } #ifdef DEBUG pr_debug("Chunk num: %d\toffset: %d\ttype: %d\tlength: %d" "\tflags: %x\n", ++i, offset, sch->type, htons(sch->length), sch->flags); #endif offset += SCTP_PAD4(ntohs(sch->length)); pr_debug("skb->len: %d\toffset: %d\n", skb->len, offset); if (SCTP_CHUNKMAP_IS_SET(info->chunkmap, sch->type)) { switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ANY: if (match_flags(flag_info, flag_count, sch->type, sch->flags)) { return true; } break; case SCTP_CHUNK_MATCH_ALL: if (match_flags(flag_info, flag_count, sch->type, sch->flags)) SCTP_CHUNKMAP_CLEAR(chunkmapcopy, sch->type); break; case SCTP_CHUNK_MATCH_ONLY: if (!match_flags(flag_info, flag_count, sch->type, sch->flags)) return false; break; } } else { switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ONLY: return false; } } } while (offset < skb->len); switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ALL: return SCTP_CHUNKMAP_IS_CLEAR(chunkmapcopy); case SCTP_CHUNK_MATCH_ANY: return false; case SCTP_CHUNK_MATCH_ONLY: return true; } /* This will never be reached, but required to stop compiler whine */ return false; } static bool sctp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_sctp_info *info = par->matchinfo; const struct sctphdr *sh; struct sctphdr _sh; if (par->fragoff != 0) { pr_debug("Dropping non-first fragment.. FIXME\n"); return false; } sh = skb_header_pointer(skb, par->thoff, sizeof(_sh), &_sh); if (sh == NULL) { pr_debug("Dropping evil TCP offset=0 tinygram.\n"); par->hotdrop = true; return false; } pr_debug("spt: %d\tdpt: %d\n", ntohs(sh->source), ntohs(sh->dest)); return SCCHECK(ntohs(sh->source) >= info->spts[0] && ntohs(sh->source) <= info->spts[1], XT_SCTP_SRC_PORTS, info->flags, info->invflags) && SCCHECK(ntohs(sh->dest) >= info->dpts[0] && ntohs(sh->dest) <= info->dpts[1], XT_SCTP_DEST_PORTS, info->flags, info->invflags) && SCCHECK(match_packet(skb, par->thoff + sizeof(_sh), info, &par->hotdrop), XT_SCTP_CHUNK_TYPES, info->flags, info->invflags); } static int sctp_mt_check(const struct xt_mtchk_param *par) { const struct xt_sctp_info *info = par->matchinfo; if (info->flag_count > ARRAY_SIZE(info->flag_info)) return -EINVAL; if (info->flags & ~XT_SCTP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~XT_SCTP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~info->flags) return -EINVAL; if (!(info->flags & XT_SCTP_CHUNK_TYPES)) return 0; if (info->chunk_match_type & (SCTP_CHUNK_MATCH_ALL | SCTP_CHUNK_MATCH_ANY | SCTP_CHUNK_MATCH_ONLY)) return 0; return -EINVAL; } static struct xt_match sctp_mt_reg[] __read_mostly = { { .name = "sctp", .family = NFPROTO_IPV4, .checkentry = sctp_mt_check, .match = sctp_mt, .matchsize = sizeof(struct xt_sctp_info), .proto = IPPROTO_SCTP, .me = THIS_MODULE }, { .name = "sctp", .family = NFPROTO_IPV6, .checkentry = sctp_mt_check, .match = sctp_mt, .matchsize = sizeof(struct xt_sctp_info), .proto = IPPROTO_SCTP, .me = THIS_MODULE }, }; static int __init sctp_mt_init(void) { return xt_register_matches(sctp_mt_reg, ARRAY_SIZE(sctp_mt_reg)); } static void __exit sctp_mt_exit(void) { xt_unregister_matches(sctp_mt_reg, ARRAY_SIZE(sctp_mt_reg)); } module_init(sctp_mt_init); module_exit(sctp_mt_exit); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * iptables module for DCCP protocol header matching * * (C) 2005 by Harald Welte <laforge@netfilter.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/ip.h> #include <linux/dccp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_dccp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: DCCP protocol packet match"); MODULE_ALIAS("ipt_dccp"); MODULE_ALIAS("ip6t_dccp"); #define DCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ || (!!((invflag) & (option)) ^ (cond))) static unsigned char *dccp_optbuf; static DEFINE_SPINLOCK(dccp_buflock); static inline bool dccp_find_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, const struct dccp_hdr *dh, bool *hotdrop) { /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ const unsigned char *op; unsigned int optoff = __dccp_hdr_len(dh); unsigned int optlen = dh->dccph_doff*4 - __dccp_hdr_len(dh); unsigned int i; if (dh->dccph_doff * 4 < __dccp_hdr_len(dh)) goto invalid; if (!optlen) return false; spin_lock_bh(&dccp_buflock); op = skb_header_pointer(skb, protoff + optoff, optlen, dccp_optbuf); if (op == NULL) { /* If we don't have the whole header, drop packet. */ goto partial; } for (i = 0; i < optlen; ) { if (op[i] == option) { spin_unlock_bh(&dccp_buflock); return true; } if (op[i] < 2 || i == optlen - 1) i++; else i += op[i + 1] ? : 1; } spin_unlock_bh(&dccp_buflock); return false; partial: spin_unlock_bh(&dccp_buflock); invalid: *hotdrop = true; return false; } static inline bool match_types(const struct dccp_hdr *dh, u_int16_t typemask) { return typemask & (1 << dh->dccph_type); } static inline bool match_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, const struct dccp_hdr *dh, bool *hotdrop) { return dccp_find_option(option, skb, protoff, dh, hotdrop); } static bool dccp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_dccp_info *info = par->matchinfo; const struct dccp_hdr *dh; struct dccp_hdr _dh; if (par->fragoff != 0) return false; dh = skb_header_pointer(skb, par->thoff, sizeof(_dh), &_dh); if (dh == NULL) { par->hotdrop = true; return false; } return DCCHECK(ntohs(dh->dccph_sport) >= info->spts[0] && ntohs(dh->dccph_sport) <= info->spts[1], XT_DCCP_SRC_PORTS, info->flags, info->invflags) && DCCHECK(ntohs(dh->dccph_dport) >= info->dpts[0] && ntohs(dh->dccph_dport) <= info->dpts[1], XT_DCCP_DEST_PORTS, info->flags, info->invflags) && DCCHECK(match_types(dh, info->typemask), XT_DCCP_TYPE, info->flags, info->invflags) && DCCHECK(match_option(info->option, skb, par->thoff, dh, &par->hotdrop), XT_DCCP_OPTION, info->flags, info->invflags); } static int dccp_mt_check(const struct xt_mtchk_param *par) { const struct xt_dccp_info *info = par->matchinfo; if (info->flags & ~XT_DCCP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~XT_DCCP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~info->flags) return -EINVAL; return 0; } static struct xt_match dccp_mt_reg[] __read_mostly = { { .name = "dccp", .family = NFPROTO_IPV4, .checkentry = dccp_mt_check, .match = dccp_mt, .matchsize = sizeof(struct xt_dccp_info), .proto = IPPROTO_DCCP, .me = THIS_MODULE, }, { .name = "dccp", .family = NFPROTO_IPV6, .checkentry = dccp_mt_check, .match = dccp_mt, .matchsize = sizeof(struct xt_dccp_info), .proto = IPPROTO_DCCP, .me = THIS_MODULE, }, }; static int __init dccp_mt_init(void) { int ret; pr_warn_once("The DCCP match is deprecated and scheduled to be removed in 2027.\n" "Please contact the netfilter-devel mailing list or update your iptables rules\n"); /* doff is 8 bits, so the maximum option size is (4*256). Don't put * this in BSS since DaveM is worried about locked TLB's for kernel * BSS. */ dccp_optbuf = kmalloc(256 * 4, GFP_KERNEL); if (!dccp_optbuf) return -ENOMEM; ret = xt_register_matches(dccp_mt_reg, ARRAY_SIZE(dccp_mt_reg)); if (ret) goto out_kfree; return ret; out_kfree: kfree(dccp_optbuf); return ret; } static void __exit dccp_mt_exit(void) { xt_unregister_matches(dccp_mt_reg, ARRAY_SIZE(dccp_mt_reg)); kfree(dccp_optbuf); } module_init(dccp_mt_init); module_exit(dccp_mt_exit); |
| 35 3 3 21339 2842 21339 2 2 2 2 1302 22 17846 1281 17943 19719 246 19719 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * AppArmor security module * * This file contains AppArmor label definitions * * Copyright 2017 Canonical Ltd. */ #ifndef __AA_LABEL_H #define __AA_LABEL_H #include <linux/atomic.h> #include <linux/audit.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> #include "apparmor.h" #include "lib.h" struct aa_ns; struct aa_ruleset; #define LOCAL_VEC_ENTRIES 8 #define DEFINE_VEC(T, V) \ struct aa_ ## T *(_ ## V ## _localtmp)[LOCAL_VEC_ENTRIES]; \ struct aa_ ## T **(V) #define vec_setup(T, V, N, GFP) \ ({ \ if ((N) <= LOCAL_VEC_ENTRIES) { \ typeof(N) i; \ (V) = (_ ## V ## _localtmp); \ for (i = 0; i < (N); i++) \ (V)[i] = NULL; \ } else \ (V) = kzalloc(sizeof(struct aa_ ## T *) * (N), (GFP)); \ (V) ? 0 : -ENOMEM; \ }) #define vec_cleanup(T, V, N) \ do { \ int i; \ for (i = 0; i < (N); i++) { \ if (!IS_ERR_OR_NULL((V)[i])) \ aa_put_ ## T((V)[i]); \ } \ if ((V) != _ ## V ## _localtmp) \ kfree(V); \ } while (0) #define vec_last(VEC, SIZE) ((VEC)[(SIZE) - 1]) #define vec_ns(VEC, SIZE) (vec_last((VEC), (SIZE))->ns) #define vec_labelset(VEC, SIZE) (&vec_ns((VEC), (SIZE))->labels) #define cleanup_domain_vec(V, L) cleanup_label_vec((V), (L)->size) struct aa_profile; #define VEC_FLAG_TERMINATE 1 int aa_vec_unique(struct aa_profile **vec, int n, int flags); struct aa_label *aa_vec_find_or_create_label(struct aa_profile **vec, int len, gfp_t gfp); #define aa_sort_and_merge_vec(N, V) \ aa_sort_and_merge_profiles((N), (struct aa_profile **)(V)) /* struct aa_labelset - set of labels for a namespace * * Labels are reference counted; aa_labelset does not contribute to label * reference counts. Once a label's last refcount is put it is removed from * the set. */ struct aa_labelset { rwlock_t lock; struct rb_root root; }; #define __labelset_for_each(LS, N) \ for ((N) = rb_first(&(LS)->root); (N); (N) = rb_next(N)) enum label_flags { FLAG_HAT = 1, /* profile is a hat */ FLAG_UNCONFINED = 2, /* label unconfined only if all */ FLAG_NULL = 4, /* profile is null learning profile */ FLAG_IX_ON_NAME_ERROR = 8, /* fallback to ix on name lookup fail */ FLAG_IMMUTIBLE = 0x10, /* don't allow changes/replacement */ FLAG_USER_DEFINED = 0x20, /* user based profile - lower privs */ FLAG_NO_LIST_REF = 0x40, /* list doesn't keep profile ref */ FLAG_NS_COUNT = 0x80, /* carries NS ref count */ FLAG_IN_TREE = 0x100, /* label is in tree */ FLAG_PROFILE = 0x200, /* label is a profile */ FLAG_EXPLICIT = 0x400, /* explicit static label */ FLAG_STALE = 0x800, /* replaced/removed */ FLAG_RENAMED = 0x1000, /* label has renaming in it */ FLAG_REVOKED = 0x2000, /* label has revocation in it */ FLAG_DEBUG1 = 0x4000, FLAG_DEBUG2 = 0x8000, /* These flags must correspond with PATH_flags */ /* TODO: add new path flags */ }; struct aa_label; struct aa_proxy { struct aa_common_ref count; struct aa_label __rcu *label; }; struct label_it { int i, j; }; /* struct aa_label_base - base info of label * @count: ref count of active users * @node: rbtree position * @rcu: rcu callback struct * @proxy: is set to the label that replaced this label * @hname: text representation of the label (MAYBE_NULL) * @flags: stale and other flags - values may change under label set lock * @secid: secid that references this label * @size: number of entries in @ent[] * @mediates: bitmask for label_mediates * profile: label vec when embedded in a profile FLAG_PROFILE is set * rules: variable length rules in a profile FLAG_PROFILE is set * vec: vector of profiles comprising the compound label */ struct aa_label { struct aa_common_ref count; struct rb_node node; struct rcu_head rcu; struct aa_proxy *proxy; __counted char *hname; long flags; u32 secid; int size; u64 mediates; union { struct { /* only used is the label is a profile, size of * rules[] is determined by the profile * profile[1] is poison or null as guard */ struct aa_profile *profile[2]; DECLARE_FLEX_ARRAY(struct aa_ruleset *, rules); }; DECLARE_FLEX_ARRAY(struct aa_profile *, vec); }; }; #define last_error(E, FN) \ do { \ int __subE = (FN); \ if (__subE) \ (E) = __subE; \ } while (0) #define label_isprofile(X) ((X)->flags & FLAG_PROFILE) #define label_unconfined(X) ((X)->flags & FLAG_UNCONFINED) #define unconfined(X) label_unconfined(X) #define label_is_stale(X) ((X)->flags & FLAG_STALE) #define __label_make_stale(X) ((X)->flags |= FLAG_STALE) #define labels_ns(X) (vec_ns(&((X)->vec[0]), (X)->size)) #define labels_set(X) (&labels_ns(X)->labels) #define labels_view(X) labels_ns(X) #define labels_profile(X) ((X)->vec[(X)->size - 1]) int aa_label_next_confined(struct aa_label *l, int i); /* for each profile in a label */ #define label_for_each(I, L, P) \ for ((I).i = 0; ((P) = (L)->vec[(I).i]); ++((I).i)) /* assumes break/goto ended label_for_each */ #define label_for_each_cont(I, L, P) \ for (++((I).i); ((P) = (L)->vec[(I).i]); ++((I).i)) /* for each profile that is enforcing confinement in a label */ #define label_for_each_confined(I, L, P) \ for ((I).i = aa_label_next_confined((L), 0); \ ((P) = (L)->vec[(I).i]); \ (I).i = aa_label_next_confined((L), (I).i + 1)) #define label_for_each_in_merge(I, A, B, P) \ for ((I).i = (I).j = 0; \ ((P) = aa_label_next_in_merge(&(I), (A), (B))); \ ) #define label_for_each_not_in_set(I, SET, SUB, P) \ for ((I).i = (I).j = 0; \ ((P) = __aa_label_next_not_in_set(&(I), (SET), (SUB))); \ ) #define next_in_ns(i, NS, L) \ ({ \ typeof(i) ___i = (i); \ while ((L)->vec[___i] && (L)->vec[___i]->ns != (NS)) \ (___i)++; \ (___i); \ }) #define label_for_each_in_ns(I, NS, L, P) \ for ((I).i = next_in_ns(0, (NS), (L)); \ ((P) = (L)->vec[(I).i]); \ (I).i = next_in_ns((I).i + 1, (NS), (L))) #define fn_for_each_in_ns(L, P, FN) \ ({ \ struct label_it __i; \ struct aa_ns *__ns = labels_ns(L); \ int __E = 0; \ label_for_each_in_ns(__i, __ns, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_XXX(L, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each(L, P, FN) fn_for_each_XXX(L, P, FN) #define fn_for_each_confined(L, P, FN) fn_for_each_XXX(L, P, FN, _confined) #define fn_for_each2_XXX(L1, L2, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L1), (L2), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_in_merge(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _in_merge) #define fn_for_each_not_in_set(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _not_in_set) static inline bool label_mediates(struct aa_label *L, unsigned char C) { return (L)->mediates & (((u64) 1) << (C)); } static inline bool label_mediates_safe(struct aa_label *L, unsigned char C) { if (C > AA_CLASS_LAST) return false; return label_mediates(L, C); } void aa_labelset_destroy(struct aa_labelset *ls); void aa_labelset_init(struct aa_labelset *ls); void __aa_labelset_update_subtree(struct aa_ns *ns); void aa_label_destroy(struct aa_label *label); void aa_label_free(struct aa_label *label); void aa_label_kref(struct kref *kref); bool aa_label_init(struct aa_label *label, int size, gfp_t gfp); struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp); bool aa_label_is_subset(struct aa_label *set, struct aa_label *sub); bool aa_label_is_unconfined_subset(struct aa_label *set, struct aa_label *sub); struct aa_profile *__aa_label_next_not_in_set(struct label_it *I, struct aa_label *set, struct aa_label *sub); bool aa_label_remove(struct aa_label *label); struct aa_label *aa_label_insert(struct aa_labelset *ls, struct aa_label *l); bool aa_label_replace(struct aa_label *old, struct aa_label *new); bool aa_label_make_newest(struct aa_labelset *ls, struct aa_label *old, struct aa_label *new); struct aa_profile *aa_label_next_in_merge(struct label_it *I, struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_find_merge(struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_merge(struct aa_label *a, struct aa_label *b, gfp_t gfp); bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp); #define FLAGS_NONE 0 #define FLAG_SHOW_MODE 1 #define FLAG_VIEW_SUBNS 2 #define FLAG_HIDDEN_UNCONFINED 4 #define FLAG_ABS_ROOT 8 int aa_label_snxprint(char *str, size_t size, struct aa_ns *view, struct aa_label *label, int flags); int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); int aa_label_acntsxprint(char __counted **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_printk(struct aa_label *label, gfp_t gfp); struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str, size_t n, gfp_t gfp, bool create, bool force_stack); struct aa_label *aa_label_parse(struct aa_label *base, const char *str, gfp_t gfp, bool create, bool force_stack); static inline const char *aa_label_strn_split(const char *str, int n) { const char *pos; aa_state_t state; state = aa_dfa_matchn_until(stacksplitdfa, DFA_START, str, n, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } static inline const char *aa_label_str_split(const char *str) { const char *pos; aa_state_t state; state = aa_dfa_match_until(stacksplitdfa, DFA_START, str, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } struct aa_perms; struct aa_ruleset; int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t state, bool subns, u32 request, struct aa_perms *perms); /** * __aa_get_label - get a reference count to uncounted label reference * @l: reference to get a count on * * Returns: pointer to reference OR NULL if race is lost and reference is * being repeated. * Requires: lock held, and the return code MUST be checked */ static inline struct aa_label *__aa_get_label(struct aa_label *l) { if (l && kref_get_unless_zero(&l->count.count)) return l; return NULL; } static inline struct aa_label *aa_get_label(struct aa_label *l) { if (l) kref_get(&(l->count.count)); return l; } /** * aa_get_label_rcu - increment refcount on a label that can be replaced * @l: pointer to label that can be replaced (NOT NULL) * * Returns: pointer to a refcounted label. * else NULL if no label */ static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l) { struct aa_label *c; rcu_read_lock(); do { c = rcu_dereference(*l); } while (c && !kref_get_unless_zero(&c->count.count)); rcu_read_unlock(); return c; } /** * aa_get_newest_label - find the newest version of @l * @l: the label to check for newer versions of * * Returns: refcounted newest version of @l taking into account * replacement, renames and removals * return @l. */ static inline struct aa_label *aa_get_newest_label(struct aa_label *l) { if (!l) return NULL; if (label_is_stale(l)) { struct aa_label *tmp; AA_BUG(!l->proxy); AA_BUG(!l->proxy->label); /* BUG: only way this can happen is @l ref count and its * replacement count have gone to 0 and are on their way * to destruction. ie. we have a refcounting error */ tmp = aa_get_label_rcu(&l->proxy->label); AA_BUG(!tmp); return tmp; } return aa_get_label(l); } /** * aa_get_newest_label_condref - find the newest version of @l * @l: the label to check for newer versions of * @needput: returns whether the reference needs put * * Returns: refcounted newest version of @l taking into account * replacement, renames and removals * return @l. */ static inline struct aa_label *aa_get_newest_label_condref(struct aa_label *l, bool *needput) { if (l && unlikely(label_is_stale(l))) { struct aa_label *tmp; AA_BUG(!l->proxy); AA_BUG(!l->proxy->label); /* BUG: only way this can happen is @l ref count and its * replacement count have gone to 0 and are on their way * to destruction. ie. we have a refcounting error */ tmp = aa_get_label_rcu(&l->proxy->label); AA_BUG(!tmp); *needput = true; return tmp; } *needput = false; return l; } static inline void aa_put_label(struct aa_label *l) { if (l) kref_put(&l->count.count, aa_label_kref); } /* wrapper fn to indicate semantics of the check */ static inline bool __aa_subj_label_is_cached(struct aa_label *subj_label, struct aa_label *obj_label) { return aa_label_is_subset(obj_label, subj_label); } struct aa_proxy *aa_alloc_proxy(struct aa_label *l, gfp_t gfp); void aa_proxy_kref(struct kref *kref); static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy) { if (proxy) kref_get(&(proxy->count.count)); return proxy; } static inline void aa_put_proxy(struct aa_proxy *proxy) { if (proxy) kref_put(&proxy->count.count, aa_proxy_kref); } void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new); #endif /* __AA_LABEL_H */ |
| 8 8 8 8 8 5 8 5 5 8 8 8 5 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 2 2 2 12 2 2 12 12 2 2 12 6 6 6 6 2 2 4 10 14 18 4 12 16 12 12 2 12 12 12 10 12 12 17 10 10 8 8 8 8 2 6 8 23 23 8 4 4 8 23 23 23 7 23 18 23 22 23 22 23 6 23 6 23 6 11 12 12 2 8 8 12 12 12 20 20 20 8 20 12 17 17 17 9 8 17 10 10 10 10 10 10 10 10 10 10 10 16 23 6 2 2 2 2 2 4 3 2 2 2 2 2 4 4 4 4 4 4 6 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the NetFilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Version 1, is capable of handling both version 0 and 1 messages. * Version 0 is the plain old format. * Note Version 0 receivers will just drop Ver 1 messages. * Version 1 is capable of handle IPv6, Persistence data, * time-outs, and firewall marks. * In ver.1 "ip_vs_sync_conn_options" will be sent in netw. order. * Ver. 0 can be turned on by sysctl -w net.ipv4.vs.sync_version=0 * * Definitions Message: is a complete datagram * Sync_conn: is a part of a Message * Param Data is an option to a Sync_conn. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * ip_vs_sync: sync connection info from master load balancer to backups * through multicast * * Changes: * Alexandre Cassen : Added master & backup support at a time. * Alexandre Cassen : Added SyncID support for incoming sync * messages filtering. * Justin Ossevoort : Fix endian problem on sync message size. * Hans Schillstrom : Added Version 1: i.e. IPv6, * Persistence support, fwmark and time-out. */ #define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/inetdevice.h> #include <linux/net.h> #include <linux/completion.h> #include <linux/delay.h> #include <linux/skbuff.h> #include <linux/in.h> #include <linux/igmp.h> /* for ip_mc_join_group */ #include <linux/udp.h> #include <linux/err.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/unaligned.h> /* Used for ntoh_seq and hton_seq */ #include <net/ip.h> #include <net/sock.h> #include <net/ip_vs.h> #define IP_VS_SYNC_GROUP 0xe0000051 /* multicast addr - 224.0.0.81 */ #define IP_VS_SYNC_PORT 8848 /* multicast port */ #define SYNC_PROTO_VER 1 /* Protocol version in header */ static struct lock_class_key __ipvs_sync_key; /* * IPVS sync connection entry * Version 0, i.e. original version. */ struct ip_vs_sync_conn_v0 { __u8 reserved; /* Protocol, addresses and port numbers */ __u8 protocol; /* Which protocol (TCP/UDP) */ __be16 cport; __be16 vport; __be16 dport; __be32 caddr; /* client address */ __be32 vaddr; /* virtual address */ __be32 daddr; /* destination address */ /* Flags and state transition */ __be16 flags; /* status flags */ __be16 state; /* state info */ /* The sequence options start here */ }; struct ip_vs_sync_conn_options { struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ }; /* Sync Connection format (sync_conn) 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Type | Protocol | Ver. | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Flags | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | State | cport | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | vport | dport | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | fwmark | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | timeout (in sec.) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | ... | | IP-Addresses (v4 or v6) | | ... | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ Optional Parameters. +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Param. Type | Param. Length | Param. data | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | ... | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | Param Type | Param. Length | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Param data | | Last Param data should be padded for 32 bit alignment | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ /* * Type 0, IPv4 sync connection format */ struct ip_vs_sync_v4 { __u8 type; __u8 protocol; /* Which protocol (TCP/UDP) */ __be16 ver_size; /* Version msb 4 bits */ /* Flags and state transition */ __be32 flags; /* status flags */ __be16 state; /* state info */ /* Protocol, addresses and port numbers */ __be16 cport; __be16 vport; __be16 dport; __be32 fwmark; /* Firewall mark from skb */ __be32 timeout; /* cp timeout */ __be32 caddr; /* client address */ __be32 vaddr; /* virtual address */ __be32 daddr; /* destination address */ /* The sequence options start here */ /* PE data padded to 32bit alignment after seq. options */ }; /* * Type 2 messages IPv6 */ struct ip_vs_sync_v6 { __u8 type; __u8 protocol; /* Which protocol (TCP/UDP) */ __be16 ver_size; /* Version msb 4 bits */ /* Flags and state transition */ __be32 flags; /* status flags */ __be16 state; /* state info */ /* Protocol, addresses and port numbers */ __be16 cport; __be16 vport; __be16 dport; __be32 fwmark; /* Firewall mark from skb */ __be32 timeout; /* cp timeout */ struct in6_addr caddr; /* client address */ struct in6_addr vaddr; /* virtual address */ struct in6_addr daddr; /* destination address */ /* The sequence options start here */ /* PE data padded to 32bit alignment after seq. options */ }; union ip_vs_sync_conn { struct ip_vs_sync_v4 v4; struct ip_vs_sync_v6 v6; }; /* Bits in Type field in above */ #define STYPE_INET6 0 #define STYPE_F_INET6 (1 << STYPE_INET6) #define SVER_SHIFT 12 /* Shift to get version */ #define SVER_MASK 0x0fff /* Mask to strip version */ #define IPVS_OPT_SEQ_DATA 1 #define IPVS_OPT_PE_DATA 2 #define IPVS_OPT_PE_NAME 3 #define IPVS_OPT_PARAM 7 #define IPVS_OPT_F_SEQ_DATA (1 << (IPVS_OPT_SEQ_DATA-1)) #define IPVS_OPT_F_PE_DATA (1 << (IPVS_OPT_PE_DATA-1)) #define IPVS_OPT_F_PE_NAME (1 << (IPVS_OPT_PE_NAME-1)) #define IPVS_OPT_F_PARAM (1 << (IPVS_OPT_PARAM-1)) struct ip_vs_sync_thread_data { struct task_struct *task; struct netns_ipvs *ipvs; struct socket *sock; char *buf; int id; }; /* Version 0 definition of packet sizes */ #define SIMPLE_CONN_SIZE (sizeof(struct ip_vs_sync_conn_v0)) #define FULL_CONN_SIZE \ (sizeof(struct ip_vs_sync_conn_v0) + sizeof(struct ip_vs_sync_conn_options)) /* The master mulitcasts messages (Datagrams) to the backup load balancers in the following format. Version 1: Note, first byte should be Zero, so ver 0 receivers will drop the packet. 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | 0 | SyncID | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Count Conns | Version | Reserved, set to Zero | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (1) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | . | ~ . ~ | . | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (n) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ Version 0 Header 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Count Conns | SyncID | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | IPVS Sync Connection (1) | */ /* Version 0 header */ struct ip_vs_sync_mesg_v0 { __u8 nr_conns; __u8 syncid; __be16 size; /* ip_vs_sync_conn entries start here */ }; /* Version 1 header */ struct ip_vs_sync_mesg { __u8 reserved; /* must be zero */ __u8 syncid; __be16 size; __u8 nr_conns; __s8 version; /* SYNC_PROTO_VER */ __u16 spare; /* ip_vs_sync_conn entries start here */ }; union ipvs_sockaddr { struct sockaddr_in in; struct sockaddr_in6 in6; }; struct ip_vs_sync_buff { struct list_head list; unsigned long firstuse; /* pointers for the message data */ struct ip_vs_sync_mesg *mesg; unsigned char *head; unsigned char *end; }; /* * Copy of struct ip_vs_seq * From unaligned network order to aligned host order */ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) { memset(ho, 0, sizeof(*ho)); ho->init_seq = get_unaligned_be32(&no->init_seq); ho->delta = get_unaligned_be32(&no->delta); ho->previous_delta = get_unaligned_be32(&no->previous_delta); } /* * Copy of struct ip_vs_seq * From Aligned host order to unaligned network order */ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no) { put_unaligned_be32(ho->init_seq, &no->init_seq); put_unaligned_be32(ho->delta, &no->delta); put_unaligned_be32(ho->previous_delta, &no->previous_delta); } static inline struct ip_vs_sync_buff * sb_dequeue(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { struct ip_vs_sync_buff *sb; spin_lock_bh(&ipvs->sync_lock); if (list_empty(&ms->sync_queue)) { sb = NULL; __set_current_state(TASK_INTERRUPTIBLE); } else { sb = list_entry(ms->sync_queue.next, struct ip_vs_sync_buff, list); list_del(&sb->list); ms->sync_queue_len--; if (!ms->sync_queue_len) ms->sync_queue_delay = 0; } spin_unlock_bh(&ipvs->sync_lock); return sb; } /* * Create a new sync buffer for Version 1 proto. */ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(struct netns_ipvs *ipvs, unsigned int len) { struct ip_vs_sync_buff *sb; if (!(sb=kmalloc_obj(struct ip_vs_sync_buff, GFP_ATOMIC))) return NULL; len = max_t(unsigned int, len + sizeof(struct ip_vs_sync_mesg), ipvs->mcfg.sync_maxlen); sb->mesg = kmalloc(len, GFP_ATOMIC); if (!sb->mesg) { kfree(sb); return NULL; } sb->mesg->reserved = 0; /* old nr_conns i.e. must be zero now */ sb->mesg->version = SYNC_PROTO_VER; sb->mesg->syncid = ipvs->mcfg.syncid; sb->mesg->size = htons(sizeof(struct ip_vs_sync_mesg)); sb->mesg->nr_conns = 0; sb->mesg->spare = 0; sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg); sb->end = (unsigned char *)sb->mesg + len; sb->firstuse = jiffies; return sb; } static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb) { kfree(sb->mesg); kfree(sb); } static inline void sb_queue_tail(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { struct ip_vs_sync_buff *sb = ms->sync_buff; spin_lock(&ipvs->sync_lock); if (ipvs->sync_state & IP_VS_STATE_MASTER && ms->sync_queue_len < sysctl_sync_qlen_max(ipvs)) { if (!ms->sync_queue_len) schedule_delayed_work(&ms->master_wakeup_work, max(IPVS_SYNC_SEND_DELAY, 1)); ms->sync_queue_len++; list_add_tail(&sb->list, &ms->sync_queue); if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE) { int id = (int)(ms - ipvs->ms); wake_up_process(ipvs->master_tinfo[id].task); } } else ip_vs_sync_buff_release(sb); spin_unlock(&ipvs->sync_lock); } /* * Get the current sync buffer if it has been created for more * than the specified time or the specified time is zero. */ static inline struct ip_vs_sync_buff * get_curr_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms, unsigned long time) { struct ip_vs_sync_buff *sb; spin_lock_bh(&ipvs->sync_buff_lock); sb = ms->sync_buff; if (sb && time_after_eq(jiffies - sb->firstuse, time)) { ms->sync_buff = NULL; __set_current_state(TASK_RUNNING); } else sb = NULL; spin_unlock_bh(&ipvs->sync_buff_lock); return sb; } static inline int select_master_thread_id(struct netns_ipvs *ipvs, struct ip_vs_conn *cp) { return ((long) cp >> (1 + ilog2(sizeof(*cp)))) & ipvs->threads_mask; } /* * Create a new sync buffer for Version 0 proto. */ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs, unsigned int len) { struct ip_vs_sync_buff *sb; struct ip_vs_sync_mesg_v0 *mesg; if (!(sb=kmalloc_obj(struct ip_vs_sync_buff, GFP_ATOMIC))) return NULL; len = max_t(unsigned int, len + sizeof(struct ip_vs_sync_mesg_v0), ipvs->mcfg.sync_maxlen); sb->mesg = kmalloc(len, GFP_ATOMIC); if (!sb->mesg) { kfree(sb); return NULL; } mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg; mesg->nr_conns = 0; mesg->syncid = ipvs->mcfg.syncid; mesg->size = htons(sizeof(struct ip_vs_sync_mesg_v0)); sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0); sb->end = (unsigned char *)mesg + len; sb->firstuse = jiffies; return sb; } /* Check if connection is controlled by persistence */ static inline bool in_persistence(struct ip_vs_conn *cp) { for (cp = cp->control; cp; cp = cp->control) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) return true; } return false; } /* Check if conn should be synced. * pkts: conn packets, use sysctl_sync_threshold to avoid packet check * - (1) sync_refresh_period: reduce sync rate. Additionally, retry * sync_retries times with period of sync_refresh_period/8 * - (2) if both sync_refresh_period and sync_period are 0 send sync only * for state changes or only once when pkts matches sync_threshold * - (3) templates: rate can be reduced only with sync_refresh_period or * with (2) */ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { unsigned long orig = READ_ONCE(cp->sync_endtime); unsigned long now = jiffies; unsigned long n = (now + cp->timeout) & ~3UL; unsigned int sync_refresh_period; int sync_period; int force; /* Check if we sync in current state */ if (unlikely(cp->flags & IP_VS_CONN_F_TEMPLATE)) force = 0; else if (unlikely(sysctl_sync_persist_mode(ipvs) && in_persistence(cp))) return 0; else if (likely(cp->protocol == IPPROTO_TCP)) { if (!((1 << cp->state) & ((1 << IP_VS_TCP_S_ESTABLISHED) | (1 << IP_VS_TCP_S_FIN_WAIT) | (1 << IP_VS_TCP_S_CLOSE) | (1 << IP_VS_TCP_S_CLOSE_WAIT) | (1 << IP_VS_TCP_S_TIME_WAIT)))) return 0; force = cp->state != cp->old_state; if (force && cp->state != IP_VS_TCP_S_ESTABLISHED) goto set; } else if (unlikely(cp->protocol == IPPROTO_SCTP)) { if (!((1 << cp->state) & ((1 << IP_VS_SCTP_S_ESTABLISHED) | (1 << IP_VS_SCTP_S_SHUTDOWN_SENT) | (1 << IP_VS_SCTP_S_SHUTDOWN_RECEIVED) | (1 << IP_VS_SCTP_S_SHUTDOWN_ACK_SENT) | (1 << IP_VS_SCTP_S_CLOSED)))) return 0; force = cp->state != cp->old_state; if (force && cp->state != IP_VS_SCTP_S_ESTABLISHED) goto set; } else { /* UDP or another protocol with single state */ force = 0; } sync_refresh_period = sysctl_sync_refresh_period(ipvs); if (sync_refresh_period > 0) { long diff = n - orig; long min_diff = max(cp->timeout >> 1, 10UL * HZ); /* Avoid sync if difference is below sync_refresh_period * and below the half timeout. */ if (abs(diff) < min_t(long, sync_refresh_period, min_diff)) { int retries = orig & 3; if (retries >= sysctl_sync_retries(ipvs)) return 0; if (time_before(now, orig - cp->timeout + (sync_refresh_period >> 3))) return 0; n |= retries + 1; } } sync_period = sysctl_sync_period(ipvs); if (sync_period > 0) { if (!(cp->flags & IP_VS_CONN_F_TEMPLATE) && pkts % sync_period != sysctl_sync_threshold(ipvs)) return 0; } else if (!sync_refresh_period && pkts != sysctl_sync_threshold(ipvs)) return 0; set: cp->old_state = cp->state; n = cmpxchg(&cp->sync_endtime, orig, n); return n == orig || force; } /* * Version 0 , could be switched in by sys_ctl. * Add an ip_vs_conn information into the current sync_buff. */ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { struct ip_vs_sync_mesg_v0 *m; struct ip_vs_sync_conn_v0 *s; struct ip_vs_sync_buff *buff; struct ipvs_master_sync_state *ms; int id; unsigned int len; if (unlikely(cp->af != AF_INET)) return; /* Do not sync ONE PACKET */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) return; if (!ip_vs_sync_conn_needed(ipvs, cp, pkts)) return; spin_lock_bh(&ipvs->sync_buff_lock); if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { spin_unlock_bh(&ipvs->sync_buff_lock); return; } id = select_master_thread_id(ipvs, cp); ms = &ipvs->ms[id]; buff = ms->sync_buff; len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE : SIMPLE_CONN_SIZE; if (buff) { m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; /* Send buffer if it is for v1 */ if (buff->head + len > buff->end || !m->nr_conns) { sb_queue_tail(ipvs, ms); ms->sync_buff = NULL; buff = NULL; } } if (!buff) { buff = ip_vs_sync_buff_create_v0(ipvs, len); if (!buff) { spin_unlock_bh(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } ms->sync_buff = buff; } m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; s = (struct ip_vs_sync_conn_v0 *) buff->head; /* copy members */ s->reserved = 0; s->protocol = cp->protocol; s->cport = cp->cport; s->vport = cp->vport; s->dport = cp->dport; s->caddr = cp->caddr.ip; s->vaddr = cp->vaddr.ip; s->daddr = cp->daddr.ip; s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED); s->state = htons(cp->state); if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { struct ip_vs_sync_conn_options *opt = (struct ip_vs_sync_conn_options *)&s[1]; memcpy(opt, &cp->sync_conn_opt, sizeof(*opt)); } m->nr_conns++; m->size = htons(ntohs(m->size) + len); buff->head += len; spin_unlock_bh(&ipvs->sync_buff_lock); /* synchronize its controller if it has */ cp = cp->control; if (cp) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) pkts = atomic_inc_return(&cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); ip_vs_sync_conn(ipvs, cp, pkts); } } /* * Add an ip_vs_conn information into the current sync_buff. * Called by ip_vs_in. * Sending Version 1 messages */ void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { struct ip_vs_sync_mesg *m; union ip_vs_sync_conn *s; struct ip_vs_sync_buff *buff; struct ipvs_master_sync_state *ms; int id; __u8 *p; unsigned int len, pe_name_len, pad; /* Handle old version of the protocol */ if (sysctl_sync_ver(ipvs) == 0) { ip_vs_sync_conn_v0(ipvs, cp, pkts); return; } /* Do not sync ONE PACKET */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) goto control; sloop: if (!ip_vs_sync_conn_needed(ipvs, cp, pkts)) goto control; /* Sanity checks */ pe_name_len = 0; if (cp->pe_data_len) { if (!cp->pe_data || !cp->dest) { IP_VS_ERR_RL("SYNC, connection pe_data invalid\n"); return; } pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN); } spin_lock_bh(&ipvs->sync_buff_lock); if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { spin_unlock_bh(&ipvs->sync_buff_lock); return; } id = select_master_thread_id(ipvs, cp); ms = &ipvs->ms[id]; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) len = sizeof(struct ip_vs_sync_v6); else #endif len = sizeof(struct ip_vs_sync_v4); if (cp->flags & IP_VS_CONN_F_SEQ_MASK) len += sizeof(struct ip_vs_sync_conn_options) + 2; if (cp->pe_data_len) len += cp->pe_data_len + 2; /* + Param hdr field */ if (pe_name_len) len += pe_name_len + 2; /* check if there is a space for this one */ pad = 0; buff = ms->sync_buff; if (buff) { m = buff->mesg; pad = (4 - (size_t) buff->head) & 3; /* Send buffer if it is for v0 */ if (buff->head + len + pad > buff->end || m->reserved) { sb_queue_tail(ipvs, ms); ms->sync_buff = NULL; buff = NULL; pad = 0; } } if (!buff) { buff = ip_vs_sync_buff_create(ipvs, len); if (!buff) { spin_unlock_bh(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } ms->sync_buff = buff; m = buff->mesg; } p = buff->head; buff->head += pad + len; m->size = htons(ntohs(m->size) + pad + len); /* Add ev. padding from prev. sync_conn */ while (pad--) *(p++) = 0; s = (union ip_vs_sync_conn *)p; /* Set message type & copy members */ s->v4.type = (cp->af == AF_INET6 ? STYPE_F_INET6 : 0); s->v4.ver_size = htons(len & SVER_MASK); /* Version 0 */ s->v4.flags = htonl(cp->flags & ~IP_VS_CONN_F_HASHED); s->v4.state = htons(cp->state); s->v4.protocol = cp->protocol; s->v4.cport = cp->cport; s->v4.vport = cp->vport; s->v4.dport = cp->dport; s->v4.fwmark = htonl(cp->fwmark); s->v4.timeout = htonl(cp->timeout / HZ); m->nr_conns++; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) { p += sizeof(struct ip_vs_sync_v6); s->v6.caddr = cp->caddr.in6; s->v6.vaddr = cp->vaddr.in6; s->v6.daddr = cp->daddr.in6; } else #endif { p += sizeof(struct ip_vs_sync_v4); /* options ptr */ s->v4.caddr = cp->caddr.ip; s->v4.vaddr = cp->vaddr.ip; s->v4.daddr = cp->daddr.ip; } if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { *(p++) = IPVS_OPT_SEQ_DATA; *(p++) = sizeof(struct ip_vs_sync_conn_options); hton_seq((struct ip_vs_seq *)p, &cp->in_seq); p += sizeof(struct ip_vs_seq); hton_seq((struct ip_vs_seq *)p, &cp->out_seq); p += sizeof(struct ip_vs_seq); } /* Handle pe data */ if (cp->pe_data_len && cp->pe_data) { *(p++) = IPVS_OPT_PE_DATA; *(p++) = cp->pe_data_len; memcpy(p, cp->pe_data, cp->pe_data_len); p += cp->pe_data_len; if (pe_name_len) { /* Add PE_NAME */ *(p++) = IPVS_OPT_PE_NAME; *(p++) = pe_name_len; memcpy(p, cp->pe->name, pe_name_len); p += pe_name_len; } } spin_unlock_bh(&ipvs->sync_buff_lock); control: /* synchronize its controller if it has */ cp = cp->control; if (!cp) return; if (cp->flags & IP_VS_CONN_F_TEMPLATE) pkts = atomic_inc_return(&cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); goto sloop; } /* * fill_param used by version 1 */ static inline int ip_vs_conn_fill_param_sync(struct netns_ipvs *ipvs, int af, union ip_vs_sync_conn *sc, struct ip_vs_conn_param *p, __u8 *pe_data, unsigned int pe_data_len, __u8 *pe_name, unsigned int pe_name_len) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_conn_fill_param(ipvs, af, sc->v6.protocol, (const union nf_inet_addr *)&sc->v6.caddr, sc->v6.cport, (const union nf_inet_addr *)&sc->v6.vaddr, sc->v6.vport, p); else #endif ip_vs_conn_fill_param(ipvs, af, sc->v4.protocol, (const union nf_inet_addr *)&sc->v4.caddr, sc->v4.cport, (const union nf_inet_addr *)&sc->v4.vaddr, sc->v4.vport, p); /* Handle pe data */ if (pe_data_len) { if (pe_name_len) { char buff[IP_VS_PENAME_MAXLEN+1]; memcpy(buff, pe_name, pe_name_len); buff[pe_name_len]=0; p->pe = __ip_vs_pe_getbyname(buff); if (!p->pe) { IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", buff); return 1; } } else { IP_VS_ERR_RL("BACKUP, Invalid PE parameters\n"); return 1; } p->pe_data = kmemdup(pe_data, pe_data_len, GFP_ATOMIC); if (!p->pe_data) { module_put(p->pe->module); return -ENOMEM; } p->pe_data_len = pe_data_len; } return 0; } /* * Connection Add / Update. * Common for version 0 and 1 reception of backup sync_conns. * Param: ... * timeout is in sec. */ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *param, unsigned int flags, unsigned int state, unsigned int protocol, unsigned int type, const union nf_inet_addr *daddr, __be16 dport, unsigned long timeout, __u32 fwmark, struct ip_vs_sync_conn_options *opt) { struct ip_vs_dest *dest; struct ip_vs_conn *cp; if (!(flags & IP_VS_CONN_F_TEMPLATE)) { cp = ip_vs_conn_in_get(param); if (cp && ((cp->dport != dport) || !ip_vs_addr_equal(cp->daf, &cp->daddr, daddr))) { if (!(flags & IP_VS_CONN_F_INACTIVE)) { ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); cp = NULL; } else { /* This is the expiration message for the * connection that was already replaced, so we * just ignore it. */ __ip_vs_conn_put(cp); kfree(param->pe_data); return; } } } else { cp = ip_vs_ct_in_get(param); } if (cp) { /* Free pe_data */ kfree(param->pe_data); dest = cp->dest; spin_lock_bh(&cp->lock); if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE && !(flags & IP_VS_CONN_F_TEMPLATE) && dest) { if (flags & IP_VS_CONN_F_INACTIVE) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); } else { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); } } flags &= IP_VS_CONN_F_BACKUP_UPD_MASK; flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK; cp->flags = flags; spin_unlock_bh(&cp->lock); if (!dest) ip_vs_try_bind_dest(cp); } else { /* * Find the appropriate destination for the connection. * If it is not found the connection will remain unbound * but still handled. */ rcu_read_lock(); /* This function is only invoked by the synchronization * code. We do not currently support heterogeneous pools * with synchronization, so we can make the assumption that * the svc_af is the same as the dest_af */ dest = ip_vs_find_dest(ipvs, type, type, daddr, dport, param->vaddr, param->vport, protocol, fwmark, flags); cp = ip_vs_conn_new(param, type, daddr, dport, flags, dest, fwmark); rcu_read_unlock(); if (!cp) { kfree(param->pe_data); IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } if (!(flags & IP_VS_CONN_F_TEMPLATE)) kfree(param->pe_data); } if (opt) { cp->in_seq = opt->in_seq; cp->out_seq = opt->out_seq; } atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs)); cp->state = state; cp->old_state = cp->state; /* * For Ver 0 messages style * - Not possible to recover the right timeout for templates * - can not find the right fwmark * virtual service. If needed, we can do it for * non-fwmark persistent services. * Ver 1 messages style. * - No problem. */ if (timeout) { if (timeout > MAX_SCHEDULE_TIMEOUT / HZ) timeout = MAX_SCHEDULE_TIMEOUT / HZ; cp->timeout = timeout*HZ; } else { struct ip_vs_proto_data *pd; pd = ip_vs_proto_data_get(ipvs, protocol); if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table) cp->timeout = pd->timeout_table[state]; else cp->timeout = (3*60*HZ); } ip_vs_conn_put(cp); } /* * Process received multicast message for Version 0 */ static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer, const size_t buflen) { struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer; struct ip_vs_sync_conn_v0 *s; struct ip_vs_sync_conn_options *opt; struct ip_vs_protocol *pp; struct ip_vs_conn_param param; char *p; int i; p = (char *)buffer + sizeof(struct ip_vs_sync_mesg_v0); for (i=0; i<m->nr_conns; i++) { unsigned int flags, state; if (p + SIMPLE_CONN_SIZE > buffer+buflen) { IP_VS_ERR_RL("BACKUP v0, bogus conn\n"); return; } s = (struct ip_vs_sync_conn_v0 *) p; flags = ntohs(s->flags) | IP_VS_CONN_F_SYNC; flags &= ~IP_VS_CONN_F_HASHED; if (flags & IP_VS_CONN_F_SEQ_MASK) { opt = (struct ip_vs_sync_conn_options *)&s[1]; p += FULL_CONN_SIZE; if (p > buffer+buflen) { IP_VS_ERR_RL("BACKUP v0, Dropping buffer bogus conn options\n"); return; } } else { opt = NULL; p += SIMPLE_CONN_SIZE; } state = ntohs(s->state); if (!(flags & IP_VS_CONN_F_TEMPLATE)) { pp = ip_vs_proto_get(s->protocol); if (!pp) { IP_VS_DBG(2, "BACKUP v0, Unsupported protocol %u\n", s->protocol); continue; } if (state >= pp->num_states) { IP_VS_DBG(2, "BACKUP v0, Invalid %s state %u\n", pp->name, state); continue; } } else { if (state >= IP_VS_CTPL_S_LAST) IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n", state); } ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol, (const union nf_inet_addr *)&s->caddr, s->cport, (const union nf_inet_addr *)&s->vaddr, s->vport, ¶m); /* Send timeout as Zero */ ip_vs_proc_conn(ipvs, ¶m, flags, state, s->protocol, AF_INET, (union nf_inet_addr *)&s->daddr, s->dport, 0, 0, opt); } } /* * Handle options */ static inline int ip_vs_proc_seqopt(__u8 *p, unsigned int plen, __u32 *opt_flags, struct ip_vs_sync_conn_options *opt) { struct ip_vs_sync_conn_options *topt; topt = (struct ip_vs_sync_conn_options *)p; if (plen != sizeof(struct ip_vs_sync_conn_options)) { IP_VS_DBG(2, "BACKUP, bogus conn options length\n"); return -EINVAL; } if (*opt_flags & IPVS_OPT_F_SEQ_DATA) { IP_VS_DBG(2, "BACKUP, conn options found twice\n"); return -EINVAL; } ntoh_seq(&topt->in_seq, &opt->in_seq); ntoh_seq(&topt->out_seq, &opt->out_seq); *opt_flags |= IPVS_OPT_F_SEQ_DATA; return 0; } static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len, __u8 **data, unsigned int maxlen, __u32 *opt_flags, __u32 flag) { if (plen > maxlen) { IP_VS_DBG(2, "BACKUP, bogus par.data len > %d\n", maxlen); return -EINVAL; } if (*opt_flags & flag) { IP_VS_DBG(2, "BACKUP, Par.data found twice 0x%x\n", flag); return -EINVAL; } *data_len = plen; *data = p; *opt_flags |= flag; return 0; } /* * Process a Version 1 sync. connection */ static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *msg_end) { struct ip_vs_sync_conn_options opt; union ip_vs_sync_conn *s; struct ip_vs_protocol *pp; struct ip_vs_conn_param param; __u32 flags; unsigned int af, state, pe_data_len=0, pe_name_len=0; __u8 *pe_data=NULL, *pe_name=NULL; __u32 opt_flags=0; int retc=0; s = (union ip_vs_sync_conn *) p; if (s->v6.type & STYPE_F_INET6) { #ifdef CONFIG_IP_VS_IPV6 af = AF_INET6; p += sizeof(struct ip_vs_sync_v6); #else IP_VS_DBG(3,"BACKUP, IPv6 msg received, and IPVS is not compiled for IPv6\n"); retc = 10; goto out; #endif } else if (!s->v4.type) { af = AF_INET; p += sizeof(struct ip_vs_sync_v4); } else { return -10; } if (p > msg_end) return -20; /* Process optional params check Type & Len. */ while (p < msg_end) { int ptype; int plen; if (p+2 > msg_end) return -30; ptype = *(p++); plen = *(p++); if (!plen || ((p + plen) > msg_end)) return -40; /* Handle seq option p = param data */ switch (ptype & ~IPVS_OPT_F_PARAM) { case IPVS_OPT_SEQ_DATA: if (ip_vs_proc_seqopt(p, plen, &opt_flags, &opt)) return -50; break; case IPVS_OPT_PE_DATA: if (ip_vs_proc_str(p, plen, &pe_data_len, &pe_data, IP_VS_PEDATA_MAXLEN, &opt_flags, IPVS_OPT_F_PE_DATA)) return -60; break; case IPVS_OPT_PE_NAME: if (ip_vs_proc_str(p, plen,&pe_name_len, &pe_name, IP_VS_PENAME_MAXLEN, &opt_flags, IPVS_OPT_F_PE_NAME)) return -70; break; default: /* Param data mandatory ? */ if (!(ptype & IPVS_OPT_F_PARAM)) { IP_VS_DBG(3, "BACKUP, Unknown mandatory param %d found\n", ptype & ~IPVS_OPT_F_PARAM); retc = 20; goto out; } } p += plen; /* Next option */ } /* Get flags and Mask off unsupported */ flags = ntohl(s->v4.flags) & IP_VS_CONN_F_BACKUP_MASK; flags |= IP_VS_CONN_F_SYNC; state = ntohs(s->v4.state); if (!(flags & IP_VS_CONN_F_TEMPLATE)) { pp = ip_vs_proto_get(s->v4.protocol); if (!pp) { IP_VS_DBG(3,"BACKUP, Unsupported protocol %u\n", s->v4.protocol); retc = 30; goto out; } if (state >= pp->num_states) { IP_VS_DBG(3, "BACKUP, Invalid %s state %u\n", pp->name, state); retc = 40; goto out; } } else { if (state >= IP_VS_CTPL_S_LAST) IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n", state); } if (ip_vs_conn_fill_param_sync(ipvs, af, s, ¶m, pe_data, pe_data_len, pe_name, pe_name_len)) { retc = 50; goto out; } /* If only IPv4, just silent skip IPv6 */ if (af == AF_INET) ip_vs_proc_conn(ipvs, ¶m, flags, state, s->v4.protocol, af, (union nf_inet_addr *)&s->v4.daddr, s->v4.dport, ntohl(s->v4.timeout), ntohl(s->v4.fwmark), (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #ifdef CONFIG_IP_VS_IPV6 else ip_vs_proc_conn(ipvs, ¶m, flags, state, s->v6.protocol, af, (union nf_inet_addr *)&s->v6.daddr, s->v6.dport, ntohl(s->v6.timeout), ntohl(s->v6.fwmark), (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #endif ip_vs_pe_put(param.pe); return 0; /* Error exit */ out: IP_VS_DBG(2, "BACKUP, Single msg dropped err:%d\n", retc); return retc; } /* * Process received multicast message and create the corresponding * ip_vs_conn entries. * Handles Version 0 & 1 */ static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer, const size_t buflen) { struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer; __u8 *p, *msg_end; int i, nr_conns; if (buflen < sizeof(struct ip_vs_sync_mesg_v0)) { IP_VS_DBG(2, "BACKUP, message header too short\n"); return; } if (buflen != ntohs(m2->size)) { IP_VS_DBG(2, "BACKUP, bogus message size\n"); return; } /* SyncID sanity check */ if (ipvs->bcfg.syncid != 0 && m2->syncid != ipvs->bcfg.syncid) { IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid); return; } /* Handle version 1 message */ if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0) && (m2->spare == 0)) { msg_end = buffer + sizeof(struct ip_vs_sync_mesg); nr_conns = m2->nr_conns; for (i=0; i<nr_conns; i++) { union ip_vs_sync_conn *s; unsigned int size; int retc; p = msg_end; if (p + sizeof(s->v4) > buffer+buflen) { IP_VS_ERR_RL("BACKUP, Dropping buffer, too small\n"); return; } s = (union ip_vs_sync_conn *)p; size = ntohs(s->v4.ver_size) & SVER_MASK; msg_end = p + size; /* Basic sanity checks */ if (msg_end > buffer+buflen) { IP_VS_ERR_RL("BACKUP, Dropping buffer, msg > buffer\n"); return; } if (ntohs(s->v4.ver_size) >> SVER_SHIFT) { IP_VS_ERR_RL("BACKUP, Dropping buffer, Unknown version %d\n", ntohs(s->v4.ver_size) >> SVER_SHIFT); return; } /* Process a single sync_conn */ retc = ip_vs_proc_sync_conn(ipvs, p, msg_end); if (retc < 0) { IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n", retc); return; } /* Make sure we have 32 bit alignment */ msg_end = p + ((size + 3) & ~3); } } else { /* Old type of message */ ip_vs_process_message_v0(ipvs, buffer, buflen); return; } } /* * Setup sndbuf (mode=1) or rcvbuf (mode=0) */ static void set_sock_size(struct sock *sk, int mode, int val) { /* setsockopt(sock, SOL_SOCKET, SO_SNDBUF, &val, sizeof(val)); */ /* setsockopt(sock, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)); */ lock_sock(sk); if (mode) { val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2, READ_ONCE(sysctl_wmem_max)); sk->sk_sndbuf = val * 2; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; } else { val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2, READ_ONCE(sysctl_rmem_max)); sk->sk_rcvbuf = val * 2; sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); } /* * Setup loopback of outgoing multicasts on a sending socket */ static void set_mcast_loop(struct sock *sk, u_char loop) { /* setsockopt(sock, SOL_IP, IP_MULTICAST_LOOP, &loop, sizeof(loop)); */ inet_assign_bit(MC_LOOP, sk, loop); #ifdef CONFIG_IP_VS_IPV6 if (READ_ONCE(sk->sk_family) == AF_INET6) { /* IPV6_MULTICAST_LOOP */ inet6_assign_bit(MC6_LOOP, sk, loop); } #endif } /* * Specify TTL for outgoing multicasts on a sending socket */ static void set_mcast_ttl(struct sock *sk, u_char ttl) { struct inet_sock *inet = inet_sk(sk); /* setsockopt(sock, SOL_IP, IP_MULTICAST_TTL, &ttl, sizeof(ttl)); */ lock_sock(sk); WRITE_ONCE(inet->mc_ttl, ttl); #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); /* IPV6_MULTICAST_HOPS */ WRITE_ONCE(np->mcast_hops, ttl); } #endif release_sock(sk); } /* Control fragmentation of messages */ static void set_mcast_pmtudisc(struct sock *sk, int val) { struct inet_sock *inet = inet_sk(sk); /* setsockopt(sock, SOL_IP, IP_MTU_DISCOVER, &val, sizeof(val)); */ lock_sock(sk); WRITE_ONCE(inet->pmtudisc, val); #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); /* IPV6_MTU_DISCOVER */ WRITE_ONCE(np->pmtudisc, val); } #endif release_sock(sk); } /* * Specifiy default interface for outgoing multicasts */ static int set_mcast_if(struct sock *sk, struct net_device *dev) { struct inet_sock *inet = inet_sk(sk); if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; lock_sock(sk); inet->mc_index = dev->ifindex; /* inet->mc_addr = 0; */ #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); /* IPV6_MULTICAST_IF */ WRITE_ONCE(np->mcast_oif, dev->ifindex); } #endif release_sock(sk); return 0; } /* * Join a multicast group. * the group is specified by a class D multicast address 224.0.0.0/8 * in the in_addr structure passed in as a parameter. */ static int join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev) { struct ip_mreqn mreq; int ret; memset(&mreq, 0, sizeof(mreq)); memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr)); if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; mreq.imr_ifindex = dev->ifindex; lock_sock(sk); ret = ip_mc_join_group(sk, &mreq); release_sock(sk); return ret; } #ifdef CONFIG_IP_VS_IPV6 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, struct net_device *dev) { int ret; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; lock_sock(sk); ret = ipv6_sock_mc_join(sk, dev->ifindex, addr); release_sock(sk); return ret; } #endif static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) { __be32 addr; struct sockaddr_in sin; addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); if (!addr) pr_err("You probably need to specify IP address on " "multicast interface.\n"); IP_VS_DBG(7, "binding socket with (%s) %pI4\n", dev->name, &addr); /* Now bind the socket with the address of multicast interface */ sin.sin_family = AF_INET; sin.sin_addr.s_addr = addr; sin.sin_port = 0; return kernel_bind(sock, (struct sockaddr_unsized *)&sin, sizeof(sin)); } static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, struct ipvs_sync_daemon_cfg *c, int id) { if (AF_INET6 == c->mcast_af) { sa->in6 = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_port = htons(c->mcast_port + id), }; sa->in6.sin6_addr = c->mcast_group.in6; *salen = sizeof(sa->in6); } else { sa->in = (struct sockaddr_in) { .sin_family = AF_INET, .sin_port = htons(c->mcast_port + id), }; sa->in.sin_addr = c->mcast_group.in; *salen = sizeof(sa->in); } } /* * Set up sending multicast socket over UDP */ static int make_send_sock(struct netns_ipvs *ipvs, int id, struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; struct socket *sock; int result, salen; /* First create a socket */ result = sock_create_kern(ipvs->net, ipvs->mcfg.mcast_af, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); goto error; } *sock_ret = sock; result = set_mcast_if(sock->sk, dev); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; } set_mcast_loop(sock->sk, 0); set_mcast_ttl(sock->sk, ipvs->mcfg.mcast_ttl); /* Allow fragmentation if MTU changes */ set_mcast_pmtudisc(sock->sk, IP_PMTUDISC_DONT); result = sysctl_sync_sock_size(ipvs); if (result > 0) set_sock_size(sock->sk, 1, result); if (AF_INET == ipvs->mcfg.mcast_af) result = bind_mcastif_addr(sock, dev); else result = 0; if (result < 0) { pr_err("Error binding address of the mcast interface\n"); goto error; } get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); result = kernel_connect(sock, (struct sockaddr_unsized *)&mcast_addr, salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); goto error; } return 0; error: return result; } /* * Set up receiving multicast socket over UDP */ static int make_receive_sock(struct netns_ipvs *ipvs, int id, struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; struct socket *sock; int result, salen; /* First create a socket */ result = sock_create_kern(ipvs->net, ipvs->bcfg.mcast_af, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); goto error; } *sock_ret = sock; /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = SK_CAN_REUSE; result = sysctl_sync_sock_size(ipvs); if (result > 0) set_sock_size(sock->sk, 0, result); get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); sock->sk->sk_bound_dev_if = dev->ifindex; result = kernel_bind(sock, (struct sockaddr_unsized *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); goto error; } /* join the multicast group */ #ifdef CONFIG_IP_VS_IPV6 if (ipvs->bcfg.mcast_af == AF_INET6) result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr, dev); else #endif result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr, dev); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; } return 0; error: return result; } static int ip_vs_send_async(struct socket *sock, const char *buffer, const size_t length) { struct msghdr msg = {.msg_flags = MSG_DONTWAIT|MSG_NOSIGNAL}; struct kvec iov; int len; iov.iov_base = (void *)buffer; iov.iov_len = length; len = kernel_sendmsg(sock, &msg, &iov, 1, (size_t)(length)); return len; } static int ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg) { int msize; int ret; msize = ntohs(msg->size); ret = ip_vs_send_async(sock, (char *)msg, msize); if (ret >= 0 || ret == -EAGAIN) return ret; pr_err("ip_vs_send_async error %d\n", ret); return 0; } static int ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) { struct msghdr msg = {NULL,}; struct kvec iov = {buffer, buflen}; int len; /* Receive a packet */ iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, buflen); len = sock_recvmsg(sock, &msg, MSG_DONTWAIT); if (len < 0) return len; return len; } /* Wakeup the master thread for sending */ static void master_wakeup_work_handler(struct work_struct *work) { struct ipvs_master_sync_state *ms = container_of(work, struct ipvs_master_sync_state, master_wakeup_work.work); struct netns_ipvs *ipvs = ms->ipvs; spin_lock_bh(&ipvs->sync_lock); if (ms->sync_queue_len && ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) { int id = (int)(ms - ipvs->ms); ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE; wake_up_process(ipvs->master_tinfo[id].task); } spin_unlock_bh(&ipvs->sync_lock); } /* Get next buffer to send */ static inline struct ip_vs_sync_buff * next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { struct ip_vs_sync_buff *sb; sb = sb_dequeue(ipvs, ms); if (sb) return sb; /* Do not delay entries in buffer for more than 2 seconds */ return get_curr_sync_buff(ipvs, ms, IPVS_SYNC_FLUSH_TIME); } static int sync_thread_master(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; struct ipvs_master_sync_state *ms = &ipvs->ms[tinfo->id]; struct sock *sk = tinfo->sock->sk; struct ip_vs_sync_buff *sb; pr_info("sync thread started: state = MASTER, mcast_ifn = %s, " "syncid = %d, id = %d\n", ipvs->mcfg.mcast_ifn, ipvs->mcfg.syncid, tinfo->id); for (;;) { sb = next_sync_buff(ipvs, ms); if (unlikely(kthread_should_stop())) break; if (!sb) { schedule_timeout(IPVS_SYNC_CHECK_PERIOD); continue; } while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) { /* (Ab)use interruptible sleep to avoid increasing * the load avg. */ __wait_event_interruptible(*sk_sleep(sk), sock_writeable(sk) || kthread_should_stop()); if (unlikely(kthread_should_stop())) goto done; } ip_vs_sync_buff_release(sb); } done: __set_current_state(TASK_RUNNING); if (sb) ip_vs_sync_buff_release(sb); /* clean up the sync_buff queue */ while ((sb = sb_dequeue(ipvs, ms))) ip_vs_sync_buff_release(sb); __set_current_state(TASK_RUNNING); /* clean up the current sync_buff */ sb = get_curr_sync_buff(ipvs, ms, 0); if (sb) ip_vs_sync_buff_release(sb); return 0; } static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; struct sock *sk = tinfo->sock->sk; struct udp_sock *up = udp_sk(sk); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " "syncid = %d, id = %d\n", ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { wait_event_interruptible(*sk_sleep(sk), !skb_queue_empty_lockless(&sk->sk_receive_queue) || !skb_queue_empty_lockless(&up->reader_queue) || kthread_should_stop()); /* do we have data now? */ while (!skb_queue_empty_lockless(&sk->sk_receive_queue) || !skb_queue_empty_lockless(&up->reader_queue)) { len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->bcfg.sync_maxlen); if (len <= 0) { if (len != -EAGAIN) pr_err("receiving message error\n"); break; } ip_vs_process_message(ipvs, tinfo->buf, len); } } return 0; } int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { struct ip_vs_sync_thread_data *ti = NULL, *tinfo; struct task_struct *task; struct net_device *dev; char *name; int (*threadfn)(void *data); int id = 0, count, hlen; int result = -ENOMEM; u16 mtu, min_mtu; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); /* increase the module use count */ if (!ip_vs_use_count_inc()) return -ENOPROTOOPT; /* Backup server can be started without services just to sync conns, * make sure conn_tab is created even if ipvs->enable is 0. */ if (state == IP_VS_STATE_BACKUP) { mutex_lock(&ipvs->service_mutex); if (!rcu_dereference_protected(ipvs->conn_tab, 1)) { int lfactor = sysctl_conn_lfactor(ipvs); int new_size = ip_vs_conn_desired_size(ipvs, NULL, lfactor); struct ip_vs_rht *tc_new; tc_new = ip_vs_conn_tab_alloc(ipvs, new_size, lfactor); if (!tc_new) { mutex_unlock(&ipvs->service_mutex); result = -ENOMEM; goto out_module; } rcu_assign_pointer(ipvs->conn_tab, tc_new); } mutex_unlock(&ipvs->service_mutex); } /* Do not hold one mutex and then to block on another */ for (;;) { rtnl_lock(); if (mutex_trylock(&ipvs->sync_mutex)) break; rtnl_unlock(); mutex_lock(&ipvs->sync_mutex); if (rtnl_trylock()) break; mutex_unlock(&ipvs->sync_mutex); } if (!ipvs->sync_state) { count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX); ipvs->threads_mask = count - 1; } else count = ipvs->threads_mask + 1; if (c->mcast_af == AF_UNSPEC) { c->mcast_af = AF_INET; c->mcast_group.ip = cpu_to_be32(IP_VS_SYNC_GROUP); } if (!c->mcast_port) c->mcast_port = IP_VS_SYNC_PORT; if (!c->mcast_ttl) c->mcast_ttl = 1; dev = __dev_get_by_name(ipvs->net, c->mcast_ifn); if (!dev) { pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); result = -ENODEV; goto out_early; } hlen = (AF_INET6 == c->mcast_af) ? sizeof(struct ipv6hdr) + sizeof(struct udphdr) : sizeof(struct iphdr) + sizeof(struct udphdr); mtu = (state == IP_VS_STATE_BACKUP) ? clamp(dev->mtu, 1500U, 65535U) : 1500U; min_mtu = (state == IP_VS_STATE_BACKUP) ? 1024 : 1; if (c->sync_maxlen) c->sync_maxlen = clamp_t(unsigned int, c->sync_maxlen, min_mtu, 65535 - hlen); else c->sync_maxlen = mtu - hlen; if (state == IP_VS_STATE_MASTER) { result = -EEXIST; if (ipvs->ms) goto out_early; ipvs->mcfg = *c; name = "ipvs-m:%d:%d"; threadfn = sync_thread_master; } else if (state == IP_VS_STATE_BACKUP) { result = -EEXIST; if (ipvs->backup_tinfo) goto out_early; ipvs->bcfg = *c; name = "ipvs-b:%d:%d"; threadfn = sync_thread_backup; } else { result = -EINVAL; goto out_early; } if (state == IP_VS_STATE_MASTER) { struct ipvs_master_sync_state *ms; result = -ENOMEM; ipvs->ms = kzalloc_objs(ipvs->ms[0], count); if (!ipvs->ms) goto out; ms = ipvs->ms; for (id = 0; id < count; id++, ms++) { INIT_LIST_HEAD(&ms->sync_queue); ms->sync_queue_len = 0; ms->sync_queue_delay = 0; INIT_DELAYED_WORK(&ms->master_wakeup_work, master_wakeup_work_handler); ms->ipvs = ipvs; } } result = -ENOMEM; ti = kzalloc_objs(struct ip_vs_sync_thread_data, count); if (!ti) goto out; for (id = 0; id < count; id++) { tinfo = &ti[id]; tinfo->ipvs = ipvs; if (state == IP_VS_STATE_BACKUP) { result = -ENOMEM; tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, GFP_KERNEL); if (!tinfo->buf) goto out; } tinfo->id = id; if (state == IP_VS_STATE_MASTER) result = make_send_sock(ipvs, id, dev, &tinfo->sock); else result = make_receive_sock(ipvs, id, dev, &tinfo->sock); if (result < 0) goto out; task = kthread_run(threadfn, tinfo, name, ipvs->gen, id); if (IS_ERR(task)) { result = PTR_ERR(task); goto out; } tinfo->task = task; } /* mark as active */ if (state == IP_VS_STATE_MASTER) ipvs->master_tinfo = ti; else ipvs->backup_tinfo = ti; spin_lock_bh(&ipvs->sync_buff_lock); ipvs->sync_state |= state; spin_unlock_bh(&ipvs->sync_buff_lock); mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); return 0; out: /* We do not need RTNL lock anymore, release it here so that * sock_release below can use rtnl_lock to leave the mcast group. */ rtnl_unlock(); id = min(id, count - 1); if (ti) { for (tinfo = ti + id; tinfo >= ti; tinfo--) { if (tinfo->task) kthread_stop(tinfo->task); } } if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { kfree(ipvs->ms); ipvs->ms = NULL; } mutex_unlock(&ipvs->sync_mutex); /* No more mutexes, release socks */ if (ti) { for (tinfo = ti + id; tinfo >= ti; tinfo--) { if (tinfo->sock) sock_release(tinfo->sock); kfree(tinfo->buf); } kfree(ti); } /* decrease the module use count */ ip_vs_use_count_dec(); return result; out_early: mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); out_module: /* decrease the module use count */ ip_vs_use_count_dec(); return result; } int stop_sync_thread(struct netns_ipvs *ipvs, int state) { struct ip_vs_sync_thread_data *ti, *tinfo; int id; int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); mutex_lock(&ipvs->sync_mutex); if (state == IP_VS_STATE_MASTER) { retc = -ESRCH; if (!ipvs->ms) goto err; ti = ipvs->master_tinfo; /* * The lock synchronizes with sb_queue_tail(), so that we don't * add sync buffers to the queue, when we are already in * progress of stopping the master sync daemon. */ spin_lock_bh(&ipvs->sync_buff_lock); spin_lock(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; spin_unlock(&ipvs->sync_lock); spin_unlock_bh(&ipvs->sync_buff_lock); retc = 0; for (id = ipvs->threads_mask; id >= 0; id--) { struct ipvs_master_sync_state *ms = &ipvs->ms[id]; int ret; tinfo = &ti[id]; pr_info("stopping master sync thread %d ...\n", task_pid_nr(tinfo->task)); cancel_delayed_work_sync(&ms->master_wakeup_work); ret = kthread_stop(tinfo->task); if (retc >= 0) retc = ret; } kfree(ipvs->ms); ipvs->ms = NULL; ipvs->master_tinfo = NULL; } else if (state == IP_VS_STATE_BACKUP) { retc = -ESRCH; if (!ipvs->backup_tinfo) goto err; ti = ipvs->backup_tinfo; ipvs->sync_state &= ~IP_VS_STATE_BACKUP; retc = 0; for (id = ipvs->threads_mask; id >= 0; id--) { int ret; tinfo = &ti[id]; pr_info("stopping backup sync thread %d ...\n", task_pid_nr(tinfo->task)); ret = kthread_stop(tinfo->task); if (retc >= 0) retc = ret; } ipvs->backup_tinfo = NULL; } else { goto err; } id = ipvs->threads_mask; mutex_unlock(&ipvs->sync_mutex); /* No more mutexes, release socks */ for (tinfo = ti + id; tinfo >= ti; tinfo--) { if (tinfo->sock) sock_release(tinfo->sock); kfree(tinfo->buf); } kfree(ti); /* decrease the module use count */ ip_vs_use_count_dec(); return retc; err: mutex_unlock(&ipvs->sync_mutex); return retc; } /* * Initialize data struct for each netns */ int __net_init ip_vs_sync_net_init(struct netns_ipvs *ipvs) { __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); return 0; } void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs) { int retc; retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER); if (retc && retc != -ESRCH) pr_err("Failed to stop Master Daemon\n"); retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP); if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); } |
| 10206 10135 10137 10177 86 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/uaccess.h> #include <linux/kernel.h> #include <asm/vsyscall.h> #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { unsigned long vaddr = (unsigned long)unsafe_src; /* * Do not allow userspace addresses. This disallows * normal userspace and the userspace guard page: */ if (vaddr < TASK_SIZE_MAX + PAGE_SIZE) return false; /* * Reading from the vsyscall page may cause an unhandled fault in * certain cases. Though it is at an address above TASK_SIZE_MAX, it is * usually considered as a user space address. */ if (is_vsyscall_vaddr(vaddr)) return false; /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. */ if (!boot_cpu_data.x86_virt_bits) return true; return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits); } #else bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return (unsigned long)unsafe_src >= TASK_SIZE_MAX; } #endif |
| 21 11 11 19 19 19 19 19 11 11 11 21 22 1 22 22 21 11 19 21 21 22 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 | // SPDX-License-Identifier: GPL-2.0-only /* * Persistent Memory Driver * * Copyright (c) 2014-2015, Intel Corporation. * Copyright (c) 2015, Christoph Hellwig <hch@lst.de>. * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>. */ #include <linux/blkdev.h> #include <linux/pagemap.h> #include <linux/hdreg.h> #include <linux/init.h> #include <linux/platform_device.h> #include <linux/set_memory.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/badblocks.h> #include <linux/memremap.h> #include <linux/kstrtox.h> #include <linux/vmalloc.h> #include <linux/blk-mq.h> #include <linux/slab.h> #include <linux/uio.h> #include <linux/dax.h> #include <linux/nd.h> #include <linux/mm.h> #include <asm/cacheflush.h> #include "pmem.h" #include "btt.h" #include "pfn.h" #include "nd.h" static struct device *to_dev(struct pmem_device *pmem) { /* * nvdimm bus services need a 'dev' parameter, and we record the device * at init in bb.dev. */ return pmem->bb.dev; } static struct nd_region *to_region(struct pmem_device *pmem) { return to_nd_region(to_dev(pmem)->parent); } static phys_addr_t pmem_to_phys(struct pmem_device *pmem, phys_addr_t offset) { return pmem->phys_addr + offset; } static sector_t to_sect(struct pmem_device *pmem, phys_addr_t offset) { return (offset - pmem->data_offset) >> SECTOR_SHIFT; } static phys_addr_t to_offset(struct pmem_device *pmem, sector_t sector) { return (sector << SECTOR_SHIFT) + pmem->data_offset; } static void pmem_mkpage_present(struct pmem_device *pmem, phys_addr_t offset, unsigned int len) { phys_addr_t phys = pmem_to_phys(pmem, offset); unsigned long pfn_start, pfn_end, pfn; /* only pmem in the linear map supports HWPoison */ if (is_vmalloc_addr(pmem->virt_addr)) return; pfn_start = PHYS_PFN(phys); pfn_end = pfn_start + PHYS_PFN(len); for (pfn = pfn_start; pfn < pfn_end; pfn++) { struct page *page = pfn_to_page(pfn); /* * Note, no need to hold a get_dev_pagemap() reference * here since we're in the driver I/O path and * outstanding I/O requests pin the dev_pagemap. */ if (test_and_clear_pmem_poison(page)) clear_mce_nospec(pfn); } } static void pmem_clear_bb(struct pmem_device *pmem, sector_t sector, long blks) { if (blks == 0) return; badblocks_clear(&pmem->bb, sector, blks); if (pmem->bb_state) sysfs_notify_dirent(pmem->bb_state); } static long __pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, unsigned int len) { phys_addr_t phys = pmem_to_phys(pmem, offset); long cleared = nvdimm_clear_poison(to_dev(pmem), phys, len); if (cleared > 0) { pmem_mkpage_present(pmem, offset, cleared); arch_invalidate_pmem(pmem->virt_addr + offset, len); } return cleared; } static blk_status_t pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, unsigned int len) { long cleared = __pmem_clear_poison(pmem, offset, len); if (cleared < 0) return BLK_STS_IOERR; pmem_clear_bb(pmem, to_sect(pmem, offset), cleared >> SECTOR_SHIFT); if (cleared < len) return BLK_STS_IOERR; return BLK_STS_OK; } static void write_pmem(void *pmem_addr, struct page *page, unsigned int off, unsigned int len) { unsigned int chunk; void *mem; while (len) { mem = kmap_local_page(page); chunk = min_t(unsigned int, len, PAGE_SIZE - off); memcpy_flushcache(pmem_addr, mem + off, chunk); kunmap_local(mem); len -= chunk; off = 0; page++; pmem_addr += chunk; } } static blk_status_t read_pmem(struct page *page, unsigned int off, void *pmem_addr, unsigned int len) { unsigned int chunk; unsigned long rem; void *mem; while (len) { mem = kmap_local_page(page); chunk = min_t(unsigned int, len, PAGE_SIZE - off); rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk); kunmap_local(mem); if (rem) return BLK_STS_IOERR; len -= chunk; off = 0; page++; pmem_addr += chunk; } return BLK_STS_OK; } static blk_status_t pmem_do_read(struct pmem_device *pmem, struct page *page, unsigned int page_off, sector_t sector, unsigned int len) { blk_status_t rc; phys_addr_t pmem_off = to_offset(pmem, sector); void *pmem_addr = pmem->virt_addr + pmem_off; if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) return BLK_STS_IOERR; rc = read_pmem(page, page_off, pmem_addr, len); flush_dcache_page(page); return rc; } static blk_status_t pmem_do_write(struct pmem_device *pmem, struct page *page, unsigned int page_off, sector_t sector, unsigned int len) { phys_addr_t pmem_off = to_offset(pmem, sector); void *pmem_addr = pmem->virt_addr + pmem_off; if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) { blk_status_t rc = pmem_clear_poison(pmem, pmem_off, len); if (rc != BLK_STS_OK) return rc; } flush_dcache_page(page); write_pmem(pmem_addr, page, page_off, len); return BLK_STS_OK; } static void pmem_submit_bio(struct bio *bio) { int ret = 0; blk_status_t rc = 0; bool do_acct; unsigned long start; struct bio_vec bvec; struct bvec_iter iter; struct pmem_device *pmem = bio->bi_bdev->bd_disk->private_data; struct nd_region *nd_region = to_region(pmem); if (bio->bi_opf & REQ_PREFLUSH) ret = nvdimm_flush(nd_region, bio); do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue); if (do_acct) start = bio_start_io_acct(bio); bio_for_each_segment(bvec, bio, iter) { if (op_is_write(bio_op(bio))) rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset, iter.bi_sector, bvec.bv_len); else rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset, iter.bi_sector, bvec.bv_len); if (rc) { bio->bi_status = rc; break; } } if (do_acct) bio_end_io_acct(bio, start); if (bio->bi_opf & REQ_FUA) ret = nvdimm_flush(nd_region, bio); if (ret) bio->bi_status = errno_to_blk_status(ret); bio_endio(bio); } /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, unsigned long *pfn) { resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset; sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT; unsigned int num = PFN_PHYS(nr_pages) >> SECTOR_SHIFT; struct badblocks *bb = &pmem->bb; sector_t first_bad; sector_t num_bad; if (kaddr) *kaddr = pmem->virt_addr + offset; if (pfn) *pfn = PHYS_PFN(pmem->phys_addr + offset); if (bb->count && badblocks_check(bb, sector, num, &first_bad, &num_bad)) { long actual_nr; if (mode != DAX_RECOVERY_WRITE) return -EHWPOISON; /* * Set the recovery stride is set to kernel page size because * the underlying driver and firmware clear poison functions * don't appear to handle large chunk(such as 2MiB) reliably. */ actual_nr = PHYS_PFN( PAGE_ALIGN((first_bad - sector) << SECTOR_SHIFT)); dev_dbg(pmem->bb.dev, "start sector(%llu), nr_pages(%ld), first_bad(%llu), actual_nr(%ld)\n", sector, nr_pages, first_bad, actual_nr); if (actual_nr) return actual_nr; return 1; } /* * If badblocks are present but not in the range, limit known good range * to the requested range. */ if (bb->count) return nr_pages; return PHYS_PFN(pmem->size - pmem->pfn_pad - offset); } static const struct block_device_operations pmem_fops = { .owner = THIS_MODULE, .submit_bio = pmem_submit_bio, }; static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { struct pmem_device *pmem = dax_get_private(dax_dev); return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0, PFN_PHYS(pgoff) >> SECTOR_SHIFT, PAGE_SIZE)); } static long pmem_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, unsigned long *pfn) { struct pmem_device *pmem = dax_get_private(dax_dev); return __pmem_direct_access(pmem, pgoff, nr_pages, mode, kaddr, pfn); } /* * The recovery write thread started out as a normal pwrite thread and * when the filesystem was told about potential media error in the * range, filesystem turns the normal pwrite to a dax_recovery_write. * * The recovery write consists of clearing media poison, clearing page * HWPoison bit, re-enable page-wide read-write permission, flush the * caches and finally write. A competing pread thread will be held * off during the recovery process since data read back might not be * valid, and this is achieved by clearing the badblock records after * the recovery write is complete. Competing recovery write threads * are already serialized by writer lock held by dax_iomap_rw(). */ static size_t pmem_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { struct pmem_device *pmem = dax_get_private(dax_dev); size_t olen, len, off; phys_addr_t pmem_off; struct device *dev = pmem->bb.dev; long cleared; off = offset_in_page(addr); len = PFN_PHYS(PFN_UP(off + bytes)); if (!is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) >> SECTOR_SHIFT, len)) return _copy_from_iter_flushcache(addr, bytes, i); /* * Not page-aligned range cannot be recovered. This should not * happen unless something else went wrong. */ if (off || !PAGE_ALIGNED(bytes)) { dev_dbg(dev, "Found poison, but addr(%p) or bytes(%#zx) not page aligned\n", addr, bytes); return 0; } pmem_off = PFN_PHYS(pgoff) + pmem->data_offset; cleared = __pmem_clear_poison(pmem, pmem_off, len); if (cleared > 0 && cleared < len) { dev_dbg(dev, "poison cleared only %ld out of %zu bytes\n", cleared, len); return 0; } if (cleared < 0) { dev_dbg(dev, "poison clear failed: %ld\n", cleared); return 0; } olen = _copy_from_iter_flushcache(addr, bytes, i); pmem_clear_bb(pmem, to_sect(pmem, pmem_off), cleared >> SECTOR_SHIFT); return olen; } static const struct dax_operations pmem_dax_ops = { .direct_access = pmem_dax_direct_access, .zero_page_range = pmem_dax_zero_page_range, .recovery_write = pmem_recovery_write, }; static ssize_t write_cache_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pmem_device *pmem = dev_to_disk(dev)->private_data; return sprintf(buf, "%d\n", !!dax_write_cache_enabled(pmem->dax_dev)); } static ssize_t write_cache_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct pmem_device *pmem = dev_to_disk(dev)->private_data; bool write_cache; int rc; rc = kstrtobool(buf, &write_cache); if (rc) return rc; dax_write_cache(pmem->dax_dev, write_cache); return len; } static DEVICE_ATTR_RW(write_cache); static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n) { #ifndef CONFIG_ARCH_HAS_PMEM_API if (a == &dev_attr_write_cache.attr) return 0; #endif return a->mode; } static struct attribute *dax_attributes[] = { &dev_attr_write_cache.attr, NULL, }; static const struct attribute_group dax_attribute_group = { .name = "dax", .attrs = dax_attributes, .is_visible = dax_visible, }; static const struct attribute_group *pmem_attribute_groups[] = { &dax_attribute_group, NULL, }; static void pmem_release_disk(void *__pmem) { struct pmem_device *pmem = __pmem; dax_remove_host(pmem->disk); kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); del_gendisk(pmem->disk); put_disk(pmem->disk); } static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap, unsigned long pfn, unsigned long nr_pages, int mf_flags) { struct pmem_device *pmem = container_of(pgmap, struct pmem_device, pgmap); u64 offset = PFN_PHYS(pfn) - pmem->phys_addr - pmem->data_offset; u64 len = nr_pages << PAGE_SHIFT; return dax_holder_notify_failure(pmem->dax_dev, offset, len, mf_flags); } static const struct dev_pagemap_ops fsdax_pagemap_ops = { .memory_failure = pmem_pagemap_memory_failure, }; static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) { struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); struct nd_region *nd_region = to_nd_region(dev->parent); struct queue_limits lim = { .logical_block_size = pmem_sector_size(ndns), .physical_block_size = PAGE_SIZE, .max_hw_sectors = UINT_MAX, .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_SYNCHRONOUS, }; int nid = dev_to_node(dev), fua; struct resource *res = &nsio->res; struct range bb_range; struct nd_pfn *nd_pfn = NULL; struct dax_device *dax_dev; struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; struct gendisk *disk; void *addr; int rc; pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); if (!pmem) return -ENOMEM; rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve()); if (rc) return rc; /* while nsio_rw_bytes is active, parse a pfn info block if present */ if (is_nd_pfn(dev)) { nd_pfn = to_nd_pfn(dev); rc = nvdimm_setup_pfn(nd_pfn, &pmem->pgmap); if (rc) return rc; } /* we're attaching a block device, disable raw namespace access */ devm_namespace_disable(dev, ndns); dev_set_drvdata(dev, pmem); pmem->phys_addr = res->start; pmem->size = resource_size(res); fua = nvdimm_has_flush(nd_region); if (!IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) || fua < 0) { dev_warn(dev, "unable to guarantee persistence of writes\n"); fua = 0; } if (fua) lim.features |= BLK_FEAT_FUA; if (is_nd_pfn(dev) || pmem_should_map_pages(dev)) lim.features |= BLK_FEAT_DAX; if (!devm_request_mem_region(dev, res->start, resource_size(res), dev_name(&ndns->dev))) { dev_warn(dev, "could not reserve region %pR\n", res); return -EBUSY; } disk = blk_alloc_disk(&lim, nid); if (IS_ERR(disk)) return PTR_ERR(disk); pmem->disk = disk; pmem->pgmap.owner = pmem; if (is_nd_pfn(dev)) { pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); pfn_sb = nd_pfn->pfn_sb; pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); pmem->pfn_pad = resource_size(res) - range_len(&pmem->pgmap.range); bb_range = pmem->pgmap.range; bb_range.start += pmem->data_offset; } else if (pmem_should_map_pages(dev)) { pmem->pgmap.range.start = res->start; pmem->pgmap.range.end = res->end; pmem->pgmap.nr_range = 1; pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); bb_range = pmem->pgmap.range; } else { addr = devm_memremap(dev, pmem->phys_addr, pmem->size, ARCH_MEMREMAP_PMEM); bb_range.start = res->start; bb_range.end = res->end; } if (IS_ERR(addr)) { rc = PTR_ERR(addr); goto out; } pmem->virt_addr = addr; disk->fops = &pmem_fops; disk->private_data = pmem; nvdimm_namespace_disk_name(ndns, disk->disk_name); set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) / 512); if (devm_init_badblocks(dev, &pmem->bb)) return -ENOMEM; nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range); disk->bb = &pmem->bb; dax_dev = alloc_dax(pmem, &pmem_dax_ops); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); if (rc != -EOPNOTSUPP) goto out; } else { set_dax_nocache(dax_dev); set_dax_nomc(dax_dev); if (is_nvdimm_sync(nd_region)) set_dax_synchronous(dax_dev); pmem->dax_dev = dax_dev; rc = dax_add_host(dax_dev, disk); if (rc) goto out_cleanup_dax; dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); } rc = device_add_disk(dev, disk, pmem_attribute_groups); if (rc) goto out_remove_host; if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) return -ENOMEM; nvdimm_check_and_set_ro(disk); pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd, "badblocks"); if (!pmem->bb_state) dev_warn(dev, "'badblocks' notification disabled\n"); return 0; out_remove_host: dax_remove_host(pmem->disk); out_cleanup_dax: kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); out: put_disk(pmem->disk); return rc; } static int nd_pmem_probe(struct device *dev) { int ret; struct nd_namespace_common *ndns; ndns = nvdimm_namespace_common_probe(dev); if (IS_ERR(ndns)) return PTR_ERR(ndns); if (is_nd_btt(dev)) return nvdimm_namespace_attach_btt(ndns); if (is_nd_pfn(dev)) return pmem_attach_disk(dev, ndns); ret = devm_namespace_enable(dev, ndns, nd_info_block_reserve()); if (ret) return ret; ret = nd_btt_probe(dev, ndns); if (ret == 0) return -ENXIO; /* * We have two failure conditions here, there is no * info reserver block or we found a valid info reserve block * but failed to initialize the pfn superblock. * * For the first case consider namespace as a raw pmem namespace * and attach a disk. * * For the latter, consider this a success and advance the namespace * seed. */ ret = nd_pfn_probe(dev, ndns); if (ret == 0) return -ENXIO; else if (ret == -EOPNOTSUPP) return ret; ret = nd_dax_probe(dev, ndns); if (ret == 0) return -ENXIO; else if (ret == -EOPNOTSUPP) return ret; /* probe complete, attach handles namespace enabling */ devm_namespace_disable(dev, ndns); return pmem_attach_disk(dev, ndns); } static void nd_pmem_remove(struct device *dev) { struct pmem_device *pmem = dev_get_drvdata(dev); if (is_nd_btt(dev)) nvdimm_namespace_detach_btt(to_nd_btt(dev)); else { /* * Note, this assumes device_lock() context to not * race nd_pmem_notify() */ sysfs_put(pmem->bb_state); pmem->bb_state = NULL; } nvdimm_flush(to_nd_region(dev->parent), NULL); } static void nd_pmem_shutdown(struct device *dev) { nvdimm_flush(to_nd_region(dev->parent), NULL); } static void pmem_revalidate_poison(struct device *dev) { struct nd_region *nd_region; resource_size_t offset = 0, end_trunc = 0; struct nd_namespace_common *ndns; struct nd_namespace_io *nsio; struct badblocks *bb; struct range range; struct kernfs_node *bb_state; if (is_nd_btt(dev)) { struct nd_btt *nd_btt = to_nd_btt(dev); ndns = nd_btt->ndns; nd_region = to_nd_region(ndns->dev.parent); nsio = to_nd_namespace_io(&ndns->dev); bb = &nsio->bb; bb_state = NULL; } else { struct pmem_device *pmem = dev_get_drvdata(dev); nd_region = to_region(pmem); bb = &pmem->bb; bb_state = pmem->bb_state; if (is_nd_pfn(dev)) { struct nd_pfn *nd_pfn = to_nd_pfn(dev); struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; ndns = nd_pfn->ndns; offset = pmem->data_offset + __le32_to_cpu(pfn_sb->start_pad); end_trunc = __le32_to_cpu(pfn_sb->end_trunc); } else { ndns = to_ndns(dev); } nsio = to_nd_namespace_io(&ndns->dev); } range.start = nsio->res.start + offset; range.end = nsio->res.end - end_trunc; nvdimm_badblocks_populate(nd_region, bb, &range); if (bb_state) sysfs_notify_dirent(bb_state); } static void pmem_revalidate_region(struct device *dev) { struct pmem_device *pmem; if (is_nd_btt(dev)) { struct nd_btt *nd_btt = to_nd_btt(dev); struct btt *btt = nd_btt->btt; nvdimm_check_and_set_ro(btt->btt_disk); return; } pmem = dev_get_drvdata(dev); nvdimm_check_and_set_ro(pmem->disk); } static void nd_pmem_notify(struct device *dev, enum nvdimm_event event) { switch (event) { case NVDIMM_REVALIDATE_POISON: pmem_revalidate_poison(dev); break; case NVDIMM_REVALIDATE_REGION: pmem_revalidate_region(dev); break; default: dev_WARN_ONCE(dev, 1, "notify: unknown event: %d\n", event); break; } } MODULE_ALIAS("pmem"); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM); static struct nd_device_driver nd_pmem_driver = { .probe = nd_pmem_probe, .remove = nd_pmem_remove, .notify = nd_pmem_notify, .shutdown = nd_pmem_shutdown, .drv = { .name = "nd_pmem", }, .type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM, }; module_nd_driver(nd_pmem_driver); MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>"); MODULE_DESCRIPTION("NVDIMM Persistent Memory Driver"); MODULE_LICENSE("GPL v2"); |
| 5 5 5 5 106 106 106 105 105 105 145 145 145 145 145 15 13 13 15 15 15 15 15 14 15 15 15 15 10 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Advanced Linux Sound Architecture * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/device.h> #include <linux/module.h> #include <linux/debugfs.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/info.h> #include <sound/control.h> #include <sound/initval.h> #include <linux/kmod.h> #include <linux/mutex.h> static int major = CONFIG_SND_MAJOR; int snd_major; EXPORT_SYMBOL(snd_major); static int cards_limit = 1; MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>"); MODULE_DESCRIPTION("Advanced Linux Sound Architecture driver for soundcards."); MODULE_LICENSE("GPL"); module_param(major, int, 0444); MODULE_PARM_DESC(major, "Major # for sound driver."); module_param(cards_limit, int, 0444); MODULE_PARM_DESC(cards_limit, "Count of auto-loadable soundcards."); MODULE_ALIAS_CHARDEV_MAJOR(CONFIG_SND_MAJOR); /* this one holds the actual max. card number currently available. * as default, it's identical with cards_limit option. when more * modules are loaded manually, this limit number increases, too. */ int snd_ecards_limit; EXPORT_SYMBOL(snd_ecards_limit); #ifdef CONFIG_SND_DEBUG struct dentry *sound_debugfs_root; EXPORT_SYMBOL_GPL(sound_debugfs_root); #endif static struct snd_minor *snd_minors[SNDRV_OS_MINORS]; static DEFINE_MUTEX(sound_mutex); #ifdef CONFIG_MODULES /** * snd_request_card - try to load the card module * @card: the card number * * Tries to load the module "snd-card-X" for the given card number * via request_module. Returns immediately if already loaded. */ void snd_request_card(int card) { if (snd_card_locked(card)) return; if (card < 0 || card >= cards_limit) return; request_module("snd-card-%i", card); } EXPORT_SYMBOL(snd_request_card); static void snd_request_other(int minor) { char *str; switch (minor) { case SNDRV_MINOR_SEQUENCER: str = "snd-seq"; break; case SNDRV_MINOR_TIMER: str = "snd-timer"; break; default: return; } request_module(str); } #endif /* modular kernel */ /** * snd_lookup_minor_data - get user data of a registered device * @minor: the minor number * @type: device type (SNDRV_DEVICE_TYPE_XXX) * * Checks that a minor device with the specified type is registered, and returns * its user data pointer. * * This function increments the reference counter of the card instance * if an associated instance with the given minor number and type is found. * The caller must call snd_card_unref() appropriately later. * * Return: The user data pointer if the specified device is found. %NULL * otherwise. */ void *snd_lookup_minor_data(unsigned int minor, int type) { struct snd_minor *mreg; void *private_data; if (minor >= ARRAY_SIZE(snd_minors)) return NULL; guard(mutex)(&sound_mutex); mreg = snd_minors[minor]; if (mreg && mreg->type == type) { private_data = mreg->private_data; if (private_data && mreg->card_ptr) get_device(&mreg->card_ptr->card_dev); } else private_data = NULL; return private_data; } EXPORT_SYMBOL(snd_lookup_minor_data); #ifdef CONFIG_MODULES static struct snd_minor *autoload_device(unsigned int minor) { int dev; mutex_unlock(&sound_mutex); /* release lock temporarily */ dev = SNDRV_MINOR_DEVICE(minor); if (dev == SNDRV_MINOR_CONTROL) { /* /dev/aloadC? */ int card = SNDRV_MINOR_CARD(minor); struct snd_card *ref = snd_card_ref(card); if (!ref) snd_request_card(card); else snd_card_unref(ref); } else if (dev == SNDRV_MINOR_GLOBAL) { /* /dev/aloadSEQ */ snd_request_other(minor); } mutex_lock(&sound_mutex); /* reacquire lock */ return snd_minors[minor]; } #else /* !CONFIG_MODULES */ #define autoload_device(minor) NULL #endif /* CONFIG_MODULES */ static int snd_open(struct inode *inode, struct file *file) { unsigned int minor = iminor(inode); struct snd_minor *mptr = NULL; const struct file_operations *new_fops; int err = 0; if (minor >= ARRAY_SIZE(snd_minors)) return -ENODEV; scoped_guard(mutex, &sound_mutex) { mptr = snd_minors[minor]; if (mptr == NULL) { mptr = autoload_device(minor); if (!mptr) return -ENODEV; } new_fops = fops_get(mptr->f_ops); } if (!new_fops) return -ENODEV; replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode, file); return err; } static const struct file_operations snd_fops = { .owner = THIS_MODULE, .open = snd_open, .llseek = noop_llseek, }; #ifdef CONFIG_SND_DYNAMIC_MINORS static int snd_find_free_minor(int type, struct snd_card *card, int dev) { int minor; /* static minors for module auto loading */ if (type == SNDRV_DEVICE_TYPE_SEQUENCER) return SNDRV_MINOR_SEQUENCER; if (type == SNDRV_DEVICE_TYPE_TIMER) return SNDRV_MINOR_TIMER; for (minor = 0; minor < ARRAY_SIZE(snd_minors); ++minor) { /* skip static minors still used for module auto loading */ if (SNDRV_MINOR_DEVICE(minor) == SNDRV_MINOR_CONTROL) continue; if (minor == SNDRV_MINOR_SEQUENCER || minor == SNDRV_MINOR_TIMER) continue; if (!snd_minors[minor]) return minor; } return -EBUSY; } #else static int snd_find_free_minor(int type, struct snd_card *card, int dev) { int minor; switch (type) { case SNDRV_DEVICE_TYPE_SEQUENCER: case SNDRV_DEVICE_TYPE_TIMER: minor = type; break; case SNDRV_DEVICE_TYPE_CONTROL: if (snd_BUG_ON(!card)) return -EINVAL; minor = SNDRV_MINOR(card->number, type); break; case SNDRV_DEVICE_TYPE_HWDEP: case SNDRV_DEVICE_TYPE_RAWMIDI: case SNDRV_DEVICE_TYPE_PCM_PLAYBACK: case SNDRV_DEVICE_TYPE_PCM_CAPTURE: if (snd_BUG_ON(!card)) return -EINVAL; minor = SNDRV_MINOR(card->number, type + dev); break; case SNDRV_DEVICE_TYPE_COMPRESS: if (snd_BUG_ON(!card)) return -EINVAL; if (dev < 0 || dev >= SNDRV_MINOR_HWDEP - SNDRV_MINOR_COMPRESS) return -EINVAL; minor = SNDRV_MINOR(card->number, type + dev); break; default: return -EINVAL; } if (snd_BUG_ON(minor < 0 || minor >= SNDRV_OS_MINORS)) return -EINVAL; if (snd_minors[minor]) return -EBUSY; return minor; } #endif /** * snd_register_device - Register the ALSA device file for the card * @type: the device type, SNDRV_DEVICE_TYPE_XXX * @card: the card instance * @dev: the device index * @f_ops: the file operations * @private_data: user pointer for f_ops->open() * @device: the device to register * * Registers an ALSA device file for the given card. * The operators have to be set in reg parameter. * * Return: Zero if successful, or a negative error code on failure. */ int snd_register_device(int type, struct snd_card *card, int dev, const struct file_operations *f_ops, void *private_data, struct device *device) { int minor; int err = 0; struct snd_minor *preg; if (snd_BUG_ON(!device)) return -EINVAL; preg = kmalloc_obj(*preg); if (preg == NULL) return -ENOMEM; preg->type = type; preg->card = card ? card->number : -1; preg->device = dev; preg->f_ops = f_ops; preg->private_data = private_data; preg->card_ptr = card; guard(mutex)(&sound_mutex); minor = snd_find_free_minor(type, card, dev); if (minor < 0) { err = minor; goto error; } preg->dev = device; device->devt = MKDEV(major, minor); err = device_add(device); if (err < 0) goto error; snd_minors[minor] = preg; error: if (err < 0) kfree(preg); return err; } EXPORT_SYMBOL(snd_register_device); /** * snd_unregister_device - unregister the device on the given card * @dev: the device instance * * Unregisters the device file already registered via * snd_register_device(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_unregister_device(struct device *dev) { int minor; struct snd_minor *preg; guard(mutex)(&sound_mutex); for (minor = 0; minor < ARRAY_SIZE(snd_minors); ++minor) { preg = snd_minors[minor]; if (preg && preg->dev == dev) { snd_minors[minor] = NULL; device_del(dev); kfree(preg); break; } } if (minor >= ARRAY_SIZE(snd_minors)) return -ENOENT; return 0; } EXPORT_SYMBOL(snd_unregister_device); #ifdef CONFIG_SND_PROC_FS /* * INFO PART */ static const char *snd_device_type_name(int type) { switch (type) { case SNDRV_DEVICE_TYPE_CONTROL: return "control"; case SNDRV_DEVICE_TYPE_HWDEP: return "hardware dependent"; case SNDRV_DEVICE_TYPE_RAWMIDI: return "raw midi"; case SNDRV_DEVICE_TYPE_PCM_PLAYBACK: return "digital audio playback"; case SNDRV_DEVICE_TYPE_PCM_CAPTURE: return "digital audio capture"; case SNDRV_DEVICE_TYPE_SEQUENCER: return "sequencer"; case SNDRV_DEVICE_TYPE_TIMER: return "timer"; case SNDRV_DEVICE_TYPE_COMPRESS: return "compress"; default: return "?"; } } static void snd_minor_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int minor; struct snd_minor *mptr; guard(mutex)(&sound_mutex); for (minor = 0; minor < SNDRV_OS_MINORS; ++minor) { mptr = snd_minors[minor]; if (!mptr) continue; if (mptr->card >= 0) { if (mptr->device >= 0) snd_iprintf(buffer, "%3i: [%2i-%2i]: %s\n", minor, mptr->card, mptr->device, snd_device_type_name(mptr->type)); else snd_iprintf(buffer, "%3i: [%2i] : %s\n", minor, mptr->card, snd_device_type_name(mptr->type)); } else snd_iprintf(buffer, "%3i: : %s\n", minor, snd_device_type_name(mptr->type)); } } int __init snd_minor_info_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "devices", NULL); if (!entry) return -ENOMEM; entry->c.text.read = snd_minor_info_read; return snd_info_register(entry); /* freed in error path */ } #endif /* CONFIG_SND_PROC_FS */ /* * INIT PART */ static int __init alsa_sound_init(void) { snd_major = major; snd_ecards_limit = cards_limit; if (register_chrdev(major, "alsa", &snd_fops)) { pr_err("ALSA core: unable to register native major device number %d\n", major); return -EIO; } if (snd_info_init() < 0) { unregister_chrdev(major, "alsa"); return -ENOMEM; } #ifdef CONFIG_SND_DEBUG sound_debugfs_root = debugfs_create_dir("sound", NULL); #endif #ifndef MODULE pr_info("Advanced Linux Sound Architecture Driver Initialized.\n"); #endif return 0; } static void __exit alsa_sound_exit(void) { #ifdef CONFIG_SND_DEBUG debugfs_remove(sound_debugfs_root); #endif snd_info_done(); unregister_chrdev(major, "alsa"); } subsys_initcall(alsa_sound_init); module_exit(alsa_sound_exit); |
| 73 73 1 1 1 1 1 1 1 1 1 1 1 8 8 8 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 | // SPDX-License-Identifier: GPL-2.0 /* * Central processing for nfsd. * * Authors: Olaf Kirch (okir@monad.swb.de) * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/sched/signal.h> #include <linux/freezer.h> #include <linux/module.h> #include <linux/fs_struct.h> #include <linux/swap.h> #include <linux/siphash.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/lockd/bind.h> #include <linux/nfsacl.h> #include <linux/nfslocalio.h> #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include "nfsd.h" #include "cache.h" #include "vfs.h" #include "netns.h" #include "filecache.h" #include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_SVC atomic_t nfsd_th_cnt = ATOMIC_INIT(0); static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static int nfsd_acl_rpcbind_set(struct net *, const struct svc_program *, u32, int, unsigned short, unsigned short); static __be32 nfsd_acl_init_request(struct svc_rqst *, const struct svc_program *, struct svc_process_info *); #endif static int nfsd_rpcbind_set(struct net *, const struct svc_program *, u32, int, unsigned short, unsigned short); static __be32 nfsd_init_request(struct svc_rqst *, const struct svc_program *, struct svc_process_info *); /* * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members * of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks. * * Finally, the nfsd_mutex also protects some of the global variables that are * accessed when nfsd starts and that are settable via the write_* routines in * nfsctl.c. In particular: * * user_recovery_dirname * user_lease_time * nfsd_versions */ DEFINE_MUTEX(nfsd_mutex); #if IS_ENABLED(CONFIG_NFS_LOCALIO) static const struct svc_version *localio_versions[] = { [1] = &localio_version1, }; #define NFSD_LOCALIO_NRVERS ARRAY_SIZE(localio_versions) #endif /* CONFIG_NFS_LOCALIO */ #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static const struct svc_version *nfsd_acl_version[] = { # if defined(CONFIG_NFSD_V2_ACL) [2] = &nfsd_acl_version2, # endif # if defined(CONFIG_NFSD_V3_ACL) [3] = &nfsd_acl_version3, # endif }; #define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = { #if defined(CONFIG_NFSD_V2) [2] = &nfsd_version2, #endif [3] = &nfsd_version3, #if defined(CONFIG_NFSD_V4) [4] = &nfsd_version4, #endif }; struct svc_program nfsd_programs[] = { { .pg_prog = NFS_PROGRAM, /* program number */ .pg_nvers = NFSD_MAXVERS+1, /* nr of entries in nfsd_version */ .pg_vers = nfsd_version, /* version table */ .pg_name = "nfsd", /* program name */ .pg_class = "nfsd", /* authentication class */ .pg_authenticate = svc_set_client, /* export authentication */ .pg_init_request = nfsd_init_request, .pg_rpcbind_set = nfsd_rpcbind_set, }, #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) { .pg_prog = NFS_ACL_PROGRAM, .pg_nvers = NFSD_ACL_NRVERS, .pg_vers = nfsd_acl_version, .pg_name = "nfsacl", .pg_class = "nfsd", .pg_authenticate = svc_set_client, .pg_init_request = nfsd_acl_init_request, .pg_rpcbind_set = nfsd_acl_rpcbind_set, }, #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ #if IS_ENABLED(CONFIG_NFS_LOCALIO) { .pg_prog = NFS_LOCALIO_PROGRAM, .pg_nvers = NFSD_LOCALIO_NRVERS, .pg_vers = localio_versions, .pg_name = "nfslocalio", .pg_class = "nfsd", .pg_authenticate = svc_set_client, .pg_init_request = svc_generic_init_request, .pg_rpcbind_set = svc_generic_rpcbind_set, } #endif /* CONFIG_NFS_LOCALIO */ }; bool nfsd_support_version(int vers) { if (vers >= NFSD_MINVERS && vers <= NFSD_MAXVERS) return nfsd_version[vers] != NULL; return false; } int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change) { if (vers < NFSD_MINVERS || vers > NFSD_MAXVERS) return 0; switch(change) { case NFSD_SET: nn->nfsd_versions[vers] = nfsd_support_version(vers); break; case NFSD_CLEAR: nn->nfsd_versions[vers] = false; break; case NFSD_TEST: return nn->nfsd_versions[vers]; case NFSD_AVAIL: return nfsd_support_version(vers); } return 0; } static void nfsd_adjust_nfsd_versions4(struct nfsd_net *nn) { unsigned i; for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) { if (nn->nfsd4_minorversions[i]) return; } nfsd_vers(nn, 4, NFSD_CLEAR); } int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change) { if (minorversion > NFSD_SUPPORTED_MINOR_VERSION && change != NFSD_AVAIL) return -1; switch(change) { case NFSD_SET: nfsd_vers(nn, 4, NFSD_SET); nn->nfsd4_minorversions[minorversion] = nfsd_vers(nn, 4, NFSD_TEST); break; case NFSD_CLEAR: nn->nfsd4_minorversions[minorversion] = false; nfsd_adjust_nfsd_versions4(nn); break; case NFSD_TEST: return nn->nfsd4_minorversions[minorversion]; case NFSD_AVAIL: return minorversion <= NFSD_SUPPORTED_MINOR_VERSION && nfsd_vers(nn, 4, NFSD_AVAIL); } return 0; } bool nfsd_net_try_get(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); return (nn && percpu_ref_tryget_live(&nn->nfsd_net_ref)); } void nfsd_net_put(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); percpu_ref_put(&nn->nfsd_net_ref); } static void nfsd_net_done(struct percpu_ref *ref) { struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); complete(&nn->nfsd_net_confirm_done); } static void nfsd_net_free(struct percpu_ref *ref) { struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref); complete(&nn->nfsd_net_free_done); } /* * Maximum number of nfsd processes */ #define NFSD_MAXSERVS 8192 int nfsd_nrthreads(struct net *net) { int i, rv = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); mutex_lock(&nfsd_mutex); if (nn->nfsd_serv) for (i = 0; i < nn->nfsd_serv->sv_nrpools; ++i) rv += nn->nfsd_serv->sv_pools[i].sp_nrthrmax; mutex_unlock(&nfsd_mutex); return rv; } static int nfsd_users = 0; static int nfsd_startup_generic(void) { int ret; if (nfsd_users++) return 0; ret = nfsd_file_cache_init(); if (ret) goto dec_users; ret = nfs4_state_start(); if (ret) goto out_file_cache; return 0; out_file_cache: nfsd_file_cache_shutdown(); dec_users: nfsd_users--; return ret; } static void nfsd_shutdown_generic(void) { if (--nfsd_users) return; nfs4_state_shutdown(); nfsd_file_cache_shutdown(); } static bool nfsd_needs_lockd(struct nfsd_net *nn) { return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST); } /** * nfsd_copy_write_verifier - Atomically copy a write verifier * @verf: buffer in which to receive the verifier cookie * @nn: NFS net namespace * * This function provides a wait-free mechanism for copying the * namespace's write verifier without tearing it. */ void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn) { unsigned int seq; do { seq = read_seqbegin(&nn->writeverf_lock); memcpy(verf, nn->writeverf, sizeof(nn->writeverf)); } while (read_seqretry(&nn->writeverf_lock, seq)); } static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn) { struct timespec64 now; u64 verf; /* * Because the time value is hashed, y2038 time_t overflow * is irrelevant in this usage. */ ktime_get_raw_ts64(&now); verf = siphash_2u64(now.tv_sec, now.tv_nsec, &nn->siphash_key); memcpy(nn->writeverf, &verf, sizeof(nn->writeverf)); } /** * nfsd_reset_write_verifier - Generate a new write verifier * @nn: NFS net namespace * * This function updates the ->writeverf field of @nn. This field * contains an opaque cookie that, according to Section 18.32.3 of * RFC 8881, "the client can use to determine whether a server has * changed instance state (e.g., server restart) between a call to * WRITE and a subsequent call to either WRITE or COMMIT. This * cookie MUST be unchanged during a single instance of the NFSv4.1 * server and MUST be unique between instances of the NFSv4.1 * server." */ void nfsd_reset_write_verifier(struct nfsd_net *nn) { write_seqlock(&nn->writeverf_lock); nfsd_reset_write_verifier_locked(nn); write_sequnlock(&nn->writeverf_lock); } /* * Crank up a set of per-namespace resources for a new NFSD instance, * including lockd, a duplicate reply cache, an open file cache * instance, and a cache of NFSv4 state objects. */ static int nfsd_startup_net(struct net *net, const struct cred *cred) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; if (nn->nfsd_net_up) return 0; ret = nfsd_startup_generic(); if (ret) return ret; if (list_empty(&nn->nfsd_serv->sv_permsocks)) { pr_warn("NFSD: Failed to start, no listeners configured.\n"); ret = -EIO; goto out_socks; } if (nfsd_needs_lockd(nn) && !nn->lockd_up) { ret = lockd_up(net, cred); if (ret) goto out_socks; nn->lockd_up = true; } ret = nfsd_file_cache_start_net(net); if (ret) goto out_lockd; ret = nfsd_reply_cache_init(nn); if (ret) goto out_filecache; #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_init_umount_work(nn); #endif ret = nfs4_state_start_net(net); if (ret) goto out_reply_cache; nn->nfsd_net_up = true; return 0; out_reply_cache: nfsd_reply_cache_shutdown(nn); out_filecache: nfsd_file_cache_shutdown_net(net); out_lockd: if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; } out_socks: nfsd_shutdown_generic(); return ret; } static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (nn->nfsd_net_up) { percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); wait_for_completion(&nn->nfsd_net_confirm_done); nfsd_export_flush(net); nfs4_state_shutdown_net(net); nfsd_reply_cache_shutdown(nn); nfsd_file_cache_shutdown_net(net); if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; } wait_for_completion(&nn->nfsd_net_free_done); } percpu_ref_exit(&nn->nfsd_net_ref); if (nn->nfsd_net_up) nfsd_shutdown_generic(); nn->nfsd_net_up = false; } static DEFINE_SPINLOCK(nfsd_notifier_lock); static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct net_device *dev = ifa->ifa_dev->dev; struct net *net = dev_net(dev); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in sin; if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local); sin.sin_family = AF_INET; sin.sin_addr.s_addr = ifa->ifa_local; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin); } spin_unlock(&nfsd_notifier_lock); out: return NOTIFY_DONE; } static struct notifier_block nfsd_inetaddr_notifier = { .notifier_call = nfsd_inetaddr_event, }; #if IS_ENABLED(CONFIG_IPV6) static int nfsd_inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct net_device *dev = ifa->idev->dev; struct net *net = dev_net(dev); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in6 sin6; if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ifa->addr; if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) sin6.sin6_scope_id = ifa->idev->dev->ifindex; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6); } spin_unlock(&nfsd_notifier_lock); out: return NOTIFY_DONE; } static struct notifier_block nfsd_inet6addr_notifier = { .notifier_call = nfsd_inet6addr_event, }; #endif /* Only used under nfsd_mutex, so this atomic may be overkill: */ static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0); /** * nfsd_destroy_serv - tear down NFSD's svc_serv for a namespace * @net: network namespace the NFS service is associated with */ void nfsd_destroy_serv(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv = nn->nfsd_serv; lockdep_assert_held(&nfsd_mutex); spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = NULL; spin_unlock(&nfsd_notifier_lock); /* check if the notifier still has clients */ if (atomic_dec_return(&nfsd_notifier_refcount) == 0) { unregister_inetaddr_notifier(&nfsd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } /* * write_ports can create the server without actually starting * any threads. If we get shut down before any threads are * started, then nfsd_destroy_serv will be run before any of this * other initialization has been done except the rpcb information. */ svc_xprt_destroy_all(serv, net, true); nfsd_shutdown_net(net); svc_destroy(&serv); } void nfsd_reset_versions(struct nfsd_net *nn) { int i; for (i = 0; i <= NFSD_MAXVERS; i++) if (nfsd_vers(nn, i, NFSD_TEST)) return; for (i = 0; i <= NFSD_MAXVERS; i++) if (i != 4) nfsd_vers(nn, i, NFSD_SET); else { int minor = 0; while (nfsd_minorversion(nn, minor, NFSD_SET) >= 0) minor++; } } static int nfsd_get_default_max_blksize(void) { struct sysinfo i; unsigned long long target; unsigned long ret; si_meminfo(&i); target = (i.totalram - i.totalhigh) << PAGE_SHIFT; /* * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig * machines, but only uses 32K on 128M machines. Bottom out at * 8K on 32M and smaller. Of course, this is only a default. */ target >>= 12; ret = NFSSVC_DEFBLKSIZE; while (ret > target && ret >= 8*1024*2) ret /= 2; return ret; } void nfsd_shutdown_threads(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; mutex_lock(&nfsd_mutex); serv = nn->nfsd_serv; if (serv == NULL) { mutex_unlock(&nfsd_mutex); return; } /* Kill outstanding nfsd threads */ svc_set_num_threads(serv, 0, 0); nfsd_destroy_serv(net); mutex_unlock(&nfsd_mutex); } struct svc_rqst *nfsd_current_rqst(void) { if (kthread_func(current) == nfsd) return kthread_data(current); return NULL; } int nfsd_create_serv(struct net *net) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; WARN_ON(!mutex_is_locked(&nfsd_mutex)); if (nn->nfsd_serv) return 0; error = percpu_ref_init(&nn->nfsd_net_ref, nfsd_net_free, 0, GFP_KERNEL); if (error) return error; init_completion(&nn->nfsd_net_free_done); init_completion(&nn->nfsd_net_confirm_done); if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(nn); serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs), &nn->nfsd_svcstats, nfsd_max_blksize, nfsd); if (serv == NULL) { percpu_ref_exit(&nn->nfsd_net_ref); return -ENOMEM; } error = svc_bind(serv, net); if (error < 0) { svc_destroy(&serv); percpu_ref_exit(&nn->nfsd_net_ref); return error; } spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = serv; spin_unlock(&nfsd_notifier_lock); /* check if the notifier is already set */ if (atomic_inc_return(&nfsd_notifier_refcount) == 1) { register_inetaddr_notifier(&nfsd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } nfsd_reset_write_verifier(nn); return 0; } int nfsd_nrpools(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (nn->nfsd_serv == NULL) return 0; else return nn->nfsd_serv->sv_nrpools; } int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv = nn->nfsd_serv; int i; if (serv) for (i = 0; i < serv->sv_nrpools && i < n; i++) nthreads[i] = serv->sv_pools[i].sp_nrthrmax; return 0; } /** * nfsd_set_nrthreads - set the number of running threads in the net's service * @n: number of array members in @nthreads * @nthreads: array of thread counts for each pool * @net: network namespace to operate within * * This function alters the number of running threads for the given network * namespace in each pool. If passed an array longer then the number of pools * the extra pool settings are ignored. If passed an array shorter than the * number of pools, the missing values are interpreted as 0's. * * Returns 0 on success or a negative errno on error. */ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) { int i = 0; int tot = 0; int err = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); lockdep_assert_held(&nfsd_mutex); if (nn->nfsd_serv == NULL || n <= 0) return 0; /* Special case: When n == 1, distribute threads equally among pools. */ if (n == 1) return svc_set_num_threads(nn->nfsd_serv, nn->min_threads, nthreads[0]); if (n > nn->nfsd_serv->sv_nrpools) n = nn->nfsd_serv->sv_nrpools; /* enforce a global maximum number of threads */ tot = 0; for (i = 0; i < n; i++) { nthreads[i] = min(nthreads[i], NFSD_MAXSERVS); tot += nthreads[i]; } if (tot > NFSD_MAXSERVS) { /* total too large: scale down requested numbers */ for (i = 0; i < n && tot > 0; i++) { int new = nthreads[i] * NFSD_MAXSERVS / tot; tot -= (nthreads[i] - new); nthreads[i] = new; } for (i = 0; i < n && tot > 0; i++) { nthreads[i]--; tot--; } } /* apply the new numbers */ for (i = 0; i < n; i++) { err = svc_set_pool_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i], nn->min_threads, nthreads[i]); if (err) goto out; } /* Anything undefined in array is considered to be 0 */ for (i = n; i < nn->nfsd_serv->sv_nrpools; ++i) { err = svc_set_pool_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i], 0, 0); if (err) goto out; } out: return err; } /** * nfsd_svc: start up or shut down the nfsd server * @n: number of array members in @nthreads * @nthreads: array of thread counts for each pool * @net: network namespace to operate within * @cred: credentials to use for xprt creation * @scope: server scope value (defaults to nodename) * * Adjust the number of threads in each pool and return the new * total number of threads in the service. */ int nfsd_svc(int n, int *nthreads, struct net *net, const struct cred *cred, const char *scope) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; lockdep_assert_held(&nfsd_mutex); dprintk("nfsd: creating service\n"); strscpy(nn->nfsd_name, scope ? scope : utsname()->nodename, sizeof(nn->nfsd_name)); error = nfsd_create_serv(net); if (error) goto out; serv = nn->nfsd_serv; error = nfsd_startup_net(net, cred); if (error) goto out_put; error = nfsd_set_nrthreads(n, nthreads, net); if (error) goto out_put; error = serv->sv_nrthreads; out_put: if (serv->sv_nrthreads == 0) nfsd_destroy_serv(net); out: return error; } #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static bool nfsd_support_acl_version(int vers) { if (vers >= NFSD_ACL_MINVERS && vers < NFSD_ACL_NRVERS) return nfsd_acl_version[vers] != NULL; return false; } static int nfsd_acl_rpcbind_set(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { if (!nfsd_support_acl_version(version) || !nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) return 0; return svc_generic_rpcbind_set(net, progp, version, family, proto, port); } static __be32 nfsd_acl_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, struct svc_process_info *ret) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); int i; if (likely(nfsd_support_acl_version(rqstp->rq_vers) && nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) return svc_generic_init_request(rqstp, progp, ret); ret->mismatch.lovers = NFSD_ACL_NRVERS; for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) { if (nfsd_support_acl_version(rqstp->rq_vers) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.lovers = i; break; } } if (ret->mismatch.lovers == NFSD_ACL_NRVERS) return rpc_prog_unavail; ret->mismatch.hivers = NFSD_ACL_MINVERS; for (i = NFSD_ACL_NRVERS - 1; i >= NFSD_ACL_MINVERS; i--) { if (nfsd_support_acl_version(rqstp->rq_vers) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.hivers = i; break; } } return rpc_prog_mismatch; } #endif static int nfsd_rpcbind_set(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { if (!nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) return 0; return svc_generic_rpcbind_set(net, progp, version, family, proto, port); } static __be32 nfsd_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, struct svc_process_info *ret) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); int i; if (likely(nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) return svc_generic_init_request(rqstp, progp, ret); ret->mismatch.lovers = NFSD_MAXVERS + 1; for (i = NFSD_MINVERS; i <= NFSD_MAXVERS; i++) { if (nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.lovers = i; break; } } if (ret->mismatch.lovers > NFSD_MAXVERS) return rpc_prog_unavail; ret->mismatch.hivers = NFSD_MINVERS; for (i = NFSD_MAXVERS; i >= NFSD_MINVERS; i--) { if (nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.hivers = i; break; } } return rpc_prog_mismatch; } /* * This is the NFS server kernel thread */ static int nfsd(void *vrqstp) { struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp; struct svc_pool *pool = rqstp->rq_pool; struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list); struct net *net = perm_sock->xpt_net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfsd_thread_local_info ntli = { }; bool have_mutex = false; /* At this point, the thread shares current->fs * with the init process. We need to create files with the * umask as defined by the client instead of init's umask. */ svc_thread_init_status(rqstp, unshare_fs_struct()); current->fs->umask = 0; atomic_inc(&nfsd_th_cnt); set_freezable(); /* use dynamic allocation if ntli should ever become large */ static_assert(sizeof(struct nfsd_thread_local_info) < 256); rqstp->rq_private = &ntli; /* * The main request loop */ while (!svc_thread_should_stop(rqstp)) { switch (svc_recv(rqstp, 5 * HZ)) { case -ETIMEDOUT: /* No work arrived within the timeout window */ if (mutex_trylock(&nfsd_mutex)) { if (pool->sp_nrthreads > pool->sp_nrthrmin) { trace_nfsd_dynthread_kill(net, pool); set_bit(RQ_VICTIM, &rqstp->rq_flags); have_mutex = true; } else { mutex_unlock(&nfsd_mutex); } } else { trace_nfsd_dynthread_trylock_fail(net, pool); } break; case -EBUSY: /* No idle threads; consider spawning another */ if (pool->sp_nrthreads < pool->sp_nrthrmax) { if (mutex_trylock(&nfsd_mutex)) { if (pool->sp_nrthreads < pool->sp_nrthrmax) { int ret; trace_nfsd_dynthread_start(net, pool); ret = svc_new_thread(rqstp->rq_server, pool); if (ret) pr_notice_ratelimited("%s: unable to spawn new thread: %d\n", __func__, ret); } mutex_unlock(&nfsd_mutex); } else { trace_nfsd_dynthread_trylock_fail(net, pool); } } clear_bit(SP_TASK_STARTING, &pool->sp_flags); break; default: break; } nfsd_file_net_dispose(nn); } atomic_dec(&nfsd_th_cnt); /* Release the thread */ svc_exit_thread(rqstp); if (have_mutex) mutex_unlock(&nfsd_mutex); return 0; } /** * nfsd_dispatch - Process an NFS or NFSACL or LOCALIO Request * @rqstp: incoming request * * This RPC dispatcher integrates the NFS server's duplicate reply cache. * * Return values: * %0: Processing complete; do not send a Reply * %1: Processing complete; send Reply in rqstp->rq_res */ int nfsd_dispatch(struct svc_rqst *rqstp) { struct nfsd_thread_local_info *ntli = rqstp->rq_private; const struct svc_procedure *proc = rqstp->rq_procinfo; __be32 *statp = rqstp->rq_accept_statp; struct nfsd_cacherep *rp; unsigned int start, len; __be32 *nfs_reply; /* * Give the xdr decoder a chance to change this if it wants * (necessary in the NFSv4.0 compound case) */ ntli->ntli_cachetype = proc->pc_cachetype; /* * ->pc_decode advances the argument stream past the NFS * Call header, so grab the header's starting location and * size now for the call to nfsd_cache_lookup(). */ start = xdr_stream_pos(&rqstp->rq_arg_stream); len = xdr_stream_remaining(&rqstp->rq_arg_stream); if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; /* * Release rq_status_counter setting it to an odd value after the rpc * request has been properly parsed. rq_status_counter is used to * notify the consumers if the rqstp fields are stable * (rq_status_counter is odd) or not meaningful (rq_status_counter * is even). */ smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1); rp = NULL; switch (nfsd_cache_lookup(rqstp, start, len, &rp)) { case RC_DOIT: break; case RC_REPLY: goto out_cached_reply; case RC_DROPIT: goto out_dropit; } nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; /* * Release rq_status_counter setting it to an even value after the rpc * request has been properly processed. */ smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1); nfsd_cache_update(rqstp, rp, ntli->ntli_cachetype, nfs_reply); out_cached_reply: return 1; out_decode_err: trace_nfsd_garbage_args_err(rqstp); *statp = rpc_garbage_args; return 1; out_update_drop: nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); out_dropit: return 0; out_encode_err: trace_nfsd_cant_encode_err(rqstp); nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); *statp = rpc_system_err; return 1; } /** * nfssvc_decode_voidarg - Decode void arguments * @rqstp: Server RPC transaction context * @xdr: XDR stream positioned at arguments to decode * * Return values: * %false: Arguments were not valid * %true: Decoding was successful */ bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return true; } /** * nfssvc_encode_voidres - Encode void results * @rqstp: Server RPC transaction context * @xdr: XDR stream into which to encode results * * Return values: * %false: Local error while encoding * %true: Encoding was successful */ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return true; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _VT_KERN_H #define _VT_KERN_H /* * this really is an extension of the vc_cons structure in console.c, but * with information needed by the vt package */ #include <linux/vt.h> #include <linux/kd.h> #include <linux/tty.h> #include <linux/mutex.h> #include <linux/console_struct.h> #include <linux/mm.h> #include <linux/consolemap.h> #include <linux/notifier.h> void kd_mksound(unsigned int hz, unsigned int ticks); int kbd_rate(struct kbd_repeat *rep); extern int fg_console, last_console, want_console; /* console.c */ int vc_allocate(unsigned int console); int vc_cons_allocated(unsigned int console); int __vc_resize(struct vc_data *vc, unsigned int cols, unsigned int lines, bool from_user); struct vc_data *vc_deallocate(unsigned int console); void reset_palette(struct vc_data *vc); void do_blank_screen(int entering_gfx); void do_unblank_screen(int leaving_gfx); void poke_blanked_console(void); int con_font_op(struct vc_data *vc, struct console_font_op *op); int con_set_cmap(unsigned char __user *cmap); int con_get_cmap(unsigned char __user *cmap); void scrollback(struct vc_data *vc); void scrollfront(struct vc_data *vc, int lines); void clear_buffer_attributes(struct vc_data *vc); void update_region(struct vc_data *vc, unsigned long start, int count); void redraw_screen(struct vc_data *vc, int is_switch); #define update_screen(x) redraw_screen(x, 0) #define switch_screen(x) redraw_screen(x, 1) static inline int vc_resize(struct vc_data *vc, unsigned int cols, unsigned int lines) { return __vc_resize(vc, cols, lines, false); } struct tty_struct; int tioclinux(struct tty_struct *tty, unsigned long arg); #ifdef CONFIG_CONSOLE_TRANSLATIONS /* consolemap.c */ struct unipair; int con_set_trans_old(unsigned char __user * table); int con_get_trans_old(unsigned char __user * table); int con_set_trans_new(unsigned short __user * table); int con_get_trans_new(unsigned short __user * table); int con_clear_unimap(struct vc_data *vc); int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list); int con_get_unimap(struct vc_data *vc, ushort ct, ushort __user *uct, struct unipair __user *list); int con_set_default_unimap(struct vc_data *vc); void con_free_unimap(struct vc_data *vc); int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); #else static inline int con_set_trans_old(unsigned char __user *table) { return 0; } static inline int con_get_trans_old(unsigned char __user *table) { return -EINVAL; } static inline int con_set_trans_new(unsigned short __user *table) { return 0; } static inline int con_get_trans_new(unsigned short __user *table) { return -EINVAL; } static inline int con_clear_unimap(struct vc_data *vc) { return 0; } static inline int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list) { return 0; } static inline int con_get_unimap(struct vc_data *vc, ushort ct, ushort __user *uct, struct unipair __user *list) { return -EINVAL; } static inline int con_set_default_unimap(struct vc_data *vc) { return 0; } static inline void con_free_unimap(struct vc_data *vc) { } static inline void con_protect_unimap(struct vc_data *vc, int rdonly) { } static inline int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc) { return 0; } #endif /* vt.c */ void vt_event_post(unsigned int event, unsigned int old, unsigned int new); int vt_waitactive(int n); void change_console(struct vc_data *new_vc); void reset_vc(struct vc_data *vc); int do_unbind_con_driver(const struct consw *csw, int first, int last, int deflt); int vty_init(const struct file_operations *console_fops); extern bool vt_dont_switch; extern int default_utf8; extern int global_cursor_default; struct vt_spawn_console { spinlock_t lock; struct pid *pid; int sig; }; extern struct vt_spawn_console vt_spawn_con; int vt_move_to_console(unsigned int vt, int alloc); /* Interfaces for VC notification of character events (for accessibility etc) */ struct vt_notifier_param { struct vc_data *vc; /* VC on which the update happened */ unsigned int c; /* Printed char */ }; int register_vt_notifier(struct notifier_block *nb); int unregister_vt_notifier(struct notifier_block *nb); void hide_boot_cursor(bool hide); /* keyboard provided interfaces */ int vt_do_diacrit(unsigned int cmd, void __user *up, int eperm); int vt_do_kdskbmode(unsigned int console, unsigned int arg); int vt_do_kdskbmeta(unsigned int console, unsigned int arg); int vt_do_kbkeycode_ioctl(int cmd, struct kbkeycode __user *user_kbkc, int perm); int vt_do_kdsk_ioctl(int cmd, struct kbentry __user *user_kbe, int perm, unsigned int console); int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm); int vt_do_kdskled(unsigned int console, int cmd, unsigned long arg, int perm); int vt_do_kdgkbmode(unsigned int console); int vt_do_kdgkbmeta(unsigned int console); void vt_reset_unicode(unsigned int console); int vt_get_shift_state(void); void vt_reset_keyboard(unsigned int console); int vt_get_leds(unsigned int console, int flag); int vt_get_kbd_mode_bit(unsigned int console, int bit); void vt_set_kbd_mode_bit(unsigned int console, int bit); void vt_clr_kbd_mode_bit(unsigned int console, int bit); void vt_set_led_state(unsigned int console, int leds); void vt_kbd_con_start(unsigned int console); void vt_kbd_con_stop(unsigned int console); #endif /* _VT_KERN_H */ |
| 4903 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM printk #if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PRINTK_H #include <linux/tracepoint.h> TRACE_EVENT(console, TP_PROTO(const char *text, size_t len), TP_ARGS(text, len), TP_STRUCT__entry( __dynamic_array(char, msg, len + 1) ), TP_fast_assign( /* * Each trace entry is printed in a new line. * If the msg finishes with '\n', cut it off * to avoid blank lines in the trace. */ if ((len > 0) && (text[len-1] == '\n')) len -= 1; memcpy(__get_str(msg), text, len); __get_str(msg)[len] = 0; ), TP_printk("%s", __get_str(msg)) ); #endif /* _TRACE_PRINTK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 23 4 4 4 3 2 3 3 3 7 7 3 4 7 7 7 11 10 8 8 3 5 7 2 5 2 5 4 2 2 17 17 27 24 10 26 25 24 1 3 2 1 1 23 22 8 18 11 7 10 1 10 5 10 27 1 1 12 1 13 16 16 73 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/filter.h> #include <linux/bpf.h> #include <net/netlink.h> #include <net/sock.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_bpf.h> #include <net/tc_act/tc_bpf.h> #include <net/tc_wrapper.h> #define ACT_BPF_NAME_LEN 256 struct tcf_bpf_cfg { struct bpf_prog *filter; struct sock_filter *bpf_ops; const char *bpf_name; u16 bpf_num_ops; bool is_ebpf; }; static struct tc_action_ops act_bpf_ops; TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { bool at_ingress = skb_at_tc_ingress(skb); struct tcf_bpf *prog = to_bpf(act); struct bpf_prog *filter; int action, filter_res; tcf_lastuse_update(&prog->tcf_tm); bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb); filter = rcu_dereference_bh(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); filter_res = bpf_prog_run_data_pointers(filter, skb); __skb_pull(skb, skb->mac_len); } else { filter_res = bpf_prog_run_data_pointers(filter, skb); } if (unlikely(!skb->tstamp && skb->tstamp_type)) skb->tstamp_type = SKB_CLOCK_REALTIME; if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); /* A BPF program may overwrite the default action opcode. * Similarly as in cls_bpf, if filter_res == -1 we use the * default action specified from tc. * * In case a different well-known TC_ACT opcode has been * returned, it will overwrite the default one. * * For everything else that is unknown, TC_ACT_UNSPEC is * returned. */ switch (filter_res) { case TC_ACT_PIPE: case TC_ACT_RECLASSIFY: case TC_ACT_OK: case TC_ACT_REDIRECT: action = filter_res; break; case TC_ACT_SHOT: action = filter_res; qstats_cpu_drop_inc(prog->common.cpu_qstats); break; case TC_ACT_UNSPEC: action = prog->tcf_action; break; default: action = TC_ACT_UNSPEC; break; } return action; } static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog) { return !prog->bpf_ops; } static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog, struct sk_buff *skb) { struct nlattr *nla; if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops)) return -EMSGSIZE; nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops * sizeof(struct sock_filter)); if (nla == NULL) return -EMSGSIZE; memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); return 0; } static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, struct sk_buff *skb) { struct nlattr *nla; if (prog->bpf_name && nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; if (nla_put_u32(skb, TCA_ACT_BPF_ID, prog->filter->aux->id)) return -EMSGSIZE; nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; memcpy(nla_data(nla), prog->filter->tag, nla_len(nla)); return 0; } static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref) { unsigned char *tp = skb_tail_pointer(skb); struct tcf_bpf *prog = to_bpf(act); struct tc_act_bpf opt = { .index = prog->tcf_index, .refcnt = refcount_read(&prog->tcf_refcnt) - ref, .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind, }; struct tcf_t tm; int ret; spin_lock_bh(&prog->tcf_lock); opt.action = prog->tcf_action; if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (tcf_bpf_is_ebpf(prog)) ret = tcf_bpf_dump_ebpf_info(prog, skb); else ret = tcf_bpf_dump_bpf_info(prog, skb); if (ret) goto nla_put_failure; tcf_tm_dump(&tm, &prog->tcf_tm); if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm, TCA_ACT_BPF_PAD)) goto nla_put_failure; spin_unlock_bh(&prog->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&prog->tcf_lock); nlmsg_trim(skb, tp); return -1; } static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, [TCA_ACT_BPF_FD] = { .type = NLA_U32 }, [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN }, [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { struct sock_filter *bpf_ops; struct sock_fprog_kern fprog_tmp; struct bpf_prog *fp; u16 bpf_size, bpf_num_ops; int ret; bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]); if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) return -EINVAL; bpf_size = bpf_num_ops * sizeof(*bpf_ops); if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS])) return -EINVAL; bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL); if (bpf_ops == NULL) return -ENOMEM; fprog_tmp.len = bpf_num_ops; fprog_tmp.filter = bpf_ops; ret = bpf_prog_create(&fp, &fprog_tmp); if (ret < 0) { kfree(bpf_ops); return ret; } cfg->bpf_ops = bpf_ops; cfg->bpf_num_ops = bpf_num_ops; cfg->filter = fp; cfg->is_ebpf = false; return 0; } static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { struct bpf_prog *fp; char *name = NULL; u32 bpf_fd; bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]); fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_ACT); if (IS_ERR(fp)) return PTR_ERR(fp); if (tb[TCA_ACT_BPF_NAME]) { name = nla_memdup(tb[TCA_ACT_BPF_NAME], GFP_KERNEL); if (!name) { bpf_prog_put(fp); return -ENOMEM; } } cfg->bpf_name = name; cfg->filter = fp; cfg->is_ebpf = true; return 0; } static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) { struct bpf_prog *filter = cfg->filter; if (filter) { if (cfg->is_ebpf) bpf_prog_put(filter); else bpf_prog_destroy(filter); } kfree(cfg->bpf_ops); kfree(cfg->bpf_name); } static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, struct tcf_bpf_cfg *cfg) { cfg->is_ebpf = tcf_bpf_is_ebpf(prog); /* updates to prog->filter are prevented, since it's called either * with tcf lock or during final cleanup in rcu callback */ cfg->filter = rcu_dereference_protected(prog->filter, 1); cfg->bpf_ops = prog->bpf_ops; cfg->bpf_name = prog->bpf_name; } static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; u32 index; if (!nla) return -EINVAL; ret = nla_parse_nested_deprecated(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_ACT_BPF_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); index = parm->index; ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { ret = tcf_idr_create(tn, index, est, act, &act_bpf_ops, bind, true, flags); if (ret < 0) { tcf_idr_cleanup(tn, index); return ret; } res = ACT_P_CREATED; } else if (ret > 0) { /* Don't override defaults. */ if (bind) return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*act, bind); return -EEXIST; } } else { return ret; } ret = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (ret < 0) goto release_idr; is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; is_ebpf = tb[TCA_ACT_BPF_FD]; if (is_bpf == is_ebpf) { ret = -EINVAL; goto put_chain; } memset(&cfg, 0, sizeof(cfg)); ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : tcf_bpf_init_from_efd(tb, &cfg); if (ret < 0) goto put_chain; prog = to_bpf(*act); spin_lock_bh(&prog->tcf_lock); if (res != ACT_P_CREATED) tcf_bpf_prog_fill_cfg(prog, &old); prog->bpf_ops = cfg.bpf_ops; prog->bpf_name = cfg.bpf_name; if (cfg.bpf_num_ops) prog->bpf_num_ops = cfg.bpf_num_ops; goto_ch = tcf_action_set_ctrlact(*act, parm->action, goto_ch); rcu_assign_pointer(prog->filter, cfg.filter); spin_unlock_bh(&prog->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (res != ACT_P_CREATED) { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); } return res; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*act, bind); return ret; } static void tcf_bpf_cleanup(struct tc_action *act) { struct tcf_bpf_cfg tmp; tcf_bpf_prog_fill_cfg(to_bpf(act), &tmp); tcf_bpf_cfg_cleanup(&tmp); } static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .id = TCA_ID_BPF, .owner = THIS_MODULE, .act = tcf_bpf_act, .dump = tcf_bpf_dump, .cleanup = tcf_bpf_cleanup, .init = tcf_bpf_init, .size = sizeof(struct tcf_bpf), }; MODULE_ALIAS_NET_ACT("bpf"); static __net_init int bpf_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); return tc_action_net_init(net, tn, &act_bpf_ops); } static void __net_exit bpf_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_bpf_ops.net_id); } static struct pernet_operations bpf_net_ops = { .init = bpf_init_net, .exit_batch = bpf_exit_net, .id = &act_bpf_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init bpf_init_module(void) { return tcf_register_action(&act_bpf_ops, &bpf_net_ops); } static void __exit bpf_cleanup_module(void) { tcf_unregister_action(&act_bpf_ops, &bpf_net_ops); } module_init(bpf_init_module); module_exit(bpf_cleanup_module); MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>"); MODULE_DESCRIPTION("TC BPF based action"); MODULE_LICENSE("GPL v2"); |
| 73 73 73 73 73 73 73 73 73 73 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Neil Brown <neilb@cse.unsw.edu.au> * J. Bruce Fields <bfields@umich.edu> * Andy Adamson <andros@umich.edu> * Dug Song <dugsong@monkey.org> * * RPCSEC_GSS server authentication. * This implements RPCSEC_GSS as defined in rfc2203 (rpcsec_gss) and rfc2078 * (gssapi) * * The RPCSEC_GSS involves three stages: * 1/ context creation * 2/ data exchange * 3/ context destruction * * Context creation is handled largely by upcalls to user-space. * In particular, GSS_Accept_sec_context is handled by an upcall * Data exchange is handled entirely within the kernel * In particular, GSS_GetMIC, GSS_VerifyMIC, GSS_Seal, GSS_Unseal are in-kernel. * Context destruction is handled in-kernel * GSS_Delete_sec_context is in-kernel * * Context creation is initiated by a RPCSEC_GSS_INIT request arriving. * The context handle and gss_token are used as a key into the rpcsec_init cache. * The content of this cache includes some of the outputs of GSS_Accept_sec_context, * being major_status, minor_status, context_handle, reply_token. * These are sent back to the client. * Sequence window management is handled by the kernel. The window size if currently * a compile time constant. * * When user-space is happy that a context is established, it places an entry * in the rpcsec_context cache. The key for this cache is the context_handle. * The content includes: * uid/gidlist - for determining access rights * mechanism type * mechanism specific information, such as a key * */ #include <linux/slab.h> #include <linux/types.h> #include <linux/module.h> #include <linux/pagemap.h> #include <linux/user_namespace.h> #include <linux/sunrpc/auth_gss.h> #include <linux/sunrpc/gss_err.h> #include <linux/sunrpc/svcauth.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/gss_krb5.h> #include <trace/events/rpcgss.h> #include "gss_rpc_upcall.h" /* * Unfortunately there isn't a maximum checksum size exported via the * GSS API. Manufacture one based on GSS mechanisms supported by this * implementation. */ #define GSS_MAX_CKSUMSIZE (GSS_KRB5_TOK_HDR_LEN + GSS_KRB5_MAX_CKSUM_LEN) /* * This value may be increased in the future to accommodate other * usage of the scratch buffer. */ #define GSS_SCRATCH_SIZE GSS_MAX_CKSUMSIZE struct gss_svc_data { /* decoded gss client cred: */ struct rpc_gss_wire_cred clcred; u32 gsd_databody_offset; struct rsc *rsci; /* for temporary results */ __be32 gsd_seq_num; u8 gsd_scratch[GSS_SCRATCH_SIZE]; }; /* The rpcsec_init cache is used for mapping RPCSEC_GSS_{,CONT_}INIT requests * into replies. * * Key is context handle (\x if empty) and gss_token. * Content is major_status minor_status (integers) context_handle, reply_token. * */ static int netobj_equal(struct xdr_netobj *a, struct xdr_netobj *b) { return a->len == b->len && 0 == memcmp(a->data, b->data, a->len); } #define RSI_HASHBITS 6 #define RSI_HASHMAX (1<<RSI_HASHBITS) struct rsi { struct cache_head h; struct xdr_netobj in_handle, in_token; struct xdr_netobj out_handle, out_token; int major_status, minor_status; struct rcu_head rcu_head; }; static struct rsi *rsi_update(struct cache_detail *cd, struct rsi *new, struct rsi *old); static struct rsi *rsi_lookup(struct cache_detail *cd, struct rsi *item); static void rsi_free(struct rsi *rsii) { kfree(rsii->in_handle.data); kfree(rsii->in_token.data); kfree(rsii->out_handle.data); kfree(rsii->out_token.data); } static void rsi_free_rcu(struct rcu_head *head) { struct rsi *rsii = container_of(head, struct rsi, rcu_head); rsi_free(rsii); kfree(rsii); } static void rsi_put(struct kref *ref) { struct rsi *rsii = container_of(ref, struct rsi, h.ref); call_rcu(&rsii->rcu_head, rsi_free_rcu); } static inline int rsi_hash(struct rsi *item) { return hash_mem(item->in_handle.data, item->in_handle.len, RSI_HASHBITS) ^ hash_mem(item->in_token.data, item->in_token.len, RSI_HASHBITS); } static int rsi_match(struct cache_head *a, struct cache_head *b) { struct rsi *item = container_of(a, struct rsi, h); struct rsi *tmp = container_of(b, struct rsi, h); return netobj_equal(&item->in_handle, &tmp->in_handle) && netobj_equal(&item->in_token, &tmp->in_token); } static int dup_to_netobj(struct xdr_netobj *dst, char *src, int len) { dst->len = len; dst->data = (len ? kmemdup(src, len, GFP_KERNEL) : NULL); if (len && !dst->data) return -ENOMEM; return 0; } static inline int dup_netobj(struct xdr_netobj *dst, struct xdr_netobj *src) { return dup_to_netobj(dst, src->data, src->len); } static void rsi_init(struct cache_head *cnew, struct cache_head *citem) { struct rsi *new = container_of(cnew, struct rsi, h); struct rsi *item = container_of(citem, struct rsi, h); new->out_handle.data = NULL; new->out_handle.len = 0; new->out_token.data = NULL; new->out_token.len = 0; new->in_handle.len = item->in_handle.len; item->in_handle.len = 0; new->in_token.len = item->in_token.len; item->in_token.len = 0; new->in_handle.data = item->in_handle.data; item->in_handle.data = NULL; new->in_token.data = item->in_token.data; item->in_token.data = NULL; } static void update_rsi(struct cache_head *cnew, struct cache_head *citem) { struct rsi *new = container_of(cnew, struct rsi, h); struct rsi *item = container_of(citem, struct rsi, h); BUG_ON(new->out_handle.data || new->out_token.data); new->out_handle.len = item->out_handle.len; item->out_handle.len = 0; new->out_token.len = item->out_token.len; item->out_token.len = 0; new->out_handle.data = item->out_handle.data; item->out_handle.data = NULL; new->out_token.data = item->out_token.data; item->out_token.data = NULL; new->major_status = item->major_status; new->minor_status = item->minor_status; } static struct cache_head *rsi_alloc(void) { struct rsi *rsii = kmalloc_obj(*rsii); if (rsii) return &rsii->h; else return NULL; } static int rsi_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_upcall_warn(cd, h); } static void rsi_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { struct rsi *rsii = container_of(h, struct rsi, h); qword_addhex(bpp, blen, rsii->in_handle.data, rsii->in_handle.len); qword_addhex(bpp, blen, rsii->in_token.data, rsii->in_token.len); (*bpp)[-1] = '\n'; WARN_ONCE(*blen < 0, "RPCSEC/GSS credential too large - please use gssproxy\n"); } static int rsi_parse(struct cache_detail *cd, char *mesg, int mlen) { /* context token expiry major minor context token */ char *buf = mesg; char *ep; int len; struct rsi rsii, *rsip = NULL; time64_t expiry; int status = -EINVAL; memset(&rsii, 0, sizeof(rsii)); /* handle */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.in_handle, buf, len)) goto out; /* token */ len = qword_get(&mesg, buf, mlen); status = -EINVAL; if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.in_token, buf, len)) goto out; rsip = rsi_lookup(cd, &rsii); if (!rsip) goto out; rsii.h.flags = 0; /* expiry */ status = get_expiry(&mesg, &expiry); if (status) goto out; status = -EINVAL; /* major/minor */ len = qword_get(&mesg, buf, mlen); if (len <= 0) goto out; rsii.major_status = simple_strtoul(buf, &ep, 10); if (*ep) goto out; len = qword_get(&mesg, buf, mlen); if (len <= 0) goto out; rsii.minor_status = simple_strtoul(buf, &ep, 10); if (*ep) goto out; /* out_handle */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.out_handle, buf, len)) goto out; /* out_token */ len = qword_get(&mesg, buf, mlen); status = -EINVAL; if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.out_token, buf, len)) goto out; rsii.h.expiry_time = expiry; rsip = rsi_update(cd, &rsii, rsip); status = 0; out: rsi_free(&rsii); if (rsip) cache_put(&rsip->h, cd); else status = -ENOMEM; return status; } static const struct cache_detail rsi_cache_template = { .owner = THIS_MODULE, .hash_size = RSI_HASHMAX, .name = "auth.rpcsec.init", .cache_put = rsi_put, .cache_upcall = rsi_upcall, .cache_request = rsi_request, .cache_parse = rsi_parse, .match = rsi_match, .init = rsi_init, .update = update_rsi, .alloc = rsi_alloc, }; static struct rsi *rsi_lookup(struct cache_detail *cd, struct rsi *item) { struct cache_head *ch; int hash = rsi_hash(item); ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash); if (ch) return container_of(ch, struct rsi, h); else return NULL; } static struct rsi *rsi_update(struct cache_detail *cd, struct rsi *new, struct rsi *old) { struct cache_head *ch; int hash = rsi_hash(new); ch = sunrpc_cache_update(cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct rsi, h); else return NULL; } /* * The rpcsec_context cache is used to store a context that is * used in data exchange. * The key is a context handle. The content is: * uid, gidlist, mechanism, service-set, mech-specific-data */ #define RSC_HASHBITS 10 #define RSC_HASHMAX (1<<RSC_HASHBITS) #define GSS_SEQ_WIN 128 struct gss_svc_seq_data { /* highest seq number seen so far: */ u32 sd_max; /* for i such that sd_max-GSS_SEQ_WIN < i <= sd_max, the i-th bit of * sd_win is nonzero iff sequence number i has been seen already: */ unsigned long sd_win[GSS_SEQ_WIN/BITS_PER_LONG]; spinlock_t sd_lock; }; struct rsc { struct cache_head h; struct xdr_netobj handle; struct svc_cred cred; struct gss_svc_seq_data seqdata; struct gss_ctx *mechctx; struct rcu_head rcu_head; }; static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old); static struct rsc *rsc_lookup(struct cache_detail *cd, struct rsc *item); static void rsc_free(struct rsc *rsci) { kfree(rsci->handle.data); if (rsci->mechctx) gss_delete_sec_context(&rsci->mechctx); free_svc_cred(&rsci->cred); } static void rsc_free_rcu(struct rcu_head *head) { struct rsc *rsci = container_of(head, struct rsc, rcu_head); kfree(rsci->handle.data); kfree(rsci); } static void rsc_put(struct kref *ref) { struct rsc *rsci = container_of(ref, struct rsc, h.ref); if (rsci->mechctx) gss_delete_sec_context(&rsci->mechctx); free_svc_cred(&rsci->cred); call_rcu(&rsci->rcu_head, rsc_free_rcu); } static inline int rsc_hash(struct rsc *rsci) { return hash_mem(rsci->handle.data, rsci->handle.len, RSC_HASHBITS); } static int rsc_match(struct cache_head *a, struct cache_head *b) { struct rsc *new = container_of(a, struct rsc, h); struct rsc *tmp = container_of(b, struct rsc, h); return netobj_equal(&new->handle, &tmp->handle); } static void rsc_init(struct cache_head *cnew, struct cache_head *ctmp) { struct rsc *new = container_of(cnew, struct rsc, h); struct rsc *tmp = container_of(ctmp, struct rsc, h); new->handle.len = tmp->handle.len; tmp->handle.len = 0; new->handle.data = tmp->handle.data; tmp->handle.data = NULL; new->mechctx = NULL; init_svc_cred(&new->cred); } static void update_rsc(struct cache_head *cnew, struct cache_head *ctmp) { struct rsc *new = container_of(cnew, struct rsc, h); struct rsc *tmp = container_of(ctmp, struct rsc, h); new->mechctx = tmp->mechctx; tmp->mechctx = NULL; memset(&new->seqdata, 0, sizeof(new->seqdata)); spin_lock_init(&new->seqdata.sd_lock); new->cred = tmp->cred; init_svc_cred(&tmp->cred); } static struct cache_head * rsc_alloc(void) { struct rsc *rsci = kmalloc_obj(*rsci); if (rsci) return &rsci->h; else return NULL; } static int rsc_upcall(struct cache_detail *cd, struct cache_head *h) { return -EINVAL; } static int rsc_parse(struct cache_detail *cd, char *mesg, int mlen) { /* contexthandle expiry [ uid gid N <n gids> mechname ...mechdata... ] */ char *buf = mesg; int id; int len, rv; struct rsc rsci, *rscp = NULL; time64_t expiry; int status = -EINVAL; struct gss_api_mech *gm = NULL; memset(&rsci, 0, sizeof(rsci)); /* context handle */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsci.handle, buf, len)) goto out; rsci.h.flags = 0; /* expiry */ status = get_expiry(&mesg, &expiry); if (status) goto out; status = -EINVAL; rscp = rsc_lookup(cd, &rsci); if (!rscp) goto out; /* uid, or NEGATIVE */ rv = get_int(&mesg, &id); if (rv == -EINVAL) goto out; if (rv == -ENOENT) set_bit(CACHE_NEGATIVE, &rsci.h.flags); else { int N, i; /* * NOTE: we skip uid_valid()/gid_valid() checks here: * instead, * -1 id's are later mapped to the * (export-specific) anonymous id by nfsd_setuser. * * (But supplementary gid's get no such special * treatment so are checked for validity here.) */ /* uid */ rsci.cred.cr_uid = make_kuid(current_user_ns(), id); /* gid */ if (get_int(&mesg, &id)) goto out; rsci.cred.cr_gid = make_kgid(current_user_ns(), id); /* number of additional gid's */ if (get_int(&mesg, &N)) goto out; if (N < 0 || N > NGROUPS_MAX) goto out; status = -ENOMEM; rsci.cred.cr_group_info = groups_alloc(N); if (rsci.cred.cr_group_info == NULL) goto out; /* gid's */ status = -EINVAL; for (i=0; i<N; i++) { kgid_t kgid; if (get_int(&mesg, &id)) goto out; kgid = make_kgid(current_user_ns(), id); if (!gid_valid(kgid)) goto out; rsci.cred.cr_group_info->gid[i] = kgid; } groups_sort(rsci.cred.cr_group_info); /* mech name */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; gm = rsci.cred.cr_gss_mech = gss_mech_get_by_name(buf); status = -EOPNOTSUPP; if (!gm) goto out; status = -EINVAL; /* mech-specific data: */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = gss_import_sec_context(buf, len, gm, &rsci.mechctx, NULL, GFP_KERNEL); if (status) goto out; /* get client name */ len = qword_get(&mesg, buf, mlen); if (len > 0) { rsci.cred.cr_principal = kstrdup(buf, GFP_KERNEL); if (!rsci.cred.cr_principal) { status = -ENOMEM; goto out; } } } rsci.h.expiry_time = expiry; rscp = rsc_update(cd, &rsci, rscp); status = 0; out: rsc_free(&rsci); if (rscp) cache_put(&rscp->h, cd); else status = -ENOMEM; return status; } static const struct cache_detail rsc_cache_template = { .owner = THIS_MODULE, .hash_size = RSC_HASHMAX, .name = "auth.rpcsec.context", .cache_put = rsc_put, .cache_upcall = rsc_upcall, .cache_parse = rsc_parse, .match = rsc_match, .init = rsc_init, .update = update_rsc, .alloc = rsc_alloc, }; static struct rsc *rsc_lookup(struct cache_detail *cd, struct rsc *item) { struct cache_head *ch; int hash = rsc_hash(item); ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash); if (ch) return container_of(ch, struct rsc, h); else return NULL; } static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old) { struct cache_head *ch; int hash = rsc_hash(new); ch = sunrpc_cache_update(cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct rsc, h); else return NULL; } static struct rsc * gss_svc_searchbyctx(struct cache_detail *cd, struct xdr_netobj *handle) { struct rsc rsci; struct rsc *found; memset(&rsci, 0, sizeof(rsci)); if (dup_to_netobj(&rsci.handle, handle->data, handle->len)) return NULL; found = rsc_lookup(cd, &rsci); rsc_free(&rsci); if (!found) return NULL; if (cache_check(cd, &found->h, NULL)) return NULL; return found; } /** * gss_check_seq_num - GSS sequence number window check * @rqstp: RPC Call to use when reporting errors * @rsci: cached GSS context state (updated on return) * @seq_num: sequence number to check * * Implements sequence number algorithm as specified in * RFC 2203, Section 5.3.3.1. "Context Management". * * Return values: * %true: @rqstp's GSS sequence number is inside the window * %false: @rqstp's GSS sequence number is outside the window */ static bool gss_check_seq_num(const struct svc_rqst *rqstp, struct rsc *rsci, u32 seq_num) { struct gss_svc_seq_data *sd = &rsci->seqdata; bool result = false; spin_lock(&sd->sd_lock); if (seq_num > sd->sd_max) { if (seq_num >= sd->sd_max + GSS_SEQ_WIN) { memset(sd->sd_win, 0, sizeof(sd->sd_win)); sd->sd_max = seq_num; } else while (sd->sd_max < seq_num) { sd->sd_max++; __clear_bit(sd->sd_max % GSS_SEQ_WIN, sd->sd_win); } __set_bit(seq_num % GSS_SEQ_WIN, sd->sd_win); goto ok; } else if (seq_num + GSS_SEQ_WIN <= sd->sd_max) { goto toolow; } if (__test_and_set_bit(seq_num % GSS_SEQ_WIN, sd->sd_win)) goto alreadyseen; ok: result = true; out: spin_unlock(&sd->sd_lock); return result; toolow: trace_rpcgss_svc_seqno_low(rqstp, seq_num, sd->sd_max - GSS_SEQ_WIN, sd->sd_max); goto out; alreadyseen: trace_rpcgss_svc_seqno_seen(rqstp, seq_num); goto out; } /* * Decode and verify a Call's verifier field. For RPC_AUTH_GSS Calls, * the body of this field contains a variable length checksum. * * GSS-specific auth_stat values are mandated by RFC 2203 Section * 5.3.3.3. */ static int svcauth_gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, __be32 *rpcstart, struct rpc_gss_wire_cred *gc) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct gss_ctx *ctx_id = rsci->mechctx; u32 flavor, maj_stat; struct xdr_buf rpchdr; struct xdr_netobj checksum; struct kvec iov; /* * Compute the checksum of the incoming Call from the * XID field to credential field: */ iov.iov_base = rpcstart; iov.iov_len = (u8 *)xdr->p - (u8 *)rpcstart; xdr_buf_from_iov(&iov, &rpchdr); /* Call's verf field: */ if (xdr_stream_decode_opaque_auth(xdr, &flavor, (void **)&checksum.data, &checksum.len) < 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } if (flavor != RPC_AUTH_GSS || checksum.len < XDR_UNIT) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } if (rqstp->rq_deferred) return SVC_OK; maj_stat = gss_verify_mic(ctx_id, &rpchdr, &checksum); if (maj_stat != GSS_S_COMPLETE) { trace_rpcgss_svc_mic(rqstp, maj_stat); rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; return SVC_DENIED; } if (gc->gc_seq > MAXSEQ) { trace_rpcgss_svc_seqno_large(rqstp, gc->gc_seq); rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; return SVC_DENIED; } if (!gss_check_seq_num(rqstp, rsci, gc->gc_seq)) return SVC_DROP; return SVC_OK; } /* * Construct and encode a Reply's verifier field. The verifier's body * field contains a variable-length checksum of the GSS sequence * number. */ static bool svcauth_gss_encode_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq) { struct gss_svc_data *gsd = rqstp->rq_auth_data; u32 maj_stat; struct xdr_buf verf_data; struct xdr_netobj checksum; struct kvec iov; gsd->gsd_seq_num = cpu_to_be32(seq); iov.iov_base = &gsd->gsd_seq_num; iov.iov_len = XDR_UNIT; xdr_buf_from_iov(&iov, &verf_data); checksum.data = gsd->gsd_scratch; maj_stat = gss_get_mic(ctx_id, &verf_data, &checksum); if (maj_stat != GSS_S_COMPLETE) goto bad_mic; return xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_GSS, checksum.data, checksum.len) > 0; bad_mic: trace_rpcgss_svc_get_mic(rqstp, maj_stat); return false; } struct gss_domain { struct auth_domain h; u32 pseudoflavor; }; static struct auth_domain * find_gss_auth_domain(struct gss_ctx *ctx, u32 svc) { char *name; name = gss_service_to_auth_domain_name(ctx->mech_type, svc); if (!name) return NULL; return auth_domain_find(name); } static struct auth_ops svcauthops_gss; u32 svcauth_gss_flavor(struct auth_domain *dom) { struct gss_domain *gd = container_of(dom, struct gss_domain, h); return gd->pseudoflavor; } EXPORT_SYMBOL_GPL(svcauth_gss_flavor); struct auth_domain * svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name) { struct gss_domain *new; struct auth_domain *test; int stat = -ENOMEM; new = kmalloc_obj(*new); if (!new) goto out; kref_init(&new->h.ref); new->h.name = kstrdup(name, GFP_KERNEL); if (!new->h.name) goto out_free_dom; new->h.flavour = &svcauthops_gss; new->pseudoflavor = pseudoflavor; test = auth_domain_lookup(name, &new->h); if (test != &new->h) { pr_warn("svc: duplicate registration of gss pseudo flavour %s.\n", name); stat = -EADDRINUSE; auth_domain_put(test); goto out_free_name; } return test; out_free_name: kfree(new->h.name); out_free_dom: kfree(new); out: return ERR_PTR(stat); } EXPORT_SYMBOL_GPL(svcauth_gss_register_pseudoflavor); /* * RFC 2203, Section 5.3.2.2 * * struct rpc_gss_integ_data { * opaque databody_integ<>; * opaque checksum<>; * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; */ static noinline_for_stack int svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) { struct gss_svc_data *gsd = rqstp->rq_auth_data; struct xdr_stream *xdr = &rqstp->rq_arg_stream; u32 len, offset, seq_num, maj_stat; struct xdr_buf *buf = xdr->buf; struct xdr_buf databody_integ; struct xdr_netobj checksum; /* Did we already verify the signature on the original pass through? */ if (rqstp->rq_deferred) return 0; if (xdr_stream_decode_u32(xdr, &len) < 0) goto unwrap_failed; if (len & 3) goto unwrap_failed; offset = xdr_stream_pos(xdr); if (xdr_buf_subsegment(buf, &databody_integ, offset, len)) goto unwrap_failed; /* * The xdr_stream now points to the @seq_num field. The next * XDR data item is the @arg field, which contains the clear * text RPC program payload. The checksum, which follows the * @arg field, is located and decoded without updating the * xdr_stream. */ offset += len; if (xdr_decode_word(buf, offset, &checksum.len)) goto unwrap_failed; if (checksum.len > sizeof(gsd->gsd_scratch)) goto unwrap_failed; checksum.data = gsd->gsd_scratch; if (read_bytes_from_xdr_buf(buf, offset + XDR_UNIT, checksum.data, checksum.len)) goto unwrap_failed; maj_stat = gss_verify_mic(ctx, &databody_integ, &checksum); if (maj_stat != GSS_S_COMPLETE) goto bad_mic; /* The received seqno is protected by the checksum. */ if (xdr_stream_decode_u32(xdr, &seq_num) < 0) goto unwrap_failed; if (seq_num != seq) goto bad_seqno; xdr_truncate_decode(xdr, XDR_UNIT + checksum.len); return 0; unwrap_failed: trace_rpcgss_svc_unwrap_failed(rqstp); return -EINVAL; bad_seqno: trace_rpcgss_svc_seqno_bad(rqstp, seq, seq_num); return -EINVAL; bad_mic: trace_rpcgss_svc_mic(rqstp, maj_stat); return -EINVAL; } /* * RFC 2203, Section 5.3.2.3 * * struct rpc_gss_priv_data { * opaque databody_priv<> * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; */ static noinline_for_stack int svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; u32 len, maj_stat, seq_num, offset; struct xdr_buf *buf = xdr->buf; unsigned int saved_len; if (xdr_stream_decode_u32(xdr, &len) < 0) goto unwrap_failed; if (rqstp->rq_deferred) { /* Already decrypted last time through! The sequence number * check at out_seq is unnecessary but harmless: */ goto out_seq; } if (len > xdr_stream_remaining(xdr)) goto unwrap_failed; offset = xdr_stream_pos(xdr); saved_len = buf->len; maj_stat = gss_unwrap(ctx, offset, offset + len, buf); if (maj_stat != GSS_S_COMPLETE) goto bad_unwrap; xdr->nwords -= XDR_QUADLEN(saved_len - buf->len); out_seq: /* gss_unwrap() decrypted the sequence number. */ if (xdr_stream_decode_u32(xdr, &seq_num) < 0) goto unwrap_failed; if (seq_num != seq) goto bad_seqno; return 0; unwrap_failed: trace_rpcgss_svc_unwrap_failed(rqstp); return -EINVAL; bad_seqno: trace_rpcgss_svc_seqno_bad(rqstp, seq, seq_num); return -EINVAL; bad_unwrap: trace_rpcgss_svc_unwrap(rqstp, maj_stat); return -EINVAL; } static enum svc_auth_status svcauth_gss_set_client(struct svc_rqst *rqstp) { struct gss_svc_data *svcdata = rqstp->rq_auth_data; struct rsc *rsci = svcdata->rsci; struct rpc_gss_wire_cred *gc = &svcdata->clcred; int stat; rqstp->rq_auth_stat = rpc_autherr_badcred; /* * A gss export can be specified either by: * export *(sec=krb5,rw) * or by * export gss/krb5(rw) * The latter is deprecated; but for backwards compatibility reasons * the nfsd code will still fall back on trying it if the former * doesn't work; so we try to make both available to nfsd, below. */ rqstp->rq_gssclient = find_gss_auth_domain(rsci->mechctx, gc->gc_svc); if (rqstp->rq_gssclient == NULL) return SVC_DENIED; stat = svcauth_unix_set_client(rqstp); if (stat == SVC_DROP || stat == SVC_CLOSE) return stat; rqstp->rq_auth_stat = rpc_auth_ok; return SVC_OK; } static bool svcauth_gss_proc_init_verf(struct cache_detail *cd, struct svc_rqst *rqstp, struct xdr_netobj *out_handle, int *major_status, u32 seq_num) { struct xdr_stream *xdr = &rqstp->rq_res_stream; struct rsc *rsci; bool rc; if (*major_status != GSS_S_COMPLETE) goto null_verifier; rsci = gss_svc_searchbyctx(cd, out_handle); if (rsci == NULL) { *major_status = GSS_S_NO_CONTEXT; goto null_verifier; } rc = svcauth_gss_encode_verf(rqstp, rsci->mechctx, seq_num); cache_put(&rsci->h, cd); return rc; null_verifier: return xdr_stream_encode_opaque_auth(xdr, RPC_AUTH_NULL, NULL, 0) > 0; } static void gss_free_in_token_pages(struct gssp_in_token *in_token) { int i; i = 0; while (in_token->pages[i]) put_page(in_token->pages[i++]); kfree(in_token->pages); in_token->pages = NULL; } static int gss_read_proxy_verf(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc, struct xdr_netobj *in_handle, struct gssp_in_token *in_token) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; unsigned int length, pgto_offs, pgfrom_offs; int pages, i, pgto, pgfrom; size_t to_offs, from_offs; u32 inlen; if (dup_netobj(in_handle, &gc->gc_ctx)) return SVC_CLOSE; /* * RFC 2203 Section 5.2.2 * * struct rpc_gss_init_arg { * opaque gss_token<>; * }; */ if (xdr_stream_decode_u32(xdr, &inlen) < 0) goto out_denied_free; if (inlen > xdr_stream_remaining(xdr)) goto out_denied_free; pages = DIV_ROUND_UP(inlen, PAGE_SIZE); in_token->pages = kzalloc_objs(struct page *, pages + 1); if (!in_token->pages) goto out_denied_free; in_token->page_base = 0; in_token->page_len = inlen; for (i = 0; i < pages; i++) { in_token->pages[i] = alloc_page(GFP_KERNEL); if (!in_token->pages[i]) { gss_free_in_token_pages(in_token); goto out_denied_free; } } length = min_t(unsigned int, inlen, (char *)xdr->end - (char *)xdr->p); if (length) memcpy(page_address(in_token->pages[0]), xdr->p, length); inlen -= length; to_offs = length; from_offs = rqstp->rq_arg.page_base; while (inlen) { pgto = to_offs >> PAGE_SHIFT; pgfrom = from_offs >> PAGE_SHIFT; pgto_offs = to_offs & ~PAGE_MASK; pgfrom_offs = from_offs & ~PAGE_MASK; length = min_t(unsigned int, inlen, min_t(unsigned int, PAGE_SIZE - pgto_offs, PAGE_SIZE - pgfrom_offs)); memcpy(page_address(in_token->pages[pgto]) + pgto_offs, page_address(rqstp->rq_arg.pages[pgfrom]) + pgfrom_offs, length); to_offs += length; from_offs += length; inlen -= length; } return 0; out_denied_free: kfree(in_handle->data); return SVC_DENIED; } /* * RFC 2203, Section 5.2.3.1. * * struct rpc_gss_init_res { * opaque handle<>; * unsigned int gss_major; * unsigned int gss_minor; * unsigned int seq_window; * opaque gss_token<>; * }; */ static bool svcxdr_encode_gss_init_res(struct xdr_stream *xdr, struct xdr_netobj *handle, struct xdr_netobj *gss_token, unsigned int major_status, unsigned int minor_status, u32 seq_num) { if (xdr_stream_encode_opaque(xdr, handle->data, handle->len) < 0) return false; if (xdr_stream_encode_u32(xdr, major_status) < 0) return false; if (xdr_stream_encode_u32(xdr, minor_status) < 0) return false; if (xdr_stream_encode_u32(xdr, seq_num) < 0) return false; if (xdr_stream_encode_opaque(xdr, gss_token->data, gss_token->len) < 0) return false; return true; } /* * Having read the cred already and found we're in the context * initiation case, read the verifier and initiate (or check the results * of) upcalls to userspace for help with context initiation. If * the upcall results are available, write the verifier and result. * Otherwise, drop the request pending an answer to the upcall. */ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct rsi *rsip, rsikey; __be32 *p; u32 len; int ret; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); memset(&rsikey, 0, sizeof(rsikey)); if (dup_netobj(&rsikey.in_handle, &gc->gc_ctx)) return SVC_CLOSE; /* * RFC 2203 Section 5.2.2 * * struct rpc_gss_init_arg { * opaque gss_token<>; * }; */ if (xdr_stream_decode_u32(xdr, &len) < 0) { kfree(rsikey.in_handle.data); return SVC_DENIED; } p = xdr_inline_decode(xdr, len); if (!p) { kfree(rsikey.in_handle.data); return SVC_DENIED; } rsikey.in_token.data = kmalloc(len, GFP_KERNEL); if (ZERO_OR_NULL_PTR(rsikey.in_token.data)) { kfree(rsikey.in_handle.data); return SVC_CLOSE; } memcpy(rsikey.in_token.data, p, len); rsikey.in_token.len = len; /* Perform upcall, or find upcall result: */ rsip = rsi_lookup(sn->rsi_cache, &rsikey); rsi_free(&rsikey); if (!rsip) return SVC_CLOSE; if (cache_check(sn->rsi_cache, &rsip->h, &rqstp->rq_chandle) < 0) /* No upcall result: */ return SVC_CLOSE; ret = SVC_CLOSE; if (!svcauth_gss_proc_init_verf(sn->rsc_cache, rqstp, &rsip->out_handle, &rsip->major_status, GSS_SEQ_WIN)) goto out; if (!svcxdr_set_accept_stat(rqstp)) goto out; if (!svcxdr_encode_gss_init_res(&rqstp->rq_res_stream, &rsip->out_handle, &rsip->out_token, rsip->major_status, rsip->minor_status, GSS_SEQ_WIN)) goto out; ret = SVC_COMPLETE; out: cache_put(&rsip->h, sn->rsi_cache); return ret; } static int gss_proxy_save_rsc(struct cache_detail *cd, struct gssp_upcall_data *ud, uint64_t *handle) { struct rsc rsci, *rscp = NULL; static atomic64_t ctxhctr; long long ctxh; struct gss_api_mech *gm = NULL; time64_t expiry; int status; memset(&rsci, 0, sizeof(rsci)); /* context handle */ status = -ENOMEM; /* the handle needs to be just a unique id, * use a static counter */ ctxh = atomic64_inc_return(&ctxhctr); /* make a copy for the caller */ *handle = ctxh; /* make a copy for the rsc cache */ if (dup_to_netobj(&rsci.handle, (char *)handle, sizeof(uint64_t))) goto out; rscp = rsc_lookup(cd, &rsci); if (!rscp) goto out; /* creds */ if (!ud->found_creds) { /* userspace seem buggy, we should always get at least a * mapping to nobody */ goto out; } else { struct timespec64 boot; /* steal creds */ rsci.cred = ud->creds; memset(&ud->creds, 0, sizeof(struct svc_cred)); status = -EOPNOTSUPP; /* get mech handle from OID */ gm = gss_mech_get_by_OID(&ud->mech_oid); if (!gm) goto out; rsci.cred.cr_gss_mech = gm; status = -EINVAL; /* mech-specific data: */ status = gss_import_sec_context(ud->out_handle.data, ud->out_handle.len, gm, &rsci.mechctx, &expiry, GFP_KERNEL); if (status) goto out; getboottime64(&boot); expiry -= boot.tv_sec; } rsci.h.expiry_time = expiry; rscp = rsc_update(cd, &rsci, rscp); status = 0; out: rsc_free(&rsci); if (rscp) cache_put(&rscp->h, cd); else status = -ENOMEM; return status; } static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc) { struct xdr_netobj cli_handle; struct gssp_upcall_data ud; uint64_t handle; int status; int ret; struct net *net = SVC_NET(rqstp); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); memset(&ud, 0, sizeof(ud)); ret = gss_read_proxy_verf(rqstp, gc, &ud.in_handle, &ud.in_token); if (ret) return ret; ret = SVC_CLOSE; /* Perform synchronous upcall to gss-proxy */ status = gssp_accept_sec_context_upcall(net, &ud); if (status) goto out; trace_rpcgss_svc_accept_upcall(rqstp, ud.major_status, ud.minor_status); switch (ud.major_status) { case GSS_S_CONTINUE_NEEDED: cli_handle = ud.out_handle; break; case GSS_S_COMPLETE: status = gss_proxy_save_rsc(sn->rsc_cache, &ud, &handle); if (status) goto out; cli_handle.data = (u8 *)&handle; cli_handle.len = sizeof(handle); break; default: goto out; } if (!svcauth_gss_proc_init_verf(sn->rsc_cache, rqstp, &cli_handle, &ud.major_status, GSS_SEQ_WIN)) goto out; if (!svcxdr_set_accept_stat(rqstp)) goto out; if (!svcxdr_encode_gss_init_res(&rqstp->rq_res_stream, &cli_handle, &ud.out_token, ud.major_status, ud.minor_status, GSS_SEQ_WIN)) goto out; ret = SVC_COMPLETE; out: gss_free_in_token_pages(&ud.in_token); gssp_free_upcall_data(&ud); return ret; } /* * Try to set the sn->use_gss_proxy variable to a new value. We only allow * it to be changed if it's currently undefined (-1). If it's any other value * then return -EBUSY unless the type wouldn't have changed anyway. */ static int set_gss_proxy(struct net *net, int type) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int ret; WARN_ON_ONCE(type != 0 && type != 1); ret = cmpxchg(&sn->use_gss_proxy, -1, type); if (ret != -1 && ret != type) return -EBUSY; return 0; } static bool use_gss_proxy(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); /* If use_gss_proxy is still undefined, then try to disable it */ if (sn->use_gss_proxy == -1) set_gss_proxy(net, 0); return sn->use_gss_proxy; } static noinline_for_stack int svcauth_gss_proc_init(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; u32 flavor, len; void *body; /* Call's verf field: */ if (xdr_stream_decode_opaque_auth(xdr, &flavor, &body, &len) < 0) return SVC_GARBAGE; if (flavor != RPC_AUTH_NULL || len != 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } if (gc->gc_proc == RPC_GSS_PROC_INIT && gc->gc_ctx.len != 0) { rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } if (!use_gss_proxy(SVC_NET(rqstp))) return svcauth_gss_legacy_init(rqstp, gc); return svcauth_gss_proxy_init(rqstp, gc); } #ifdef CONFIG_PROC_FS static ssize_t write_gssp(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct net *net = pde_data(file_inode(file)); char tbuf[20]; unsigned long i; int res; if (*ppos || count > sizeof(tbuf)-1) return -EINVAL; if (copy_from_user(tbuf, buf, count)) return -EFAULT; tbuf[count] = 0; res = kstrtoul(tbuf, 0, &i); if (res) return res; if (i != 1) return -EINVAL; res = set_gssp_clnt(net); if (res) return res; res = set_gss_proxy(net, 1); if (res) return res; return count; } static ssize_t read_gssp(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct net *net = pde_data(file_inode(file)); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); unsigned long p = *ppos; char tbuf[10]; size_t len; snprintf(tbuf, sizeof(tbuf), "%d\n", sn->use_gss_proxy); len = strlen(tbuf); if (p >= len) return 0; len -= p; if (len > count) len = count; if (copy_to_user(buf, (void *)(tbuf+p), len)) return -EFAULT; *ppos += len; return len; } static const struct proc_ops use_gss_proxy_proc_ops = { .proc_open = nonseekable_open, .proc_write = write_gssp, .proc_read = read_gssp, }; static int create_use_gss_proxy_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct proc_dir_entry **p = &sn->use_gssp_proc; sn->use_gss_proxy = -1; *p = proc_create_data("use-gss-proxy", S_IFREG | 0600, sn->proc_net_rpc, &use_gss_proxy_proc_ops, net); if (!*p) return -ENOMEM; init_gssp_clnt(sn); return 0; } static void destroy_use_gss_proxy_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); if (sn->use_gssp_proc) { remove_proc_entry("use-gss-proxy", sn->proc_net_rpc); clear_gssp_clnt(sn); } } static ssize_t read_gss_krb5_enctypes(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct rpcsec_gss_oid oid = { .len = 9, .data = "\x2a\x86\x48\x86\xf7\x12\x01\x02\x02", }; struct gss_api_mech *mech; ssize_t ret; mech = gss_mech_get_by_OID(&oid); if (!mech) return 0; if (!mech->gm_upcall_enctypes) { gss_mech_put(mech); return 0; } ret = simple_read_from_buffer(buf, count, ppos, mech->gm_upcall_enctypes, strlen(mech->gm_upcall_enctypes)); gss_mech_put(mech); return ret; } static const struct proc_ops gss_krb5_enctypes_proc_ops = { .proc_open = nonseekable_open, .proc_read = read_gss_krb5_enctypes, }; static int create_krb5_enctypes_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); sn->gss_krb5_enctypes = proc_create_data("gss_krb5_enctypes", S_IFREG | 0444, sn->proc_net_rpc, &gss_krb5_enctypes_proc_ops, net); return sn->gss_krb5_enctypes ? 0 : -ENOMEM; } static void destroy_krb5_enctypes_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); if (sn->gss_krb5_enctypes) remove_proc_entry("gss_krb5_enctypes", sn->proc_net_rpc); } #else /* CONFIG_PROC_FS */ static int create_use_gss_proxy_proc_entry(struct net *net) { return 0; } static void destroy_use_gss_proxy_proc_entry(struct net *net) {} static int create_krb5_enctypes_proc_entry(struct net *net) { return 0; } static void destroy_krb5_enctypes_proc_entry(struct net *net) {} #endif /* CONFIG_PROC_FS */ /* * The Call's credential body should contain a struct rpc_gss_cred_t. * * RFC 2203 Section 5 * * struct rpc_gss_cred_t { * union switch (unsigned int version) { * case RPCSEC_GSS_VERS_1: * struct { * rpc_gss_proc_t gss_proc; * unsigned int seq_num; * rpc_gss_service_t service; * opaque handle<>; * } rpc_gss_cred_vers_1_t; * } * }; */ static bool svcauth_gss_decode_credbody(struct xdr_stream *xdr, struct rpc_gss_wire_cred *gc, __be32 **rpcstart) { ssize_t handle_len; u32 body_len; __be32 *p; p = xdr_inline_decode(xdr, XDR_UNIT); if (!p) return false; /* * start of rpc packet is 7 u32's back from here: * xid direction rpcversion prog vers proc flavour */ *rpcstart = p - 7; body_len = be32_to_cpup(p); if (body_len > RPC_MAX_AUTH_SIZE) return false; /* struct rpc_gss_cred_t */ if (xdr_stream_decode_u32(xdr, &gc->gc_v) < 0) return false; if (xdr_stream_decode_u32(xdr, &gc->gc_proc) < 0) return false; if (xdr_stream_decode_u32(xdr, &gc->gc_seq) < 0) return false; if (xdr_stream_decode_u32(xdr, &gc->gc_svc) < 0) return false; handle_len = xdr_stream_decode_opaque_inline(xdr, (void **)&gc->gc_ctx.data, body_len); if (handle_len < 0) return false; if (body_len != XDR_UNIT * 5 + xdr_align_size(handle_len)) return false; gc->gc_ctx.len = handle_len; return true; } /** * svcauth_gss_accept - Decode and validate incoming RPC_AUTH_GSS credential * @rqstp: RPC transaction * * Return values: * %SVC_OK: Success * %SVC_COMPLETE: GSS context lifetime event * %SVC_DENIED: Credential or verifier is not valid * %SVC_GARBAGE: Failed to decode credential or verifier * %SVC_CLOSE: Temporary failure * * The rqstp->rq_auth_stat field is also set (see RFCs 2203 and 5531). */ static enum svc_auth_status svcauth_gss_accept(struct svc_rqst *rqstp) { struct gss_svc_data *svcdata = rqstp->rq_auth_data; __be32 *rpcstart; struct rpc_gss_wire_cred *gc; struct rsc *rsci = NULL; int ret; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); rqstp->rq_auth_stat = rpc_autherr_failed; if (!svcdata) svcdata = kmalloc_obj(*svcdata); if (!svcdata) goto auth_err; rqstp->rq_auth_data = svcdata; svcdata->gsd_databody_offset = 0; svcdata->rsci = NULL; gc = &svcdata->clcred; rqstp->rq_auth_stat = rpc_autherr_badcred; if (!svcauth_gss_decode_credbody(&rqstp->rq_arg_stream, gc, &rpcstart)) goto auth_err; if (gc->gc_v != RPC_GSS_VERSION) goto auth_err; switch (gc->gc_proc) { case RPC_GSS_PROC_INIT: case RPC_GSS_PROC_CONTINUE_INIT: if (rqstp->rq_proc != 0) goto auth_err; return svcauth_gss_proc_init(rqstp, gc); case RPC_GSS_PROC_DESTROY: if (rqstp->rq_proc != 0) goto auth_err; fallthrough; case RPC_GSS_PROC_DATA: rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; rsci = gss_svc_searchbyctx(sn->rsc_cache, &gc->gc_ctx); if (!rsci) goto auth_err; switch (svcauth_gss_verify_header(rqstp, rsci, rpcstart, gc)) { case SVC_OK: break; case SVC_DENIED: goto auth_err; case SVC_DROP: goto drop; } break; default: if (rqstp->rq_proc != 0) goto auth_err; rqstp->rq_auth_stat = rpc_autherr_rejectedcred; goto auth_err; } /* now act upon the command: */ switch (gc->gc_proc) { case RPC_GSS_PROC_DESTROY: if (!svcauth_gss_encode_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; if (!svcxdr_set_accept_stat(rqstp)) goto auth_err; /* Delete the entry from the cache_list and call cache_put */ sunrpc_cache_unhash(sn->rsc_cache, &rsci->h); goto complete; case RPC_GSS_PROC_DATA: rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; if (!svcauth_gss_encode_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; if (!svcxdr_set_accept_stat(rqstp)) goto auth_err; svcdata->gsd_databody_offset = xdr_stream_pos(&rqstp->rq_res_stream); rqstp->rq_cred = rsci->cred; get_group_info(rsci->cred.cr_group_info); rqstp->rq_auth_stat = rpc_autherr_badcred; switch (gc->gc_svc) { case RPC_GSS_SVC_NONE: break; case RPC_GSS_SVC_INTEGRITY: /* placeholders for body length and seq. number: */ xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2); if (svcauth_gss_unwrap_integ(rqstp, gc->gc_seq, rsci->mechctx)) goto garbage_args; svcxdr_set_auth_slack(rqstp, RPC_MAX_AUTH_SIZE); break; case RPC_GSS_SVC_PRIVACY: /* placeholders for body length and seq. number: */ xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2); if (svcauth_gss_unwrap_priv(rqstp, gc->gc_seq, rsci->mechctx)) goto garbage_args; svcxdr_set_auth_slack(rqstp, RPC_MAX_AUTH_SIZE * 2); break; default: goto auth_err; } svcdata->rsci = rsci; cache_get(&rsci->h); rqstp->rq_cred.cr_flavor = gss_svc_to_pseudoflavor( rsci->mechctx->mech_type, GSS_C_QOP_DEFAULT, gc->gc_svc); ret = SVC_OK; trace_rpcgss_svc_authenticate(rqstp, gc); goto out; } garbage_args: ret = SVC_GARBAGE; goto out; auth_err: xdr_truncate_encode(&rqstp->rq_res_stream, XDR_UNIT * 2); ret = SVC_DENIED; goto out; complete: ret = SVC_COMPLETE; goto out; drop: ret = SVC_CLOSE; out: if (rsci) cache_put(&rsci->h, sn->rsc_cache); return ret; } static u32 svcauth_gss_prepare_to_wrap(struct svc_rqst *rqstp, struct gss_svc_data *gsd) { u32 offset; /* Release can be called twice, but we only wrap once. */ offset = gsd->gsd_databody_offset; gsd->gsd_databody_offset = 0; /* AUTH_ERROR replies are not wrapped. */ if (rqstp->rq_auth_stat != rpc_auth_ok) return 0; /* Also don't wrap if the accept_stat is nonzero: */ if (*rqstp->rq_accept_statp != rpc_success) return 0; return offset; } /* * RFC 2203, Section 5.3.2.2 * * struct rpc_gss_integ_data { * opaque databody_integ<>; * opaque checksum<>; * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; * * The RPC Reply message has already been XDR-encoded. rq_res_stream * is now positioned so that the checksum can be written just past * the RPC Reply message. */ static int svcauth_gss_wrap_integ(struct svc_rqst *rqstp) { struct gss_svc_data *gsd = rqstp->rq_auth_data; struct xdr_stream *xdr = &rqstp->rq_res_stream; struct rpc_gss_wire_cred *gc = &gsd->clcred; struct xdr_buf *buf = xdr->buf; struct xdr_buf databody_integ; struct xdr_netobj checksum; u32 offset, maj_stat; offset = svcauth_gss_prepare_to_wrap(rqstp, gsd); if (!offset) goto out; if (xdr_buf_subsegment(buf, &databody_integ, offset + XDR_UNIT, buf->len - offset - XDR_UNIT)) goto wrap_failed; /* Buffer space for these has already been reserved in * svcauth_gss_accept(). */ if (xdr_encode_word(buf, offset, databody_integ.len)) goto wrap_failed; if (xdr_encode_word(buf, offset + XDR_UNIT, gc->gc_seq)) goto wrap_failed; checksum.data = gsd->gsd_scratch; maj_stat = gss_get_mic(gsd->rsci->mechctx, &databody_integ, &checksum); if (maj_stat != GSS_S_COMPLETE) goto bad_mic; if (xdr_stream_encode_opaque(xdr, checksum.data, checksum.len) < 0) goto wrap_failed; xdr_commit_encode(xdr); out: return 0; bad_mic: trace_rpcgss_svc_get_mic(rqstp, maj_stat); return -EINVAL; wrap_failed: trace_rpcgss_svc_wrap_failed(rqstp); return -EINVAL; } /* * RFC 2203, Section 5.3.2.3 * * struct rpc_gss_priv_data { * opaque databody_priv<> * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; * * gss_wrap() expands the size of the RPC message payload in the * response buffer. The main purpose of svcauth_gss_wrap_priv() * is to ensure there is adequate space in the response buffer to * avoid overflow during the wrap. */ static int svcauth_gss_wrap_priv(struct svc_rqst *rqstp) { struct gss_svc_data *gsd = rqstp->rq_auth_data; struct rpc_gss_wire_cred *gc = &gsd->clcred; struct xdr_buf *buf = &rqstp->rq_res; struct kvec *head = buf->head; struct kvec *tail = buf->tail; u32 offset, pad, maj_stat; __be32 *p; offset = svcauth_gss_prepare_to_wrap(rqstp, gsd); if (!offset) return 0; /* * Buffer space for this field has already been reserved * in svcauth_gss_accept(). Note that the GSS sequence * number is encrypted along with the RPC reply payload. */ if (xdr_encode_word(buf, offset + XDR_UNIT, gc->gc_seq)) goto wrap_failed; /* * If there is currently tail data, make sure there is * room for the head, tail, and 2 * RPC_MAX_AUTH_SIZE in * the page, and move the current tail data such that * there is RPC_MAX_AUTH_SIZE slack space available in * both the head and tail. */ if (tail->iov_base) { if (tail->iov_base >= head->iov_base + PAGE_SIZE) goto wrap_failed; if (tail->iov_base < head->iov_base) goto wrap_failed; if (tail->iov_len + head->iov_len + 2 * RPC_MAX_AUTH_SIZE > PAGE_SIZE) goto wrap_failed; memmove(tail->iov_base + RPC_MAX_AUTH_SIZE, tail->iov_base, tail->iov_len); tail->iov_base += RPC_MAX_AUTH_SIZE; } /* * If there is no current tail data, make sure there is * room for the head data, and 2 * RPC_MAX_AUTH_SIZE in the * allotted page, and set up tail information such that there * is RPC_MAX_AUTH_SIZE slack space available in both the * head and tail. */ if (!tail->iov_base) { if (head->iov_len + 2 * RPC_MAX_AUTH_SIZE > PAGE_SIZE) goto wrap_failed; tail->iov_base = head->iov_base + head->iov_len + RPC_MAX_AUTH_SIZE; tail->iov_len = 0; } maj_stat = gss_wrap(gsd->rsci->mechctx, offset + XDR_UNIT, buf, buf->pages); if (maj_stat != GSS_S_COMPLETE) goto bad_wrap; /* Wrapping can change the size of databody_priv. */ if (xdr_encode_word(buf, offset, buf->len - offset - XDR_UNIT)) goto wrap_failed; pad = xdr_pad_size(buf->len - offset - XDR_UNIT); p = (__be32 *)(tail->iov_base + tail->iov_len); memset(p, 0, pad); tail->iov_len += pad; buf->len += pad; return 0; wrap_failed: trace_rpcgss_svc_wrap_failed(rqstp); return -EINVAL; bad_wrap: trace_rpcgss_svc_wrap(rqstp, maj_stat); return -ENOMEM; } /** * svcauth_gss_release - Wrap payload and release resources * @rqstp: RPC transaction context * * Return values: * %0: the Reply is ready to be sent * %-ENOMEM: failed to allocate memory * %-EINVAL: encoding error */ static int svcauth_gss_release(struct svc_rqst *rqstp) { struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); struct gss_svc_data *gsd = rqstp->rq_auth_data; struct rpc_gss_wire_cred *gc; int stat; if (!gsd) goto out; gc = &gsd->clcred; if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; switch (gc->gc_svc) { case RPC_GSS_SVC_NONE: break; case RPC_GSS_SVC_INTEGRITY: stat = svcauth_gss_wrap_integ(rqstp); if (stat) goto out_err; break; case RPC_GSS_SVC_PRIVACY: stat = svcauth_gss_wrap_priv(rqstp); if (stat) goto out_err; break; /* * For any other gc_svc value, svcauth_gss_accept() already set * the auth_error appropriately; just fall through: */ } out: stat = 0; out_err: if (rqstp->rq_client) auth_domain_put(rqstp->rq_client); rqstp->rq_client = NULL; if (rqstp->rq_gssclient) auth_domain_put(rqstp->rq_gssclient); rqstp->rq_gssclient = NULL; if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; if (gsd && gsd->rsci) { cache_put(&gsd->rsci->h, sn->rsc_cache); gsd->rsci = NULL; } return stat; } static void svcauth_gss_domain_release_rcu(struct rcu_head *head) { struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head); struct gss_domain *gd = container_of(dom, struct gss_domain, h); kfree(dom->name); kfree(gd); } static void svcauth_gss_domain_release(struct auth_domain *dom) { call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu); } static rpc_authflavor_t svcauth_gss_pseudoflavor(struct svc_rqst *rqstp) { return svcauth_gss_flavor(rqstp->rq_gssclient); } static struct auth_ops svcauthops_gss = { .name = "rpcsec_gss", .owner = THIS_MODULE, .flavour = RPC_AUTH_GSS, .accept = svcauth_gss_accept, .release = svcauth_gss_release, .domain_release = svcauth_gss_domain_release, .set_client = svcauth_gss_set_client, .pseudoflavor = svcauth_gss_pseudoflavor, }; static int rsi_cache_create_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&rsi_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->rsi_cache = cd; return 0; } static void rsi_cache_destroy_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->rsi_cache; sn->rsi_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } static int rsc_cache_create_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&rsc_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->rsc_cache = cd; return 0; } static void rsc_cache_destroy_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->rsc_cache; sn->rsc_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } int gss_svc_init_net(struct net *net) { int rv; rv = rsc_cache_create_net(net); if (rv) return rv; rv = rsi_cache_create_net(net); if (rv) goto out1; rv = create_use_gss_proxy_proc_entry(net); if (rv) goto out2; rv = create_krb5_enctypes_proc_entry(net); if (rv) goto out3; return 0; out3: destroy_use_gss_proxy_proc_entry(net); out2: rsi_cache_destroy_net(net); out1: rsc_cache_destroy_net(net); return rv; } void gss_svc_shutdown_net(struct net *net) { destroy_krb5_enctypes_proc_entry(net); destroy_use_gss_proxy_proc_entry(net); rsi_cache_destroy_net(net); rsc_cache_destroy_net(net); } int gss_svc_init(void) { return svc_auth_register(RPC_AUTH_GSS, &svcauthops_gss); } void gss_svc_shutdown(void) { svc_auth_unregister(RPC_AUTH_GSS); } |
| 1040 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_SIMD_H #define _ASM_SIMD_H #include <asm/fpu/api.h> #include <linux/compiler_attributes.h> #include <linux/types.h> /* * may_use_simd - whether it is allowable at this time to issue SIMD * instructions or access the SIMD register file */ static __must_check inline bool may_use_simd(void) { return irq_fpu_usable(); } #endif /* _ASM_SIMD_H */ |
| 20 20 20 20 20 20 20 20 1 20 20 20 20 20 20 19 20 20 20 20 20 20 20 20 20 3 3 18 20 20 20 20 20 21 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | // SPDX-License-Identifier: GPL-2.0-or-later /* Direct I/O support. * * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/uio.h> #include <linux/sched/mm.h> #include <linux/task_io_accounting_ops.h> #include <linux/netfs.h> #include "internal.h" static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; size_t rsize; rsize = umin(subreq->len, rreq->io_streams[0].sreq_max_len); subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, rreq->io_streams[0].sreq_max_segs); if (limit < rsize) { subreq->len = limit; trace_netfs_sreq(subreq, netfs_sreq_trace_limited); } } trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); subreq->io_iter = rreq->buffer.iter; iov_iter_truncate(&subreq->io_iter, subreq->len); iov_iter_advance(&rreq->buffer.iter, subreq->len); } /* * Perform a read to a buffer from the server, slicing up the region to be read * according to the network rsize. */ static void netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) { unsigned long long start = rreq->start; ssize_t size = rreq->len; int ret; do { struct netfs_io_subrequest *subreq; ssize_t slice; subreq = netfs_alloc_subrequest(rreq); if (!subreq) { /* Stash the error in the request if there's not * already an error set. */ cmpxchg(&rreq->error, 0, -ENOMEM); break; } subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start; subreq->len = size; netfs_queue_read(rreq, subreq); netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { netfs_cancel_read(subreq, ret); break; } } netfs_prepare_dio_read_iterator(subreq); slice = subreq->len; size -= slice; start += slice; rreq->submitted += slice; if (size <= 0) { smp_wmb(); /* Write lists before ALL_QUEUED. */ set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); } rreq->netfs_ops->issue_read(subreq); if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) netfs_wait_for_paused_read(rreq); if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) break; cond_resched(); } while (size > 0); if (unlikely(size > 0)) { smp_wmb(); /* Write lists before ALL_QUEUED. */ set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); netfs_wake_collector(rreq); } } /* * Perform a read to an application buffer, bypassing the pagecache and the * local disk cache. */ static ssize_t netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync) { ssize_t ret; _enter("R=%x %llx-%llx", rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); if (rreq->len == 0) { pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); netfs_put_request(rreq, netfs_rreq_trace_put_discard); return -EIO; } // TODO: Use bounce buffer if requested inode_dio_begin(rreq->inode); netfs_dispatch_unbuffered_reads(rreq); /* The collector will get run, even if we don't manage to submit any * subreqs, so we shouldn't call inode_dio_end() here. */ if (sync) ret = netfs_wait_for_read(rreq); else ret = -EIOCBQUEUED; _leave(" = %zd", ret); return ret; } /** * netfs_unbuffered_read_iter_locked - Perform an unbuffered or direct I/O read * @iocb: The I/O control descriptor describing the read * @iter: The output buffer (also specifies read length) * * Perform an unbuffered I/O or direct I/O from the file in @iocb to the * output buffer. No use is made of the pagecache. * * The caller must hold any appropriate locks. */ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter) { struct netfs_io_request *rreq; ssize_t ret; size_t orig_count = iov_iter_count(iter); bool sync = is_sync_kiocb(iocb); _enter(""); if (!orig_count) return 0; /* Don't update atime */ ret = kiocb_write_and_wait(iocb, orig_count); if (ret < 0) return ret; file_accessed(iocb->ki_filp); rreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp, iocb->ki_pos, orig_count, iocb->ki_flags & IOCB_DIRECT ? NETFS_DIO_READ : NETFS_UNBUFFERED_READ); if (IS_ERR(rreq)) return PTR_ERR(rreq); netfs_stat(&netfs_n_rh_dio_read); trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_dio_read); /* If this is an async op, we have to keep track of the destination * buffer for ourselves as the caller's iterator will be trashed when * we return. * * In such a case, extract an iterator to represent as much of the the * output buffer as we can manage. Note that the extraction might not * be able to allocate a sufficiently large bvec array and may shorten * the request. */ if (user_backed_iter(iter)) { ret = netfs_extract_user_iter(iter, rreq->len, &rreq->buffer.iter, 0); if (ret < 0) goto error_put; rreq->direct_bv = (struct bio_vec *)rreq->buffer.iter.bvec; rreq->direct_bv_count = ret; rreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); rreq->len = iov_iter_count(&rreq->buffer.iter); } else { rreq->buffer.iter = *iter; rreq->len = orig_count; rreq->direct_bv_unpin = false; iov_iter_advance(iter, orig_count); } // TODO: Set up bounce buffer if needed if (!sync) { rreq->iocb = iocb; __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags); } ret = netfs_unbuffered_read(rreq, sync); if (ret < 0) goto out; /* May be -EIOCBQUEUED */ if (sync) { // TODO: Copy from bounce buffer iocb->ki_pos += rreq->transferred; ret = rreq->transferred; } out: netfs_put_request(rreq, netfs_rreq_trace_put_return); if (ret > 0) orig_count -= ret; return ret; error_put: netfs_put_failed_request(rreq); return ret; } EXPORT_SYMBOL(netfs_unbuffered_read_iter_locked); /** * netfs_unbuffered_read_iter - Perform an unbuffered or direct I/O read * @iocb: The I/O control descriptor describing the read * @iter: The output buffer (also specifies read length) * * Perform an unbuffered I/O or direct I/O from the file in @iocb to the * output buffer. No use is made of the pagecache. */ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; if (!iter->count) return 0; /* Don't update atime */ ret = netfs_start_io_direct(inode); if (ret == 0) { ret = netfs_unbuffered_read_iter_locked(iocb, iter); netfs_end_io_direct(inode); } return ret; } EXPORT_SYMBOL(netfs_unbuffered_read_iter); |
| 2 171 109 109 5 62 114 99 21 114 5 114 114 110 5 113 110 4 114 2 113 21 21 21 112 21 112 2 12 112 65 40 40 40 21 21 1 1 1 20 66 66 66 42 42 97 21 112 111 112 97 97 20 21 21 20 21 2 2 2 21 21 21 21 97 96 96 97 112 112 112 1 112 112 112 112 111 21 112 1 1 65 41 40 36 40 41 41 66 66 65 40 40 40 66 65 51 51 51 33 33 3 3 33 33 33 51 38 3 3 3 3 3 3 3 40 6 6 2 1 4 1 4 3 3 3 4 3 3 3 3 3 2 69 65 68 6 40 3 3 3 39 2 2 1 1 1 2 97 99 99 99 99 99 99 97 97 96 96 1 42 42 42 41 41 41 26 26 161 173 10 10 10 10 7 10 11 7 11 9 9 8 8 8 1 1 270 3 3 2 2 2 1 1 1 1 2 1 1 1 1 1 6 5 6 2 2 1 2 6 15 14 9 9 8 8 9 6 6 6 9 15 9 7 7 7 7 7 1 6 6 1 6 7 2 1 2 2 2 1 2 7 7 15 91 91 91 91 91 16 16 16 16 16 16 16 16 16 21 21 21 20 21 21 20 8 8 7 8 33 33 18 19 19 19 18 23 5 7 7 7 10 10 5 10 10 10 10 10 6 11 10 8 8 8 8 11 9 7 7 3 2 2 1 8 4 7 8 11 4 5 5 5 5 5 5 5 5 56 5 2 264 89 26 37 127 5 227 97 264 3 13 6 3 3 3 121 121 9 1 1 1 1 1 1 150 148 150 150 111 150 110 150 150 3 150 115 114 150 148 148 147 56 56 109 110 148 148 148 148 113 113 108 148 147 148 1 4 3 4 3 3 4 2 2 2 3 3 3 3 3 3 3 1 1 1 1 1 1 1 3 1 2 2 3 2 3 7 3 7 4 2 5 5 2 1 3 3 3 3 3 3 7 2 11 10 10 1 1 1 11 11 9 1 8 7 1 8 7 6 6 5 6 1 11 6 6 6 19 19 17 16 1 16 15 11 6 15 19 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/switchdev.h> #include "br_private.h" #include "br_private_tunnel.h" static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid); static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct net_bridge_vlan *vle = ptr; u16 vid = *(u16 *)arg->key; return vle->vid != vid; } static const struct rhashtable_params br_vlan_rht_params = { .head_offset = offsetof(struct net_bridge_vlan, vnode), .key_offset = offsetof(struct net_bridge_vlan, vid), .key_len = sizeof(u16), .nelem_hint = 3, .max_size = VLAN_N_VID, .obj_cmpfn = br_vlan_cmp, .automatic_shrinking = true, }; static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) { return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, const struct net_bridge_vlan *v) { if (vg->pvid == v->vid) return; smp_wmb(); br_vlan_set_pvid_state(vg, v->state); vg->pvid = v->vid; } static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid != vid) return; smp_wmb(); vg->pvid = 0; } /* Update the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED flags of @v. * If @commit is false, return just whether the BRIDGE_VLAN_INFO_PVID and * BRIDGE_VLAN_INFO_UNTAGGED bits of @flags would produce any change onto @v. */ static bool __vlan_flags_update(struct net_bridge_vlan *v, u16 flags, bool commit) { struct net_bridge_vlan_group *vg; bool change; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); /* check if anything would be changed on commit */ change = !!(flags & BRIDGE_VLAN_INFO_PVID) == !!(vg->pvid != v->vid) || ((flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED); if (!commit) goto out; if (flags & BRIDGE_VLAN_INFO_PVID) __vlan_add_pvid(vg, v); else __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; out: return change; } static bool __vlan_flags_would_change(struct net_bridge_vlan *v, u16 flags) { return __vlan_flags_update(v, flags, false); } static void __vlan_flags_commit(struct net_bridge_vlan *v, u16 flags) { __vlan_flags_update(v, flags, true); } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ err = br_switchdev_port_vlan_no_foreign_add(dev, v->vid, flags, false, extack); if (err != -EOPNOTSUPP) { v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV | BR_VLFLAG_TAGGING_BY_SWITCHDEV; return err; } err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err == -EOPNOTSUPP) return vlan_vid_add(dev, br->vlan_proto, v->vid); v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV; return err; } static void __vlan_add_list(struct net_bridge_vlan *v) { struct net_bridge_vlan_group *vg; struct list_head *headp, *hpos; struct net_bridge_vlan *vent; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); } static void __vlan_del_list(struct net_bridge_vlan *v) { list_del_rcu(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, const struct net_bridge_vlan *v) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q del. */ err = br_switchdev_port_vlan_del(dev, v->vid); if (!(v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)) vlan_vid_del(dev, br->vlan_proto, v->vid); return err == -EOPNOTSUPP ? 0 : err; } /* Returns a master vlan, if it didn't exist it gets created. In all cases * a reference is taken to the master vlan before returning. */ static struct net_bridge_vlan * br_vlan_get_master(struct net_bridge *br, u16 vid, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *masterv; vg = br_vlan_group(br); masterv = br_vlan_find(vg, vid); if (!masterv) { bool changed; /* missing global ctx, create it now */ if (br_vlan_add(br, vid, 0, &changed, extack)) return NULL; masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; refcount_set(&masterv->refcnt, 1); return masterv; } refcount_inc(&masterv->refcnt); return masterv; } static void br_master_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(!br_vlan_is_master(v)); free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_put_master(struct net_bridge_vlan *masterv) { struct net_bridge_vlan_group *vg; if (!br_vlan_is_master(masterv)) return; vg = br_vlan_group(masterv->br); if (refcount_dec_and_test(&masterv->refcnt)) { rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); br_multicast_toggle_one_vlan(masterv, false); br_multicast_ctx_deinit(&masterv->br_mcast_ctx); call_rcu(&masterv->rcu, br_master_vlan_rcu_free); } } static void nbp_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(br_vlan_is_master(v)); /* if we had per-port stats configured then free them here */ if (v->priv_flags & BR_VLFLAG_PER_PORT_STATS) free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_init_state(struct net_bridge_vlan *v) { struct net_bridge *br; if (br_vlan_is_master(v)) br = v->br; else br = v->port->br; if (br_opt_get(br, BROPT_MST_ENABLED)) { br_mst_vlan_init_state(v); return; } v->state = BR_STATE_FORWARDING; v->msti = 0; } /* This is the shared VLAN add function which works for both ports and bridge * devices. There are four possible calls to this function in terms of the * vlan entry type: * 1. vlan is being added on a port (no master flags, global entry exists) * 2. vlan is being added on a bridge (both master and brentry flags) * 3. vlan is being added on a port, but a global entry didn't exist which * is being created right now (master flag set, brentry flag unset), the * global entry is used for global per-vlan features, but not for filtering * 4. same as 3 but with both master and brentry flags set so the entry * will be used for filtering in both the port and the bridge */ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge_vlan *masterv = NULL; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_device *dev; struct net_bridge *br; int err; if (br_vlan_is_master(v)) { br = v->br; dev = br->dev; vg = br_vlan_group(br); } else { p = v->port; br = p->br; dev = p->dev; vg = nbp_vlan_group(p); } if (p) { /* Add VLAN to the device filter if it is supported. * This ensures tagged traffic enters the bridge when * promiscuous mode is disabled by br_manage_promisc(). */ err = __vlan_vid_add(dev, br, v, flags, extack); if (err) goto out; /* need to work on the master vlan too */ if (flags & BRIDGE_VLAN_INFO_MASTER) { bool changed; err = br_vlan_add(br, v->vid, flags | BRIDGE_VLAN_INFO_BRENTRY, &changed, extack); if (err) goto out_filt; if (changed) br_vlan_notify(br, NULL, v->vid, 0, RTM_NEWVLAN); } masterv = br_vlan_get_master(br, v->vid, extack); if (!masterv) { err = -ENOMEM; goto out_filt; } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!v->stats) { err = -ENOMEM; goto out_filt; } v->priv_flags |= BR_VLFLAG_PER_PORT_STATS; } else { v->stats = masterv->stats; } br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx); } else { if (br_vlan_should_use(v)) { err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err && err != -EOPNOTSUPP) goto out; } br_multicast_ctx_init(br, v, &v->br_mcast_ctx); v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED; } /* Add the dev mac and count the vlan only if it's usable */ if (br_vlan_should_use(v)) { if (!br_opt_get(br, BROPT_FDB_LOCAL_VLAN_0)) { err = br_fdb_add_local(br, p, dev->dev_addr, v->vid); if (err) { br_err(br, "failed insert local address into bridge forwarding table\n"); goto out_filt; } } vg->num_vlans++; } /* set the state before publishing */ br_vlan_init_state(v); err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); if (err) goto out_fdb_insert; __vlan_add_list(v); __vlan_flags_commit(v, flags); br_multicast_toggle_one_vlan(v, true); if (p) nbp_vlan_set_vlan_dev_state(p, v->vid); out: return err; out_fdb_insert: if (br_vlan_should_use(v)) { br_fdb_find_delete_local(br, p, dev->dev_addr, v->vid); vg->num_vlans--; } out_filt: if (p) { __vlan_vid_del(dev, br, v); if (masterv) { if (v->stats && masterv->stats != v->stats) free_percpu(v->stats); v->stats = NULL; br_vlan_put_master(masterv); v->brvlan = NULL; } } else { br_switchdev_port_vlan_del(dev, v->vid); } goto out; } static int __vlan_del(struct net_bridge_vlan *v) { struct net_bridge_vlan *masterv = v; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0; if (br_vlan_is_master(v)) { vg = br_vlan_group(v->br); } else { p = v->port; vg = nbp_vlan_group(v->port); masterv = v->brvlan; } __vlan_delete_pvid(vg, v->vid); if (p) { err = __vlan_vid_del(p->dev, p->br, v); if (err) goto out; } else { err = br_switchdev_port_vlan_del(v->br->dev, v->vid); if (err && err != -EOPNOTSUPP) goto out; err = 0; } if (br_vlan_should_use(v)) { v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans--; } if (masterv != v) { vlan_tunnel_info_del(vg, v); rhashtable_remove_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); __vlan_del_list(v); nbp_vlan_set_vlan_dev_state(p, v->vid); br_multicast_toggle_one_vlan(v, false); br_multicast_port_ctx_deinit(&v->port_mcast_ctx); call_rcu(&v->rcu, nbp_vlan_rcu_free); } br_vlan_put_master(masterv); out: return err; } static void __vlan_group_free(struct net_bridge_vlan_group *vg) { WARN_ON(!list_empty(&vg->vlan_list)); rhashtable_destroy(&vg->vlan_hash); vlan_tunnel_deinit(vg); kfree(vg); } static void __vlan_flush(const struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; u16 v_start = 0, v_end = 0; int err; __vlan_delete_pvid(vg, vg->pvid); list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { /* take care of disjoint ranges */ if (!v_start) { v_start = vlan->vid; } else if (vlan->vid - v_end != 1) { /* found range end, notify and start next one */ br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); v_start = vlan->vid; } v_end = vlan->vid; err = __vlan_del(vlan); if (err) { br_err(br, "port %u(%s) failed to delete vlan %d: %pe\n", (unsigned int) p->port_no, p->dev->name, vlan->vid, ERR_PTR(err)); } } /* notify about the last/whole vlan range */ if (v_start) br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); } struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg, struct sk_buff *skb) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* At this point, we know that the frame was filtered and contains * a valid vlan id. If the vlan id has untagged flag set, * send untagged; otherwise, send tagged. */ br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { kfree_skb(skb); return NULL; } } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->tx_bytes, skb->len); u64_stats_inc(&stats->tx_packets); u64_stats_update_end(&stats->syncp); } /* If the skb will be sent using forwarding offload, the assumption is * that the switchdev will inject the packet into hardware together * with the bridge VLAN, so that it can be forwarded according to that * VLAN. The switchdev should deal with popping the VLAN header in * hardware on each egress port as appropriate. So only strip the VLAN * header if forwarding offload is not being used. */ if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED && !br_switchdev_frame_uses_tx_fwd_offload(skb)) __vlan_hwaccel_clear_tag(skb); if (p && (p->flags & BR_VLAN_TUNNEL) && br_handle_egress_vlan_tunnel(skb, v)) { kfree_skb(skb); return NULL; } out: return skb; } /* Called under RCU */ static bool __allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; bool tagged; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. */ if (unlikely(!skb_vlan_tag_present(skb) && skb->protocol == br->vlan_proto)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } if (!br_vlan_get_tag(skb, vid)) { /* Tagged frame */ if (skb->vlan_proto != br->vlan_proto) { /* Protocol-mismatch, empty out vlan_tci for new tag */ skb_push(skb, ETH_HLEN); skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (unlikely(!skb)) return false; skb_pull(skb, ETH_HLEN); skb_reset_mac_len(skb); *vid = 0; tagged = false; } else { tagged = true; } } else { /* Untagged frame */ tagged = false; } if (!*vid) { u16 pvid = br_get_pvid(vg); /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which * vlan untagged or priority-tagged traffic belongs to. */ if (!pvid) goto drop; /* PVID is set on this port. Any untagged or priority-tagged * ingress frame is considered to belong to this vlan. */ *vid = pvid; if (likely(!tagged)) /* Untagged Frame. */ __vlan_hwaccel_put_tag(skb, br->vlan_proto, pvid); else /* Priority-tagged Frame. * At this point, we know that skb->vlan_tci VID * field was 0. * We update only VID field and preserve PCP field. */ skb->vlan_tci |= pvid; /* if snooping and stats are disabled we can avoid the lookup */ if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && !br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); if (!br_vlan_state_allowed(*state, true)) goto drop; } return true; } } v = br_vlan_find(vg, *vid); if (!v || !br_vlan_should_use(v)) goto drop; if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_state(v); if (!br_vlan_state_allowed(*state, true)) goto drop; } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->rx_bytes, skb->len); u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } *vlan = v; return true; drop: kfree_skb(skb); return false; } bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ *vlan = NULL; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) { BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; } return __allowed_ingress(br, vg, skb, vid, state, vlan); } /* Called under RCU. */ bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); if (v && br_vlan_should_use(v) && br_vlan_state_allowed(br_vlan_get_state(v), false)) return true; return false; } /* Called under RCU */ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; struct net_bridge_vlan *v; /* If filtering was disabled at input, let it pass. */ if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return true; vg = nbp_vlan_group_rcu(p); if (!vg || !vg->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { *vid = br_get_pvid(vg); if (!*vid || !br_vlan_state_allowed(br_vlan_get_pvid_state(vg), true)) return false; return true; } v = br_vlan_find(vg, *vid); if (v && br_vlan_state_allowed(br_vlan_get_state(v), true)) return true; return false; } static int br_vlan_add_existing(struct net_bridge *br, struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u16 flags, bool *changed, struct netlink_ext_ack *extack) { bool becomes_brentry = false; bool would_change = false; int err; if (!br_vlan_is_brentry(vlan)) { /* Trying to change flags of non-existent bridge vlan */ if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) return -EINVAL; becomes_brentry = true; } else { would_change = __vlan_flags_would_change(vlan, flags); } /* Master VLANs that aren't brentries weren't notified before, * time to notify them now. */ if (becomes_brentry || would_change) { err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, would_change, extack); if (err && err != -EOPNOTSUPP) return err; } if (becomes_brentry) { /* It was only kept for port vlans, now make it real */ err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid); if (err) { br_err(br, "failed to insert local address into bridge forwarding table\n"); goto err_fdb_insert; } refcount_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; *changed = true; br_multicast_toggle_one_vlan(vlan, true); } __vlan_flags_commit(vlan, flags); if (would_change) *changed = true; return 0; err_fdb_insert: br_switchdev_port_vlan_del(br->dev, vlan->vid); return err; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vg = br_vlan_group(br); vlan = br_vlan_find(vg, vid); if (vlan) return br_vlan_add_existing(br, vg, vlan, flags, changed, extack); vlan = kzalloc_obj(*vlan); if (!vlan) return -ENOMEM; vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vlan->stats) { kfree(vlan); return -ENOMEM; } vlan->vid = vid; vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; vlan->br = br; if (flags & BRIDGE_VLAN_INFO_BRENTRY) refcount_set(&vlan->refcnt, 1); ret = __vlan_add(vlan, flags, extack); if (ret) { free_percpu(vlan->stats); kfree(vlan); } else { *changed = true; } return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; ASSERT_RTNL(); vg = br_vlan_group(br); v = br_vlan_find(vg, vid); if (!v || !br_vlan_is_brentry(v)) return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); br_fdb_delete_by_port(br, NULL, vid, 0); vlan_tunnel_info_del(vg, v); return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = br_vlan_group(br); __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); synchronize_net(); __vlan_group_free(vg); } struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { if (!vg) return NULL; return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ static void recalculate_group_addr(struct net_bridge *br) { if (br_opt_get(br, BROPT_GROUP_ADDR_SET)) return; spin_lock_bh(&br->lock); if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) { /* Bridge Group Address */ br->group_addr[5] = 0x00; } else { /* vlan_enabled && ETH_P_8021AD */ /* Provider Bridge Group Address */ br->group_addr[5] = 0x08; } spin_unlock_bh(&br->lock); } /* Must be protected by RTNL. */ void br_recalculate_fwd_mask(struct net_bridge *br) { if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; else /* vlan_enabled && ETH_P_8021AD */ br->group_fwd_mask_required = BR_GROUPFWD_8021AD & ~(1u << br->group_addr[5]); } int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = val, }; int err; if (br_opt_get(br, BROPT_VLAN_ENABLED) == !!val) return 0; br_opt_toggle(br, BROPT_VLAN_ENABLED, !!val); err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) { br_opt_toggle(br, BROPT_VLAN_ENABLED, !val); return err; } br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); if (!val && br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { br_info(br, "vlan filtering disabled, automatically disabling multicast vlan snooping\n"); br_multicast_toggle_vlan_snooping(br, false, NULL); } return 0; } bool br_vlan_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return br_opt_get(br, BROPT_VLAN_ENABLED); } EXPORT_SYMBOL_GPL(br_vlan_enabled); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) { struct net_bridge *br = netdev_priv(dev); *p_proto = ntohs(br->vlan_proto); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_proto); int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_protocol = ntohs(proto), }; int err = 0; struct net_bridge_port *p; struct net_bridge_vlan *vlan; struct net_bridge_vlan_group *vg; __be16 oldproto = br->vlan_proto; if (br->vlan_proto == proto) return 0; err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } } br->vlan_proto = proto; recalculate_group_addr(br); br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, oldproto, vlan->vid); } } return 0; err_filt: attr.u.vlan_protocol = ntohs(oldproto); switchdev_port_attr_set(br->dev, &attr, NULL); list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } list_for_each_entry_continue_reverse(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } } return err; } int br_vlan_set_proto(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { if (!eth_type_vlan(htons(val))) return -EPROTONOSUPPORT; return __br_vlan_set_proto(br, htons(val), extack); } int br_vlan_set_stats(struct net_bridge *br, unsigned long val) { switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_ENABLED, !!val); break; default: return -EINVAL; } return 0; } int br_vlan_set_stats_per_port(struct net_bridge *br, unsigned long val) { struct net_bridge_port *p; /* allow to change the option if there are no port vlans configured */ list_for_each_entry(p, &br->port_list, list) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); if (vg->num_vlans) return -EBUSY; } switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_PER_PORT, !!val); break; default: return -EINVAL; } return 0; } static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 vid) { struct net_bridge_vlan *v; if (vid != vg->pvid) return false; v = br_vlan_lookup(&vg->vlan_hash, vid); if (v && br_vlan_should_use(v) && (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return true; return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) { struct net_bridge_port *p; u16 pvid = br->default_pvid; /* Disable default_pvid on all ports where it is still * configured. */ if (vlan_default_pvid(br_vlan_group(br), pvid)) { if (!br_vlan_delete(br, pvid)) br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } list_for_each_entry(p, &br->port_list, list) { if (vlan_default_pvid(nbp_vlan_group(p), pvid) && !nbp_vlan_delete(p, pvid)) br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } br->default_pvid = 0; } int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, struct netlink_ext_ack *extack) { const struct net_bridge_vlan *pvent; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; unsigned long *changed; bool vlchange; u16 old_pvid; int err = 0; if (!pvid) { br_vlan_disable_default_pvid(br); return 0; } changed = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!changed) return -ENOMEM; old_pvid = br->default_pvid; /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = br_vlan_group(br); pvent = br_vlan_find(vg, pvid); if ((!old_pvid || vlan_default_pvid(vg, old_pvid)) && (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, extack); if (err) goto out; if (br_vlan_delete(br, old_pvid)) br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN); __set_bit(0, changed); } list_for_each_entry(p, &br->port_list, list) { /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = nbp_vlan_group(p); if ((old_pvid && !vlan_default_pvid(vg, old_pvid)) || br_vlan_find(vg, pvid)) continue; err = nbp_vlan_add(p, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, extack); if (err) goto err_port; if (nbp_vlan_delete(p, old_pvid)) br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN); __set_bit(p->port_no, changed); } br->default_pvid = pvid; out: bitmap_free(changed); return err; err_port: list_for_each_entry_continue_reverse(p, &br->port_list, list) { if (!test_bit(p->port_no, changed)) continue; if (old_pvid) { nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, NULL); br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN); } nbp_vlan_delete(p, pvid); br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } if (test_bit(0, changed)) { if (old_pvid) { br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, NULL); br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN); } br_vlan_delete(br, pvid); br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } goto out; } int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { u16 pvid = val; int err = 0; if (val >= VLAN_VID_MASK) return -EINVAL; if (pvid == br->default_pvid) goto out; /* Only allow default pvid change when filtering is disabled */ if (br_opt_get(br, BROPT_VLAN_ENABLED)) { pr_info_once("Please disable vlan filtering to change default_pvid\n"); err = -EPERM; goto out; } err = __br_vlan_set_default_pvid(br, pvid, extack); out: return err; } int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc_obj(*vg); if (!vg) goto out; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); out: return ret; err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: kfree(vg); goto out; } int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = br_opt_get(p->br, BROPT_VLAN_ENABLED), }; struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc_obj(struct net_bridge_vlan_group); if (!vg) goto out; ret = switchdev_port_attr_set(p->dev, &attr, extack); if (ret && ret != -EOPNOTSUPP) goto err_vlan_enabled; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { bool changed; ret = nbp_vlan_add(p, p->br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &changed, extack); if (ret) goto err_vlan_add; br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN); } out: return ret; err_vlan_add: RCU_INIT_POINTER(p->vlgrp, NULL); synchronize_rcu(); vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: err_vlan_enabled: kfree(vg); goto out; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { bool would_change = __vlan_flags_would_change(vlan, flags); if (would_change) { /* Pass the flags to the hardware bridge */ ret = br_switchdev_port_vlan_add(port->dev, vid, flags, true, extack); if (ret && ret != -EOPNOTSUPP) return ret; } __vlan_flags_commit(vlan, flags); *changed = would_change; return 0; } vlan = kzalloc_obj(*vlan); if (!vlan) return -ENOMEM; vlan->vid = vid; vlan->port = port; ret = __vlan_add(vlan, flags, extack); if (ret) kfree(vlan); else *changed = true; return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_bridge_vlan *v; ASSERT_RTNL(); v = br_vlan_find(nbp_vlan_group(port), vid); if (!v) return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = nbp_vlan_group(port); __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); synchronize_net(); __vlan_group_free(vg); } void br_vlan_get_stats(const struct net_bridge_vlan *v, struct pcpu_sw_netstats *stats) { int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { u64 rxpackets, rxbytes, txpackets, txbytes; struct pcpu_sw_netstats *cpu_stats; unsigned int start; cpu_stats = per_cpu_ptr(v->stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); rxpackets = u64_stats_read(&cpu_stats->rx_packets); rxbytes = u64_stats_read(&cpu_stats->rx_bytes); txbytes = u64_stats_read(&cpu_stats->tx_bytes); txpackets = u64_stats_read(&cpu_stats->tx_packets); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rxpackets); u64_stats_add(&stats->rx_bytes, rxbytes); u64_stats_add(&stats->tx_bytes, txbytes); u64_stats_add(&stats->tx_packets, txpackets); } } int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); void br_vlan_fill_forward_path_pvid(struct net_bridge *br, struct net_device_path_ctx *ctx, struct net_device_path *path) { struct net_bridge_vlan_group *vg; int idx = ctx->num_vlans - 1; u16 vid; path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return; vg = br_vlan_group_rcu(br); if (idx >= 0 && ctx->vlan[idx].proto == br->vlan_proto) { vid = ctx->vlan[idx].id; } else { path->bridge.vlan_mode = DEV_PATH_BR_VLAN_TAG; vid = br_get_pvid(vg); } path->bridge.vlan_id = vid; path->bridge.vlan_proto = br->vlan_proto; } int br_vlan_fill_forward_path_mode(struct net_bridge *br, struct net_bridge_port *dst, struct net_device_path *path) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return 0; vg = nbp_vlan_group_rcu(dst); v = br_vlan_find(vg, path->bridge.vlan_id); if (!v || !br_vlan_should_use(v)) return -EINVAL; if (!(v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return 0; if (path->bridge.vlan_mode == DEV_PATH_BR_VLAN_TAG) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; else if (v->priv_flags & BR_VLFLAG_TAGGING_BY_SWITCHDEV) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG_HW; else path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG; return 0; } int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info_rcu); static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) { return is_vlan_dev(dev) && !!(vlan_dev_priv(dev)->flags & VLAN_FLAG_BRIDGE_BINDING); } static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev, __always_unused struct netdev_nested_priv *priv) { return br_vlan_is_bind_vlan_dev(dev); } static bool br_vlan_has_upper_bind_vlan_dev(struct net_device *dev) { int found; rcu_read_lock(); found = netdev_walk_all_upper_dev_rcu(dev, br_vlan_is_bind_vlan_dev_fn, NULL); rcu_read_unlock(); return !!found; } struct br_vlan_bind_walk_data { u16 vid; struct net_device *result; }; static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev, struct netdev_nested_priv *priv) { struct br_vlan_bind_walk_data *data = priv->data; int found = 0; if (br_vlan_is_bind_vlan_dev(dev) && vlan_dev_priv(dev)->vlan_id == data->vid) { data->result = dev; found = 1; } return found; } static struct net_device * br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid) { struct br_vlan_bind_walk_data data = { .vid = vid, }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn, &priv); rcu_read_unlock(); return data.result; } static bool br_vlan_is_dev_up(const struct net_device *dev) { return !!(dev->flags & IFF_UP) && netif_oper_up(dev); } static void br_vlan_set_vlan_dev_state(const struct net_bridge *br, struct net_device *vlan_dev) { u16 vid = vlan_dev_priv(vlan_dev)->vlan_id; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; bool has_carrier = false; if (!netif_carrier_ok(br->dev)) { netif_carrier_off(vlan_dev); return; } list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); if (br_vlan_find(vg, vid) && br_vlan_is_dev_up(p->dev)) { has_carrier = true; break; } } if (has_carrier) netif_carrier_on(vlan_dev); else netif_carrier_off(vlan_dev); } static void br_vlan_set_all_vlan_dev_state(struct net_bridge_port *p) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); struct net_bridge_vlan *vlan; struct net_device *vlan_dev; list_for_each_entry(vlan, &vg->vlan_list, vlist) { vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vlan->vid); if (vlan_dev) { if (br_vlan_is_dev_up(p->dev)) { if (netif_carrier_ok(p->br->dev)) netif_carrier_on(vlan_dev); } else { br_vlan_set_vlan_dev_state(p->br, vlan_dev); } } } } static void br_vlan_toggle_bridge_binding(struct net_device *br_dev, bool enable) { struct net_bridge *br = netdev_priv(br_dev); if (enable) br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true); else br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, br_vlan_has_upper_bind_vlan_dev(br_dev)); } static void br_vlan_upper_change(struct net_device *dev, struct net_device *upper_dev, bool linking) { struct net_bridge *br = netdev_priv(dev); if (!br_vlan_is_bind_vlan_dev(upper_dev)) return; br_vlan_toggle_bridge_binding(dev, linking); if (linking) br_vlan_set_vlan_dev_state(br, upper_dev); } struct br_vlan_link_state_walk_data { struct net_bridge *br; }; static int br_vlan_link_state_change_fn(struct net_device *vlan_dev, struct netdev_nested_priv *priv) { struct br_vlan_link_state_walk_data *data = priv->data; if (br_vlan_is_bind_vlan_dev(vlan_dev)) br_vlan_set_vlan_dev_state(data->br, vlan_dev); return 0; } static void br_vlan_link_state_change(struct net_device *dev, struct net_bridge *br) { struct br_vlan_link_state_walk_data data = { .br = br }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn, &priv); rcu_read_unlock(); } /* Must be protected by RTNL. */ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) { struct net_device *vlan_dev; if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vid); if (vlan_dev) br_vlan_set_vlan_dev_state(p->br, vlan_dev); } /* Must be protected by RTNL. */ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; struct net_bridge *br = netdev_priv(dev); int vlcmd = 0, ret = 0; bool changed = false; switch (event) { case NETDEV_REGISTER: ret = br_vlan_add(br, br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); vlcmd = RTM_NEWVLAN; break; case NETDEV_UNREGISTER: changed = !br_vlan_delete(br, br->default_pvid); vlcmd = RTM_DELVLAN; break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); break; case NETDEV_CHANGE: case NETDEV_UP: if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) break; br_vlan_link_state_change(dev, br); break; } if (changed) br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd); return ret; } void br_vlan_vlan_upper_event(struct net_device *br_dev, struct net_device *vlan_dev, unsigned long event) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlan_dev); struct net_bridge *br = netdev_priv(br_dev); bool bridge_binding; switch (event) { case NETDEV_CHANGE: case NETDEV_UP: break; default: return; } bridge_binding = vlan->flags & VLAN_FLAG_BRIDGE_BINDING; br_vlan_toggle_bridge_binding(br_dev, bridge_binding); if (bridge_binding) br_vlan_set_vlan_dev_state(br, vlan_dev); else if (!bridge_binding && netif_carrier_ok(br_dev)) netif_carrier_on(vlan_dev); } /* Must be protected by RTNL. */ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) { if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; switch (event) { case NETDEV_CHANGE: case NETDEV_DOWN: case NETDEV_UP: br_vlan_set_all_vlan_dev_state(p); break; } } static bool br_vlan_stats_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) { struct pcpu_sw_netstats stats; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS); if (!nest) return false; br_vlan_get_stats(v, &stats); if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_BYTES, u64_stats_read(&stats.rx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_PACKETS, u64_stats_read(&stats.rx_packets), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_BYTES, u64_stats_read(&stats.tx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_PACKETS, u64_stats_read(&stats.tx_packets), BRIDGE_VLANDB_STATS_PAD)) goto out_err; nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, const struct net_bridge_port *p, u16 flags, bool dump_stats) { struct bridge_vlan_info info; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY); if (!nest) return false; memset(&info, 0, sizeof(info)); info.vid = vid; if (flags & BRIDGE_VLAN_INFO_UNTAGGED) info.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (flags & BRIDGE_VLAN_INFO_PVID) info.flags |= BRIDGE_VLAN_INFO_PVID; if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info)) goto out_err; if (vid_range && vid < vid_range && !(flags & BRIDGE_VLAN_INFO_PVID) && nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range)) goto out_err; if (v_opts) { if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) goto out_err; } nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } static size_t rtnl_vlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */ + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */ + nla_total_size(sizeof(struct bridge_vlan_info)) /* BRIDGE_VLANDB_ENTRY_INFO */ + br_vlan_opts_nl_size(); /* bridge vlan options */ } void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v = NULL; struct br_vlan_msg *bvm; struct nlmsghdr *nlh; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 flags = 0; int ifindex; /* right now notifications are done only with rtnl held */ ASSERT_RTNL(); if (p) { ifindex = p->dev->ifindex; vg = nbp_vlan_group(p); net = dev_net(p->dev); } else { ifindex = br->dev->ifindex; vg = br_vlan_group(br); net = dev_net(br->dev); } skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL); if (!skb) goto out_err; err = -EMSGSIZE; nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0); if (!nlh) goto out_err; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = AF_BRIDGE; bvm->ifindex = ifindex; switch (cmd) { case RTM_NEWVLAN: /* need to find the vlan due to flags/options */ v = br_vlan_find(vg, vid); if (!v || !br_vlan_should_use(v)) goto out_kfree; flags = v->flags; if (br_get_pvid(vg) == v->vid) flags |= BRIDGE_VLAN_INFO_PVID; break; case RTM_DELVLAN: break; default: goto out_kfree; } if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); return; out_err: rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err); out_kfree: kfree_skb(skb); } /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) { return v_curr->vid - range_end->vid == 1 && range_end->flags == v_curr->flags && br_vlan_opts_eq_range(v_curr, range_end); } static int br_vlan_dump_dev(const struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb, u32 dump_flags) { struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; bool dump_global = !!(dump_flags & BRIDGE_VLANDB_DUMPF_GLOBAL); bool dump_stats = !!(dump_flags & BRIDGE_VLANDB_DUMPF_STATS); struct net_bridge_vlan_group *vg; int idx = 0, s_idx = cb->args[1]; struct nlmsghdr *nlh = NULL; struct net_bridge_port *p; struct br_vlan_msg *bvm; struct net_bridge *br; int err = 0; u16 pvid; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) return -EINVAL; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); p = NULL; } else { /* global options are dumped only for bridge devices */ if (dump_global) return 0; p = br_port_get_rcu(dev); if (WARN_ON(!p)) return -EINVAL; vg = nbp_vlan_group_rcu(p); br = p->br; } if (!vg) return 0; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = PF_BRIDGE; bvm->ifindex = dev->ifindex; pvid = br_get_pvid(vg); /* idx must stay at range's beginning until it is filled in */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!dump_global && !br_vlan_should_use(v)) continue; if (idx < s_idx) { idx++; continue; } if (!range_start) { range_start = v; range_end = v; continue; } if (dump_global) { if (br_vlan_global_opts_can_enter_range(v, range_end)) goto update_end; if (!br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } else if (dump_stats || v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) { u16 vlan_flags = br_vlan_flags(range_start, pvid); if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } update_end: range_end = v; } /* err will be 0 and range_start will be set in 3 cases here: * - first vlan (range_start == range_end) * - last vlan (range_start == range_end, not in range) * - last vlan range (range_start != range_end, in range) */ if (!err && range_start) { if (dump_global && !br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) err = -EMSGSIZE; else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } cb->args[1] = err ? idx : 0; nlmsg_end(skb, nlh); return err; } static const struct nla_policy br_vlan_db_dump_pol[BRIDGE_VLANDB_DUMP_MAX + 1] = { [BRIDGE_VLANDB_DUMP_FLAGS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *dtb[BRIDGE_VLANDB_DUMP_MAX + 1]; int idx = 0, err = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; u32 dump_flags = 0; err = nlmsg_parse(cb->nlh, sizeof(*bvm), dtb, BRIDGE_VLANDB_DUMP_MAX, br_vlan_db_dump_pol, cb->extack); if (err < 0) return err; bvm = nlmsg_data(cb->nlh); if (dtb[BRIDGE_VLANDB_DUMP_FLAGS]) dump_flags = nla_get_u32(dtb[BRIDGE_VLANDB_DUMP_FLAGS]); rcu_read_lock(); if (bvm->ifindex) { dev = dev_get_by_index_rcu(net, bvm->ifindex); if (!dev) { err = -ENODEV; goto out_err; } err = br_vlan_dump_dev(dev, skb, cb, dump_flags); /* if the dump completed without an error we return 0 here */ if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { if (idx < s_idx) goto skip; err = br_vlan_dump_dev(dev, skb, cb, dump_flags); if (err == -EMSGSIZE) break; skip: idx++; } } cb->args[0] = idx; rcu_read_unlock(); return skb->len; out_err: rcu_read_unlock(); return err; } static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { [BRIDGE_VLANDB_ENTRY_INFO] = NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)), [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), [BRIDGE_VLANDB_ENTRY_NEIGH_FORWARD_GRAT] = NLA_POLICY_MAX(NLA_U8, 1), }; static int br_vlan_rtm_process_one(struct net_device *dev, const struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL; struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1]; bool changed = false, skip_processing = false; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0, cmdmap = 0; struct net_bridge *br; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { p = br_port_get_rtnl(dev); if (WARN_ON(!p)) return -ENODEV; br = p->br; vg = nbp_vlan_group(p); } if (WARN_ON(!vg)) return -ENODEV; err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr, br_vlan_db_policy, extack); if (err) return err; if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) { NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info"); return -EINVAL; } memset(&vrange_end, 0, sizeof(vrange_end)); vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]); if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | BRIDGE_VLAN_INFO_RANGE_END)) { NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls"); return -EINVAL; } if (!br_vlan_valid_id(vinfo->vid, extack)) return -EINVAL; if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) { vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]); /* validate user-provided flags without RANGE_BEGIN */ vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags; vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; /* vinfo_last is the range start, vinfo the range end */ vinfo_last = vinfo; vinfo = &vrange_end; if (!br_vlan_valid_id(vinfo->vid, extack) || !br_vlan_valid_range(vinfo, vinfo_last, extack)) return -EINVAL; } switch (cmd) { case RTM_NEWVLAN: cmdmap = RTM_SETLINK; skip_processing = !!(vinfo->flags & BRIDGE_VLAN_INFO_ONLY_OPTS); break; case RTM_DELVLAN: cmdmap = RTM_DELLINK; break; } if (!skip_processing) { struct bridge_vlan_info *tmp_last = vinfo_last; /* br_process_vlan_info may overwrite vinfo_last */ err = br_process_vlan_info(br, p, cmdmap, vinfo, &tmp_last, &changed, extack); /* notify first if anything changed */ if (changed) br_ifinfo_notify(cmdmap, br, p); if (err) return err; } /* deal with options */ if (cmd == RTM_NEWVLAN) { struct net_bridge_vlan *range_start, *range_end; if (vinfo_last) { range_start = br_vlan_find(vg, vinfo_last->vid); range_end = br_vlan_find(vg, vinfo->vid); } else { range_start = br_vlan_find(vg, vinfo->vid); range_end = range_start; } err = br_vlan_process_options(br, p, range_start, range_end, tb, extack); } return err; } static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; struct nlattr *attr; int err, vlans = 0; int rem; /* this should validate the header and check for remaining bytes */ err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL, extack); if (err < 0) return err; bvm = nlmsg_data(nlh); dev = __dev_get_by_index(net, bvm->ifindex); if (!dev) return -ENODEV; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port"); return -EINVAL; } nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { switch (nla_type(attr)) { case BRIDGE_VLANDB_ENTRY: err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, extack); break; case BRIDGE_VLANDB_GLOBAL_OPTIONS: err = br_vlan_rtm_process_global_options(dev, attr, nlh->nlmsg_type, extack); break; default: continue; } vlans++; if (err) break; } if (!vlans) { NL_SET_ERR_MSG_MOD(extack, "No vlans found to process"); err = -EINVAL; } return err; } static const struct rtnl_msg_handler br_vlan_rtnl_msg_handlers[] = { {THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN, br_vlan_rtm_process, NULL, 0}, {THIS_MODULE, PF_BRIDGE, RTM_DELVLAN, br_vlan_rtm_process, NULL, 0}, {THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL, br_vlan_rtm_dump, 0}, }; int br_vlan_rtnl_init(void) { return rtnl_register_many(br_vlan_rtnl_msg_handlers); } void br_vlan_rtnl_uninit(void) { rtnl_unregister_many(br_vlan_rtnl_msg_handlers); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PROJID_H #define _LINUX_PROJID_H /* * A set of types for the internal kernel types representing project ids. * * The types defined in this header allow distinguishing which project ids in * the kernel are values used by userspace and which project id values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/types.h> struct user_namespace; extern struct user_namespace init_user_ns; typedef __kernel_uid32_t projid_t; typedef struct { projid_t val; } kprojid_t; static inline projid_t __kprojid_val(kprojid_t projid) { return projid.val; } #define KPROJIDT_INIT(value) (kprojid_t){ value } #define INVALID_PROJID KPROJIDT_INIT(-1) #define OVERFLOW_PROJID 65534 static inline bool projid_eq(kprojid_t left, kprojid_t right) { return __kprojid_val(left) == __kprojid_val(right); } static inline bool projid_lt(kprojid_t left, kprojid_t right) { return __kprojid_val(left) < __kprojid_val(right); } static inline bool projid_valid(kprojid_t projid) { return !projid_eq(projid, INVALID_PROJID); } #ifdef CONFIG_USER_NS extern kprojid_t make_kprojid(struct user_namespace *from, projid_t projid); extern projid_t from_kprojid(struct user_namespace *to, kprojid_t projid); extern projid_t from_kprojid_munged(struct user_namespace *to, kprojid_t projid); static inline bool kprojid_has_mapping(struct user_namespace *ns, kprojid_t projid) { return from_kprojid(ns, projid) != (projid_t)-1; } #else static inline kprojid_t make_kprojid(struct user_namespace *from, projid_t projid) { return KPROJIDT_INIT(projid); } static inline projid_t from_kprojid(struct user_namespace *to, kprojid_t kprojid) { return __kprojid_val(kprojid); } static inline projid_t from_kprojid_munged(struct user_namespace *to, kprojid_t kprojid) { projid_t projid = from_kprojid(to, kprojid); if (projid == (projid_t)-1) projid = OVERFLOW_PROJID; return projid; } static inline bool kprojid_has_mapping(struct user_namespace *ns, kprojid_t projid) { return true; } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_PROJID_H */ |
| 8 8 8 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/seq_file.h> #include <net/ip.h> #include <net/mptcp.h> #include <net/snmp.h> #include <net/net_namespace.h> #include "mib.h" static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPCapableSYNRX", MPTCP_MIB_MPCAPABLEPASSIVE), SNMP_MIB_ITEM("MPCapableSYNTX", MPTCP_MIB_MPCAPABLEACTIVE), SNMP_MIB_ITEM("MPCapableSYNACKRX", MPTCP_MIB_MPCAPABLEACTIVEACK), SNMP_MIB_ITEM("MPCapableACKRX", MPTCP_MIB_MPCAPABLEPASSIVEACK), SNMP_MIB_ITEM("MPCapableFallbackACK", MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK), SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK), SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP), SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED), SNMP_MIB_ITEM("MPCapableEndpAttempt", MPTCP_MIB_MPCAPABLEENDPATTEMPT), SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT), SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), SNMP_MIB_ITEM("MPJoinRejected", MPTCP_MIB_JOINREJECTED), SNMP_MIB_ITEM("MPJoinSynTx", MPTCP_MIB_JOINSYNTX), SNMP_MIB_ITEM("MPJoinSynTxCreatSkErr", MPTCP_MIB_JOINSYNTXCREATSKERR), SNMP_MIB_ITEM("MPJoinSynTxBindErr", MPTCP_MIB_JOINSYNTXBINDERR), SNMP_MIB_ITEM("MPJoinSynTxConnectErr", MPTCP_MIB_JOINSYNTXCONNECTERR), SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), SNMP_MIB_ITEM("DSSCorruptionFallback", MPTCP_MIB_DSSCORRUPTIONFALLBACK), SNMP_MIB_ITEM("DSSCorruptionReset", MPTCP_MIB_DSSCORRUPTIONRESET), SNMP_MIB_ITEM("InfiniteMapTx", MPTCP_MIB_INFINITEMAPTX), SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), SNMP_MIB_ITEM("DSSNoMatchTCP", MPTCP_MIB_DSSTCPMISMATCH), SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR), SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL), SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE), SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE), SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW), SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA), SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), SNMP_MIB_ITEM("AddAddrTx", MPTCP_MIB_ADDADDRTX), SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP), SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), SNMP_MIB_ITEM("EchoAddTx", MPTCP_MIB_ECHOADDTX), SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP), SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD), SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP), SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX), SNMP_MIB_ITEM("MPJoinPortSynAckRx", MPTCP_MIB_JOINPORTSYNACKRX), SNMP_MIB_ITEM("MPJoinPortAckRx", MPTCP_MIB_JOINPORTACKRX), SNMP_MIB_ITEM("MismatchPortSynRx", MPTCP_MIB_MISMATCHPORTSYNRX), SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX), SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP), SNMP_MIB_ITEM("RmAddrTx", MPTCP_MIB_RMADDRTX), SNMP_MIB_ITEM("RmAddrTxDrop", MPTCP_MIB_RMADDRTXDROP), SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), SNMP_MIB_ITEM("MPFailTx", MPTCP_MIB_MPFAILTX), SNMP_MIB_ITEM("MPFailRx", MPTCP_MIB_MPFAILRX), SNMP_MIB_ITEM("MPFastcloseTx", MPTCP_MIB_MPFASTCLOSETX), SNMP_MIB_ITEM("MPFastcloseRx", MPTCP_MIB_MPFASTCLOSERX), SNMP_MIB_ITEM("MPRstTx", MPTCP_MIB_MPRSTTX), SNMP_MIB_ITEM("MPRstRx", MPTCP_MIB_MPRSTRX), SNMP_MIB_ITEM("SubflowStale", MPTCP_MIB_SUBFLOWSTALE), SNMP_MIB_ITEM("SubflowRecover", MPTCP_MIB_SUBFLOWRECOVER), SNMP_MIB_ITEM("SndWndShared", MPTCP_MIB_SNDWNDSHARED), SNMP_MIB_ITEM("RcvWndShared", MPTCP_MIB_RCVWNDSHARED), SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE), SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT), SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB), SNMP_MIB_ITEM("Blackhole", MPTCP_MIB_BLACKHOLE), SNMP_MIB_ITEM("MPCapableDataFallback", MPTCP_MIB_MPCAPABLEDATAFALLBACK), SNMP_MIB_ITEM("MD5SigFallback", MPTCP_MIB_MD5SIGFALLBACK), SNMP_MIB_ITEM("DssFallback", MPTCP_MIB_DSSFALLBACK), SNMP_MIB_ITEM("SimultConnectFallback", MPTCP_MIB_SIMULTCONNFALLBACK), SNMP_MIB_ITEM("FallbackFailed", MPTCP_MIB_FALLBACKFAILED), SNMP_MIB_ITEM("WinProbe", MPTCP_MIB_WINPROBE), }; /* mptcp_mib_alloc - allocate percpu mib counters * * These are allocated when the first mptcp socket is created so * we do not waste percpu memory if mptcp isn't in use. */ bool mptcp_mib_alloc(struct net *net) { struct mptcp_mib __percpu *mib = alloc_percpu(struct mptcp_mib); if (!mib) return false; if (cmpxchg(&net->mib.mptcp_statistics, NULL, mib)) free_percpu(mib); return true; } void mptcp_seq_show(struct seq_file *seq) { unsigned long sum[ARRAY_SIZE(mptcp_snmp_list)]; const int cnt = ARRAY_SIZE(mptcp_snmp_list); struct net *net = seq->private; int i; seq_puts(seq, "MPTcpExt:"); for (i = 0; i < cnt; i++) seq_printf(seq, " %s", mptcp_snmp_list[i].name); seq_puts(seq, "\nMPTcpExt:"); memset(sum, 0, sizeof(sum)); if (net->mib.mptcp_statistics) snmp_get_cpu_field_batch_cnt(sum, mptcp_snmp_list, cnt, net->mib.mptcp_statistics); for (i = 0; i < cnt; i++) seq_printf(seq, " %lu", sum[i]); seq_putc(seq, '\n'); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * mount.c - operations for initializing and mounting configfs. * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/configfs.h> #include "configfs_internal.h" /* Random magic number */ #define CONFIGFS_MAGIC 0x62656570 static struct vfsmount *configfs_mount = NULL; struct kmem_cache *configfs_dir_cachep; static int configfs_mnt_count = 0; static void configfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); free_inode_nonrcu(inode); } static const struct super_operations configfs_ops = { .statfs = simple_statfs, .drop_inode = inode_just_drop, .free_inode = configfs_free_inode, }; static struct config_group configfs_root_group = { .cg_item = { .ci_namebuf = "root", .ci_name = configfs_root_group.cg_item.ci_namebuf, }, }; int configfs_is_root(struct config_item *item) { return item == &configfs_root_group.cg_item; } static struct configfs_dirent configfs_root = { .s_sibling = LIST_HEAD_INIT(configfs_root.s_sibling), .s_children = LIST_HEAD_INIT(configfs_root.s_children), .s_element = &configfs_root_group.cg_item, .s_type = CONFIGFS_ROOT, .s_iattr = NULL, }; static int configfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dentry *root; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = CONFIGFS_MAGIC; sb->s_op = &configfs_ops; sb->s_time_gran = 1; inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, &configfs_root, sb); if (inode) { inode->i_op = &configfs_root_inode_operations; inode->i_fop = &configfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); } else { pr_debug("could not get root inode\n"); return -ENOMEM; } root = d_make_root(inode); if (!root) { pr_debug("%s: could not get root dentry!\n",__func__); return -ENOMEM; } config_group_init(&configfs_root_group); configfs_root_group.cg_item.ci_dentry = root; root->d_fsdata = &configfs_root; sb->s_root = root; set_default_d_op(sb, &configfs_dentry_ops); /* the rest get that */ sb->s_d_flags |= DCACHE_DONTCACHE; return 0; } static int configfs_get_tree(struct fs_context *fc) { return get_tree_single(fc, configfs_fill_super); } static const struct fs_context_operations configfs_context_ops = { .get_tree = configfs_get_tree, }; static int configfs_init_fs_context(struct fs_context *fc) { fc->ops = &configfs_context_ops; return 0; } static struct file_system_type configfs_fs_type = { .owner = THIS_MODULE, .name = "configfs", .init_fs_context = configfs_init_fs_context, .kill_sb = kill_anon_super, }; MODULE_ALIAS_FS("configfs"); struct dentry *configfs_pin_fs(void) { int err = simple_pin_fs(&configfs_fs_type, &configfs_mount, &configfs_mnt_count); return err ? ERR_PTR(err) : configfs_mount->mnt_root; } void configfs_release_fs(void) { simple_release_fs(&configfs_mount, &configfs_mnt_count); } static int __init configfs_init(void) { int err = -ENOMEM; configfs_dir_cachep = kmem_cache_create("configfs_dir_cache", sizeof(struct configfs_dirent), 0, 0, NULL); if (!configfs_dir_cachep) goto out; err = sysfs_create_mount_point(kernel_kobj, "config"); if (err) goto out2; err = register_filesystem(&configfs_fs_type); if (err) goto out3; return 0; out3: pr_err("Unable to register filesystem!\n"); sysfs_remove_mount_point(kernel_kobj, "config"); out2: kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; out: return err; } static void __exit configfs_exit(void) { unregister_filesystem(&configfs_fs_type); sysfs_remove_mount_point(kernel_kobj, "config"); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; } MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); MODULE_VERSION("0.0.2"); MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration."); core_initcall(configfs_init); module_exit(configfs_exit); |
| 366 367 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | // SPDX-License-Identifier: GPL-2.0+ /* * IMA support for appraising module-style appended signatures. * * Copyright (C) 2019 IBM Corporation * * Author: * Thiago Jung Bauermann <bauerman@linux.ibm.com> */ #include <linux/types.h> #include <linux/module_signature.h> #include <keys/asymmetric-type.h> #include <crypto/pkcs7.h> #include "ima.h" struct modsig { struct pkcs7_message *pkcs7_msg; enum hash_algo hash_algo; /* This digest will go in the 'd-modsig' field of the IMA template. */ const u8 *digest; u32 digest_size; /* * This is what will go to the measurement list if the template requires * storing the signature. */ int raw_pkcs7_len; u8 raw_pkcs7[] __counted_by(raw_pkcs7_len); }; /* * ima_read_modsig - Read modsig from buf. * * Return: 0 on success, error code otherwise. */ int ima_read_modsig(enum ima_hooks func, const void *buf, loff_t buf_len, struct modsig **modsig) { const size_t marker_len = strlen(MODULE_SIGNATURE_MARKER); const struct module_signature *sig; struct modsig *hdr; size_t sig_len; const void *p; int rc; if (buf_len <= marker_len + sizeof(*sig)) return -ENOENT; p = buf + buf_len - marker_len; if (memcmp(p, MODULE_SIGNATURE_MARKER, marker_len)) return -ENOENT; buf_len -= marker_len; sig = (const struct module_signature *)(p - sizeof(*sig)); rc = mod_check_sig(sig, buf_len, func_tokens[func]); if (rc) return rc; sig_len = be32_to_cpu(sig->sig_len); buf_len -= sig_len + sizeof(*sig); /* Allocate sig_len additional bytes to hold the raw PKCS#7 data. */ hdr = kzalloc_flex(*hdr, raw_pkcs7, sig_len); if (!hdr) return -ENOMEM; hdr->raw_pkcs7_len = sig_len; hdr->pkcs7_msg = pkcs7_parse_message(buf + buf_len, sig_len); if (IS_ERR(hdr->pkcs7_msg)) { rc = PTR_ERR(hdr->pkcs7_msg); kfree(hdr); return rc; } memcpy(hdr->raw_pkcs7, buf + buf_len, sig_len); /* We don't know the hash algorithm yet. */ hdr->hash_algo = HASH_ALGO__LAST; *modsig = hdr; return 0; } /** * ima_collect_modsig - Calculate the file hash without the appended signature. * @modsig: parsed module signature * @buf: data to verify the signature on * @size: data size * * Since the modsig is part of the file contents, the hash used in its signature * isn't the same one ordinarily calculated by IMA. Therefore PKCS7 code * calculates a separate one for signature verification. */ void ima_collect_modsig(struct modsig *modsig, const void *buf, loff_t size) { int rc; /* * Provide the file contents (minus the appended sig) so that the PKCS7 * code can calculate the file hash. */ size -= modsig->raw_pkcs7_len + strlen(MODULE_SIGNATURE_MARKER) + sizeof(struct module_signature); rc = pkcs7_supply_detached_data(modsig->pkcs7_msg, buf, size); if (rc) return; /* Ask the PKCS7 code to calculate the file hash. */ rc = pkcs7_get_digest(modsig->pkcs7_msg, &modsig->digest, &modsig->digest_size, &modsig->hash_algo); } int ima_modsig_verify(struct key *keyring, const struct modsig *modsig) { return verify_pkcs7_message_sig(NULL, 0, modsig->pkcs7_msg, keyring, VERIFYING_MODULE_SIGNATURE, NULL, NULL); } int ima_get_modsig_digest(const struct modsig *modsig, enum hash_algo *algo, const u8 **digest, u32 *digest_size) { *algo = modsig->hash_algo; *digest = modsig->digest; *digest_size = modsig->digest_size; return 0; } int ima_get_raw_modsig(const struct modsig *modsig, const void **data, u32 *data_len) { *data = &modsig->raw_pkcs7; *data_len = modsig->raw_pkcs7_len; return 0; } void ima_free_modsig(struct modsig *modsig) { if (!modsig) return; pkcs7_free_message(modsig->pkcs7_msg); kfree(modsig); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org> * (C) 2011 Intra2net AG <https://www.intra2net.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nfnetlink_acct.h> #include <linux/netfilter/xt_nfacct.h> MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("Xtables: match for the extended accounting infrastructure"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_nfacct"); MODULE_ALIAS("ip6t_nfacct"); static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) { int overquota; const struct xt_nfacct_match_info *info = par->targinfo; nfnl_acct_update(skb, info->nfacct); overquota = nfnl_acct_overquota(xt_net(par), info->nfacct); return overquota != NFACCT_UNDERQUOTA; } static int nfacct_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_nfacct_match_info *info = par->matchinfo; struct nf_acct *nfacct; nfacct = nfnl_acct_find_get(par->net, info->name); if (nfacct == NULL) { pr_info_ratelimited("accounting object `%.*s' does not exist\n", NFACCT_NAME_MAX, info->name); return -ENOENT; } info->nfacct = nfacct; return 0; } static void nfacct_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_nfacct_match_info *info = par->matchinfo; nfnl_acct_put(info->nfacct); } static struct xt_match nfacct_mt_reg[] __read_mostly = { { .name = "nfacct", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = nfacct_mt_checkentry, .match = nfacct_mt, .destroy = nfacct_mt_destroy, .matchsize = sizeof(struct xt_nfacct_match_info), .usersize = offsetof(struct xt_nfacct_match_info, nfacct), .me = THIS_MODULE, }, { .name = "nfacct", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = nfacct_mt_checkentry, .match = nfacct_mt, .destroy = nfacct_mt_destroy, .matchsize = sizeof(struct xt_nfacct_match_info_v1), .usersize = offsetof(struct xt_nfacct_match_info_v1, nfacct), .me = THIS_MODULE, }, }; static int __init nfacct_mt_init(void) { return xt_register_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } static void __exit nfacct_mt_exit(void) { xt_unregister_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } module_init(nfacct_mt_init); module_exit(nfacct_mt_exit); |
| 7580 7401 7390 4138 364 325 61 61 154 164 7619 7612 7625 7623 7645 7620 7627 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; kasan_check_write(dst, count); check_object_size(dst, count, false); if (can_do_masked_user_access()) { long retval; src = masked_user_read_access_begin(src); retval = do_strncpy_from_user(dst, src, count, count); user_read_access_end(); return retval; } max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 73 73 73 5 5 73 73 73 73 73 73 73 73 73 73 73 73 73 73 73 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sunrpc/cache.c * * Generic code for various authentication-related caches * used by sunrpc clients and servers. * * Copyright (C) 2002 Neil Brown <neilb@cse.unsw.edu.au> */ #include <linux/types.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/hex.h> #include <linux/slab.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/string_helpers.h> #include <linux/uaccess.h> #include <linux/poll.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/net.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/pagemap.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <net/genetlink.h> #include <trace/events/sunrpc.h> #include "netns.h" #include "netlink.h" #include "fail.h" #define RPCDBG_FACILITY RPCDBG_CACHE static bool cache_defer_req(struct cache_req *req, struct cache_head *item); static void cache_revisit_request(struct cache_head *item); static void cache_init(struct cache_head *h, struct cache_detail *detail) { time64_t now = seconds_since_boot(); INIT_HLIST_NODE(&h->cache_list); h->flags = 0; kref_init(&h->ref); h->expiry_time = now + CACHE_NEW_EXPIRY; if (now <= detail->flush_time) /* ensure it isn't already expired */ now = detail->flush_time + 1; h->last_refresh = now; } static void cache_fresh_unlocked(struct cache_head *head, struct cache_detail *detail); static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail, struct cache_head *key, int hash) { struct hlist_head *head = &detail->hash_table[hash]; struct cache_head *tmp; rcu_read_lock(); hlist_for_each_entry_rcu(tmp, head, cache_list) { if (!detail->match(tmp, key)) continue; if (test_bit(CACHE_VALID, &tmp->flags) && cache_is_expired(detail, tmp)) continue; tmp = cache_get_rcu(tmp); rcu_read_unlock(); return tmp; } rcu_read_unlock(); return NULL; } static void sunrpc_begin_cache_remove_entry(struct cache_head *ch, struct cache_detail *cd) { /* Must be called under cd->hash_lock */ hlist_del_init_rcu(&ch->cache_list); set_bit(CACHE_CLEANED, &ch->flags); cd->entries --; } static void sunrpc_end_cache_remove_entry(struct cache_head *ch, struct cache_detail *cd) { cache_fresh_unlocked(ch, cd); cache_put(ch, cd); } static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, struct cache_head *key, int hash) { struct cache_head *new, *tmp, *freeme = NULL; struct hlist_head *head = &detail->hash_table[hash]; new = detail->alloc(); if (!new) return NULL; /* must fully initialise 'new', else * we might get lose if we need to * cache_put it soon. */ cache_init(new, detail); detail->init(new, key); spin_lock(&detail->hash_lock); /* check if entry appeared while we slept */ hlist_for_each_entry_rcu(tmp, head, cache_list, lockdep_is_held(&detail->hash_lock)) { if (!detail->match(tmp, key)) continue; if (test_bit(CACHE_VALID, &tmp->flags) && cache_is_expired(detail, tmp)) { sunrpc_begin_cache_remove_entry(tmp, detail); trace_cache_entry_expired(detail, tmp); freeme = tmp; break; } cache_get(tmp); spin_unlock(&detail->hash_lock); cache_put(new, detail); return tmp; } cache_get(new); hlist_add_head_rcu(&new->cache_list, head); detail->entries++; if (detail->nextcheck > new->expiry_time) detail->nextcheck = new->expiry_time + 1; spin_unlock(&detail->hash_lock); if (freeme) sunrpc_end_cache_remove_entry(freeme, detail); return new; } struct cache_head *sunrpc_cache_lookup_rcu(struct cache_detail *detail, struct cache_head *key, int hash) { struct cache_head *ret; ret = sunrpc_cache_find_rcu(detail, key, hash); if (ret) return ret; /* Didn't find anything, insert an empty entry */ return sunrpc_cache_add_entry(detail, key, hash); } EXPORT_SYMBOL_GPL(sunrpc_cache_lookup_rcu); static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch); static void cache_fresh_locked(struct cache_head *head, time64_t expiry, struct cache_detail *detail) { time64_t now = seconds_since_boot(); if (now <= detail->flush_time) /* ensure it isn't immediately treated as expired */ now = detail->flush_time + 1; head->expiry_time = expiry; head->last_refresh = now; smp_wmb(); /* paired with smp_rmb() in cache_is_valid() */ set_bit(CACHE_VALID, &head->flags); } static void cache_fresh_unlocked(struct cache_head *head, struct cache_detail *detail) { if (test_and_clear_bit(CACHE_PENDING, &head->flags)) { cache_revisit_request(head); cache_dequeue(detail, head); } } static void cache_make_negative(struct cache_detail *detail, struct cache_head *h) { set_bit(CACHE_NEGATIVE, &h->flags); trace_cache_entry_make_negative(detail, h); } static void cache_entry_update(struct cache_detail *detail, struct cache_head *h, struct cache_head *new) { if (!test_bit(CACHE_NEGATIVE, &new->flags)) { detail->update(h, new); trace_cache_entry_update(detail, h); } else { cache_make_negative(detail, h); } } struct cache_head *sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash) { /* The 'old' entry is to be replaced by 'new'. * If 'old' is not VALID, we update it directly, * otherwise we need to replace it */ struct cache_head *tmp; if (!test_bit(CACHE_VALID, &old->flags)) { spin_lock(&detail->hash_lock); if (!test_bit(CACHE_VALID, &old->flags)) { cache_entry_update(detail, old, new); cache_fresh_locked(old, new->expiry_time, detail); spin_unlock(&detail->hash_lock); cache_fresh_unlocked(old, detail); return old; } spin_unlock(&detail->hash_lock); } /* We need to insert a new entry */ tmp = detail->alloc(); if (!tmp) { cache_put(old, detail); return NULL; } cache_init(tmp, detail); detail->init(tmp, old); spin_lock(&detail->hash_lock); cache_entry_update(detail, tmp, new); cache_get(tmp); hlist_add_head_rcu(&tmp->cache_list, &detail->hash_table[hash]); detail->entries++; cache_fresh_locked(tmp, new->expiry_time, detail); cache_fresh_locked(old, 0, detail); spin_unlock(&detail->hash_lock); cache_fresh_unlocked(tmp, detail); cache_fresh_unlocked(old, detail); cache_put(old, detail); return tmp; } EXPORT_SYMBOL_GPL(sunrpc_cache_update); static inline int cache_is_valid(struct cache_head *h) { if (!test_bit(CACHE_VALID, &h->flags)) return -EAGAIN; else { /* entry is valid */ if (test_bit(CACHE_NEGATIVE, &h->flags)) return -ENOENT; else { /* * In combination with write barrier in * sunrpc_cache_update, ensures that anyone * using the cache entry after this sees the * updated contents: */ smp_rmb(); return 0; } } } static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h) { int rv; spin_lock(&detail->hash_lock); rv = cache_is_valid(h); if (rv == -EAGAIN) { cache_make_negative(detail, h); cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY, detail); rv = -ENOENT; } spin_unlock(&detail->hash_lock); cache_fresh_unlocked(h, detail); return rv; } int cache_check_rcu(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp) { int rv; time64_t refresh_age, age; /* First decide return status as best we can */ rv = cache_is_valid(h); /* now see if we want to start an upcall */ refresh_age = (h->expiry_time - h->last_refresh); age = seconds_since_boot() - h->last_refresh; if (rqstp == NULL) { if (rv == -EAGAIN) rv = -ENOENT; } else if (rv == -EAGAIN || (h->expiry_time != 0 && age > refresh_age/2)) { dprintk("RPC: Want update, refage=%lld, age=%lld\n", refresh_age, age); switch (detail->cache_upcall(detail, h)) { case -EINVAL: rv = try_to_negate_entry(detail, h); break; case -EAGAIN: cache_fresh_unlocked(h, detail); break; } } if (rv == -EAGAIN) { if (!cache_defer_req(rqstp, h)) { /* * Request was not deferred; handle it as best * we can ourselves: */ rv = cache_is_valid(h); if (rv == -EAGAIN) rv = -ETIMEDOUT; } } return rv; } EXPORT_SYMBOL_GPL(cache_check_rcu); /* * This is the generic cache management routine for all * the authentication caches. * It checks the currency of a cache item and will (later) * initiate an upcall to fill it if needed. * * * Returns 0 if the cache_head can be used, or cache_puts it and returns * -EAGAIN if upcall is pending and request has been queued * -ETIMEDOUT if upcall failed or request could not be queue or * upcall completed but item is still invalid (implying that * the cache item has been replaced with a newer one). * -ENOENT if cache entry was negative */ int cache_check(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp) { int rv; rv = cache_check_rcu(detail, h, rqstp); if (rv) cache_put(h, detail); return rv; } EXPORT_SYMBOL_GPL(cache_check); /* * caches need to be periodically cleaned. * For this we maintain a list of cache_detail and * a current pointer into that list and into the table * for that entry. * * Each time cache_clean is called it finds the next non-empty entry * in the current table and walks the list in that entry * looking for entries that can be removed. * * An entry gets removed if: * - The expiry is before current time * - The last_refresh time is before the flush_time for that cache * * later we might drop old entries with non-NEVER expiry if that table * is getting 'full' for some definition of 'full' * * The question of "how often to scan a table" is an interesting one * and is answered in part by the use of the "nextcheck" field in the * cache_detail. * When a scan of a table begins, the nextcheck field is set to a time * that is well into the future. * While scanning, if an expiry time is found that is earlier than the * current nextcheck time, nextcheck is set to that expiry time. * If the flush_time is ever set to a time earlier than the nextcheck * time, the nextcheck time is then set to that flush_time. * * A table is then only scanned if the current time is at least * the nextcheck time. * */ static LIST_HEAD(cache_list); static DEFINE_SPINLOCK(cache_list_lock); static struct cache_detail *current_detail; static int current_index; static void do_cache_clean(struct work_struct *work); static struct delayed_work cache_cleaner; void sunrpc_init_cache_detail(struct cache_detail *cd) { spin_lock_init(&cd->hash_lock); INIT_LIST_HEAD(&cd->requests); INIT_LIST_HEAD(&cd->readers); spin_lock_init(&cd->queue_lock); init_waitqueue_head(&cd->queue_wait); cd->next_seqno = 1; spin_lock(&cache_list_lock); cd->nextcheck = 0; cd->entries = 0; atomic_set(&cd->writers, 0); cd->last_close = 0; cd->last_warn = -1; list_add(&cd->others, &cache_list); spin_unlock(&cache_list_lock); /* start the cleaning process */ queue_delayed_work(system_power_efficient_wq, &cache_cleaner, 0); } EXPORT_SYMBOL_GPL(sunrpc_init_cache_detail); void sunrpc_destroy_cache_detail(struct cache_detail *cd) { cache_purge(cd); spin_lock(&cache_list_lock); spin_lock(&cd->hash_lock); if (current_detail == cd) current_detail = NULL; list_del_init(&cd->others); spin_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); if (list_empty(&cache_list)) { /* module must be being unloaded so its safe to kill the worker */ cancel_delayed_work_sync(&cache_cleaner); } } EXPORT_SYMBOL_GPL(sunrpc_destroy_cache_detail); /* clean cache tries to find something to clean * and cleans it. * It returns 1 if it cleaned something, * 0 if it didn't find anything this time * -1 if it fell off the end of the list. */ static int cache_clean(void) { int rv = 0; struct list_head *next; spin_lock(&cache_list_lock); /* find a suitable table if we don't already have one */ while (current_detail == NULL || current_index >= current_detail->hash_size) { if (current_detail) next = current_detail->others.next; else next = cache_list.next; if (next == &cache_list) { current_detail = NULL; spin_unlock(&cache_list_lock); return -1; } current_detail = list_entry(next, struct cache_detail, others); if (current_detail->nextcheck > seconds_since_boot()) current_index = current_detail->hash_size; else { current_index = 0; current_detail->nextcheck = seconds_since_boot()+30*60; } } spin_lock(¤t_detail->hash_lock); /* find a non-empty bucket in the table */ while (current_index < current_detail->hash_size && hlist_empty(¤t_detail->hash_table[current_index])) current_index++; /* find a cleanable entry in the bucket and clean it, or set to next bucket */ if (current_index < current_detail->hash_size) { struct cache_head *ch = NULL; struct cache_detail *d; struct hlist_head *head; struct hlist_node *tmp; /* Ok, now to clean this strand */ head = ¤t_detail->hash_table[current_index]; hlist_for_each_entry_safe(ch, tmp, head, cache_list) { if (current_detail->nextcheck > ch->expiry_time) current_detail->nextcheck = ch->expiry_time+1; if (!cache_is_expired(current_detail, ch)) continue; sunrpc_begin_cache_remove_entry(ch, current_detail); trace_cache_entry_expired(current_detail, ch); rv = 1; break; } spin_unlock(¤t_detail->hash_lock); d = current_detail; if (!ch) current_index ++; spin_unlock(&cache_list_lock); if (ch) sunrpc_end_cache_remove_entry(ch, d); } else { spin_unlock(¤t_detail->hash_lock); spin_unlock(&cache_list_lock); } return rv; } /* * We want to regularly clean the cache, so we need to schedule some work ... */ static void do_cache_clean(struct work_struct *work) { int delay; if (list_empty(&cache_list)) return; if (cache_clean() == -1) delay = round_jiffies_relative(30*HZ); else delay = 5; queue_delayed_work(system_power_efficient_wq, &cache_cleaner, delay); } /* * Clean all caches promptly. This just calls cache_clean * repeatedly until we are sure that every cache has had a chance to * be fully cleaned */ void cache_flush(void) { while (cache_clean() != -1) cond_resched(); while (cache_clean() != -1) cond_resched(); } EXPORT_SYMBOL_GPL(cache_flush); void cache_purge(struct cache_detail *detail) { struct cache_head *ch = NULL; struct hlist_head *head = NULL; int i = 0; spin_lock(&detail->hash_lock); if (!detail->entries) { spin_unlock(&detail->hash_lock); return; } dprintk("RPC: %d entries in %s cache\n", detail->entries, detail->name); for (i = 0; i < detail->hash_size; i++) { head = &detail->hash_table[i]; while (!hlist_empty(head)) { ch = hlist_entry(head->first, struct cache_head, cache_list); sunrpc_begin_cache_remove_entry(ch, detail); spin_unlock(&detail->hash_lock); sunrpc_end_cache_remove_entry(ch, detail); spin_lock(&detail->hash_lock); } } spin_unlock(&detail->hash_lock); } EXPORT_SYMBOL_GPL(cache_purge); /* * Deferral and Revisiting of Requests. * * If a cache lookup finds a pending entry, we * need to defer the request and revisit it later. * All deferred requests are stored in a hash table, * indexed by "struct cache_head *". * As it may be wasteful to store a whole request * structure, we allow the request to provide a * deferred form, which must contain a * 'struct cache_deferred_req' * This cache_deferred_req contains a method to allow * it to be revisited when cache info is available */ #define DFR_HASHSIZE (PAGE_SIZE/sizeof(struct list_head)) #define DFR_HASH(item) ((((long)item)>>4 ^ (((long)item)>>13)) % DFR_HASHSIZE) #define DFR_MAX 300 /* ??? */ static DEFINE_SPINLOCK(cache_defer_lock); static LIST_HEAD(cache_defer_list); static struct hlist_head cache_defer_hash[DFR_HASHSIZE]; static int cache_defer_cnt; static void __unhash_deferred_req(struct cache_deferred_req *dreq) { hlist_del_init(&dreq->hash); if (!list_empty(&dreq->recent)) { list_del_init(&dreq->recent); cache_defer_cnt--; } } static void __hash_deferred_req(struct cache_deferred_req *dreq, struct cache_head *item) { int hash = DFR_HASH(item); INIT_LIST_HEAD(&dreq->recent); hlist_add_head(&dreq->hash, &cache_defer_hash[hash]); } static void setup_deferral(struct cache_deferred_req *dreq, struct cache_head *item, int count_me) { dreq->item = item; spin_lock(&cache_defer_lock); __hash_deferred_req(dreq, item); if (count_me) { cache_defer_cnt++; list_add(&dreq->recent, &cache_defer_list); } spin_unlock(&cache_defer_lock); } struct thread_deferred_req { struct cache_deferred_req handle; struct completion completion; }; static void cache_restart_thread(struct cache_deferred_req *dreq, int too_many) { struct thread_deferred_req *dr = container_of(dreq, struct thread_deferred_req, handle); complete(&dr->completion); } static void cache_wait_req(struct cache_req *req, struct cache_head *item) { struct thread_deferred_req sleeper; struct cache_deferred_req *dreq = &sleeper.handle; sleeper.completion = COMPLETION_INITIALIZER_ONSTACK(sleeper.completion); dreq->revisit = cache_restart_thread; setup_deferral(dreq, item, 0); if (!test_bit(CACHE_PENDING, &item->flags) || wait_for_completion_interruptible_timeout( &sleeper.completion, req->thread_wait) <= 0) { /* The completion wasn't completed, so we need * to clean up */ spin_lock(&cache_defer_lock); if (!hlist_unhashed(&sleeper.handle.hash)) { __unhash_deferred_req(&sleeper.handle); spin_unlock(&cache_defer_lock); } else { /* cache_revisit_request already removed * this from the hash table, but hasn't * called ->revisit yet. It will very soon * and we need to wait for it. */ spin_unlock(&cache_defer_lock); wait_for_completion(&sleeper.completion); } } } static void cache_limit_defers(void) { /* Make sure we haven't exceed the limit of allowed deferred * requests. */ struct cache_deferred_req *discard = NULL; if (cache_defer_cnt <= DFR_MAX) return; spin_lock(&cache_defer_lock); /* Consider removing either the first or the last */ if (cache_defer_cnt > DFR_MAX) { if (get_random_u32_below(2)) discard = list_entry(cache_defer_list.next, struct cache_deferred_req, recent); else discard = list_entry(cache_defer_list.prev, struct cache_deferred_req, recent); __unhash_deferred_req(discard); } spin_unlock(&cache_defer_lock); if (discard) discard->revisit(discard, 1); } #if IS_ENABLED(CONFIG_FAIL_SUNRPC) static inline bool cache_defer_immediately(void) { return !fail_sunrpc.ignore_cache_wait && should_fail(&fail_sunrpc.attr, 1); } #else static inline bool cache_defer_immediately(void) { return false; } #endif /* Return true if and only if a deferred request is queued. */ static bool cache_defer_req(struct cache_req *req, struct cache_head *item) { struct cache_deferred_req *dreq; if (!cache_defer_immediately()) { cache_wait_req(req, item); if (!test_bit(CACHE_PENDING, &item->flags)) return false; } dreq = req->defer(req); if (dreq == NULL) return false; setup_deferral(dreq, item, 1); if (!test_bit(CACHE_PENDING, &item->flags)) /* Bit could have been cleared before we managed to * set up the deferral, so need to revisit just in case */ cache_revisit_request(item); cache_limit_defers(); return true; } static void cache_revisit_request(struct cache_head *item) { struct cache_deferred_req *dreq; struct hlist_node *tmp; int hash = DFR_HASH(item); LIST_HEAD(pending); spin_lock(&cache_defer_lock); hlist_for_each_entry_safe(dreq, tmp, &cache_defer_hash[hash], hash) if (dreq->item == item) { __unhash_deferred_req(dreq); list_add(&dreq->recent, &pending); } spin_unlock(&cache_defer_lock); while (!list_empty(&pending)) { dreq = list_entry(pending.next, struct cache_deferred_req, recent); list_del_init(&dreq->recent); dreq->revisit(dreq, 0); } } void cache_clean_deferred(void *owner) { struct cache_deferred_req *dreq, *tmp; LIST_HEAD(pending); spin_lock(&cache_defer_lock); list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) { if (dreq->owner == owner) { __unhash_deferred_req(dreq); list_add(&dreq->recent, &pending); } } spin_unlock(&cache_defer_lock); while (!list_empty(&pending)) { dreq = list_entry(pending.next, struct cache_deferred_req, recent); list_del_init(&dreq->recent); dreq->revisit(dreq, 1); } } /* * communicate with user-space * * We have a magic /proc file - /proc/net/rpc/<cachename>/channel. * On read, you get a full request, or block. * On write, an update request is processed. * Poll works if anything to read, and always allows write. */ struct cache_request { struct list_head list; struct cache_head *item; char *buf; int len; int readers; u64 seqno; }; struct cache_reader { struct list_head list; int offset; /* if non-0, we have a refcnt on next request */ u64 next_seqno; }; static int cache_request(struct cache_detail *detail, struct cache_request *crq) { char *bp = crq->buf; int len = PAGE_SIZE; detail->cache_request(detail, crq->item, &bp, &len); if (len < 0) return -E2BIG; return PAGE_SIZE - len; } static struct cache_request * cache_next_request(struct cache_detail *cd, u64 seqno) { struct cache_request *rq; list_for_each_entry(rq, &cd->requests, list) if (rq->seqno >= seqno) return rq; return NULL; } static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; struct inode *inode = file_inode(filp); int err; if (count == 0) return 0; inode_lock(inode); /* protect against multiple concurrent * readers on this file */ again: spin_lock(&cd->queue_lock); /* need to find next request */ rq = cache_next_request(cd, rp->next_seqno); if (!rq) { spin_unlock(&cd->queue_lock); inode_unlock(inode); WARN_ON_ONCE(rp->offset); return 0; } if (rp->offset == 0) rq->readers++; spin_unlock(&cd->queue_lock); if (rq->len == 0) { err = cache_request(cd, rq); if (err < 0) goto out; rq->len = err; } if (rp->offset == 0 && !test_bit(CACHE_PENDING, &rq->item->flags)) { err = -EAGAIN; rp->next_seqno = rq->seqno + 1; } else { if (rp->offset + count > rq->len) count = rq->len - rp->offset; err = -EFAULT; if (copy_to_user(buf, rq->buf + rp->offset, count)) goto out; rp->offset += count; if (rp->offset >= rq->len) { rp->offset = 0; rp->next_seqno = rq->seqno + 1; } err = 0; } out: if (rp->offset == 0) { /* need to release rq */ spin_lock(&cd->queue_lock); rq->readers--; if (rq->readers == 0 && !test_bit(CACHE_PENDING, &rq->item->flags)) { list_del(&rq->list); spin_unlock(&cd->queue_lock); cache_put(rq->item, cd); kfree(rq->buf); kfree(rq); } else spin_unlock(&cd->queue_lock); } if (err == -EAGAIN) goto again; inode_unlock(inode); return err ? err : count; } static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, size_t count, struct cache_detail *cd) { ssize_t ret; if (count == 0) return -EINVAL; if (copy_from_user(kaddr, buf, count)) return -EFAULT; kaddr[count] = '\0'; ret = cd->cache_parse(cd, kaddr, count); if (!ret) ret = count; return ret; } static ssize_t cache_downcall(struct address_space *mapping, const char __user *buf, size_t count, struct cache_detail *cd) { char *write_buf; ssize_t ret = -ENOMEM; if (count >= 32768) { /* 32k is max userland buffer, lets check anyway */ ret = -EINVAL; goto out; } write_buf = kvmalloc(count + 1, GFP_KERNEL); if (!write_buf) goto out; ret = cache_do_downcall(write_buf, buf, count, cd); kvfree(write_buf); out: return ret; } static ssize_t cache_write(struct file *filp, const char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { struct address_space *mapping = filp->f_mapping; struct inode *inode = file_inode(filp); ssize_t ret = -EINVAL; if (!cd->cache_parse) goto out; inode_lock(inode); ret = cache_downcall(mapping, buf, count, cd); inode_unlock(inode); out: return ret; } static __poll_t cache_poll(struct file *filp, poll_table *wait, struct cache_detail *cd) { __poll_t mask; struct cache_reader *rp = filp->private_data; poll_wait(filp, &cd->queue_wait, wait); /* alway allow write */ mask = EPOLLOUT | EPOLLWRNORM; if (!rp) return mask; spin_lock(&cd->queue_lock); if (cache_next_request(cd, rp->next_seqno)) mask |= EPOLLIN | EPOLLRDNORM; spin_unlock(&cd->queue_lock); return mask; } static int cache_ioctl(struct inode *ino, struct file *filp, unsigned int cmd, unsigned long arg, struct cache_detail *cd) { int len = 0; struct cache_reader *rp = filp->private_data; struct cache_request *rq; if (cmd != FIONREAD || !rp) return -EINVAL; spin_lock(&cd->queue_lock); /* only find the length remaining in current request, * or the length of the next request */ rq = cache_next_request(cd, rp->next_seqno); if (rq) len = rq->len - rp->offset; spin_unlock(&cd->queue_lock); return put_user(len, (int __user *)arg); } static int cache_open(struct inode *inode, struct file *filp, struct cache_detail *cd) { struct cache_reader *rp = NULL; if (!cd || !try_module_get(cd->owner)) return -EACCES; nonseekable_open(inode, filp); if (filp->f_mode & FMODE_READ) { rp = kmalloc_obj(*rp); if (!rp) { module_put(cd->owner); return -ENOMEM; } rp->offset = 0; rp->next_seqno = 0; spin_lock(&cd->queue_lock); list_add(&rp->list, &cd->readers); spin_unlock(&cd->queue_lock); } if (filp->f_mode & FMODE_WRITE) atomic_inc(&cd->writers); filp->private_data = rp; return 0; } static int cache_release(struct inode *inode, struct file *filp, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; if (rp) { struct cache_request *rq = NULL; spin_lock(&cd->queue_lock); if (rp->offset) { struct cache_request *cr; cr = cache_next_request(cd, rp->next_seqno); if (cr) { cr->readers--; if (cr->readers == 0 && !test_bit(CACHE_PENDING, &cr->item->flags)) { list_del(&cr->list); rq = cr; } } rp->offset = 0; } list_del(&rp->list); spin_unlock(&cd->queue_lock); if (rq) { cache_put(rq->item, cd); kfree(rq->buf); kfree(rq); } filp->private_data = NULL; kfree(rp); } if (filp->f_mode & FMODE_WRITE) { atomic_dec(&cd->writers); cd->last_close = seconds_since_boot(); } module_put(cd->owner); return 0; } static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch) { struct cache_request *cr, *tmp; LIST_HEAD(dequeued); spin_lock(&detail->queue_lock); list_for_each_entry_safe(cr, tmp, &detail->requests, list) { if (cr->item != ch) continue; if (test_bit(CACHE_PENDING, &ch->flags)) /* Lost a race and it is pending again */ break; if (cr->readers != 0) continue; list_move(&cr->list, &dequeued); } spin_unlock(&detail->queue_lock); while (!list_empty(&dequeued)) { cr = list_entry(dequeued.next, struct cache_request, list); list_del(&cr->list); cache_put(cr->item, detail); kfree(cr->buf); kfree(cr); } } /* * Support routines for text-based upcalls. * Fields are separated by spaces. * Fields are either mangled to quote space tab newline slosh with slosh * or a hexified with a leading \x * Record is terminated with newline. * */ void qword_add(char **bpp, int *lp, char *str) { char *bp = *bpp; int len = *lp; int ret; if (len < 0) return; ret = string_escape_str(str, bp, len, ESCAPE_OCTAL, "\\ \n\t"); if (ret >= len) { bp += len; len = -1; } else { bp += ret; len -= ret; *bp++ = ' '; len--; } *bpp = bp; *lp = len; } EXPORT_SYMBOL_GPL(qword_add); void qword_addhex(char **bpp, int *lp, char *buf, int blen) { char *bp = *bpp; int len = *lp; if (len < 0) return; if (len > 2) { *bp++ = '\\'; *bp++ = 'x'; len -= 2; while (blen && len >= 2) { bp = hex_byte_pack(bp, *buf++); len -= 2; blen--; } } if (blen || len<1) len = -1; else { *bp++ = ' '; len--; } *bpp = bp; *lp = len; } EXPORT_SYMBOL_GPL(qword_addhex); static void warn_no_listener(struct cache_detail *detail) { if (detail->last_warn != detail->last_close) { detail->last_warn = detail->last_close; if (detail->warn_no_listener) detail->warn_no_listener(detail, detail->last_close != 0); } } static bool cache_listeners_exist(struct cache_detail *detail) { if (atomic_read(&detail->writers)) return true; if (detail->last_close == 0) /* This cache was never opened */ return false; if (detail->last_close < seconds_since_boot() - 30) /* * We allow for the possibility that someone might * restart a userspace daemon without restarting the * server; but after 30 seconds, we give up. */ return false; return true; } /* * register an upcall request to user-space and queue it up to be fetched by * the upcall daemon. * * Each request is at most one page long. */ static int cache_do_upcall(struct cache_detail *detail, struct cache_head *h) { char *buf; struct cache_request *crq; int ret = 0; if (test_bit(CACHE_CLEANED, &h->flags)) /* Too late to make an upcall */ return -EAGAIN; buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!buf) return -EAGAIN; crq = kmalloc_obj(*crq); if (!crq) { kfree(buf); return -EAGAIN; } crq->buf = buf; crq->len = 0; crq->readers = 0; spin_lock(&detail->queue_lock); if (test_bit(CACHE_PENDING, &h->flags)) { crq->item = cache_get(h); crq->seqno = detail->next_seqno++; list_add_tail(&crq->list, &detail->requests); trace_cache_entry_upcall(detail, h); } else /* Lost a race, no longer PENDING, so don't enqueue */ ret = -EAGAIN; spin_unlock(&detail->queue_lock); if (ret != -EAGAIN && detail->cache_notify) detail->cache_notify(detail, h); wake_up(&detail->queue_wait); if (ret == -EAGAIN) { kfree(buf); kfree(crq); } return ret; } int sunrpc_cache_upcall(struct cache_detail *detail, struct cache_head *h) { if (test_and_set_bit(CACHE_PENDING, &h->flags)) return 0; return cache_do_upcall(detail, h); } EXPORT_SYMBOL_GPL(sunrpc_cache_upcall); int sunrpc_cache_upcall_warn(struct cache_detail *detail, struct cache_head *h) { if (!cache_listeners_exist(detail)) { warn_no_listener(detail); trace_cache_entry_no_listener(detail, h); return -EINVAL; } return sunrpc_cache_upcall(detail, h); } EXPORT_SYMBOL_GPL(sunrpc_cache_upcall_warn); /* * parse a message from user-space and pass it * to an appropriate cache * Messages are, like requests, separated into fields by * spaces and dequotes as \xHEXSTRING or embedded \nnn octal * * Message is * reply cachename expiry key ... content.... * * key and content are both parsed by cache */ int qword_get(char **bpp, char *dest, int bufsize) { /* return bytes copied, or -1 on error */ char *bp = *bpp; int len = 0; while (*bp == ' ') bp++; if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); if (h < 0) break; l = hex_to_bin(bp[1]); if (l < 0) break; *dest++ = (h << 4) | l; bp += 2; len++; } } else { /* text with \nnn octal quoting */ while (*bp != ' ' && *bp != '\n' && *bp && len < bufsize-1) { if (*bp == '\\' && isodigit(bp[1]) && (bp[1] <= '3') && isodigit(bp[2]) && isodigit(bp[3])) { int byte = (*++bp -'0'); bp++; byte = (byte << 3) | (*bp++ - '0'); byte = (byte << 3) | (*bp++ - '0'); *dest++ = byte; len++; } else { *dest++ = *bp++; len++; } } } if (*bp != ' ' && *bp != '\n' && *bp != '\0') return -1; while (*bp == ' ') bp++; *bpp = bp; *dest = '\0'; return len; } EXPORT_SYMBOL_GPL(qword_get); /* * support /proc/net/rpc/$CACHENAME/content * as a seqfile. * We call ->cache_show passing NULL for the item to * get a header, then pass each real item in the cache */ static void *__cache_seq_start(struct seq_file *m, loff_t *pos) { loff_t n = *pos; unsigned int hash, entry; struct cache_head *ch; struct cache_detail *cd = m->private; if (!n--) return SEQ_START_TOKEN; hash = n >> 32; entry = n & ((1LL<<32) - 1); if (hash >= cd->hash_size) return NULL; hlist_for_each_entry_rcu(ch, &cd->hash_table[hash], cache_list) if (!entry--) return ch; ch = NULL; while (!ch && ++hash < cd->hash_size) ch = hlist_entry_safe(rcu_dereference( hlist_first_rcu(&cd->hash_table[hash])), struct cache_head, cache_list); *pos = ((long long)hash << 32) + 1; return ch; } static void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) { struct cache_head *ch = p; int hash = (*pos >> 32); struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) { hash = 0; ch = NULL; } while (hash < cd->hash_size) { if (ch) ch = hlist_entry_safe( rcu_dereference( hlist_next_rcu(&ch->cache_list)), struct cache_head, cache_list); else ch = hlist_entry_safe( rcu_dereference( hlist_first_rcu(&cd->hash_table[hash])), struct cache_head, cache_list); if (ch) { ++*pos; return ch; } hash++; *pos = (long long)hash << 32; } return NULL; } void *cache_seq_start_rcu(struct seq_file *m, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return __cache_seq_start(m, pos); } EXPORT_SYMBOL_GPL(cache_seq_start_rcu); void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos) { return cache_seq_next(file, p, pos); } EXPORT_SYMBOL_GPL(cache_seq_next_rcu); void cache_seq_stop_rcu(struct seq_file *m, void *p) __releases(RCU) { rcu_read_unlock(); } EXPORT_SYMBOL_GPL(cache_seq_stop_rcu); static int c_show(struct seq_file *m, void *p) { struct cache_head *cp = p; struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) return cd->cache_show(m, cd, NULL); ifdebug(CACHE) seq_printf(m, "# expiry=%lld refcnt=%d flags=%lx\n", convert_to_wallclock(cp->expiry_time), kref_read(&cp->ref), cp->flags); if (cache_check_rcu(cd, cp, NULL)) seq_puts(m, "# "); else if (cache_is_expired(cd, cp)) seq_puts(m, "# "); return cd->cache_show(m, cd, cp); } static const struct seq_operations cache_content_op = { .start = cache_seq_start_rcu, .next = cache_seq_next_rcu, .stop = cache_seq_stop_rcu, .show = c_show, }; static int content_open(struct inode *inode, struct file *file, struct cache_detail *cd) { struct seq_file *seq; int err; if (!cd || !try_module_get(cd->owner)) return -EACCES; err = seq_open(file, &cache_content_op); if (err) { module_put(cd->owner); return err; } seq = file->private_data; seq->private = cd; return 0; } static int content_release(struct inode *inode, struct file *file, struct cache_detail *cd) { int ret = seq_release(inode, file); module_put(cd->owner); return ret; } static int open_flush(struct inode *inode, struct file *file, struct cache_detail *cd) { if (!cd || !try_module_get(cd->owner)) return -EACCES; return nonseekable_open(inode, file); } static int release_flush(struct inode *inode, struct file *file, struct cache_detail *cd) { module_put(cd->owner); return 0; } static ssize_t read_flush(struct file *file, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { char tbuf[22]; size_t len; len = snprintf(tbuf, sizeof(tbuf), "%llu\n", convert_to_wallclock(cd->flush_time)); return simple_read_from_buffer(buf, count, ppos, tbuf, len); } static ssize_t write_flush(struct file *file, const char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { char tbuf[20]; char *ep; time64_t now; if (*ppos || count > sizeof(tbuf)-1) return -EINVAL; if (copy_from_user(tbuf, buf, count)) return -EFAULT; tbuf[count] = 0; simple_strtoul(tbuf, &ep, 0); if (*ep && *ep != '\n') return -EINVAL; /* Note that while we check that 'buf' holds a valid number, * we always ignore the value and just flush everything. * Making use of the number leads to races. */ now = seconds_since_boot(); /* Always flush everything, so behave like cache_purge() * Do this by advancing flush_time to the current time, * or by one second if it has already reached the current time. * Newly added cache entries will always have ->last_refresh greater * that ->flush_time, so they don't get flushed prematurely. */ if (cd->flush_time >= now) now = cd->flush_time + 1; cd->flush_time = now; cd->nextcheck = now; cache_flush(); if (cd->flush) cd->flush(); *ppos += count; return count; } static ssize_t cache_read_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return cache_read(filp, buf, count, ppos, cd); } static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return cache_write(filp, buf, count, ppos, cd); } static __poll_t cache_poll_procfs(struct file *filp, poll_table *wait) { struct cache_detail *cd = pde_data(file_inode(filp)); return cache_poll(filp, wait, cd); } static long cache_ioctl_procfs(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct cache_detail *cd = pde_data(inode); return cache_ioctl(inode, filp, cmd, arg, cd); } static int cache_open_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return cache_open(inode, filp, cd); } static int cache_release_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return cache_release(inode, filp, cd); } static const struct proc_ops cache_channel_proc_ops = { .proc_read = cache_read_procfs, .proc_write = cache_write_procfs, .proc_poll = cache_poll_procfs, .proc_ioctl = cache_ioctl_procfs, /* for FIONREAD */ .proc_open = cache_open_procfs, .proc_release = cache_release_procfs, }; static int content_open_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return content_open(inode, filp, cd); } static int content_release_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return content_release(inode, filp, cd); } static const struct proc_ops content_proc_ops = { .proc_open = content_open_procfs, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = content_release_procfs, }; static int open_flush_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return open_flush(inode, filp, cd); } static int release_flush_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return release_flush(inode, filp, cd); } static ssize_t read_flush_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return read_flush(filp, buf, count, ppos, cd); } static ssize_t write_flush_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return write_flush(filp, buf, count, ppos, cd); } static const struct proc_ops cache_flush_proc_ops = { .proc_open = open_flush_procfs, .proc_read = read_flush_procfs, .proc_write = write_flush_procfs, .proc_release = release_flush_procfs, }; static void remove_cache_proc_entries(struct cache_detail *cd) { if (cd->procfs) { proc_remove(cd->procfs); cd->procfs = NULL; } } static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) { struct proc_dir_entry *p; struct sunrpc_net *sn; if (!IS_ENABLED(CONFIG_PROC_FS)) return 0; sn = net_generic(net, sunrpc_net_id); cd->procfs = proc_mkdir(cd->name, sn->proc_net_rpc); if (cd->procfs == NULL) goto out_nomem; p = proc_create_data("flush", S_IFREG | 0600, cd->procfs, &cache_flush_proc_ops, cd); if (p == NULL) goto out_nomem; if (cd->cache_request || cd->cache_parse) { p = proc_create_data("channel", S_IFREG | 0600, cd->procfs, &cache_channel_proc_ops, cd); if (p == NULL) goto out_nomem; } if (cd->cache_show) { p = proc_create_data("content", S_IFREG | 0400, cd->procfs, &content_proc_ops, cd); if (p == NULL) goto out_nomem; } return 0; out_nomem: remove_cache_proc_entries(cd); return -ENOMEM; } void __init cache_initialize(void) { INIT_DEFERRABLE_WORK(&cache_cleaner, do_cache_clean); } int cache_register_net(struct cache_detail *cd, struct net *net) { int ret; sunrpc_init_cache_detail(cd); ret = create_cache_proc_entries(cd, net); if (ret) sunrpc_destroy_cache_detail(cd); return ret; } EXPORT_SYMBOL_GPL(cache_register_net); void cache_unregister_net(struct cache_detail *cd, struct net *net) { remove_cache_proc_entries(cd); sunrpc_destroy_cache_detail(cd); } EXPORT_SYMBOL_GPL(cache_unregister_net); struct cache_detail *cache_create_net(const struct cache_detail *tmpl, struct net *net) { struct cache_detail *cd; int i; cd = kmemdup(tmpl, sizeof(struct cache_detail), GFP_KERNEL); if (cd == NULL) return ERR_PTR(-ENOMEM); cd->hash_table = kzalloc_objs(struct hlist_head, cd->hash_size); if (cd->hash_table == NULL) { kfree(cd); return ERR_PTR(-ENOMEM); } for (i = 0; i < cd->hash_size; i++) INIT_HLIST_HEAD(&cd->hash_table[i]); cd->net = net; return cd; } EXPORT_SYMBOL_GPL(cache_create_net); void cache_destroy_net(struct cache_detail *cd, struct net *net) { kfree(cd->hash_table); kfree(cd); } EXPORT_SYMBOL_GPL(cache_destroy_net); static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_read(filp, buf, count, ppos, cd); } static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_write(filp, buf, count, ppos, cd); } static __poll_t cache_poll_pipefs(struct file *filp, poll_table *wait) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_poll(filp, wait, cd); } static long cache_ioctl_pipefs(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct cache_detail *cd = RPC_I(inode)->private; return cache_ioctl(inode, filp, cmd, arg, cd); } static int cache_open_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return cache_open(inode, filp, cd); } static int cache_release_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return cache_release(inode, filp, cd); } const struct file_operations cache_file_operations_pipefs = { .owner = THIS_MODULE, .read = cache_read_pipefs, .write = cache_write_pipefs, .poll = cache_poll_pipefs, .unlocked_ioctl = cache_ioctl_pipefs, /* for FIONREAD */ .open = cache_open_pipefs, .release = cache_release_pipefs, }; static int content_open_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return content_open(inode, filp, cd); } static int content_release_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return content_release(inode, filp, cd); } const struct file_operations content_file_operations_pipefs = { .open = content_open_pipefs, .read = seq_read, .llseek = seq_lseek, .release = content_release_pipefs, }; static int open_flush_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return open_flush(inode, filp, cd); } static int release_flush_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return release_flush(inode, filp, cd); } static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return read_flush(filp, buf, count, ppos, cd); } static ssize_t write_flush_pipefs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return write_flush(filp, buf, count, ppos, cd); } const struct file_operations cache_flush_operations_pipefs = { .open = open_flush_pipefs, .read = read_flush_pipefs, .write = write_flush_pipefs, .release = release_flush_pipefs, }; int sunrpc_cache_register_pipefs(struct dentry *parent, const char *name, umode_t umode, struct cache_detail *cd) { struct dentry *dir = rpc_create_cache_dir(parent, name, umode, cd); if (IS_ERR(dir)) return PTR_ERR(dir); cd->pipefs = dir; return 0; } EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs); void sunrpc_cache_unregister_pipefs(struct cache_detail *cd) { if (cd->pipefs) { rpc_remove_cache_dir(cd->pipefs); cd->pipefs = NULL; } } EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs); void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h) { spin_lock(&cd->hash_lock); if (!hlist_unhashed(&h->cache_list)){ sunrpc_begin_cache_remove_entry(h, cd); spin_unlock(&cd->hash_lock); sunrpc_end_cache_remove_entry(h, cd); } else spin_unlock(&cd->hash_lock); } EXPORT_SYMBOL_GPL(sunrpc_cache_unhash); /** * sunrpc_cache_requests_count - count pending upcall requests * @cd: cache_detail to query * * Returns the number of requests on the cache's request list that * still have CACHE_PENDING set. */ int sunrpc_cache_requests_count(struct cache_detail *cd) { struct cache_request *crq; int cnt = 0; spin_lock(&cd->queue_lock); list_for_each_entry(crq, &cd->requests, list) { if (test_bit(CACHE_PENDING, &crq->item->flags)) cnt++; } spin_unlock(&cd->queue_lock); return cnt; } EXPORT_SYMBOL_GPL(sunrpc_cache_requests_count); /** * sunrpc_cache_requests_snapshot - snapshot pending upcall requests * @cd: cache_detail to query * @items: array to fill with cache_head pointers (caller-allocated) * @seqnos: array to fill with sequence numbers (caller-allocated) * @max: size of the arrays * @min_seqno: only include entries with seqno > min_seqno (0 for all) * * Only entries with CACHE_PENDING set are included. Takes a reference * on each cache_head via cache_get(). Caller must call cache_put() * on each returned item when done. * * Returns the number of entries filled. */ int sunrpc_cache_requests_snapshot(struct cache_detail *cd, struct cache_head **items, u64 *seqnos, int max, u64 min_seqno) { struct cache_request *crq; int i = 0; spin_lock(&cd->queue_lock); list_for_each_entry(crq, &cd->requests, list) { if (i >= max) break; if (!test_bit(CACHE_PENDING, &crq->item->flags)) continue; if (crq->seqno <= min_seqno) continue; items[i] = cache_get(crq->item); seqnos[i] = crq->seqno; i++; } spin_unlock(&cd->queue_lock); return i; } EXPORT_SYMBOL_GPL(sunrpc_cache_requests_snapshot); /** * sunrpc_cache_notify - send a netlink notification for a cache event * @cd: cache_detail for the cache * @h: cache_head entry (unused, reserved for future use) * @cache_type: cache type identifier (e.g. SUNRPC_CACHE_TYPE_UNIX_GID) * * Sends a SUNRPC_CMD_CACHE_NOTIFY multicast message on the "exportd" * group if any listeners are present. Returns 0 on success or a * negative errno. */ int sunrpc_cache_notify(struct cache_detail *cd, struct cache_head *h, u32 cache_type) { struct genlmsghdr *hdr; struct sk_buff *msg; if (!genl_has_listeners(&sunrpc_nl_family, cd->net, SUNRPC_NLGRP_EXPORTD)) return -ENOLINK; msg = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &sunrpc_nl_family, 0, SUNRPC_CMD_CACHE_NOTIFY); if (!hdr) { nlmsg_free(msg); return -ENOMEM; } if (nla_put_u32(msg, SUNRPC_A_CACHE_NOTIFY_CACHE_TYPE, cache_type)) { nlmsg_free(msg); return -ENOMEM; } genlmsg_end(msg, hdr); return genlmsg_multicast_netns(&sunrpc_nl_family, cd->net, msg, 0, SUNRPC_NLGRP_EXPORTD, GFP_KERNEL); } EXPORT_SYMBOL_GPL(sunrpc_cache_notify); |
| 2787 2789 2789 2789 2780 9 9 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * cls_cgroup.h Control Group Classifier * * Authors: Thomas Graf <tgraf@suug.ch> */ #ifndef _NET_CLS_CGROUP_H #define _NET_CLS_CGROUP_H #include <linux/cgroup.h> #include <linux/hardirq.h> #include <linux/rcupdate.h> #include <net/sock.h> #include <net/inet_sock.h> #ifdef CONFIG_CGROUP_NET_CLASSID struct cgroup_cls_state { struct cgroup_subsys_state css; u32 classid; }; struct cgroup_cls_state *task_cls_state(struct task_struct *p); static inline u32 task_cls_classid(struct task_struct *p) { u32 classid; if (in_interrupt()) return 0; rcu_read_lock(); classid = container_of(task_css(p, net_cls_cgrp_id), struct cgroup_cls_state, css)->classid; rcu_read_unlock(); return classid; } static inline void sock_update_classid(struct sock_cgroup_data *skcd) { u32 classid; classid = task_cls_classid(current); sock_cgroup_set_classid(skcd, classid); } static inline u32 __task_get_classid(struct task_struct *task) { return task_cls_state(task)->classid; } static inline u32 task_get_classid(const struct sk_buff *skb) { u32 classid = __task_get_classid(current); /* Due to the nature of the classifier it is required to ignore all * packets originating from softirq context as accessing `current' * would lead to false results. * * This test assumes that all callers of dev_queue_xmit() explicitly * disable bh. Knowing this, it is possible to detect softirq based * calls by looking at the number of nested bh disable calls because * softirqs always disables bh. */ if (softirq_count()) { struct sock *sk = skb_to_full_sk(skb); /* If there is an sock_cgroup_classid we'll use that. */ if (!sk || !sk_fullsock(sk)) return 0; classid = sock_cgroup_classid(&sk->sk_cgrp_data); } return classid; } #else /* !CONFIG_CGROUP_NET_CLASSID */ static inline void sock_update_classid(struct sock_cgroup_data *skcd) { } static inline u32 task_get_classid(const struct sk_buff *skb) { return 0; } #endif /* CONFIG_CGROUP_NET_CLASSID */ #endif /* _NET_CLS_CGROUP_H */ |
| 1 1 8 8 7 3 5 2 3 2 2 1 1 1 1 1 1 1 7 8 7 7 1 1 1 1 1 2 2 1 1 1 13 7 7 7 1 2 1 1 1 1 6 6 1 1 1 3 2 6 6 6 1 1 1 1 2 2 1 1 1 3 2 1 48 48 48 46 7 48 79 7 7 1 1 7 7 7 4 3 2 1 3 3 3 1 1 1 2 2 1 2 2 2 3 1 1 2 2 1 2 1 2 2 2 2 2 1 2 5 5 5 5 5 4 2 4 5 4 4 1 31 3 30 82 82 78 78 79 79 79 78 2 2 2 78 1 1 249 247 248 2 2 1 1 2 251 251 20 2 1 2 1 1 1 1 1 2 1 1 1 1 1 1 1 2 2 2 1 1 7 4 25 25 1 3 3 2 1 1 1 1 2 1 1 3 3 1 1 8 3 3 2 2 1 18 1 3 1 4 1 3 2 1 1 6 11 16 17 1 1 1 3 6 1 1 1 1 1 5 47 46 47 47 20 20 20 27 31 30 31 31 18 18 18 17 293 292 2 293 1 1 1 1 2 2 1 2 1 1 328 59 2 59 2 3 1 1 6 2 1 3 8 7 6 4 8 6 6 6 5 2 5 5 5 5 5 5 3 4 5 3 4 3 5 2 5 5 5 5 5 5 5 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * KVM Microsoft Hyper-V emulation * * derived from arch/x86/kvm/x86.c * * Copyright (C) 2006 Qumranet, Inc. * Copyright (C) 2008 Qumranet, Inc. * Copyright IBM Corporation, 2008 * Copyright 2010 Red Hat, Inc. and/or its affiliates. * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com> * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> * Amit Shah <amit.shah@qumranet.com> * Ben-Ami Yassour <benami@il.ibm.com> * Andrey Smetanin <asmetanin@virtuozzo.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "x86.h" #include "lapic.h" #include "ioapic.h" #include "cpuid.h" #include "hyperv.h" #include "mmu.h" #include "xen.h" #include <linux/cpu.h> #include <linux/kvm_host.h> #include <linux/highmem.h> #include <linux/sched/cputime.h> #include <linux/spinlock.h> #include <linux/eventfd.h> #include <asm/apicdef.h> #include <asm/mshyperv.h> #include <trace/events/kvm.h> #include "trace.h" #include "irq.h" #include "fpu.h" #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK) /* * As per Hyper-V TLFS, extended hypercalls start from 0x8001 * (HvExtCallQueryCapabilities). Response of this hypercalls is a 64 bit value * where each bit tells which extended hypercall is available besides * HvExtCallQueryCapabilities. * * 0x8001 - First extended hypercall, HvExtCallQueryCapabilities, no bit * assigned. * * 0x8002 - Bit 0 * 0x8003 - Bit 1 * .. * 0x8041 - Bit 63 * * Therefore, HV_EXT_CALL_MAX = 0x8001 + 64 */ #define HV_EXT_CALL_MAX (HV_EXT_CALL_QUERY_CAPABILITIES + 64) static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick); static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint) { return atomic64_read(&synic->sint[sint]); } static inline int synic_get_sint_vector(u64 sint_value) { if (sint_value & HV_SYNIC_SINT_MASKED) return -1; return sint_value & HV_SYNIC_SINT_VECTOR_MASK; } static bool synic_has_vector_connected(struct kvm_vcpu_hv_synic *synic, int vector) { int i; for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) return true; } return false; } static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic, int vector) { int i; u64 sint_value; for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { sint_value = synic_read_sint(synic, i); if (synic_get_sint_vector(sint_value) == vector && sint_value & HV_SYNIC_SINT_AUTO_EOI) return true; } return false; } static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, int vector) { struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); bool auto_eoi_old, auto_eoi_new; if (vector < HV_SYNIC_FIRST_VALID_VECTOR) return; if (synic_has_vector_connected(synic, vector)) __set_bit(vector, synic->vec_bitmap); else __clear_bit(vector, synic->vec_bitmap); auto_eoi_old = !bitmap_empty(synic->auto_eoi_bitmap, 256); if (synic_has_vector_auto_eoi(synic, vector)) __set_bit(vector, synic->auto_eoi_bitmap); else __clear_bit(vector, synic->auto_eoi_bitmap); auto_eoi_new = !bitmap_empty(synic->auto_eoi_bitmap, 256); if (auto_eoi_old == auto_eoi_new) return; if (!enable_apicv) return; down_write(&vcpu->kvm->arch.apicv_update_lock); if (auto_eoi_new) hv->synic_auto_eoi_used++; else hv->synic_auto_eoi_used--; /* * Inhibit APICv if any vCPU is using SynIC's AutoEOI, which relies on * the hypervisor to manually inject IRQs. */ __kvm_set_or_clear_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_HYPERV, !!hv->synic_auto_eoi_used); up_write(&vcpu->kvm->arch.apicv_update_lock); } static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, u64 data, bool host) { int vector, old_vector; bool masked; vector = data & HV_SYNIC_SINT_VECTOR_MASK; masked = data & HV_SYNIC_SINT_MASKED; /* * Valid vectors are 16-255, however, nested Hyper-V attempts to write * default '0x10000' value on boot and this should not #GP. We need to * allow zero-initing the register from host as well. */ if (vector < HV_SYNIC_FIRST_VALID_VECTOR && !host && !masked) return 1; /* * Guest may configure multiple SINTs to use the same vector, so * we maintain a bitmap of vectors handled by synic, and a * bitmap of vectors with auto-eoi behavior. The bitmaps are * updated here, and atomically queried on fast paths. */ old_vector = synic_read_sint(synic, sint) & HV_SYNIC_SINT_VECTOR_MASK; atomic64_set(&synic->sint[sint], data); synic_update_vector(synic, old_vector); synic_update_vector(synic, vector); /* Load SynIC vectors into EOI exit bitmap */ kvm_make_request(KVM_REQ_SCAN_IOAPIC, hv_synic_to_vcpu(synic)); return 0; } static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu = NULL; unsigned long i; if (vpidx >= KVM_MAX_VCPUS) return NULL; vcpu = kvm_get_vcpu(kvm, vpidx); if (vcpu && kvm_hv_get_vpindex(vcpu) == vpidx) return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) if (kvm_hv_get_vpindex(vcpu) == vpidx) return vcpu; return NULL; } static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu; struct kvm_vcpu_hv_synic *synic; vcpu = get_vcpu_by_vpidx(kvm, vpidx); if (!vcpu || !to_hv_vcpu(vcpu)) return NULL; synic = to_hv_synic(vcpu); return (synic->active) ? synic : NULL; } static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint) { struct kvm *kvm = vcpu->kvm; struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_stimer *stimer; int gsi, idx; trace_kvm_hv_notify_acked_sint(vcpu->vcpu_id, sint); /* Try to deliver pending Hyper-V SynIC timers messages */ for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) { stimer = &hv_vcpu->stimer[idx]; if (stimer->msg_pending && stimer->config.enable && !stimer->config.direct_mode && stimer->config.sintx == sint) stimer_mark_pending(stimer, false); } idx = srcu_read_lock(&kvm->irq_srcu); gsi = atomic_read(&synic->sint_to_gsi[sint]); if (gsi != -1) kvm_notify_acked_gsi(kvm, gsi); srcu_read_unlock(&kvm->irq_srcu, idx); } static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr) { struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC; hv_vcpu->exit.u.synic.msr = msr; hv_vcpu->exit.u.synic.control = synic->control; hv_vcpu->exit.u.synic.evt_page = synic->evt_page; hv_vcpu->exit.u.synic.msg_page = synic->msg_page; kvm_make_request(KVM_REQ_HV_EXIT, vcpu); } static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 data, bool host) { struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); int ret; if (!synic->active && (!host || data)) return 1; trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); ret = 0; switch (msr) { case HV_X64_MSR_SCONTROL: synic->control = data; if (!host) synic_exit(synic, msr); break; case HV_X64_MSR_SVERSION: if (!host) { ret = 1; break; } synic->version = data; break; case HV_X64_MSR_SIEFP: if ((data & HV_SYNIC_SIEFP_ENABLE) && !host && !synic->dont_zero_synic_pages) if (kvm_clear_guest(vcpu->kvm, data & PAGE_MASK, PAGE_SIZE)) { ret = 1; break; } synic->evt_page = data; if (!host) synic_exit(synic, msr); break; case HV_X64_MSR_SIMP: if ((data & HV_SYNIC_SIMP_ENABLE) && !host && !synic->dont_zero_synic_pages) if (kvm_clear_guest(vcpu->kvm, data & PAGE_MASK, PAGE_SIZE)) { ret = 1; break; } synic->msg_page = data; if (!host) synic_exit(synic, msr); break; case HV_X64_MSR_EOM: { int i; if (!synic->active) break; for (i = 0; i < ARRAY_SIZE(synic->sint); i++) kvm_hv_notify_acked_sint(vcpu, i); break; } case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: ret = synic_set_sint(synic, msr - HV_X64_MSR_SINT0, data, host); break; default: ret = 1; break; } return ret; } static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); return hv_vcpu->cpuid_cache.syndbg_cap_eax & HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; } static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu) { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL) hv->hv_syndbg.control.status = vcpu->run->hyperv.u.syndbg.status; return 1; } static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG; hv_vcpu->exit.u.syndbg.msr = msr; hv_vcpu->exit.u.syndbg.control = syndbg->control.control; hv_vcpu->exit.u.syndbg.send_page = syndbg->control.send_page; hv_vcpu->exit.u.syndbg.recv_page = syndbg->control.recv_page; hv_vcpu->exit.u.syndbg.pending_page = syndbg->control.pending_page; vcpu->arch.complete_userspace_io = kvm_hv_syndbg_complete_userspace; kvm_make_request(KVM_REQ_HV_EXIT, vcpu); } static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) return 1; trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id, to_hv_vcpu(vcpu)->vp_index, msr, data); switch (msr) { case HV_X64_MSR_SYNDBG_CONTROL: syndbg->control.control = data; if (!host) syndbg_exit(vcpu, msr); break; case HV_X64_MSR_SYNDBG_STATUS: syndbg->control.status = data; break; case HV_X64_MSR_SYNDBG_SEND_BUFFER: syndbg->control.send_page = data; break; case HV_X64_MSR_SYNDBG_RECV_BUFFER: syndbg->control.recv_page = data; break; case HV_X64_MSR_SYNDBG_PENDING_BUFFER: syndbg->control.pending_page = data; if (!host) syndbg_exit(vcpu, msr); break; case HV_X64_MSR_SYNDBG_OPTIONS: syndbg->options = data; break; default: break; } return 0; } static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) return 1; switch (msr) { case HV_X64_MSR_SYNDBG_CONTROL: *pdata = syndbg->control.control; break; case HV_X64_MSR_SYNDBG_STATUS: *pdata = syndbg->control.status; break; case HV_X64_MSR_SYNDBG_SEND_BUFFER: *pdata = syndbg->control.send_page; break; case HV_X64_MSR_SYNDBG_RECV_BUFFER: *pdata = syndbg->control.recv_page; break; case HV_X64_MSR_SYNDBG_PENDING_BUFFER: *pdata = syndbg->control.pending_page; break; case HV_X64_MSR_SYNDBG_OPTIONS: *pdata = syndbg->options; break; default: break; } trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id, kvm_hv_get_vpindex(vcpu), msr, *pdata); return 0; } static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata, bool host) { int ret; if (!synic->active && !host) return 1; ret = 0; switch (msr) { case HV_X64_MSR_SCONTROL: *pdata = synic->control; break; case HV_X64_MSR_SVERSION: *pdata = synic->version; break; case HV_X64_MSR_SIEFP: *pdata = synic->evt_page; break; case HV_X64_MSR_SIMP: *pdata = synic->msg_page; break; case HV_X64_MSR_EOM: *pdata = 0; break; case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: *pdata = atomic64_read(&synic->sint[msr - HV_X64_MSR_SINT0]); break; default: ret = 1; break; } return ret; } static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) { struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); struct kvm_lapic_irq irq; int ret, vector; if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm)) return -EINVAL; if (sint >= ARRAY_SIZE(synic->sint)) return -EINVAL; vector = synic_get_sint_vector(synic_read_sint(synic, sint)); if (vector < 0) return -ENOENT; memset(&irq, 0, sizeof(irq)); irq.shorthand = APIC_DEST_SELF; irq.dest_mode = APIC_DEST_PHYSICAL; irq.delivery_mode = APIC_DM_FIXED; irq.vector = vector; irq.level = 1; ret = kvm_irq_delivery_to_apic(vcpu->kvm, vcpu->arch.apic, &irq); trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret); return ret; } int kvm_hv_synic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { struct kvm_vcpu_hv_synic *synic; if (!level) return -1; synic = synic_get(kvm, e->hv_sint.vcpu); if (!synic) return -EINVAL; return synic_set_irq(synic, e->hv_sint.sint); } void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) { struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); int i; trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector); for (i = 0; i < ARRAY_SIZE(synic->sint); i++) if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) kvm_hv_notify_acked_sint(vcpu, i); } static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vpidx, u32 sint, int gsi) { struct kvm_vcpu_hv_synic *synic; synic = synic_get(kvm, vpidx); if (!synic) return -EINVAL; if (sint >= ARRAY_SIZE(synic->sint_to_gsi)) return -EINVAL; atomic_set(&synic->sint_to_gsi[sint], gsi); return 0; } void kvm_hv_irq_routing_update(struct kvm *kvm) { struct kvm_irq_routing_table *irq_rt; struct kvm_kernel_irq_routing_entry *e; u32 gsi; irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, lockdep_is_held(&kvm->irq_lock)); for (gsi = 0; gsi < irq_rt->nr_rt_entries; gsi++) { hlist_for_each_entry(e, &irq_rt->map[gsi], link) { if (e->type == KVM_IRQ_ROUTING_HV_SINT) kvm_hv_set_sint_gsi(kvm, e->hv_sint.vcpu, e->hv_sint.sint, gsi); } } } static void synic_init(struct kvm_vcpu_hv_synic *synic) { int i; memset(synic, 0, sizeof(*synic)); synic->version = HV_SYNIC_VERSION_1; for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { atomic64_set(&synic->sint[i], HV_SYNIC_SINT_MASKED); atomic_set(&synic->sint_to_gsi[i], -1); } } static u64 get_time_ref_counter(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; u64 tsc; /* * Fall back to get_kvmclock_ns() when TSC page hasn't been set up, * is broken, disabled or being updated. */ if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET) return div_u64(get_kvmclock_ns(kvm), 100); vcpu = kvm_get_vcpu(kvm, 0); tsc = kvm_read_l1_tsc(vcpu, rdtsc()); return mul_u64_u64_shr(tsc, hv->tsc_ref.tsc_scale, 64) + hv->tsc_ref.tsc_offset; } static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick) { struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); set_bit(stimer->index, to_hv_vcpu(vcpu)->stimer_pending_bitmap); kvm_make_request(KVM_REQ_HV_STIMER, vcpu); if (vcpu_kick) kvm_vcpu_kick(vcpu); } static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer) { struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); trace_kvm_hv_stimer_cleanup(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index); hrtimer_cancel(&stimer->timer); clear_bit(stimer->index, to_hv_vcpu(vcpu)->stimer_pending_bitmap); stimer->msg_pending = false; stimer->exp_time = 0; } static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer) { struct kvm_vcpu_hv_stimer *stimer; stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer); trace_kvm_hv_stimer_callback(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index); stimer_mark_pending(stimer, true); return HRTIMER_NORESTART; } /* * stimer_start() assumptions: * a) stimer->count is not equal to 0 * b) stimer->config has HV_STIMER_ENABLE flag */ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) { u64 time_now; ktime_t ktime_now; time_now = get_time_ref_counter(hv_stimer_to_vcpu(stimer)->kvm); ktime_now = ktime_get(); if (stimer->config.periodic) { if (stimer->exp_time) { if (time_now >= stimer->exp_time) { u64 remainder; div64_u64_rem(time_now - stimer->exp_time, stimer->count, &remainder); stimer->exp_time = time_now + (stimer->count - remainder); } } else stimer->exp_time = time_now + stimer->count; trace_kvm_hv_stimer_start_periodic( hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, time_now, stimer->exp_time); hrtimer_start(&stimer->timer, ktime_add_ns(ktime_now, 100 * (stimer->exp_time - time_now)), HRTIMER_MODE_ABS); return 0; } stimer->exp_time = stimer->count; if (time_now >= stimer->count) { /* * Expire timer according to Hypervisor Top-Level Functional * specification v4(15.3.1): * "If a one shot is enabled and the specified count is in * the past, it will expire immediately." */ stimer_mark_pending(stimer, false); return 0; } trace_kvm_hv_stimer_start_one_shot(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, time_now, stimer->count); hrtimer_start(&stimer->timer, ktime_add_ns(ktime_now, 100 * (stimer->count - time_now)), HRTIMER_MODE_ABS); return 0; } static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, bool host) { union hv_stimer_config new_config = {.as_uint64 = config}, old_config = {.as_uint64 = stimer->config.as_uint64}; struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); if (!synic->active && (!host || config)) return 1; if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode && !(hv_vcpu->cpuid_cache.features_edx & HV_STIMER_DIRECT_MODE_AVAILABLE))) return 1; trace_kvm_hv_stimer_set_config(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, config, host); stimer_cleanup(stimer); if (old_config.enable && !new_config.direct_mode && new_config.sintx == 0) new_config.enable = 0; stimer->config.as_uint64 = new_config.as_uint64; if (stimer->config.enable) stimer_mark_pending(stimer, false); return 0; } static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, bool host) { struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); if (!synic->active && (!host || count)) return 1; trace_kvm_hv_stimer_set_count(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, count, host); stimer_cleanup(stimer); stimer->count = count; if (!host) { if (stimer->count == 0) stimer->config.enable = 0; else if (stimer->config.auto_enable) stimer->config.enable = 1; } if (stimer->config.enable) stimer_mark_pending(stimer, false); return 0; } static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig) { *pconfig = stimer->config.as_uint64; return 0; } static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount) { *pcount = stimer->count; return 0; } static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint, struct hv_message *src_msg, bool no_retry) { struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); int msg_off = offsetof(struct hv_message_page, sint_message[sint]); gfn_t msg_page_gfn; struct hv_message_header hv_hdr; int r; if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE)) return -ENOENT; msg_page_gfn = synic->msg_page >> PAGE_SHIFT; /* * Strictly following the spec-mandated ordering would assume setting * .msg_pending before checking .message_type. However, this function * is only called in vcpu context so the entire update is atomic from * guest POV and thus the exact order here doesn't matter. */ r = kvm_vcpu_read_guest_page(vcpu, msg_page_gfn, &hv_hdr.message_type, msg_off + offsetof(struct hv_message, header.message_type), sizeof(hv_hdr.message_type)); if (r < 0) return r; if (hv_hdr.message_type != HVMSG_NONE) { if (no_retry) return 0; hv_hdr.message_flags.msg_pending = 1; r = kvm_vcpu_write_guest_page(vcpu, msg_page_gfn, &hv_hdr.message_flags, msg_off + offsetof(struct hv_message, header.message_flags), sizeof(hv_hdr.message_flags)); if (r < 0) return r; return -EAGAIN; } r = kvm_vcpu_write_guest_page(vcpu, msg_page_gfn, src_msg, msg_off, sizeof(src_msg->header) + src_msg->header.payload_size); if (r < 0) return r; r = synic_set_irq(synic, sint); if (r < 0) return r; if (r == 0) return -EFAULT; return 0; } static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer) { struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct hv_message *msg = &stimer->msg; struct hv_timer_message_payload *payload = (struct hv_timer_message_payload *)&msg->u.payload; /* * To avoid piling up periodic ticks, don't retry message * delivery for them (within "lazy" lost ticks policy). */ bool no_retry = stimer->config.periodic; payload->expiration_time = stimer->exp_time; payload->delivery_time = get_time_ref_counter(vcpu->kvm); return synic_deliver_msg(to_hv_synic(vcpu), stimer->config.sintx, msg, no_retry); } static int stimer_notify_direct(struct kvm_vcpu_hv_stimer *stimer) { struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct kvm_lapic_irq irq = { .delivery_mode = APIC_DM_FIXED, .vector = stimer->config.apic_vector }; if (lapic_in_kernel(vcpu)) return !kvm_apic_set_irq(vcpu, &irq, NULL); return 0; } static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) { int r, direct = stimer->config.direct_mode; stimer->msg_pending = true; if (!direct) r = stimer_send_msg(stimer); else r = stimer_notify_direct(stimer); trace_kvm_hv_stimer_expiration(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, direct, r); if (!r) { stimer->msg_pending = false; if (!(stimer->config.periodic)) stimer->config.enable = 0; } } void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_stimer *stimer; u64 time_now, exp_time; int i; if (!hv_vcpu) return; for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) { stimer = &hv_vcpu->stimer[i]; if (stimer->config.enable) { exp_time = stimer->exp_time; if (exp_time) { time_now = get_time_ref_counter(vcpu->kvm); if (time_now >= exp_time) stimer_expiration(stimer); } if ((stimer->config.enable) && stimer->count) { if (!stimer->msg_pending) stimer_start(stimer); } else stimer_cleanup(stimer); } } } void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); int i; if (!hv_vcpu) return; for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_cleanup(&hv_vcpu->stimer[i]); kfree(hv_vcpu); vcpu->arch.hyperv = NULL; } bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); if (!hv_vcpu) return false; if (!(hv_vcpu->hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) return false; return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_hv_assist_page_enabled); int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); if (!hv_vcpu || !kvm_hv_assist_page_enabled(vcpu)) return -EFAULT; return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, &hv_vcpu->vp_assist_page, sizeof(struct hv_vp_assist_page)); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_hv_get_assist_page); static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer) { struct hv_message *msg = &stimer->msg; struct hv_timer_message_payload *payload = (struct hv_timer_message_payload *)&msg->u.payload; memset(&msg->header, 0, sizeof(msg->header)); msg->header.message_type = HVMSG_TIMER_EXPIRED; msg->header.payload_size = sizeof(*payload); payload->timer_index = stimer->index; payload->expiration_time = 0; payload->delivery_time = 0; } static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index) { memset(stimer, 0, sizeof(*stimer)); stimer->index = timer_index; hrtimer_setup(&stimer->timer, stimer_timer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); stimer_prepare_msg(stimer); } int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); int i; if (hv_vcpu) return 0; hv_vcpu = kzalloc_obj(struct kvm_vcpu_hv, GFP_KERNEL_ACCOUNT); if (!hv_vcpu) return -ENOMEM; vcpu->arch.hyperv = hv_vcpu; hv_vcpu->vcpu = vcpu; synic_init(&hv_vcpu->synic); bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_init(&hv_vcpu->stimer[i], i); hv_vcpu->vp_index = vcpu->vcpu_idx; for (i = 0; i < HV_NR_TLB_FLUSH_FIFOS; i++) { INIT_KFIFO(hv_vcpu->tlb_flush_fifo[i].entries); spin_lock_init(&hv_vcpu->tlb_flush_fifo[i].write_lock); } return 0; } int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) { struct kvm_vcpu_hv_synic *synic; int r; r = kvm_hv_vcpu_init(vcpu); if (r) return r; synic = to_hv_synic(vcpu); synic->active = true; synic->dont_zero_synic_pages = dont_zero_synic_pages; synic->control = HV_SYNIC_CONTROL_ENABLE; return 0; } static bool kvm_hv_msr_partition_wide(u32 msr) { bool r = false; switch (msr) { case HV_X64_MSR_GUEST_OS_ID: case HV_X64_MSR_HYPERCALL: case HV_X64_MSR_REFERENCE_TSC: case HV_X64_MSR_TIME_REF_COUNT: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_RESET: case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: case HV_X64_MSR_TSC_INVARIANT_CONTROL: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: r = true; break; } return r; } static int kvm_hv_msr_get_crash_data(struct kvm *kvm, u32 index, u64 *pdata) { struct kvm_hv *hv = to_kvm_hv(kvm); size_t size = ARRAY_SIZE(hv->hv_crash_param); if (WARN_ON_ONCE(index >= size)) return -EINVAL; *pdata = hv->hv_crash_param[array_index_nospec(index, size)]; return 0; } static int kvm_hv_msr_get_crash_ctl(struct kvm *kvm, u64 *pdata) { struct kvm_hv *hv = to_kvm_hv(kvm); *pdata = hv->hv_crash_ctl; return 0; } static int kvm_hv_msr_set_crash_ctl(struct kvm *kvm, u64 data) { struct kvm_hv *hv = to_kvm_hv(kvm); hv->hv_crash_ctl = data & HV_CRASH_CTL_CRASH_NOTIFY; return 0; } static int kvm_hv_msr_set_crash_data(struct kvm *kvm, u32 index, u64 data) { struct kvm_hv *hv = to_kvm_hv(kvm); size_t size = ARRAY_SIZE(hv->hv_crash_param); if (WARN_ON_ONCE(index >= size)) return -EINVAL; hv->hv_crash_param[array_index_nospec(index, size)] = data; return 0; } /* * The kvmclock and Hyper-V TSC page use similar formulas, and converting * between them is possible: * * kvmclock formula: * nsec = (ticks - tsc_timestamp) * tsc_to_system_mul * 2^(tsc_shift-32) * + system_time * * Hyper-V formula: * nsec/100 = ticks * scale / 2^64 + offset * * When tsc_timestamp = system_time = 0, offset is zero in the Hyper-V formula. * By dividing the kvmclock formula by 100 and equating what's left we get: * ticks * scale / 2^64 = ticks * tsc_to_system_mul * 2^(tsc_shift-32) / 100 * scale / 2^64 = tsc_to_system_mul * 2^(tsc_shift-32) / 100 * scale = tsc_to_system_mul * 2^(32+tsc_shift) / 100 * * Now expand the kvmclock formula and divide by 100: * nsec = ticks * tsc_to_system_mul * 2^(tsc_shift-32) * - tsc_timestamp * tsc_to_system_mul * 2^(tsc_shift-32) * + system_time * nsec/100 = ticks * tsc_to_system_mul * 2^(tsc_shift-32) / 100 * - tsc_timestamp * tsc_to_system_mul * 2^(tsc_shift-32) / 100 * + system_time / 100 * * Replace tsc_to_system_mul * 2^(tsc_shift-32) / 100 by scale / 2^64: * nsec/100 = ticks * scale / 2^64 * - tsc_timestamp * scale / 2^64 * + system_time / 100 * * Equate with the Hyper-V formula so that ticks * scale / 2^64 cancels out: * offset = system_time / 100 - tsc_timestamp * scale / 2^64 * * These two equivalencies are implemented in this function. */ static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock, struct ms_hyperv_tsc_page *tsc_ref) { u64 max_mul; if (!(hv_clock->flags & PVCLOCK_TSC_STABLE_BIT)) return false; /* * check if scale would overflow, if so we use the time ref counter * tsc_to_system_mul * 2^(tsc_shift+32) / 100 >= 2^64 * tsc_to_system_mul / 100 >= 2^(32-tsc_shift) * tsc_to_system_mul >= 100 * 2^(32-tsc_shift) */ max_mul = 100ull << (32 - hv_clock->tsc_shift); if (hv_clock->tsc_to_system_mul >= max_mul) return false; /* * Otherwise compute the scale and offset according to the formulas * derived above. */ tsc_ref->tsc_scale = mul_u64_u32_div(1ULL << (32 + hv_clock->tsc_shift), hv_clock->tsc_to_system_mul, 100); tsc_ref->tsc_offset = hv_clock->system_time; do_div(tsc_ref->tsc_offset, 100); tsc_ref->tsc_offset -= mul_u64_u64_shr(hv_clock->tsc_timestamp, tsc_ref->tsc_scale, 64); return true; } /* * Don't touch TSC page values if the guest has opted for TSC emulation after * migration. KVM doesn't fully support reenlightenment notifications and TSC * access emulation and Hyper-V is known to expect the values in TSC page to * stay constant before TSC access emulation is disabled from guest side * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC * frequency and guest visible TSC value across migration (and prevent it when * TSC scaling is unsupported). */ static inline bool tsc_page_update_unsafe(struct kvm_hv *hv) { return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) && hv->hv_tsc_emulation_control; } void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock) { struct kvm_hv *hv = to_kvm_hv(kvm); u32 tsc_seq; u64 gfn; BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0); guard(mutex)(&hv->hv_lock); if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || hv->hv_tsc_page_status == HV_TSC_PAGE_SET || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) return; if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) return; gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; /* * Because the TSC parameters only vary when there is a * change in the master clock, do not bother with caching. */ if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn), &tsc_seq, sizeof(tsc_seq)))) goto out_err; if (tsc_seq && tsc_page_update_unsafe(hv)) { if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) goto out_err; hv->hv_tsc_page_status = HV_TSC_PAGE_SET; return; } /* * While we're computing and writing the parameters, force the * guest to use the time reference count MSR. */ hv->tsc_ref.tsc_sequence = 0; if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) goto out_err; if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref)) goto out_err; /* Ensure sequence is zero before writing the rest of the struct. */ smp_wmb(); if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) goto out_err; /* * Now switch to the TSC page mechanism by writing the sequence. */ tsc_seq++; if (tsc_seq == 0xFFFFFFFF || tsc_seq == 0) tsc_seq = 1; /* Write the struct entirely before the non-zero sequence. */ smp_wmb(); hv->tsc_ref.tsc_sequence = tsc_seq; if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) goto out_err; hv->hv_tsc_page_status = HV_TSC_PAGE_SET; return; out_err: hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; } void kvm_hv_request_tsc_page_update(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); mutex_lock(&hv->hv_lock); if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET && !tsc_page_update_unsafe(hv)) hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED; mutex_unlock(&hv->hv_lock); } static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) { if (!hv_vcpu->enforce_cpuid) return true; switch (msr) { case HV_X64_MSR_GUEST_OS_ID: case HV_X64_MSR_HYPERCALL: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_HYPERCALL_AVAILABLE; case HV_X64_MSR_VP_RUNTIME: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_VP_RUNTIME_AVAILABLE; case HV_X64_MSR_TIME_REF_COUNT: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_TIME_REF_COUNT_AVAILABLE; case HV_X64_MSR_VP_INDEX: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_VP_INDEX_AVAILABLE; case HV_X64_MSR_RESET: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_RESET_AVAILABLE; case HV_X64_MSR_REFERENCE_TSC: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_REFERENCE_TSC_AVAILABLE; case HV_X64_MSR_SCONTROL: case HV_X64_MSR_SVERSION: case HV_X64_MSR_SIEFP: case HV_X64_MSR_SIMP: case HV_X64_MSR_EOM: case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_SYNIC_AVAILABLE; case HV_X64_MSR_STIMER0_CONFIG: case HV_X64_MSR_STIMER1_CONFIG: case HV_X64_MSR_STIMER2_CONFIG: case HV_X64_MSR_STIMER3_CONFIG: case HV_X64_MSR_STIMER0_COUNT: case HV_X64_MSR_STIMER1_COUNT: case HV_X64_MSR_STIMER2_COUNT: case HV_X64_MSR_STIMER3_COUNT: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_SYNTIMER_AVAILABLE; case HV_X64_MSR_EOI: case HV_X64_MSR_ICR: case HV_X64_MSR_TPR: case HV_X64_MSR_VP_ASSIST_PAGE: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_APIC_ACCESS_AVAILABLE; case HV_X64_MSR_TSC_FREQUENCY: case HV_X64_MSR_APIC_FREQUENCY: return hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_FREQUENCY_MSRS; case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: return hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_REENLIGHTENMENT; case HV_X64_MSR_TSC_INVARIANT_CONTROL: return hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_TSC_INVARIANT; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: return hv_vcpu->cpuid_cache.features_edx & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return hv_vcpu->cpuid_cache.features_edx & HV_FEATURE_DEBUG_MSRS_AVAILABLE; default: break; } return false; } #define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839 #define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */ /* * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC * configuration. * Such configuration can result from, for example, AMD Erratum 1386 workaround. * * Print a notice so users aren't left wondering what's suddenly gone wrong. */ static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct kvm_hv *hv = to_kvm_hv(kvm); /* Check again under the hv_lock. */ if (hv->xsaves_xsavec_checked) return; if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) != KVM_HV_WIN2016_GUEST_ID) return; hv->xsaves_xsavec_checked = true; /* UP configurations aren't affected */ if (atomic_read(&kvm->online_vcpus) < 2) return; if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) || !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVEC)) return; pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. " "If it fails to boot try disabling XSAVEC in the VM config.\n"); } void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); if (!vcpu->arch.hyperv_enabled || hv->xsaves_xsavec_checked) return; mutex_lock(&hv->hv_lock); __kvm_hv_xsaves_xsavec_maybe_warn(vcpu); mutex_unlock(&hv->hv_lock); } static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm *kvm = vcpu->kvm; struct kvm_hv *hv = to_kvm_hv(kvm); if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr))) return 1; switch (msr) { case HV_X64_MSR_GUEST_OS_ID: hv->hv_guest_os_id = data; /* setting guest os id to zero disables hypercall page */ if (!hv->hv_guest_os_id) hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; break; case HV_X64_MSR_HYPERCALL: { u8 instructions[9]; int i = 0; u64 addr; /* if guest os id is not set hypercall should remain disabled */ if (!hv->hv_guest_os_id) break; if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { hv->hv_hypercall = data; break; } /* * If Xen and Hyper-V hypercalls are both enabled, disambiguate * the same way Xen itself does, by setting the bit 31 of EAX * which is RsvdZ in the 32-bit Hyper-V hypercall ABI and just * going to be clobbered on 64-bit. */ if (kvm_xen_hypercall_enabled(kvm)) { /* orl $0x80000000, %eax */ instructions[i++] = 0x0d; instructions[i++] = 0x00; instructions[i++] = 0x00; instructions[i++] = 0x00; instructions[i++] = 0x80; } /* vmcall/vmmcall */ kvm_x86_call(patch_hypercall)(vcpu, instructions + i); i += 3; /* ret */ ((unsigned char *)instructions)[i++] = 0xc3; addr = data & HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK; if (kvm_vcpu_write_guest(vcpu, addr, instructions, i)) return 1; hv->hv_hypercall = data; break; } case HV_X64_MSR_REFERENCE_TSC: hv->hv_tsc_page = data; if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) { if (!host) hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED; else hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED; kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); } else { hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET; } break; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: return kvm_hv_msr_set_crash_data(kvm, msr - HV_X64_MSR_CRASH_P0, data); case HV_X64_MSR_CRASH_CTL: if (host) return kvm_hv_msr_set_crash_ctl(kvm, data); if (data & HV_CRASH_CTL_CRASH_NOTIFY) { vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n", hv->hv_crash_param[0], hv->hv_crash_param[1], hv->hv_crash_param[2], hv->hv_crash_param[3], hv->hv_crash_param[4]); /* Send notification about crash to user space */ kvm_make_request(KVM_REQ_HV_CRASH, vcpu); } break; case HV_X64_MSR_RESET: if (data == 1) { vcpu_debug(vcpu, "hyper-v reset requested\n"); kvm_make_request(KVM_REQ_HV_RESET, vcpu); } break; case HV_X64_MSR_REENLIGHTENMENT_CONTROL: hv->hv_reenlightenment_control = data; break; case HV_X64_MSR_TSC_EMULATION_CONTROL: hv->hv_tsc_emulation_control = data; break; case HV_X64_MSR_TSC_EMULATION_STATUS: if (data && !host) return 1; hv->hv_tsc_emulation_status = data; break; case HV_X64_MSR_TIME_REF_COUNT: /* read-only, but still ignore it if host-initiated */ if (!host) return 1; break; case HV_X64_MSR_TSC_INVARIANT_CONTROL: /* Only bit 0 is supported */ if (data & ~HV_EXPOSE_INVARIANT_TSC) return 1; /* The feature can't be disabled from the guest */ if (!host && hv->hv_invtsc_control && !data) return 1; hv->hv_invtsc_control = data; break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_set_msr(vcpu, msr, data, host); default: kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } return 0; } /* Calculate cpu time spent by current task in 100ns units */ static u64 current_task_runtime_100ns(void) { u64 utime, stime; task_cputime_adjusted(current, &utime, &stime); return div_u64(utime + stime, 100); } static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr))) return 1; switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); u32 new_vp_index = (u32)data; if (!host || new_vp_index >= KVM_MAX_VCPUS) return 1; if (new_vp_index == hv_vcpu->vp_index) return 0; /* * The VP index is initialized to vcpu_index by * kvm_hv_vcpu_postcreate so they initially match. Now the * VP index is changing, adjust num_mismatched_vp_indexes if * it now matches or no longer matches vcpu_idx. */ if (hv_vcpu->vp_index == vcpu->vcpu_idx) atomic_inc(&hv->num_mismatched_vp_indexes); else if (new_vp_index == vcpu->vcpu_idx) atomic_dec(&hv->num_mismatched_vp_indexes); hv_vcpu->vp_index = new_vp_index; break; } case HV_X64_MSR_VP_ASSIST_PAGE: { u64 gfn; unsigned long addr; if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) { hv_vcpu->hv_vapic = data; if (kvm_lapic_set_pv_eoi(vcpu, 0, 0)) return 1; break; } gfn = data >> HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT; addr = kvm_vcpu_gfn_to_hva(vcpu, gfn); if (kvm_is_error_hva(addr)) return 1; /* * Clear apic_assist portion of struct hv_vp_assist_page * only, there can be valuable data in the rest which needs * to be preserved e.g. on migration. */ if (put_user(0, (u32 __user *)addr)) return 1; hv_vcpu->hv_vapic = data; kvm_vcpu_mark_page_dirty(vcpu, gfn); if (kvm_lapic_set_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED, sizeof(struct hv_vp_assist_page))) return 1; break; } case HV_X64_MSR_EOI: return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); case HV_X64_MSR_ICR: return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); case HV_X64_MSR_TPR: return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); case HV_X64_MSR_VP_RUNTIME: if (!host) return 1; hv_vcpu->runtime_offset = data - current_task_runtime_100ns(); break; case HV_X64_MSR_SCONTROL: case HV_X64_MSR_SVERSION: case HV_X64_MSR_SIEFP: case HV_X64_MSR_SIMP: case HV_X64_MSR_EOM: case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: return synic_set_msr(to_hv_synic(vcpu), msr, data, host); case HV_X64_MSR_STIMER0_CONFIG: case HV_X64_MSR_STIMER1_CONFIG: case HV_X64_MSR_STIMER2_CONFIG: case HV_X64_MSR_STIMER3_CONFIG: { int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; return stimer_set_config(to_hv_stimer(vcpu, timer_index), data, host); } case HV_X64_MSR_STIMER0_COUNT: case HV_X64_MSR_STIMER1_COUNT: case HV_X64_MSR_STIMER2_COUNT: case HV_X64_MSR_STIMER3_COUNT: { int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; return stimer_set_count(to_hv_stimer(vcpu, timer_index), data, host); } case HV_X64_MSR_TSC_FREQUENCY: case HV_X64_MSR_APIC_FREQUENCY: /* read-only, but still ignore it if host-initiated */ if (!host) return 1; break; default: kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } return 0; } static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data = 0; struct kvm *kvm = vcpu->kvm; struct kvm_hv *hv = to_kvm_hv(kvm); if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr))) return 1; switch (msr) { case HV_X64_MSR_GUEST_OS_ID: data = hv->hv_guest_os_id; break; case HV_X64_MSR_HYPERCALL: data = hv->hv_hypercall; break; case HV_X64_MSR_TIME_REF_COUNT: data = get_time_ref_counter(kvm); break; case HV_X64_MSR_REFERENCE_TSC: data = hv->hv_tsc_page; break; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: return kvm_hv_msr_get_crash_data(kvm, msr - HV_X64_MSR_CRASH_P0, pdata); case HV_X64_MSR_CRASH_CTL: return kvm_hv_msr_get_crash_ctl(kvm, pdata); case HV_X64_MSR_RESET: data = 0; break; case HV_X64_MSR_REENLIGHTENMENT_CONTROL: data = hv->hv_reenlightenment_control; break; case HV_X64_MSR_TSC_EMULATION_CONTROL: data = hv->hv_tsc_emulation_control; break; case HV_X64_MSR_TSC_EMULATION_STATUS: data = hv->hv_tsc_emulation_status; break; case HV_X64_MSR_TSC_INVARIANT_CONTROL: data = hv->hv_invtsc_control; break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_get_msr(vcpu, msr, pdata, host); default: kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } *pdata = data; return 0; } static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data = 0; struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr))) return 1; switch (msr) { case HV_X64_MSR_VP_INDEX: data = hv_vcpu->vp_index; break; case HV_X64_MSR_EOI: return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); case HV_X64_MSR_ICR: return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); case HV_X64_MSR_TPR: return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); case HV_X64_MSR_VP_ASSIST_PAGE: data = hv_vcpu->hv_vapic; break; case HV_X64_MSR_VP_RUNTIME: data = current_task_runtime_100ns() + hv_vcpu->runtime_offset; break; case HV_X64_MSR_SCONTROL: case HV_X64_MSR_SVERSION: case HV_X64_MSR_SIEFP: case HV_X64_MSR_SIMP: case HV_X64_MSR_EOM: case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: return synic_get_msr(to_hv_synic(vcpu), msr, pdata, host); case HV_X64_MSR_STIMER0_CONFIG: case HV_X64_MSR_STIMER1_CONFIG: case HV_X64_MSR_STIMER2_CONFIG: case HV_X64_MSR_STIMER3_CONFIG: { int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; return stimer_get_config(to_hv_stimer(vcpu, timer_index), pdata); } case HV_X64_MSR_STIMER0_COUNT: case HV_X64_MSR_STIMER1_COUNT: case HV_X64_MSR_STIMER2_COUNT: case HV_X64_MSR_STIMER3_COUNT: { int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; return stimer_get_count(to_hv_stimer(vcpu, timer_index), pdata); } case HV_X64_MSR_TSC_FREQUENCY: data = (u64)vcpu->arch.virtual_tsc_khz * 1000; break; case HV_X64_MSR_APIC_FREQUENCY: data = div64_u64(1000000000ULL, vcpu->kvm->arch.apic_bus_cycle_ns); break; default: kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } *pdata = data; return 0; } int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); if (!host && !vcpu->arch.hyperv_enabled) return 1; if (kvm_hv_vcpu_init(vcpu)) return 1; if (kvm_hv_msr_partition_wide(msr)) { int r; mutex_lock(&hv->hv_lock); r = kvm_hv_set_msr_pw(vcpu, msr, data, host); mutex_unlock(&hv->hv_lock); return r; } else return kvm_hv_set_msr(vcpu, msr, data, host); } int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); if (!host && !vcpu->arch.hyperv_enabled) return 1; if (kvm_hv_vcpu_init(vcpu)) return 1; if (kvm_hv_msr_partition_wide(msr)) { int r; mutex_lock(&hv->hv_lock); r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host); mutex_unlock(&hv->hv_lock); return r; } else return kvm_hv_get_msr(vcpu, msr, pdata, host); } static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks, u64 valid_bank_mask, unsigned long *vcpu_mask) { struct kvm_hv *hv = to_kvm_hv(kvm); bool has_mismatch = atomic_read(&hv->num_mismatched_vp_indexes); u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; struct kvm_vcpu *vcpu; int bank, sbank = 0; unsigned long i; u64 *bitmap; BUILD_BUG_ON(sizeof(vp_bitmap) > sizeof(*vcpu_mask) * BITS_TO_LONGS(KVM_MAX_VCPUS)); /* * If vp_index == vcpu_idx for all vCPUs, fill vcpu_mask directly, else * fill a temporary buffer and manually test each vCPU's VP index. */ if (likely(!has_mismatch)) bitmap = (u64 *)vcpu_mask; else bitmap = vp_bitmap; /* * Each set of 64 VPs is packed into sparse_banks, with valid_bank_mask * having a '1' for each bank that exists in sparse_banks. Sets must * be in ascending order, i.e. bank0..bankN. */ memset(bitmap, 0, sizeof(vp_bitmap)); for_each_set_bit(bank, (unsigned long *)&valid_bank_mask, KVM_HV_MAX_SPARSE_VCPU_SET_BITS) bitmap[bank] = sparse_banks[sbank++]; if (likely(!has_mismatch)) return; bitmap_zero(vcpu_mask, KVM_MAX_VCPUS); kvm_for_each_vcpu(i, vcpu, kvm) { if (test_bit(kvm_hv_get_vpindex(vcpu), (unsigned long *)vp_bitmap)) __set_bit(i, vcpu_mask); } } static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_banks[]) { int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK; unsigned long sbank; BUILD_BUG_ON(BITS_PER_TYPE(valid_bank_mask) != HV_MAX_SPARSE_VCPU_BANKS); if (valid_bit_nr >= HV_MAX_SPARSE_VCPU_BANKS) return false; if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask)) return false; /* * The index into the sparse bank is the number of preceding bits in * the valid mask. Optimize for VMs with <64 vCPUs by skipping the * fancy math if there can't possibly be preceding bits. */ if (valid_bit_nr) sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr - 1, 0)); else sbank = 0; return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK, (unsigned long *)&sparse_banks[sbank]); } struct kvm_hv_hcall { /* Hypercall input data */ u64 param; u64 ingpa; u64 outgpa; u16 code; u16 var_cnt; u16 rep_cnt; u16 rep_idx; bool fast; bool rep; sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; /* * Current read offset when KVM reads hypercall input data gradually, * either offset in bytes from 'ingpa' for regular hypercalls or the * number of already consumed 'XMM halves' for 'fast' hypercalls. */ union { gpa_t data_offset; int consumed_xmm_halves; }; }; static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, u16 orig_cnt, u16 cnt_cap, u64 *data) { /* * Preserve the original count when ignoring entries via a "cap", KVM * still needs to validate the guest input (though the non-XMM path * punts on the checks). */ u16 cnt = min(orig_cnt, cnt_cap); int i, j; if (hc->fast) { /* * Each XMM holds two sparse banks, but do not count halves that * have already been consumed for hypercall parameters. */ if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves) return HV_STATUS_INVALID_HYPERCALL_INPUT; for (i = 0; i < cnt; i++) { j = i + hc->consumed_xmm_halves; if (j % 2) data[i] = sse128_hi(hc->xmm[j / 2]); else data[i] = sse128_lo(hc->xmm[j / 2]); } return 0; } return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data, cnt * sizeof(*data)); } static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 *sparse_banks) { if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS) return -EINVAL; /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */ return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS, sparse_banks); } static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[]) { return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries); } static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu, struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo, u64 *entries, int count) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); u64 flush_all_entry = KVM_HV_TLB_FLUSHALL_ENTRY; if (!hv_vcpu) return; spin_lock(&tlb_flush_fifo->write_lock); /* * All entries should fit on the fifo leaving one free for 'flush all' * entry in case another request comes in. In case there's not enough * space, just put 'flush all' entry there. */ if (count && entries && count < kfifo_avail(&tlb_flush_fifo->entries)) { WARN_ON(kfifo_in(&tlb_flush_fifo->entries, entries, count) != count); goto out_unlock; } /* * Note: full fifo always contains 'flush all' entry, no need to check the * return value. */ kfifo_in(&tlb_flush_fifo->entries, &flush_all_entry, 1); out_unlock: spin_unlock(&tlb_flush_fifo->write_lock); } int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); u64 entries[KVM_HV_TLB_FLUSH_FIFO_SIZE]; int i, j, count; gva_t gva; if (!tdp_enabled || !hv_vcpu) return -EINVAL; tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu)); count = kfifo_out(&tlb_flush_fifo->entries, entries, KVM_HV_TLB_FLUSH_FIFO_SIZE); for (i = 0; i < count; i++) { if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) goto out_flush_all; /* * Lower 12 bits of 'address' encode the number of additional * pages to flush. */ gva = entries[i] & PAGE_MASK; for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) { if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu)) continue; kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE); } ++vcpu->stat.tlb_flush; } return 0; out_flush_all: kfifo_reset_out(&tlb_flush_fifo->entries); /* Fall back to full flush. */ return -ENOSPC; } static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); unsigned long *vcpu_mask = hv_vcpu->vcpu_mask; u64 *sparse_banks = hv_vcpu->sparse_banks; struct kvm *kvm = vcpu->kvm; struct hv_tlb_flush_ex flush_ex; struct hv_tlb_flush flush; struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; /* * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE' * entries on the TLB flush fifo. The last entry, however, needs to be * always left free for 'flush all' entry which gets placed when * there is not enough space to put all the requested entries. */ u64 __tlb_flush_entries[KVM_HV_TLB_FLUSH_FIFO_SIZE - 1]; u64 *tlb_flush_entries; u64 valid_bank_mask; struct kvm_vcpu *v; unsigned long i; bool all_cpus; /* * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS * sparse banks. Fail the build if KVM's max allowed number of * vCPUs (>4096) exceeds this limit. */ BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > HV_MAX_SPARSE_VCPU_BANKS); /* * 'Slow' hypercall's first parameter is the address in guest's memory * where hypercall parameters are placed. This is either a GPA or a * nested GPA when KVM is handling the call from L2 ('direct' TLB * flush). Translate the address here so the memory can be uniformly * read with kvm_read_guest(). */ if (!hc->fast && mmu_is_nested(vcpu)) { hc->ingpa = kvm_x86_ops.nested_ops->translate_nested_gpa( vcpu, hc->ingpa, PFERR_GUEST_FINAL_MASK, NULL, 0); if (unlikely(hc->ingpa == INVALID_GPA)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST || hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) { if (hc->fast) { flush.address_space = hc->ingpa; flush.flags = hc->outgpa; flush.processor_mask = sse128_lo(hc->xmm[0]); hc->consumed_xmm_halves = 1; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush, sizeof(flush)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; hc->data_offset = sizeof(flush); } trace_kvm_hv_flush_tlb(flush.processor_mask, flush.address_space, flush.flags, is_guest_mode(vcpu)); valid_bank_mask = BIT_ULL(0); sparse_banks[0] = flush.processor_mask; /* * Work around possible WS2012 bug: it sends hypercalls * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear, * while also expecting us to flush something and crashing if * we don't. Let's treat processor_mask == 0 same as * HV_FLUSH_ALL_PROCESSORS. */ all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) || flush.processor_mask == 0; } else { if (hc->fast) { flush_ex.address_space = hc->ingpa; flush_ex.flags = hc->outgpa; memcpy(&flush_ex.hv_vp_set, &hc->xmm[0], sizeof(hc->xmm[0])); hc->consumed_xmm_halves = 2; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, sizeof(flush_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; hc->data_offset = sizeof(flush_ex); } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, flush_ex.hv_vp_set.format, flush_ex.address_space, flush_ex.flags, is_guest_mode(vcpu)); valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask; all_cpus = flush_ex.hv_vp_set.format != HV_GENERIC_SET_SPARSE_4K; if (hc->var_cnt != hweight64(valid_bank_mask)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (!all_cpus) { if (!hc->var_cnt) goto ret_success; if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } /* * Hyper-V TLFS doesn't explicitly forbid non-empty sparse vCPU * banks (and, thus, non-zero 'var_cnt') for the 'all vCPUs' * case (HV_GENERIC_SET_ALL). Always adjust data_offset and * consumed_xmm_halves to make sure TLB flush entries are read * from the correct offset. */ if (hc->fast) hc->consumed_xmm_halves += hc->var_cnt; else hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]); } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX || hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) { tlb_flush_entries = NULL; } else { if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries)) return HV_STATUS_INVALID_HYPERCALL_INPUT; tlb_flush_entries = __tlb_flush_entries; } /* * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ if (all_cpus && !is_guest_mode(vcpu)) { kvm_for_each_vcpu(i, v, kvm) { tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false); hv_tlb_flush_enqueue(v, tlb_flush_fifo, tlb_flush_entries, hc->rep_cnt); } kvm_make_all_cpus_request(kvm, KVM_REQ_HV_TLB_FLUSH); } else if (!is_guest_mode(vcpu)) { sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask); for_each_set_bit(i, vcpu_mask, KVM_MAX_VCPUS) { v = kvm_get_vcpu(kvm, i); if (!v) continue; tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false); hv_tlb_flush_enqueue(v, tlb_flush_fifo, tlb_flush_entries, hc->rep_cnt); } kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask); } else { struct kvm_vcpu_hv *hv_v; bitmap_zero(vcpu_mask, KVM_MAX_VCPUS); kvm_for_each_vcpu(i, v, kvm) { hv_v = to_hv_vcpu(v); /* * The following check races with nested vCPUs entering/exiting * and/or migrating between L1's vCPUs, however the only case when * KVM *must* flush the TLB is when the target L2 vCPU keeps * running on the same L1 vCPU from the moment of the request until * kvm_hv_flush_tlb() returns. TLB is fully flushed in all other * cases, e.g. when the target L2 vCPU migrates to a different L1 * vCPU or when the corresponding L1 vCPU temporary switches to a * different L2 vCPU while the request is being processed. */ if (!hv_v || hv_v->nested.vm_id != hv_vcpu->nested.vm_id) continue; if (!all_cpus && !hv_is_vp_in_sparse_set(hv_v->nested.vp_id, valid_bank_mask, sparse_banks)) continue; __set_bit(i, vcpu_mask); tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, true); hv_tlb_flush_enqueue(v, tlb_flush_fifo, tlb_flush_entries, hc->rep_cnt); } kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask); } ret_success: /* We always do full TLB flush, set 'Reps completed' = 'Rep Count' */ return (u64)HV_STATUS_SUCCESS | ((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); } static void kvm_hv_send_ipi_to_many(struct kvm *kvm, u32 vector, u64 *sparse_banks, u64 valid_bank_mask) { struct kvm_lapic_irq irq = { .delivery_mode = APIC_DM_FIXED, .vector = vector }; struct kvm_vcpu *vcpu; unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (sparse_banks && !hv_is_vp_in_sparse_set(kvm_hv_get_vpindex(vcpu), valid_bank_mask, sparse_banks)) continue; /* We fail only when APIC is disabled */ kvm_apic_set_irq(vcpu, &irq, NULL); } } static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); u64 *sparse_banks = hv_vcpu->sparse_banks; struct kvm *kvm = vcpu->kvm; struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; u64 valid_bank_mask; u32 vector; bool all_cpus; if (!lapic_in_kernel(vcpu)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (hc->code == HVCALL_SEND_IPI) { if (!hc->fast) { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi, sizeof(send_ipi)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; sparse_banks[0] = send_ipi.cpu_mask; vector = send_ipi.vector; } else { /* 'reserved' part of hv_send_ipi should be 0 */ if (unlikely(hc->ingpa >> 32 != 0)) return HV_STATUS_INVALID_HYPERCALL_INPUT; sparse_banks[0] = hc->outgpa; vector = (u32)hc->ingpa; } all_cpus = false; valid_bank_mask = BIT_ULL(0); trace_kvm_hv_send_ipi(vector, sparse_banks[0]); } else { if (!hc->fast) { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex, sizeof(send_ipi_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; } else { send_ipi_ex.vector = (u32)hc->ingpa; send_ipi_ex.vp_set.format = hc->outgpa; send_ipi_ex.vp_set.valid_bank_mask = sse128_lo(hc->xmm[0]); } trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector, send_ipi_ex.vp_set.format, send_ipi_ex.vp_set.valid_bank_mask); vector = send_ipi_ex.vector; valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask; all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; if (hc->var_cnt != hweight64(valid_bank_mask)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) goto check_and_send_ipi; if (!hc->var_cnt) goto ret_success; if (!hc->fast) hc->data_offset = offsetof(struct hv_send_ipi_ex, vp_set.bank_contents); else hc->consumed_xmm_halves = 1; if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } check_and_send_ipi: if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) kvm_hv_send_ipi_to_many(kvm, vector, NULL, 0); else kvm_hv_send_ipi_to_many(kvm, vector, sparse_banks, valid_bank_mask); ret_success: return HV_STATUS_SUCCESS; } void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_cpuid_entry2 *entry; vcpu->arch.hyperv_enabled = hyperv_enabled; if (!hv_vcpu) { /* * KVM should have already allocated kvm_vcpu_hv if Hyper-V is * enabled in CPUID. */ WARN_ON_ONCE(vcpu->arch.hyperv_enabled); return; } memset(&hv_vcpu->cpuid_cache, 0, sizeof(hv_vcpu->cpuid_cache)); if (!vcpu->arch.hyperv_enabled) return; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); if (entry) { hv_vcpu->cpuid_cache.features_eax = entry->eax; hv_vcpu->cpuid_cache.features_ebx = entry->ebx; hv_vcpu->cpuid_cache.features_edx = entry->edx; } entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); if (entry) { hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax; hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx; } entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); if (entry) hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_NESTED_FEATURES); if (entry) { hv_vcpu->cpuid_cache.nested_eax = entry->eax; hv_vcpu->cpuid_cache.nested_ebx = entry->ebx; } } int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce) { struct kvm_vcpu_hv *hv_vcpu; int ret = 0; if (!to_hv_vcpu(vcpu)) { if (enforce) { ret = kvm_hv_vcpu_init(vcpu); if (ret) return ret; } else { return 0; } } hv_vcpu = to_hv_vcpu(vcpu); hv_vcpu->enforce_cpuid = enforce; return ret; } static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) { bool longmode; longmode = is_64_bit_hypercall(vcpu); if (longmode) kvm_rax_write_raw(vcpu, result); else { kvm_edx_write(vcpu, result >> 32); kvm_eax_write(vcpu, result); } } static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result) { u32 tlb_lock_count = 0; int ret; if (hv_result_success(result) && is_guest_mode(vcpu) && kvm_hv_is_tlb_flush_hcall(vcpu) && kvm_read_guest(vcpu->kvm, to_hv_vcpu(vcpu)->nested.pa_page_gpa, &tlb_lock_count, sizeof(tlb_lock_count))) result = HV_STATUS_INVALID_HYPERCALL_INPUT; trace_kvm_hv_hypercall_done(result); kvm_hv_hypercall_set_result(vcpu, result); ++vcpu->stat.hypercalls; ret = kvm_skip_emulated_instruction(vcpu); if (tlb_lock_count) kvm_x86_ops.nested_ops->hv_inject_synthetic_vmexit_post_tlb_flush(vcpu); return ret; } static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) { return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result); } static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); struct eventfd_ctx *eventfd; if (unlikely(!hc->fast)) { int ret; gpa_t gpa = hc->ingpa; if ((gpa & (__alignof__(hc->ingpa) - 1)) || offset_in_page(gpa) + sizeof(hc->ingpa) > PAGE_SIZE) return HV_STATUS_INVALID_ALIGNMENT; ret = kvm_vcpu_read_guest(vcpu, gpa, &hc->ingpa, sizeof(hc->ingpa)); if (ret < 0) return HV_STATUS_INVALID_ALIGNMENT; } /* * Per spec, bits 32-47 contain the extra "flag number". However, we * have no use for it, and in all known usecases it is zero, so just * report lookup failure if it isn't. */ if (hc->ingpa & 0xffff00000000ULL) return HV_STATUS_INVALID_PORT_ID; /* remaining bits are reserved-zero */ if (hc->ingpa & ~KVM_HYPERV_CONN_ID_MASK) return HV_STATUS_INVALID_HYPERCALL_INPUT; /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */ rcu_read_lock(); eventfd = idr_find(&hv->conn_to_evt, hc->ingpa); rcu_read_unlock(); if (!eventfd) return HV_STATUS_INVALID_PORT_ID; eventfd_signal(eventfd); return HV_STATUS_SUCCESS; } static bool is_xmm_fast_hypercall(struct kvm_hv_hcall *hc) { switch (hc->code) { case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: case HVCALL_SEND_IPI_EX: return true; } return false; } static void kvm_hv_hypercall_read_xmm(struct kvm_hv_hcall *hc) { int reg; kvm_fpu_get(); for (reg = 0; reg < HV_HYPERCALL_MAX_XMM_REGISTERS; reg++) _kvm_read_sse_reg(reg, &hc->xmm[reg]); kvm_fpu_put(); } static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) { if (!hv_vcpu->enforce_cpuid) return true; switch (code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: return hv_vcpu->cpuid_cache.enlightenments_ebx && hv_vcpu->cpuid_cache.enlightenments_ebx != U32_MAX; case HVCALL_POST_MESSAGE: return hv_vcpu->cpuid_cache.features_ebx & HV_POST_MESSAGES; case HVCALL_SIGNAL_EVENT: return hv_vcpu->cpuid_cache.features_ebx & HV_SIGNAL_EVENTS; case HVCALL_POST_DEBUG_DATA: case HVCALL_RETRIEVE_DEBUG_DATA: case HVCALL_RESET_DEBUG_SESSION: /* * Return 'true' when SynDBG is disabled so the resulting code * will be HV_STATUS_INVALID_HYPERCALL_CODE. */ return !kvm_hv_is_syndbg_enabled(hv_vcpu->vcpu) || hv_vcpu->cpuid_cache.features_ebx & HV_DEBUGGING; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: if (!(hv_vcpu->cpuid_cache.enlightenments_eax & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) return false; fallthrough; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: return hv_vcpu->cpuid_cache.enlightenments_eax & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; case HVCALL_SEND_IPI_EX: if (!(hv_vcpu->cpuid_cache.enlightenments_eax & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) return false; fallthrough; case HVCALL_SEND_IPI: return hv_vcpu->cpuid_cache.enlightenments_eax & HV_X64_CLUSTER_IPI_RECOMMENDED; case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: return hv_vcpu->cpuid_cache.features_ebx & HV_ENABLE_EXTENDED_HYPERCALLS; default: break; } return true; } int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_hv_hcall hc; u64 ret = HV_STATUS_SUCCESS; /* * hypercall generates UD from non zero cpl and real mode * per HYPER-V spec */ if (kvm_x86_call(get_cpl)(vcpu) != 0 || !is_protmode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } #ifdef CONFIG_X86_64 if (is_64_bit_hypercall(vcpu)) { hc.param = kvm_rcx_read_raw(vcpu); hc.ingpa = kvm_rdx_read_raw(vcpu); hc.outgpa = kvm_r8_read_raw(vcpu); } else #endif { hc.param = ((u64)kvm_edx_read(vcpu) << 32) | kvm_eax_read(vcpu); hc.ingpa = ((u64)kvm_ebx_read(vcpu) << 32) | kvm_ecx_read(vcpu); hc.outgpa = ((u64)kvm_edi_read(vcpu) << 32) | kvm_esi_read(vcpu); } hc.code = hc.param & 0xffff; hc.var_cnt = (hc.param & HV_HYPERCALL_VARHEAD_MASK) >> HV_HYPERCALL_VARHEAD_OFFSET; hc.fast = !!(hc.param & HV_HYPERCALL_FAST_BIT); hc.rep_cnt = (hc.param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff; hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; hc.rep = !!(hc.rep_cnt || hc.rep_idx); trace_kvm_hv_hypercall(hc.code, hc.fast, hc.var_cnt, hc.rep_cnt, hc.rep_idx, hc.ingpa, hc.outgpa); if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) { ret = HV_STATUS_ACCESS_DENIED; goto hypercall_complete; } if (unlikely(hc.param & HV_HYPERCALL_RSVD_MASK)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; goto hypercall_complete; } if (hc.fast && is_xmm_fast_hypercall(&hc)) { if (unlikely(hv_vcpu->enforce_cpuid && !(hv_vcpu->cpuid_cache.features_edx & HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } kvm_hv_hypercall_read_xmm(&hc); } switch (hc.code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: if (unlikely(hc.rep || hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } kvm_vcpu_on_spin(vcpu, true); break; case HVCALL_SIGNAL_EVENT: if (unlikely(hc.rep || hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } ret = kvm_hvcall_signal_event(vcpu, &hc); if (ret != HV_STATUS_INVALID_PORT_ID) break; fallthrough; /* maybe userspace knows this conn_id */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ if (unlikely(hc.rep || hc.var_cnt || !to_hv_synic(vcpu)->active)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } goto hypercall_userspace_exit; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: if (unlikely(hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } fallthrough; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: if (unlikely(!hc.rep_cnt || hc.rep_idx)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } ret = kvm_hv_flush_tlb(vcpu, &hc); break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: if (unlikely(hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } fallthrough; case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } ret = kvm_hv_flush_tlb(vcpu, &hc); break; case HVCALL_SEND_IPI: if (unlikely(hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } fallthrough; case HVCALL_SEND_IPI_EX: if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } ret = kvm_hv_send_ipi(vcpu, &hc); break; case HVCALL_POST_DEBUG_DATA: case HVCALL_RETRIEVE_DEBUG_DATA: if (unlikely(hc.fast)) { ret = HV_STATUS_INVALID_PARAMETER; break; } fallthrough; case HVCALL_RESET_DEBUG_SESSION: { struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); if (!kvm_hv_is_syndbg_enabled(vcpu)) { ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; } if (!(syndbg->options & HV_X64_SYNDBG_OPTION_USE_HCALLS)) { ret = HV_STATUS_OPERATION_DENIED; break; } goto hypercall_userspace_exit; } case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: if (unlikely(hc.fast)) { ret = HV_STATUS_INVALID_PARAMETER; break; } goto hypercall_userspace_exit; default: ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; } hypercall_complete: return kvm_hv_hypercall_complete(vcpu, ret); hypercall_userspace_exit: vcpu->run->exit_reason = KVM_EXIT_HYPERV; vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; vcpu->run->hyperv.u.hcall.input = hc.param; vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; return 0; } void kvm_hv_init_vm(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); mutex_init(&hv->hv_lock); idr_init(&hv->conn_to_evt); } void kvm_hv_destroy_vm(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); struct eventfd_ctx *eventfd; int i; idr_for_each_entry(&hv->conn_to_evt, eventfd, i) eventfd_ctx_put(eventfd); idr_destroy(&hv->conn_to_evt); } static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd) { struct kvm_hv *hv = to_kvm_hv(kvm); struct eventfd_ctx *eventfd; int ret; eventfd = eventfd_ctx_fdget(fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); mutex_lock(&hv->hv_lock); ret = idr_alloc(&hv->conn_to_evt, eventfd, conn_id, conn_id + 1, GFP_KERNEL_ACCOUNT); mutex_unlock(&hv->hv_lock); if (ret >= 0) return 0; if (ret == -ENOSPC) ret = -EEXIST; eventfd_ctx_put(eventfd); return ret; } static int kvm_hv_eventfd_deassign(struct kvm *kvm, u32 conn_id) { struct kvm_hv *hv = to_kvm_hv(kvm); struct eventfd_ctx *eventfd; mutex_lock(&hv->hv_lock); eventfd = idr_remove(&hv->conn_to_evt, conn_id); mutex_unlock(&hv->hv_lock); if (!eventfd) return -ENOENT; synchronize_srcu(&kvm->srcu); eventfd_ctx_put(eventfd); return 0; } int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args) { if ((args->flags & ~KVM_HYPERV_EVENTFD_DEASSIGN) || (args->conn_id & ~KVM_HYPERV_CONN_ID_MASK)) return -EINVAL; if (args->flags == KVM_HYPERV_EVENTFD_DEASSIGN) return kvm_hv_eventfd_deassign(kvm, args->conn_id); return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd); } int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { uint16_t evmcs_ver = 0; struct kvm_cpuid_entry2 cpuid_entries[] = { { .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS }, { .function = HYPERV_CPUID_INTERFACE }, { .function = HYPERV_CPUID_VERSION }, { .function = HYPERV_CPUID_FEATURES }, { .function = HYPERV_CPUID_ENLIGHTMENT_INFO }, { .function = HYPERV_CPUID_IMPLEMENT_LIMITS }, { .function = HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS }, { .function = HYPERV_CPUID_SYNDBG_INTERFACE }, { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }, { .function = HYPERV_CPUID_NESTED_FEATURES }, }; int i, nent = ARRAY_SIZE(cpuid_entries); if (kvm_x86_ops.nested_ops->get_evmcs_version) evmcs_ver = kvm_x86_ops.nested_ops->get_evmcs_version(vcpu); if (cpuid->nent < nent) return -E2BIG; if (cpuid->nent > nent) cpuid->nent = nent; for (i = 0; i < nent; i++) { struct kvm_cpuid_entry2 *ent = &cpuid_entries[i]; u32 signature[3]; switch (ent->function) { case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS: memcpy(signature, "Linux KVM Hv", 12); ent->eax = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES; ent->ebx = signature[0]; ent->ecx = signature[1]; ent->edx = signature[2]; break; case HYPERV_CPUID_INTERFACE: ent->eax = HYPERV_CPUID_SIGNATURE_EAX; break; case HYPERV_CPUID_VERSION: /* * We implement some Hyper-V 2016 functions so let's use * this version. */ ent->eax = 0x00003839; ent->ebx = 0x000A0000; break; case HYPERV_CPUID_FEATURES: ent->eax |= HV_MSR_VP_RUNTIME_AVAILABLE; ent->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; ent->eax |= HV_MSR_SYNIC_AVAILABLE; ent->eax |= HV_MSR_SYNTIMER_AVAILABLE; ent->eax |= HV_MSR_APIC_ACCESS_AVAILABLE; ent->eax |= HV_MSR_HYPERCALL_AVAILABLE; ent->eax |= HV_MSR_VP_INDEX_AVAILABLE; ent->eax |= HV_MSR_RESET_AVAILABLE; ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; ent->eax |= HV_ACCESS_FREQUENCY_MSRS; ent->eax |= HV_ACCESS_REENLIGHTENMENT; ent->eax |= HV_ACCESS_TSC_INVARIANT; ent->ebx |= HV_POST_MESSAGES; ent->ebx |= HV_SIGNAL_EVENTS; ent->ebx |= HV_ENABLE_EXTENDED_HYPERCALLS; ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; ent->ebx |= HV_DEBUGGING; ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE; ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_EXT_GVA_RANGES_FLUSH; /* * Direct Synthetic timers only make sense with in-kernel * LAPIC */ if (!vcpu || lapic_in_kernel(vcpu)) ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; break; case HYPERV_CPUID_ENLIGHTMENT_INFO: ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED; ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED; if (!vcpu || lapic_in_kernel(vcpu)) ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; if (evmcs_ver) ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; if (!cpu_smt_possible()) ent->eax |= HV_X64_NO_NONARCH_CORESHARING; ent->eax |= HV_DEPRECATING_AEOI_RECOMMENDED; /* * Default number of spinlock retry attempts, matches * HyperV 2016. */ ent->ebx = 0x00000FFF; break; case HYPERV_CPUID_IMPLEMENT_LIMITS: /* Maximum number of virtual processors */ ent->eax = KVM_MAX_VCPUS; /* * Maximum number of logical processors, matches * HyperV 2016. */ ent->ebx = 64; break; case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; ent->eax |= HV_X64_NESTED_DIRECT_FLUSH; ent->eax |= HV_X64_NESTED_MSR_BITMAP; ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL; break; case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS: memcpy(signature, "Linux KVM Hv", 12); ent->eax = 0; ent->ebx = signature[0]; ent->ecx = signature[1]; ent->edx = signature[2]; break; case HYPERV_CPUID_SYNDBG_INTERFACE: memcpy(signature, "VS#1\0\0\0\0\0\0\0\0", 12); ent->eax = signature[0]; break; case HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES: ent->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; break; default: break; } } if (copy_to_user(entries, cpuid_entries, nent * sizeof(struct kvm_cpuid_entry2))) return -EFAULT; return 0; } |
| 30964 22974 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H #include <asm/rmwcc.h> #include <asm/percpu.h> #include <linux/static_call_types.h> DECLARE_PER_CPU_CACHE_HOT(int, __preempt_count); /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) /* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ static __always_inline int preempt_count(void) { return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) { int old, new; old = raw_cpu_read_4(__preempt_count); do { new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); } while (!raw_cpu_try_cmpxchg_4(__preempt_count, &old, new)); } /* * must be macros to avoid header recursion hell */ #define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ } while (0) /* * We fold the NEED_RESCHED bit into the preempt count such that * preempt_enable() can decrement and test for needing to reschedule with a * single instruction. * * We invert the actual bit, so that when the decrement hits 0 we know we both * need to resched (the bit is cleared) and can resched (no preempt count). */ static __always_inline void set_preempt_need_resched(void) { raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); } /* * The various preempt_count add/sub methods */ static __always_inline void __preempt_count_add(int val) { raw_cpu_add_4(__preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { raw_cpu_add_4(__preempt_count, -val); } /* * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule * a decrement which hits zero means we have no preempt_count and should * reschedule. */ static __always_inline bool __preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __my_cpu_var(__preempt_count), e, __percpu_arg([var])); } /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_thunk(void); #define preempt_schedule_dynamic_enabled preempt_schedule_thunk #define preempt_schedule_dynamic_disabled NULL extern asmlinkage void preempt_schedule_notrace(void); extern asmlinkage void preempt_schedule_notrace_thunk(void); #define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace_thunk #define preempt_schedule_notrace_dynamic_disabled NULL #ifdef CONFIG_PREEMPT_DYNAMIC DECLARE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled); #define __preempt_schedule() \ do { \ __STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule); \ asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule) : ASM_CALL_CONSTRAINT); \ } while (0) DECLARE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled); #define __preempt_schedule_notrace() \ do { \ __STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule_notrace); \ asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule_notrace) : ASM_CALL_CONSTRAINT); \ } while (0) #else /* PREEMPT_DYNAMIC */ #define __preempt_schedule() \ asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT); #define __preempt_schedule_notrace() \ asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT); #endif /* PREEMPT_DYNAMIC */ #endif /* PREEMPTION */ #endif /* __ASM_PREEMPT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2000-2001 Christoph Hellwig. * Copyright (c) 2016 Krzysztof Blaszkowski */ #ifndef _VXFS_SUPER_H_ #define _VXFS_SUPER_H_ /* * Veritas filesystem driver - superblock structure. * * This file contains the definition of the disk and core * superblocks of the Veritas Filesystem. */ #include <linux/types.h> /* * Superblock magic number (vxfs_super->vs_magic). */ #define VXFS_SUPER_MAGIC 0xa501FCF5 /* * The root inode. */ #define VXFS_ROOT_INO 2 /* * Num of entries in free extent array */ #define VXFS_NEFREE 32 enum vxfs_byte_order { VXFS_BO_LE, VXFS_BO_BE, }; typedef __u16 __bitwise __fs16; typedef __u32 __bitwise __fs32; typedef __u64 __bitwise __fs64; /* * VxFS superblock (disk). */ struct vxfs_sb { /* * Readonly fields for the version 1 superblock. * * Lots of this fields are no more used by version 2 * and never filesystems. */ __fs32 vs_magic; /* Magic number */ __fs32 vs_version; /* VxFS version */ __fs32 vs_ctime; /* create time - secs */ __fs32 vs_cutime; /* create time - usecs */ __fs32 __unused1; /* unused */ __fs32 __unused2; /* unused */ __fs32 vs_old_logstart; /* obsolete */ __fs32 vs_old_logend; /* obsolete */ __fs32 vs_bsize; /* block size */ __fs32 vs_size; /* number of blocks */ __fs32 vs_dsize; /* number of data blocks */ __fs32 vs_old_ninode; /* obsolete */ __fs32 vs_old_nau; /* obsolete */ __fs32 __unused3; /* unused */ __fs32 vs_old_defiextsize; /* obsolete */ __fs32 vs_old_ilbsize; /* obsolete */ __fs32 vs_immedlen; /* size of immediate data area */ __fs32 vs_ndaddr; /* number of direct extentes */ __fs32 vs_firstau; /* address of first AU */ __fs32 vs_emap; /* offset of extent map in AU */ __fs32 vs_imap; /* offset of inode map in AU */ __fs32 vs_iextop; /* offset of ExtOp. map in AU */ __fs32 vs_istart; /* offset of inode list in AU */ __fs32 vs_bstart; /* offset of fdblock in AU */ __fs32 vs_femap; /* aufirst + emap */ __fs32 vs_fimap; /* aufirst + imap */ __fs32 vs_fiextop; /* aufirst + iextop */ __fs32 vs_fistart; /* aufirst + istart */ __fs32 vs_fbstart; /* aufirst + bstart */ __fs32 vs_nindir; /* number of entries in indir */ __fs32 vs_aulen; /* length of AU in blocks */ __fs32 vs_auimlen; /* length of imap in blocks */ __fs32 vs_auemlen; /* length of emap in blocks */ __fs32 vs_auilen; /* length of ilist in blocks */ __fs32 vs_aupad; /* length of pad in blocks */ __fs32 vs_aublocks; /* data blocks in AU */ __fs32 vs_maxtier; /* log base 2 of aublocks */ __fs32 vs_inopb; /* number of inodes per blk */ __fs32 vs_old_inopau; /* obsolete */ __fs32 vs_old_inopilb; /* obsolete */ __fs32 vs_old_ndiripau; /* obsolete */ __fs32 vs_iaddrlen; /* size of indirect addr ext. */ __fs32 vs_bshift; /* log base 2 of bsize */ __fs32 vs_inoshift; /* log base 2 of inobp */ __fs32 vs_bmask; /* ~( bsize - 1 ) */ __fs32 vs_boffmask; /* bsize - 1 */ __fs32 vs_old_inomask; /* old_inopilb - 1 */ __fs32 vs_checksum; /* checksum of V1 data */ /* * Version 1, writable */ __fs32 vs_free; /* number of free blocks */ __fs32 vs_ifree; /* number of free inodes */ __fs32 vs_efree[VXFS_NEFREE]; /* number of free extents by size */ __fs32 vs_flags; /* flags ?!? */ __u8 vs_mod; /* filesystem has been changed */ __u8 vs_clean; /* clean FS */ __fs16 __unused4; /* unused */ __fs32 vs_firstlogid; /* mount time log ID */ __fs32 vs_wtime; /* last time written - sec */ __fs32 vs_wutime; /* last time written - usec */ __u8 vs_fname[6]; /* FS name */ __u8 vs_fpack[6]; /* FS pack name */ __fs32 vs_logversion; /* log format version */ __u32 __unused5; /* unused */ /* * Version 2, Read-only */ __fs32 vs_oltext[2]; /* OLT extent and replica */ __fs32 vs_oltsize; /* OLT extent size */ __fs32 vs_iauimlen; /* size of inode map */ __fs32 vs_iausize; /* size of IAU in blocks */ __fs32 vs_dinosize; /* size of inode in bytes */ __fs32 vs_old_dniaddr; /* indir levels per inode */ __fs32 vs_checksum2; /* checksum of V2 RO */ /* * Actually much more... */ }; /* * In core superblock filesystem private data for VxFS. */ struct vxfs_sb_info { struct vxfs_sb *vsi_raw; /* raw (on disk) superblock */ struct buffer_head *vsi_bp; /* buffer for raw superblock*/ struct inode *vsi_fship; /* fileset header inode */ struct inode *vsi_ilist; /* inode list inode */ struct inode *vsi_stilist; /* structural inode list inode */ u_long vsi_iext; /* initial inode list */ ino_t vsi_fshino; /* fileset header inode */ daddr_t vsi_oltext; /* OLT extent */ daddr_t vsi_oltsize; /* OLT size */ enum vxfs_byte_order byte_order; }; static inline u16 fs16_to_cpu(struct vxfs_sb_info *sbi, __fs16 a) { if (sbi->byte_order == VXFS_BO_BE) return be16_to_cpu((__force __be16)a); else return le16_to_cpu((__force __le16)a); } static inline u32 fs32_to_cpu(struct vxfs_sb_info *sbi, __fs32 a) { if (sbi->byte_order == VXFS_BO_BE) return be32_to_cpu((__force __be32)a); else return le32_to_cpu((__force __le32)a); } static inline u64 fs64_to_cpu(struct vxfs_sb_info *sbi, __fs64 a) { if (sbi->byte_order == VXFS_BO_BE) return be64_to_cpu((__force __be64)a); else return le64_to_cpu((__force __le64)a); } /* * File modes. File types above 0xf000 are vxfs internal only, they should * not be passed back to higher levels of the system. vxfs file types must * never have one of the regular file type bits set. */ enum vxfs_mode { VXFS_ISUID = 0x00000800, /* setuid */ VXFS_ISGID = 0x00000400, /* setgid */ VXFS_ISVTX = 0x00000200, /* sticky bit */ VXFS_IREAD = 0x00000100, /* read */ VXFS_IWRITE = 0x00000080, /* write */ VXFS_IEXEC = 0x00000040, /* exec */ VXFS_IFIFO = 0x00001000, /* Named pipe */ VXFS_IFCHR = 0x00002000, /* Character device */ VXFS_IFDIR = 0x00004000, /* Directory */ VXFS_IFNAM = 0x00005000, /* Xenix device ?? */ VXFS_IFBLK = 0x00006000, /* Block device */ VXFS_IFREG = 0x00008000, /* Regular file */ VXFS_IFCMP = 0x00009000, /* Compressed file ?!? */ VXFS_IFLNK = 0x0000a000, /* Symlink */ VXFS_IFSOC = 0x0000c000, /* Socket */ /* VxFS internal */ VXFS_IFFSH = 0x10000000, /* Fileset header */ VXFS_IFILT = 0x20000000, /* Inode list */ VXFS_IFIAU = 0x30000000, /* Inode allocation unit */ VXFS_IFCUT = 0x40000000, /* Current usage table */ VXFS_IFATT = 0x50000000, /* Attr. inode */ VXFS_IFLCT = 0x60000000, /* Link count table */ VXFS_IFIAT = 0x70000000, /* Indirect attribute file */ VXFS_IFEMR = 0x80000000, /* Extent map reorg file */ VXFS_IFQUO = 0x90000000, /* BSD quota file */ VXFS_IFPTI = 0xa0000000, /* "Pass through" inode */ VXFS_IFLAB = 0x11000000, /* Device label file */ VXFS_IFOLT = 0x12000000, /* OLT file */ VXFS_IFLOG = 0x13000000, /* Log file */ VXFS_IFEMP = 0x14000000, /* Extent map file */ VXFS_IFEAU = 0x15000000, /* Extent AU file */ VXFS_IFAUS = 0x16000000, /* Extent AU summary file */ VXFS_IFDEV = 0x17000000, /* Device config file */ }; #define VXFS_TYPE_MASK 0xfffff000 #define VXFS_IS_TYPE(ip,type) (((ip)->vii_mode & VXFS_TYPE_MASK) == (type)) #define VXFS_ISFIFO(x) VXFS_IS_TYPE((x),VXFS_IFIFO) #define VXFS_ISCHR(x) VXFS_IS_TYPE((x),VXFS_IFCHR) #define VXFS_ISDIR(x) VXFS_IS_TYPE((x),VXFS_IFDIR) #define VXFS_ISNAM(x) VXFS_IS_TYPE((x),VXFS_IFNAM) #define VXFS_ISBLK(x) VXFS_IS_TYPE((x),VXFS_IFBLK) #define VXFS_ISLNK(x) VXFS_IS_TYPE((x),VXFS_IFLNK) #define VXFS_ISREG(x) VXFS_IS_TYPE((x),VXFS_IFREG) #define VXFS_ISCMP(x) VXFS_IS_TYPE((x),VXFS_IFCMP) #define VXFS_ISSOC(x) VXFS_IS_TYPE((x),VXFS_IFSOC) #define VXFS_ISFSH(x) VXFS_IS_TYPE((x),VXFS_IFFSH) #define VXFS_ISILT(x) VXFS_IS_TYPE((x),VXFS_IFILT) /* * Inmode organisation types. */ enum { VXFS_ORG_NONE = 0, /* Inode has *no* format ?!? */ VXFS_ORG_EXT4 = 1, /* Ext4 */ VXFS_ORG_IMMED = 2, /* All data stored in inode */ VXFS_ORG_TYPED = 3, /* Typed extents */ }; #define VXFS_IS_ORG(ip,org) ((ip)->vii_orgtype == (org)) #define VXFS_ISNONE(ip) VXFS_IS_ORG((ip), VXFS_ORG_NONE) #define VXFS_ISEXT4(ip) VXFS_IS_ORG((ip), VXFS_ORG_EXT4) #define VXFS_ISIMMED(ip) VXFS_IS_ORG((ip), VXFS_ORG_IMMED) #define VXFS_ISTYPED(ip) VXFS_IS_ORG((ip), VXFS_ORG_TYPED) /* * Get filesystem private data from VFS superblock. */ #define VXFS_SBI(sbp) \ ((struct vxfs_sb_info *)(sbp)->s_fs_info) #endif /* _VXFS_SUPER_H_ */ |
| 291 146 138 138 137 134 137 9 9 9 138 136 3 134 293 292 2 291 291 291 1622 1621 1621 152 151 152 1594 258 258 293 1625 152 14 2 152 2 1624 2 2 1623 145 167 167 167 167 166 167 167 166 166 165 167 167 167 167 167 167 167 166 167 165 167 167 167 167 167 167 166 166 166 166 166 167 167 167 166 167 167 167 166 167 167 167 167 167 1 167 140 3 3 140 139 140 139 140 140 137 138 10 10 10 140 140 2 2 2 2 2 2 2 153 152 146 11 152 153 153 153 152 153 153 153 153 153 123 153 147 147 147 153 151 150 151 150 145 11 151 23 141 140 2 142 10 142 142 1 141 3 137 1 151 142 23 153 153 146 138 6 145 145 146 146 146 160 10 10 10 10 11 5 8 7 1 1 1 2 2 10 19 19 18 18 10 10 14 6 6 2 3 3 2 1 3 3 2 3 6 8 7 50 49 48 4 4 2 13 13 13 15 2 1 1 1 50 6 3 3 3 3 6 35 23 15 13 35 34 1 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 1 1 34 34 34 34 2 33 3 32 3 30 1 30 7 29 3 28 1 28 2 1 27 5 4 4 35 24 45 34 44 42 11 8 7 3 3 10 7 31 36 45 10 14 15 14 2 1 109 111 3 2 4 109 94 4 93 16 106 28 28 28 133 120 106 91 7 91 2 90 2 89 15 88 2 1 106 2 89 15 89 4 89 9 89 3 89 15 89 6 87 2 87 3 1 85 4 3 3 2 1 82 2 82 4 81 8 81 2 81 9 81 1 81 2 81 1 81 1 81 1 81 5 81 1 81 4 81 1 81 3 81 4 81 5 78 3 77 1 77 9 77 1 77 19 73 1 1 86 86 86 86 15 251 260 259 260 260 260 259 260 260 260 260 259 260 260 260 260 258 260 260 260 260 260 260 260 260 260 259 260 259 260 260 257 260 259 260 259 260 260 260 260 260 260 260 260 260 260 260 259 259 2 1 1 1 2 2 2 1 2 18 15 15 8 8 8 18 18 18 18 18 18 18 1 18 18 18 18 18 18 18 8 8 18 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge netlink control interface * * Authors: * Stephen Hemminger <shemminger@osdl.org> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" #include "br_private_stp.h" #include "br_private_cfm.h" #include "br_private_tunnel.h" #include "br_private_mcast_eht.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int num_vlans = 0; if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; pvid = br_get_pvid(vg); /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } return num_vlans; } static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { int num_vlans; if (!vg) return 0; if (filter_mask & RTEXT_FILTER_BRVLAN) return vg->num_vlans; rcu_read_lock(); num_vlans = __get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); return num_vlans; } static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { struct net_bridge_vlan_group *vg = NULL; struct net_bridge_port *p = NULL; struct net_bridge *br = NULL; u32 num_cfm_peer_mep_infos; u32 num_cfm_mep_infos; size_t vinfo_sz = 0; int num_vlan_infos; rcu_read_lock(); if (netif_is_bridge_port(dev)) { p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); } else if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); if (p && test_bit(BR_VLAN_TUNNEL_BIT, &p->flags)) vinfo_sz += br_get_vlan_tunnel_info_size(vg); /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); if (p && vg && (filter_mask & RTEXT_FILTER_MST)) vinfo_sz += br_mst_info_size(vg); if (!(filter_mask & RTEXT_FILTER_CFM_STATUS)) return vinfo_sz; if (!br) return vinfo_sz; /* CFM status info must be added */ br_cfm_mep_count(br, &num_cfm_mep_infos); br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos); vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */ /* For each status struct the MEP instance (u32) is added */ /* MEP instance (u32) + br_cfm_mep_status */ vinfo_sz += num_cfm_mep_infos * /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */ + nla_total_size(sizeof(u32))); /* MEP instance (u32) + br_cfm_cc_peer_status */ vinfo_sz += num_cfm_peer_mep_infos * /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */ + nla_total_size(sizeof(u32))); return vinfo_sz; } static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + nla_total_size(4) /* IFLA_BRPORT_COST */ + nla_total_size(1) /* IFLA_BRPORT_MODE */ + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_VLAN_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_FORWARD_GRAT */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_BACKUP_NHID */ + 0; } static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + nla_total_size(br_get_link_af_size_filtered(dev, filter_mask)) /* IFLA_AF_SPEC */ + nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */ } static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { unsigned long flags = READ_ONCE(p->flags); u8 mode = !!(flags & BR_HAIRPIN_MODE); struct net_bridge_port *backup_p; u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, READ_ONCE(p->priority)) || nla_put_u32(skb, IFLA_BRPORT_COST, READ_ONCE(p->path_cost)) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(flags & BR_BPDU_GUARD)) || nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, !!(flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, !!(flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD, !!(flags & BR_BCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, READ_ONCE(p->designated_port)) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, READ_ONCE(p->designated_cost)) || nla_put_u16(skb, IFLA_BRPORT_ID, READ_ONCE(p->port_id)) || nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, READ_ONCE(p->config_pending)) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(flags & BR_VLAN_TUNNEL)) || nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, !!(flags & BR_NEIGH_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_MRP_RING_OPEN, !!(flags & BR_MRP_LOST_CONT)) || nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(flags & BR_ISOLATED)) || nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(flags & BR_PORT_LOCKED)) || nla_put_u8(skb, IFLA_BRPORT_MAB, !!(flags & BR_PORT_MAB)) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, !!(flags & BR_NEIGH_VLAN_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_FORWARD_GRAT, !!(flags & BR_NEIGH_FORWARD_GRAT))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->forward_delay_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->hold_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_HOLD_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, p->multicast_ctx.multicast_router) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, p->multicast_eht_hosts_cnt) || nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, br_multicast_ngroups_get(&p->multicast_ctx)) || nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif /* we might be called only with br->lock */ rcu_read_lock(); backup_p = rcu_dereference(p->backup_port); if (backup_p) nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT, backup_p->dev->ifindex); rcu_read_unlock(); if (p->backup_nhid && nla_put_u32(skb, IFLA_BRPORT_BACKUP_NHID, p->backup_nhid)) return -EMSGSIZE; return 0; } static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, u16 vid_end, u16 flags) { struct bridge_vlan_info vinfo; if ((vid_end - vid_start) > 0) { /* add range to skb */ vinfo.vid = vid_start; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } else { vinfo.vid = vid_start; vinfo.flags = flags; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { /* Call it once more to send any left over vlans */ err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } return 0; } static int br_fill_ifvlaninfo(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct bridge_vlan_info vinfo; struct net_bridge_vlan *v; u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; vinfo.vid = v->vid; vinfo.flags = 0; if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev, bool getlink) { u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; if (port) br = port->br; else br = netdev_priv(dev); br_debug(br, "br_fill_ifinfo event %d port %s master %s\n", event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_BRIDGE; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; hdr->ifi_flags = netif_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { struct nlattr *nest; nest = nla_nest_start(skb, IFLA_PROTINFO); if (nest == NULL || br_port_fill_attrs(skb, port) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | RTEXT_FILTER_MRP | RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS | RTEXT_FILTER_MST)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; } /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ rcu_read_lock(); if (port) vg = nbp_vlan_group_rcu(port); else vg = br_vlan_group_rcu(br); if (!vg || !vg->num_vlans) { rcu_read_unlock(); goto done; } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); if (port && test_bit(BR_VLAN_TUNNEL_BIT, &port->flags)) err = br_fill_vlan_tunnel_info(skb, vg); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_MRP) { int err; if (!br_mrp_enabled(br) || port) goto done; rcu_read_lock(); err = br_mrp_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { struct nlattr *cfm_nest = NULL; int err; if (!br_cfm_created(br) || port) goto done; cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM); if (!cfm_nest) goto nla_put_failure; if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { rcu_read_lock(); err = br_cfm_config_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_CFM_STATUS) { rcu_read_lock(); err = br_cfm_status_fill_info(skb, br, getlink); rcu_read_unlock(); if (err) goto nla_put_failure; } nla_nest_end(skb, cfm_nest); } if ((filter_mask & RTEXT_FILTER_MST) && br_opt_get(br, BROPT_MST_ENABLED) && port) { const struct net_bridge_vlan_group *vg = nbp_vlan_group(port); struct nlattr *mst_nest; int err; if (!vg || !vg->num_vlans) goto done; mst_nest = nla_nest_start(skb, IFLA_BRIDGE_MST); if (!mst_nest) goto nla_put_failure; err = br_mst_fill_info(skb, vg); if (err) goto nla_put_failure; nla_nest_end(skb, mst_nest); } done: if (af) { if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0)) nla_nest_end(skb, af); else nla_nest_cancel(skb, af); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void br_info_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port, u32 filter) { struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 port_no = 0; if (WARN_ON(!port && !br)) return; if (port) { dev = port->dev; br = port->br; port_no = port->port_no; } else { dev = br->dev; } net = dev_net(dev); br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event); skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } /* Notify listeners of a change in bridge or port information */ void br_ifinfo_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; br_info_notify(event, br, port, filter); } /* * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && !(filter_mask & RTEXT_FILTER_MRP) && !(filter_mask & RTEXT_FILTER_CFM_CONFIG) && !(filter_mask & RTEXT_FILTER_CFM_STATUS)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev, true); } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo, bool *changed, struct netlink_ext_ack *extack) { bool curr_change; int err = 0; switch (cmd) { case RTM_SETLINK: if (p) { /* if the MASTER flag is set this will act on the global * per-VLAN entry as well */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags, &curr_change, extack); } else { vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags, &curr_change, extack); } if (curr_change) *changed = true; break; case RTM_DELLINK: if (p) { if (!nbp_vlan_delete(p, vinfo->vid)) *changed = true; if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) && !br_vlan_delete(p->br, vinfo->vid)) *changed = true; } else if (!br_vlan_delete(br, vinfo->vid)) { *changed = true; } break; } return err; } int br_process_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo_curr, struct bridge_vlan_info **vinfo_last, bool *changed, struct netlink_ext_ack *extack) { int err, rtm_cmd; if (!br_vlan_valid_id(vinfo_curr->vid, extack)) return -EINVAL; /* needed for vlan-only NEWVLAN/DELVLAN notifications */ rtm_cmd = br_afspec_cmd_to_rtm(cmd); if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; *vinfo_last = vinfo_curr; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; int v, v_change_start = 0; if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { bool curr_change = false; tmp_vinfo.vid = v; err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change, extack); if (err) break; if (curr_change) { *changed = curr_change; if (!v_change_start) v_change_start = v; } else { /* nothing to notify yet */ if (!v_change_start) continue; br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); v_change_start = 0; } cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); *vinfo_last = NULL; return err; } err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); if (*changed) br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd); return err; } static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd, bool *changed, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo_curr = NULL; struct bridge_vlan_info *vinfo_last = NULL; struct nlattr *attr; struct vtunnel_info tinfo_last = {}; struct vtunnel_info tinfo_curr = {}; int err = 0, rem; nla_for_each_nested(attr, af_spec, rem) { err = 0; switch (nla_type(attr)) { case IFLA_BRIDGE_VLAN_TUNNEL_INFO: if (!p || !test_bit(BR_VLAN_TUNNEL_BIT, &p->flags)) return -EINVAL; err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); if (err) return err; err = br_process_vlan_tunnel_info(br, p, cmd, &tinfo_curr, &tinfo_last, changed); if (err) return err; break; case IFLA_BRIDGE_VLAN_INFO: if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo_curr = nla_data(attr); err = br_process_vlan_info(br, p, cmd, vinfo_curr, &vinfo_last, changed, extack); if (err) return err; break; case IFLA_BRIDGE_MRP: err = br_mrp_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_CFM: err = br_cfm_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_MST: if (!p) { NL_SET_ERR_MSG(extack, "MST states can only be set on bridge ports"); return -EINVAL; } if (cmd != RTM_SETLINK) { NL_SET_ERR_MSG(extack, "MST states can only be set through RTM_SETLINK"); return -EINVAL; } err = br_mst_process(p, attr, extack); if (err) return err; break; } } return err; } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_UNSPEC] = { .strict_start_type = IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 }, [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_BRPORT_BACKUP_NHID] = { .type = NLA_U32 }, [IFLA_BRPORT_NEIGH_FORWARD_GRAT] = NLA_POLICY_MAX(NLA_U8, 1), }; /* Change the state of the port and notify spanning tree */ static int br_set_port_state(struct net_bridge_port *p, u8 state) { if (state > BR_STATE_BLOCKING) return -EINVAL; /* if kernel STP is running, don't allow changes */ if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; /* if device is not up, change is not allowed * if link is not present, only allowable state is disabled */ if (!netif_running(p->dev) || (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; br_set_state(p, state); br_port_state_selection(p->br); return 0; } /* Set/clear or port flags based on attribute */ static void br_set_port_flag(unsigned long *set_flags, unsigned long *clear_flags, struct nlattr *tb[], int attrtype, unsigned long mask) { if (tb[attrtype]) { if (nla_get_u8(tb[attrtype])) *set_flags |= mask; else *clear_flags |= mask; } } /* Process bridge protocol info on port */ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned long old_flags, flags, changed_mask; unsigned long set = 0, clear = 0; bool br_vlan_tunnel_old; int err; old_flags = READ_ONCE(p->flags); br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false; br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, BR_NEIGH_VLAN_SUPPRESS); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_NEIGH_FORWARD_GRAT, BR_NEIGH_FORWARD_GRAT); flags = (old_flags | set) & ~clear; if ((flags & BR_PORT_MAB) && (!(flags & BR_PORT_LOCKED) || !(flags & BR_LEARNING))) { NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); return -EINVAL; } if (!(flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { struct net_bridge_fdb_flush_desc desc = { .flags = BIT(BR_FDB_LOCKED), .flags_mask = BIT(BR_FDB_LOCKED), .port_ifindex = p->dev->ifindex, }; br_fdb_flush(p->br, &desc); } changed_mask = old_flags ^ flags; err = br_switchdev_set_port_flag(p, flags, changed_mask, extack); if (err) return err; do { flags = (old_flags | set) & ~clear; } while (!try_cmpxchg(&p->flags, &old_flags, flags)); if (br_vlan_tunnel_old && !(flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); br_port_flags_change(p, changed_mask); if (tb[IFLA_BRPORT_COST]) { spin_lock_bh(&p->br->lock); err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); spin_unlock_bh(&p->br->lock); if (err) return err; } if (tb[IFLA_BRPORT_PRIORITY]) { spin_lock_bh(&p->br->lock); err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); spin_unlock_bh(&p->br->lock); if (err) return err; } if (tb[IFLA_BRPORT_STATE]) { spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); spin_unlock_bh(&p->br->lock); if (err) return err; } if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); err = br_multicast_set_port_router(&p->multicast_ctx, mcast_router); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) { u32 hlimit; hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]); err = br_multicast_eht_set_hosts_limit(p, hlimit); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { u32 max_groups; max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_MACPAUSE) return -EINVAL; p->group_fwd_mask = fwd_mask; } if (tb[IFLA_BRPORT_BACKUP_PORT]) { struct net_device *backup_dev = NULL; u32 backup_ifindex; backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]); if (backup_ifindex) { backup_dev = __dev_get_by_index(dev_net(p->dev), backup_ifindex); if (!backup_dev) return -ENOENT; } err = nbp_backup_change(p, backup_dev); if (err) return err; } if (tb[IFLA_BRPORT_BACKUP_NHID]) { u32 backup_nhid = nla_get_u32(tb[IFLA_BRPORT_BACKUP_NHID]); WRITE_ONCE(p->backup_nhid, backup_nhid); } return 0; } /* Change state and parameters on port. */ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct nlattr *tb[IFLA_BRPORT_MAX + 1]; struct net_bridge_port *p; struct nlattr *protinfo; struct nlattr *afspec; bool changed = false; int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself if the AF_SPEC * is set to see if someone is setting vlan info on the bridge */ if (!p && !afspec) return -EINVAL; if (p && protinfo) { if (protinfo->nla_type & NLA_F_NESTED) { err = nla_parse_nested_deprecated(tb, IFLA_BRPORT_MAX, protinfo, br_port_policy, NULL); if (err) return err; err = br_setport(p, tb, extack); } else { /* Binary compatibility with old RSTP */ if (nla_len(protinfo) < sizeof(u8)) return -EINVAL; spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(protinfo)); spin_unlock_bh(&p->br->lock); } if (err) goto out; changed = true; } if (afspec) err = br_afspec(br, p, afspec, RTM_SETLINK, &changed, extack); if (changed) br_ifinfo_notify(RTM_NEWLINK, br, p); out: return err; } /* Delete port information */ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct net_bridge_port *p; struct nlattr *afspec; bool changed = false; int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ if (!p && !netif_is_bridge_master(dev)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); if (changed) /* Send RTM_NEWLINK because userspace * expects RTM_NEWLINK for vlan dels */ br_ifinfo_notify(RTM_NEWLINK, br, p); return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL] && !eth_type_vlan(nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]))) return -EPROTONOSUPPORT; if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); if (defpvid >= VLAN_VID_MASK) return -EINVAL; } #endif return 0; } static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return 0; return br_setport(br_port_get_rtnl(dev), data, extack); } static int br_port_fill_slave_info(struct sk_buff *skb, const struct net_device *brdev, const struct net_device *dev) { return br_port_fill_attrs(skb, br_port_get_rtnl(dev)); } static size_t br_port_get_slave_size(const struct net_device *brdev, const struct net_device *dev) { return br_port_info_size(); } static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_UNSPEC] = { .strict_start_type = IFLA_BR_FDB_N_LEARNED }, [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, [IFLA_BR_MULTI_BOOLOPT] = NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), [IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT }, [IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 }, [IFLA_BR_STP_MODE] = NLA_POLICY_RANGE(NLA_U32, BR_STP_MODE_AUTO, BR_STP_MODE_MAX), }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; if (!data) return 0; if (data[IFLA_BR_FORWARD_DELAY]) { err = br_set_forward_delay(br, nla_get_u32(data[IFLA_BR_FORWARD_DELAY])); if (err) return err; } if (data[IFLA_BR_HELLO_TIME]) { err = br_set_hello_time(br, nla_get_u32(data[IFLA_BR_HELLO_TIME])); if (err) return err; } if (data[IFLA_BR_MAX_AGE]) { err = br_set_max_age(br, nla_get_u32(data[IFLA_BR_MAX_AGE])); if (err) return err; } if (data[IFLA_BR_AGEING_TIME]) { err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME])); if (err) return err; } if (data[IFLA_BR_STP_MODE]) { u32 mode = nla_get_u32(data[IFLA_BR_STP_MODE]); if (mode != br->stp_mode) { bool stp_off = br->stp_enabled == BR_NO_STP || (data[IFLA_BR_STP_STATE] && !nla_get_u32(data[IFLA_BR_STP_STATE])); if (!stp_off) { NL_SET_ERR_MSG_MOD(extack, "Can't change STP mode while STP is enabled"); return -EBUSY; } } br->stp_mode = mode; } if (data[IFLA_BR_STP_STATE]) { u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); err = br_stp_set_enabled(br, stp_enabled, extack); if (err) return err; } if (data[IFLA_BR_PRIORITY]) { u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); br_stp_set_bridge_priority(br, priority); } if (data[IFLA_BR_VLAN_FILTERING]) { u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); err = br_vlan_filter_toggle(br, vlan_filter, extack); if (err) return err; } #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL]) { __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); err = __br_vlan_set_proto(br, vlan_proto, extack); if (err) return err; } if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); err = __br_vlan_set_default_pvid(br, defpvid, extack); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_ENABLED]) { __u8 vlan_stats = nla_get_u8(data[IFLA_BR_VLAN_STATS_ENABLED]); err = br_vlan_set_stats(br, vlan_stats); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_PER_PORT]) { __u8 per_port = nla_get_u8(data[IFLA_BR_VLAN_STATS_PER_PORT]); err = br_vlan_set_stats_per_port(br, per_port); if (err) return err; } #endif if (data[IFLA_BR_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_RESTRICTED) return -EINVAL; br->group_fwd_mask = fwd_mask; } if (data[IFLA_BR_GROUP_ADDR]) { u8 new_addr[ETH_ALEN]; if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN) return -EINVAL; memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN); if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ new_addr[5] == 2 || /* 802.3ad Slow protocols */ new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; spin_lock_bh(&br->lock); memcpy(br->group_addr, new_addr, sizeof(br->group_addr)); spin_unlock_bh(&br->lock); br_opt_toggle(br, BROPT_GROUP_ADDR_SET, true); br_recalculate_fwd_mask(br); } if (data[IFLA_BR_FDB_FLUSH]) { struct net_bridge_fdb_flush_desc desc = { .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (data[IFLA_BR_MCAST_ROUTER]) { u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); err = br_multicast_set_router(&br->multicast_ctx, multicast_router); if (err) return err; } if (data[IFLA_BR_MCAST_SNOOPING]) { u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]); err = br_multicast_toggle(br, mcast_snooping, extack); if (err) return err; } if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) { u8 val; val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); br_opt_toggle(br, BROPT_MULTICAST_QUERY_USE_IFADDR, !!val); } if (data[IFLA_BR_MCAST_QUERIER]) { u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); err = br_multicast_set_querier(&br->multicast_ctx, mcast_querier); if (err) return err; } if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n", RHT_ELASTICITY); if (data[IFLA_BR_MCAST_HASH_MAX]) br->hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]); if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); br->multicast_ctx.multicast_last_member_count = val; } if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); br->multicast_ctx.multicast_startup_query_count = val; } if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); br_multicast_set_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); br_multicast_set_startup_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_STATS_ENABLED]) { __u8 mcast_stats; mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]); br_opt_toggle(br, BROPT_MULTICAST_STATS_ENABLED, !!mcast_stats); } if (data[IFLA_BR_MCAST_IGMP_VERSION]) { __u8 igmp_version; igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]); err = br_multicast_set_igmp_version(&br->multicast_ctx, igmp_version); if (err) return err; } #if IS_ENABLED(CONFIG_IPV6) if (data[IFLA_BR_MCAST_MLD_VERSION]) { __u8 mld_version; mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]); err = br_multicast_set_mld_version(&br->multicast_ctx, mld_version); if (err) return err; } #endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (data[IFLA_BR_NF_CALL_IPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_IPTABLES, !!val); } if (data[IFLA_BR_NF_CALL_IP6TABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]); br_opt_toggle(br, BROPT_NF_CALL_IP6TABLES, !!val); } if (data[IFLA_BR_NF_CALL_ARPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_ARPTABLES, !!val); } #endif if (data[IFLA_BR_MULTI_BOOLOPT]) { struct br_boolopt_multi *bm; bm = nla_data(data[IFLA_BR_MULTI_BOOLOPT]); err = br_boolopt_multi_toggle(br, bm, extack); if (err) return err; } if (data[IFLA_BR_FDB_MAX_LEARNED]) { u32 val = nla_get_u32(data[IFLA_BR_FDB_MAX_LEARNED]); WRITE_ONCE(br->fdb_max_learned, val); } return 0; } static int br_dev_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; err = register_netdevice(dev); if (err) return err; if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } err = br_changelink(dev, tb, data, extack); if (err) br_dev_delete(dev, NULL); return err; } static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_ENABLED */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_PER_PORT */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_N_LEARNED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_MAX_LEARNED */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_STATS_ENABLED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */ br_multicast_querier_state_size() + /* IFLA_BR_MCAST_QUERIER_STATE */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */ #endif nla_total_size(sizeof(struct br_boolopt_multi)) + /* IFLA_BR_MULTI_BOOLOPT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_MODE */ 0; } static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u8 vlan_enabled = br_vlan_enabled(br->dev); struct br_boolopt_multi bm; u64 clockval; clockval = br_timer_value(&br->hello_timer); if (nla_put_u64_64bit(skb, IFLA_BR_HELLO_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->tcn_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TCN_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->topology_change_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->gc_work.timer); if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; br_boolopt_multi_get(br, &bm); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, br->group_fwd_mask) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(struct ifla_bridge_id), &br->bridge_id) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(struct ifla_bridge_id), &br->designated_root) || nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, br->topology_change_detected) || nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) || nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm) || nla_put_u32(skb, IFLA_BR_FDB_N_LEARNED, atomic_read(&br->fdb_n_learned)) || nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned) || nla_put_u32(skb, IFLA_BR_STP_MODE, br->stp_mode)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) || nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED, br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT, br_opt_get(br, BROPT_VLAN_STATS_PER_PORT))) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_ctx.multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, br_opt_get(br, BROPT_MULTICAST_ENABLED)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_ctx.multicast_querier) || nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED, br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, RHT_ELASTICITY) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, br->multicast_ctx.multicast_last_member_count) || nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, br->multicast_ctx.multicast_startup_query_count) || nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, br->multicast_ctx.multicast_igmp_version) || br_multicast_dump_querier_state(skb, &br->multicast_ctx, IFLA_BR_MCAST_QUERIER_STATE)) return -EMSGSIZE; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION, br->multicast_ctx.multicast_mld_version)) return -EMSGSIZE; #endif clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES, br_opt_get(br, BROPT_NF_CALL_IPTABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES, br_opt_get(br, BROPT_NF_CALL_IP6TABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES, br_opt_get(br, BROPT_NF_CALL_ARPTABLES) ? 1 : 0)) return -EMSGSIZE; #endif return 0; } static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) { struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; int numvls = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; vg = nbp_vlan_group(p); break; default: return 0; } if (vg) { /* we need to count all, even placeholder entries */ list_for_each_entry(v, &vg->vlan_list, vlist) numvls++; } return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) + nla_total_size_64bit(sizeof(struct br_mcast_stats)) + (p ? nla_total_size_64bit(sizeof(p->stp_xstats)) : 0) + nla_total_size(0); } static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { unsigned int limit = U16_MAX - nla_total_size(0); struct nlattr *nla __maybe_unused; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; struct nlattr *nest; int vl_idx = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; limit -= nla_total_size_64bit(sizeof(p->stp_xstats)); br = p->br; vg = nbp_vlan_group(p); break; default: return -EINVAL; } nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BRIDGE); if (!nest) return -EMSGSIZE; if (vg) { u16 pvid; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING limit -= nla_total_size_64bit(sizeof(struct br_mcast_stats)); #endif pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct bridge_vlan_xstats vxi; struct pcpu_sw_netstats stats; if (++vl_idx < *prividx) continue; if (skb_tail_pointer(skb) - (unsigned char *)nest + nla_total_size(sizeof(vxi)) >= limit) goto nla_put_failure; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; vxi.flags = v->flags; if (v->vid == pvid) vxi.flags |= BRIDGE_VLAN_INFO_PVID; br_vlan_get_stats(v, &stats); vxi.rx_bytes = u64_stats_read(&stats.rx_bytes); vxi.rx_packets = u64_stats_read(&stats.rx_packets); vxi.tx_bytes = u64_stats_read(&stats.tx_bytes); vxi.tx_packets = u64_stats_read(&stats.tx_packets); if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi)) goto nla_put_failure; } } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (++vl_idx >= *prividx) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST, sizeof(struct br_mcast_stats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; br_multicast_get_stats(br, p, nla_data(nla)); } #endif if (p) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_STP, sizeof(p->stp_xstats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; spin_lock_bh(&br->lock); memcpy(nla_data(nla), &p->stp_xstats, sizeof(p->stp_xstats)); spin_unlock_bh(&br->lock); } nla_nest_end(skb, nest); *prividx = 0; return 0; nla_put_failure: nla_nest_end(skb, nest); *prividx = vl_idx; return -EMSGSIZE; } static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, .get_link_af_size = br_get_link_af_size_filtered, }; struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .maxtype = IFLA_BR_MAX, .policy = br_policy, .validate = br_validate, .newlink = br_dev_newlink, .changelink = br_changelink, .dellink = br_dev_delete, .get_size = br_get_size, .fill_info = br_fill_info, .fill_linkxstats = br_fill_linkxstats, .get_linkxstats_size = br_get_linkxstats_size, .slave_maxtype = IFLA_BRPORT_MAX, .slave_policy = br_port_policy, .slave_changelink = br_port_slave_changelink, .get_slave_size = br_port_get_slave_size, .fill_slave_info = br_port_fill_slave_info, }; int __init br_netlink_init(void) { int err; err = br_vlan_rtnl_init(); if (err) goto out; err = rtnl_af_register(&br_af_ops); if (err) goto out_vlan; err = rtnl_link_register(&br_link_ops); if (err) goto out_af; return 0; out_af: rtnl_af_unregister(&br_af_ops); out_vlan: br_vlan_rtnl_uninit(); out: return err; } void br_netlink_fini(void) { br_vlan_rtnl_uninit(); rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } |
| 1 1 1 1 3 3 3 3 1 3 3 3 4 4 4 2 1 2 2 1 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* Common methods for dibusb-based-receivers. * * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de) * * see Documentation/driver-api/media/drivers/dvb-usb.rst for more information */ #include "dibusb.h" /* Max transfer size done by I2C transfer functions */ #define MAX_XFER_SIZE 64 static int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "set debugging level (1=info (|-able))." DVB_USB_DEBUG_STATUS); MODULE_DESCRIPTION("Common methods for dibusb-based receivers"); MODULE_LICENSE("GPL"); #define deb_info(args...) dprintk(debug,0x01,args) /* common stuff used by the different dibusb modules */ int dibusb_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff) { if (adap->priv != NULL) { struct dibusb_state *st = adap->priv; if (st->ops.fifo_ctrl != NULL) if (st->ops.fifo_ctrl(adap->fe_adap[0].fe, onoff)) { err("error while controlling the fifo of the demod."); return -ENODEV; } } return 0; } EXPORT_SYMBOL(dibusb_streaming_ctrl); int dibusb_pid_filter(struct dvb_usb_adapter *adap, int index, u16 pid, int onoff) { if (adap->priv != NULL) { struct dibusb_state *st = adap->priv; if (st->ops.pid_ctrl != NULL) st->ops.pid_ctrl(adap->fe_adap[0].fe, index, pid, onoff); } return 0; } EXPORT_SYMBOL(dibusb_pid_filter); int dibusb_pid_filter_ctrl(struct dvb_usb_adapter *adap, int onoff) { if (adap->priv != NULL) { struct dibusb_state *st = adap->priv; if (st->ops.pid_parse != NULL) if (st->ops.pid_parse(adap->fe_adap[0].fe, onoff) < 0) err("could not handle pid_parser"); } return 0; } EXPORT_SYMBOL(dibusb_pid_filter_ctrl); int dibusb_power_ctrl(struct dvb_usb_device *d, int onoff) { u8 *b; int ret; b = kmalloc(3, GFP_KERNEL); if (!b) return -ENOMEM; b[0] = DIBUSB_REQ_SET_IOCTL; b[1] = DIBUSB_IOCTL_CMD_POWER_MODE; b[2] = onoff ? DIBUSB_IOCTL_POWER_WAKEUP : DIBUSB_IOCTL_POWER_SLEEP; ret = dvb_usb_generic_write(d, b, 3); kfree(b); msleep(10); return ret; } EXPORT_SYMBOL(dibusb_power_ctrl); int dibusb2_0_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff) { int ret; u8 *b; b = kmalloc(3, GFP_KERNEL); if (!b) return -ENOMEM; if ((ret = dibusb_streaming_ctrl(adap,onoff)) < 0) goto ret; if (onoff) { b[0] = DIBUSB_REQ_SET_STREAMING_MODE; b[1] = 0x00; ret = dvb_usb_generic_write(adap->dev, b, 2); if (ret < 0) goto ret; } b[0] = DIBUSB_REQ_SET_IOCTL; b[1] = onoff ? DIBUSB_IOCTL_CMD_ENABLE_STREAM : DIBUSB_IOCTL_CMD_DISABLE_STREAM; ret = dvb_usb_generic_write(adap->dev, b, 3); ret: kfree(b); return ret; } EXPORT_SYMBOL(dibusb2_0_streaming_ctrl); int dibusb2_0_power_ctrl(struct dvb_usb_device *d, int onoff) { u8 *b; int ret; if (!onoff) return 0; b = kmalloc(3, GFP_KERNEL); if (!b) return -ENOMEM; b[0] = DIBUSB_REQ_SET_IOCTL; b[1] = DIBUSB_IOCTL_CMD_POWER_MODE; b[2] = DIBUSB_IOCTL_POWER_WAKEUP; ret = dvb_usb_generic_write(d, b, 3); kfree(b); return ret; } EXPORT_SYMBOL(dibusb2_0_power_ctrl); static int dibusb_i2c_msg(struct dvb_usb_device *d, u8 addr, u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen) { u8 *sndbuf; int ret, wo, len; /* write only ? */ wo = (rbuf == NULL || rlen == 0); len = 2 + wlen + (wo ? 0 : 2); sndbuf = kmalloc(MAX_XFER_SIZE, GFP_KERNEL); if (!sndbuf) return -ENOMEM; if (4 + wlen > MAX_XFER_SIZE) { warn("i2c wr: len=%d is too big!\n", wlen); ret = -EOPNOTSUPP; goto ret; } sndbuf[0] = wo ? DIBUSB_REQ_I2C_WRITE : DIBUSB_REQ_I2C_READ; sndbuf[1] = (addr << 1) | (wo ? 0 : 1); memcpy(&sndbuf[2], wbuf, wlen); if (!wo) { sndbuf[wlen + 2] = (rlen >> 8) & 0xff; sndbuf[wlen + 3] = rlen & 0xff; } ret = dvb_usb_generic_rw(d, sndbuf, len, rbuf, rlen, 0); ret: kfree(sndbuf); return ret; } /* * I2C master xfer function */ static int dibusb_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num) { struct dvb_usb_device *d = i2c_get_adapdata(adap); int i; if (mutex_lock_interruptible(&d->i2c_mutex) < 0) return -EAGAIN; for (i = 0; i < num; i++) { /* write/read request */ if (i+1 < num && (msg[i].flags & I2C_M_RD) == 0 && (msg[i+1].flags & I2C_M_RD)) { if (dibusb_i2c_msg(d, msg[i].addr, msg[i].buf,msg[i].len, msg[i+1].buf,msg[i+1].len) < 0) break; i++; } else if ((msg[i].flags & I2C_M_RD) == 0) { if (dibusb_i2c_msg(d, msg[i].addr, msg[i].buf,msg[i].len,NULL,0) < 0) break; } else if (msg[i].addr != 0x50) { /* 0x50 is the address of the eeprom - we need to protect it * from dibusb's bad i2c implementation: reads without * writing the offset before are forbidden */ if (dibusb_i2c_msg(d, msg[i].addr, NULL, 0, msg[i].buf, msg[i].len) < 0) break; } } mutex_unlock(&d->i2c_mutex); return i; } static u32 dibusb_i2c_func(struct i2c_adapter *adapter) { return I2C_FUNC_I2C; } struct i2c_algorithm dibusb_i2c_algo = { .master_xfer = dibusb_i2c_xfer, .functionality = dibusb_i2c_func, }; EXPORT_SYMBOL(dibusb_i2c_algo); int dibusb_read_eeprom_byte(struct dvb_usb_device *d, u8 offs, u8 *val) { u8 *buf; int rc; buf = kzalloc(2, GFP_KERNEL); if (!buf) return -ENOMEM; buf[0] = offs; rc = dibusb_i2c_msg(d, 0x50, &buf[0], 1, &buf[1], 1); *val = buf[1]; kfree(buf); return rc; } EXPORT_SYMBOL(dibusb_read_eeprom_byte); /* * common remote control stuff */ struct rc_map_table rc_map_dibusb_table[] = { /* Key codes for the little Artec T1/Twinhan/HAMA/ remote. */ { 0x0016, KEY_POWER }, { 0x0010, KEY_MUTE }, { 0x0003, KEY_1 }, { 0x0001, KEY_2 }, { 0x0006, KEY_3 }, { 0x0009, KEY_4 }, { 0x001d, KEY_5 }, { 0x001f, KEY_6 }, { 0x000d, KEY_7 }, { 0x0019, KEY_8 }, { 0x001b, KEY_9 }, { 0x0015, KEY_0 }, { 0x0005, KEY_CHANNELUP }, { 0x0002, KEY_CHANNELDOWN }, { 0x001e, KEY_VOLUMEUP }, { 0x000a, KEY_VOLUMEDOWN }, { 0x0011, KEY_RECORD }, { 0x0017, KEY_FAVORITES }, /* Heart symbol - Channel list. */ { 0x0014, KEY_PLAY }, { 0x001a, KEY_STOP }, { 0x0040, KEY_REWIND }, { 0x0012, KEY_FASTFORWARD }, { 0x000e, KEY_PREVIOUS }, /* Recall - Previous channel. */ { 0x004c, KEY_PAUSE }, { 0x004d, KEY_SCREEN }, /* Full screen mode. */ { 0x0054, KEY_AUDIO }, /* MTS - Switch to secondary audio. */ /* additional keys TwinHan VisionPlus, the Artec seemingly not have */ { 0x000c, KEY_CANCEL }, /* Cancel */ { 0x001c, KEY_EPG }, /* EPG */ { 0x0000, KEY_TAB }, /* Tab */ { 0x0048, KEY_INFO }, /* Preview */ { 0x0004, KEY_LIST }, /* RecordList */ { 0x000f, KEY_TEXT }, /* Teletext */ /* Key codes for the KWorld/ADSTech/JetWay remote. */ { 0x8612, KEY_POWER }, { 0x860f, KEY_SELECT }, /* source */ { 0x860c, KEY_UNKNOWN }, /* scan */ { 0x860b, KEY_EPG }, { 0x8610, KEY_MUTE }, { 0x8601, KEY_1 }, { 0x8602, KEY_2 }, { 0x8603, KEY_3 }, { 0x8604, KEY_4 }, { 0x8605, KEY_5 }, { 0x8606, KEY_6 }, { 0x8607, KEY_7 }, { 0x8608, KEY_8 }, { 0x8609, KEY_9 }, { 0x860a, KEY_0 }, { 0x8618, KEY_ZOOM }, { 0x861c, KEY_UNKNOWN }, /* preview */ { 0x8613, KEY_UNKNOWN }, /* snap */ { 0x8600, KEY_UNDO }, { 0x861d, KEY_RECORD }, { 0x860d, KEY_STOP }, { 0x860e, KEY_PAUSE }, { 0x8616, KEY_PLAY }, { 0x8611, KEY_BACK }, { 0x8619, KEY_FORWARD }, { 0x8614, KEY_UNKNOWN }, /* pip */ { 0x8615, KEY_ESC }, { 0x861a, KEY_UP }, { 0x861e, KEY_DOWN }, { 0x861f, KEY_LEFT }, { 0x861b, KEY_RIGHT }, /* Key codes for the DiBcom MOD3000 remote. */ { 0x8000, KEY_MUTE }, { 0x8001, KEY_TEXT }, { 0x8002, KEY_HOME }, { 0x8003, KEY_POWER }, { 0x8004, KEY_RED }, { 0x8005, KEY_GREEN }, { 0x8006, KEY_YELLOW }, { 0x8007, KEY_BLUE }, { 0x8008, KEY_DVD }, { 0x8009, KEY_AUDIO }, { 0x800a, KEY_IMAGES }, /* Pictures */ { 0x800b, KEY_VIDEO }, { 0x800c, KEY_BACK }, { 0x800d, KEY_UP }, { 0x800e, KEY_RADIO }, { 0x800f, KEY_EPG }, { 0x8010, KEY_LEFT }, { 0x8011, KEY_OK }, { 0x8012, KEY_RIGHT }, { 0x8013, KEY_UNKNOWN }, /* SAP */ { 0x8014, KEY_TV }, { 0x8015, KEY_DOWN }, { 0x8016, KEY_MENU }, /* DVD Menu */ { 0x8017, KEY_LAST }, { 0x8018, KEY_RECORD }, { 0x8019, KEY_STOP }, { 0x801a, KEY_PAUSE }, { 0x801b, KEY_PLAY }, { 0x801c, KEY_PREVIOUS }, { 0x801d, KEY_REWIND }, { 0x801e, KEY_FASTFORWARD }, { 0x801f, KEY_NEXT}, { 0x8040, KEY_1 }, { 0x8041, KEY_2 }, { 0x8042, KEY_3 }, { 0x8043, KEY_CHANNELUP }, { 0x8044, KEY_4 }, { 0x8045, KEY_5 }, { 0x8046, KEY_6 }, { 0x8047, KEY_CHANNELDOWN }, { 0x8048, KEY_7 }, { 0x8049, KEY_8 }, { 0x804a, KEY_9 }, { 0x804b, KEY_VOLUMEUP }, { 0x804c, KEY_CLEAR }, { 0x804d, KEY_0 }, { 0x804e, KEY_ENTER }, { 0x804f, KEY_VOLUMEDOWN }, }; EXPORT_SYMBOL(rc_map_dibusb_table); int dibusb_rc_query(struct dvb_usb_device *d, u32 *event, int *state) { u8 *buf; int ret; buf = kmalloc(5, GFP_KERNEL); if (!buf) return -ENOMEM; buf[0] = DIBUSB_REQ_POLL_REMOTE; ret = dvb_usb_generic_rw(d, buf, 1, buf, 5, 0); if (ret < 0) goto ret; dvb_usb_nec_rc_key_to_event(d, buf, event, state); if (buf[0] != 0) deb_info("key: %*ph\n", 5, buf); ret: kfree(buf); return ret; } EXPORT_SYMBOL(dibusb_rc_query); |
| 10 3 16 8 2 3 2 8 2 2 13 8 8 8 8 1 1 1 1 1 12 36 36 36 36 36 10 2 1 1 1 12 10 9 9 9 1 1 1 12 5 5 3 3 2 1 1 1 1 1 5 19 7 7 13 19 19 5 17 19 4 1 3 3 2 1 1 1 1 1 1 1 4 19 19 5 17 17 17 17 12 7 12 12 3 12 12 25 17 20 15 12 11 7 4 25 25 20 10 19 5 23 9 15 23 7 25 25 17 10 2 8 16 5 25 7 3 7 7 21 22 21 22 22 22 22 22 22 22 1 22 22 22 5 29 5 5 19 19 19 19 19 19 19 17 19 7 18 18 18 18 18 2 16 18 18 18 1 1 18 18 11 11 10 10 10 10 10 7 10 6 4 4 4 29 4 4 1 3 4 4 4 30 30 30 30 30 11 30 30 14 14 14 13 14 8 26 23 34 38 1 20 20 10 1 20 51 70 4 1 3 2 68 1 67 5 1 66 3 1 65 5 1 71 9 20 9 29 29 39 39 30 29 30 30 30 10 8 7 5 2 3 6 4 2 46 10 7 39 39 39 38 24 38 3 1 35 37 1 37 46 51 64 10 10 64 10 1 9 6 5 1 58 17 17 1 16 1 15 59 3 3 1 2 56 2 2 2 1 1 57 4 2 3 56 7 4 3 49 2 56 6 56 2 56 3 2 1 55 12 11 43 2 3 51 4 6 3 51 5 12 7 47 4 7 3 50 2 2 50 1 1 5 64 36 2 38 27 26 26 6 11 11 5 5 8 31 38 51 51 51 46 36 6 4 6 1 6 4 6 13 13 13 6 4 4 6 6 10 83 91 92 71 71 52 52 92 91 71 70 3 52 51 6 92 92 92 92 92 92 92 92 92 8 92 92 3 1663 19 1665 1 1666 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * GENEVE: Generic Network Virtualization Encapsulation * * Copyright (c) 2015 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/hash.h> #include <net/dst_metadata.h> #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/geneve.h> #include <net/gro.h> #include <net/netdev_lock.h> #include <net/protocol.h> #define GENEVE_NETDEV_VER "0.6" #define GENEVE_N_VID (1u << 24) #define GENEVE_VID_MASK (GENEVE_N_VID - 1) #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); #define GENEVE_VER 0 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr)) #define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN) #define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN) #define GENEVE_OPT_NETDEV_CLASS 0x100 #define GENEVE_OPT_GRO_HINT_SIZE 8 #define GENEVE_OPT_GRO_HINT_TYPE 1 #define GENEVE_OPT_GRO_HINT_LEN 1 struct geneve_opt_gro_hint { u8 inner_proto_id:2, nested_is_v6:1; u8 nested_nh_offset; u8 nested_tp_offset; u8 nested_hdr_len; }; struct geneve_skb_cb { unsigned int gro_hint_len; struct geneve_opt_gro_hint gro_hint; }; #define GENEVE_SKB_CB(__skb) ((struct geneve_skb_cb *)&((__skb)->cb[0])) /* per-network namespace private data for this module */ struct geneve_net { struct list_head geneve_list; /* sock_list is protected by rtnl lock */ struct list_head sock_list; }; static unsigned int geneve_net_id; struct geneve_dev_node { struct hlist_node hlist; struct geneve_dev *geneve; }; struct geneve_config { bool collect_md; bool dualstack; bool use_udp6_rx_checksums; bool ttl_inherit; bool gro_hint; enum ifla_geneve_df df; bool inner_proto_inherit; u16 port_min; u16 port_max; /* Must be last --ends in a flexible-array member. */ struct ip_tunnel_info info; }; /* Pseudo network device */ struct geneve_dev { struct geneve_dev_node hlist4; /* vni hash table for IPv4 socket */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_dev_node hlist6; /* vni hash table for IPv6 socket */ #endif struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */ #endif struct list_head next; /* geneve's per namespace list */ struct gro_cells gro_cells; struct geneve_config cfg; }; struct geneve_sock { bool collect_md; bool gro_hint; struct list_head list; struct sock *sk; struct rcu_head rcu; int refcnt; struct hlist_head vni_list[VNI_HASH_SIZE]; }; static const __be16 proto_id_map[] = { htons(ETH_P_TEB), htons(ETH_P_IPV6), htons(ETH_P_IP) }; static int proto_to_id(__be16 proto) { int i; for (i = 0; i < ARRAY_SIZE(proto_id_map); i++) if (proto_id_map[i] == proto) return i; return -1; } static inline __u32 geneve_net_vni_hash(u8 vni[3]) { __u32 vnid; vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2]; return hash_32(vnid, VNI_HASH_BITS); } static __be64 vni_to_tunnel_id(const __u8 *vni) { #ifdef __BIG_ENDIAN return (vni[0] << 16) | (vni[1] << 8) | vni[2]; #else return (__force __be64)(((__force u64)vni[0] << 40) | ((__force u64)vni[1] << 48) | ((__force u64)vni[2] << 56)); #endif } /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { #ifdef __BIG_ENDIAN vni[0] = (__force __u8)(tun_id >> 16); vni[1] = (__force __u8)(tun_id >> 8); vni[2] = (__force __u8)tun_id; #else vni[0] = (__force __u8)((__force u64)tun_id >> 40); vni[1] = (__force __u8)((__force u64)tun_id >> 48); vni[2] = (__force __u8)((__force u64)tun_id >> 56); #endif } static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni) { return !memcmp(vni, &tun_id[5], 3); } static sa_family_t geneve_get_sk_family(struct geneve_sock *gs) { return gs->sk->sk_family; } static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, __be32 addr, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && addr == node->geneve->cfg.info.key.u.ipv4.dst) return node->geneve; } return NULL; } #if IS_ENABLED(CONFIG_IPV6) static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs, struct in6_addr addr6, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && ipv6_addr_equal(&addr6, &node->geneve->cfg.info.key.u.ipv6.dst)) return node->geneve; } return NULL; } #endif static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { return (struct genevehdr *)(udp_hdr(skb) + 1); } static struct geneve_dev *geneve_lookup_skb(struct geneve_sock *gs, struct sk_buff *skb) { static u8 zero_vni[3]; u8 *vni; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph; __be32 addr; iph = ip_hdr(skb); /* outer IP header... */ if (gs->collect_md) { vni = zero_vni; addr = 0; } else { vni = geneve_hdr(skb)->vni; addr = iph->saddr; } return geneve_lookup(gs, addr, vni); #if IS_ENABLED(CONFIG_IPV6) } else if (geneve_get_sk_family(gs) == AF_INET6) { static struct in6_addr zero_addr6; struct ipv6hdr *ip6h; struct in6_addr addr6; ip6h = ipv6_hdr(skb); /* outer IPv6 header... */ if (gs->collect_md) { vni = zero_vni; addr6 = zero_addr6; } else { vni = geneve_hdr(skb)->vni; addr6 = ip6h->saddr; } return geneve6_lookup(gs, addr6, vni); #endif } return NULL; } /* geneve receive/decap routine */ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct sk_buff *skb, const struct genevehdr *gnvh) { struct metadata_dst *tun_dst = NULL; unsigned int len; int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_KEY_BIT, flags); __assign_bit(IP_TUNNEL_OAM_BIT, flags, gnvh->oam); __assign_bit(IP_TUNNEL_CRIT_OPT_BIT, flags, gnvh->critical); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); if (!tun_dst) { dev_dstats_rx_dropped(geneve->dev); goto drop; } /* Update tunnel dst according to Geneve options. */ ip_tunnel_flags_zero(flags); __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, flags); ip_tunnel_info_opts_set(&tun_dst->u.tun_info, gnvh->options, gnvh->opt_len * 4, flags); } else { /* Drop packets w/ critical options, * since we don't support any... */ if (gnvh->critical) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } if (tun_dst) skb_dst_set(skb, &tun_dst->dst); if (gnvh->proto_type == htons(ETH_P_TEB)) { skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, geneve->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } else { skb_reset_mac_header(skb); skb->dev = geneve->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(geneve->dev, rx_length_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err)) { if (log_ecn_error) { if (geneve_get_sk_family(gs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); #if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); #endif } if (err > 1) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } /* Skip the additional GRO stage when hints are in use. */ len = skb->len; if (skb->encapsulation) err = netif_rx(skb); else err = gro_cells_receive(&geneve->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_dstats_rx_add(geneve->dev, len); return; drop: /* Consume bad packet */ kfree_skb(skb); } /* Setup stats when device is created */ static int geneve_init(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); int err; err = gro_cells_init(&geneve->gro_cells, dev); if (err) return err; err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL); if (err) { gro_cells_destroy(&geneve->gro_cells); return err; } netdev_lockdep_set_classes(dev); return 0; } static void geneve_uninit(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); dst_cache_destroy(&geneve->cfg.info.dst_cache); gro_cells_destroy(&geneve->gro_cells); } static int geneve_hlen(const struct genevehdr *gh) { return sizeof(*gh) + gh->opt_len * 4; } /* * Look for GRO hint in the genenve options; if not found or does not pass basic * sanitization return 0, otherwise the offset WRT the geneve hdr start. */ static unsigned int geneve_opt_gro_hint_off(const struct genevehdr *gh, __be16 *type, unsigned int *gh_len) { struct geneve_opt *opt = (void *)(gh + 1); unsigned int id, opt_len = gh->opt_len; struct geneve_opt_gro_hint *gro_hint; while (opt_len >= (GENEVE_OPT_GRO_HINT_SIZE >> 2)) { if (opt->opt_class == htons(GENEVE_OPT_NETDEV_CLASS) && opt->type == GENEVE_OPT_GRO_HINT_TYPE && opt->length == GENEVE_OPT_GRO_HINT_LEN) goto found; /* check for bad opt len */ if (opt->length + 1 >= opt_len) return 0; /* next opt */ opt_len -= opt->length + 1; opt = ((void *)opt) + ((opt->length + 1) << 2); } return 0; found: gro_hint = (struct geneve_opt_gro_hint *)opt->opt_data; /* * Sanitize the hinted hdrs: the nested transport is UDP and must fit * the overall hinted hdr size. */ if (gro_hint->nested_tp_offset + sizeof(struct udphdr) > gro_hint->nested_hdr_len) return 0; if (gro_hint->nested_nh_offset + (gro_hint->nested_is_v6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr)) > gro_hint->nested_tp_offset) return 0; /* Allow only supported L2. */ id = gro_hint->inner_proto_id; if (id >= ARRAY_SIZE(proto_id_map)) return 0; *type = proto_id_map[id]; *gh_len += gro_hint->nested_hdr_len; return (void *)gro_hint - (void *)gh; } static const struct geneve_opt_gro_hint * geneve_opt_gro_hint(const struct genevehdr *gh, unsigned int hint_off) { return (const struct geneve_opt_gro_hint *)((void *)gh + hint_off); } static unsigned int geneve_sk_gro_hint_off(const struct sock *sk, const struct genevehdr *gh, __be16 *type, unsigned int *gh_len) { const struct geneve_sock *gs = rcu_dereference_sk_user_data(sk); if (!gs || !gs->gro_hint) return 0; return geneve_opt_gro_hint_off(gh, type, gh_len); } /* Validate the packet headers pointed by data WRT the provided hint */ static bool geneve_opt_gro_hint_validate(void *data, const struct geneve_opt_gro_hint *gro_hint) { void *nested_nh = data + gro_hint->nested_nh_offset; struct iphdr *iph; if (gro_hint->nested_is_v6) { struct ipv6hdr *ipv6h = nested_nh; struct ipv6_opt_hdr *opth; int offset, len; if (ipv6h->nexthdr == IPPROTO_UDP) return true; offset = sizeof(*ipv6h) + gro_hint->nested_nh_offset; while (offset + sizeof(*opth) <= gro_hint->nested_tp_offset) { opth = data + offset; len = ipv6_optlen(opth); if (len + offset > gro_hint->nested_tp_offset) return false; if (opth->nexthdr == IPPROTO_UDP) return true; offset += len; } return false; } iph = nested_nh; if (*(u8 *)iph != 0x45 || ip_is_fragment(iph) || iph->protocol != IPPROTO_UDP || ip_fast_csum((u8 *)iph, 5)) return false; return true; } /* * Validate the skb headers following the specified geneve hdr vs the * provided hint, including nested L4 checksum. * The caller already ensured that the relevant amount of data is available * in the linear part. */ static bool geneve_opt_gro_hint_validate_csum(const struct sk_buff *skb, const struct genevehdr *gh, const struct geneve_opt_gro_hint *gro_hint) { unsigned int plen, gh_len = geneve_hlen(gh); void *nested = (void *)gh + gh_len; struct udphdr *nested_uh; unsigned int nested_len; struct ipv6hdr *ipv6h; struct iphdr *iph; __wsum csum, psum; if (!geneve_opt_gro_hint_validate(nested, gro_hint)) return false; /* Use GRO hints with nested csum only if the outer header has csum. */ nested_uh = nested + gro_hint->nested_tp_offset; if (!nested_uh->check || skb->ip_summed == CHECKSUM_PARTIAL) return true; if (!NAPI_GRO_CB(skb)->csum_valid) return false; /* Compute the complete checksum up to the nested transport. */ plen = gh_len + gro_hint->nested_tp_offset; csum = csum_sub(NAPI_GRO_CB(skb)->csum, csum_partial(gh, plen, 0)); nested_len = skb_gro_len(skb) - plen; /* Compute the nested pseudo header csum. */ ipv6h = nested + gro_hint->nested_nh_offset; iph = (struct iphdr *)ipv6h; psum = gro_hint->nested_is_v6 ? ~csum_unfold(csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, nested_len, IPPROTO_UDP, 0)) : csum_tcpudp_nofold(iph->saddr, iph->daddr, nested_len, IPPROTO_UDP, 0); return !csum_fold(csum_add(psum, csum)); } static int geneve_post_decap_hint(const struct sock *sk, struct sk_buff *skb, unsigned int gh_len, struct genevehdr **geneveh) { const struct geneve_opt_gro_hint *gro_hint; unsigned int len, total_len, hint_off; struct ipv6hdr *ipv6h; struct iphdr *iph; struct udphdr *uh; __be16 p; hint_off = geneve_sk_gro_hint_off(sk, *geneveh, &p, &len); if (!hint_off) return 0; if (!skb_is_gso(skb)) return 0; gro_hint = geneve_opt_gro_hint(*geneveh, hint_off); if (unlikely(!pskb_may_pull(skb, gro_hint->nested_hdr_len))) return -ENOMEM; *geneveh = geneve_hdr(skb); gro_hint = geneve_opt_gro_hint(*geneveh, hint_off); /* * Validate hints from untrusted source before accessing * the headers; csum will be checked later by the nested * protocol rx path. */ if (unlikely(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY && !geneve_opt_gro_hint_validate(skb->data, gro_hint))) return -EINVAL; ipv6h = (void *)skb->data + gro_hint->nested_nh_offset; iph = (struct iphdr *)ipv6h; total_len = skb->len - gro_hint->nested_nh_offset; if (total_len >= GRO_LEGACY_MAX_SIZE) return -E2BIG; /* * After stripping the outer encap, the packet still carries a * tunnel encapsulation: the nested one. */ skb->encapsulation = 1; /* GSO expect a valid transpor header, move it to the current one. */ skb_set_transport_header(skb, gro_hint->nested_tp_offset); /* Adjust the nested IP{6} hdr to actual GSO len. */ if (gro_hint->nested_is_v6) { ipv6h->payload_len = htons(total_len - sizeof(*ipv6h)); } else { __be16 old_len = iph->tot_len; iph->tot_len = htons(total_len); /* For IPv4 additionally adjust the nested csum. */ csum_replace2(&iph->check, old_len, iph->tot_len); ip_send_check(iph); } /* Adjust the nested UDP header len and checksum. */ uh = udp_hdr(skb); uh->len = htons(skb->len - gro_hint->nested_tp_offset); if (uh->check) { len = skb->len - gro_hint->nested_tp_offset; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; if (gro_hint->nested_is_v6) uh->check = ~udp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0); else uh->check = ~udp_v4_check(len, iph->saddr, iph->daddr, 0); } else { skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; } return 0; } /* Callback from net/ipv4/udp.c to receive packets */ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_dev *geneve; struct geneve_sock *gs; __be16 inner_proto; int opts_len; /* Need UDP and Geneve header to be present */ if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) goto drop; /* Return packets with reserved bits set */ geneveh = geneve_hdr(skb); if (unlikely(geneveh->ver != GENEVE_VER)) goto drop; gs = rcu_dereference_sk_user_data(sk); if (!gs) goto drop; geneve = geneve_lookup_skb(gs, skb); if (!geneve) goto drop; inner_proto = geneveh->proto_type; if (unlikely((!geneve->cfg.inner_proto_inherit && inner_proto != htons(ETH_P_TEB)))) { dev_dstats_rx_dropped(geneve->dev); goto drop; } opts_len = geneveh->opt_len * 4; if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto, !net_eq(geneve->net, dev_net(geneve->dev)))) { dev_dstats_rx_dropped(geneve->dev); goto drop; } /* * After hint processing, the transport header points to the inner one * and we can't use anymore on geneve_hdr(). */ geneveh = geneve_hdr(skb); if (geneve_post_decap_hint(sk, skb, sizeof(struct genevehdr) + opts_len, &geneveh)) { DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } geneve_rx(geneve, gs, skb, geneveh); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_sock *gs; u8 zero_vni[3] = { 0 }; u8 *vni = zero_vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + GENEVE_BASE_HLEN)) return -EINVAL; geneveh = geneve_hdr(skb); if (geneveh->ver != GENEVE_VER) return -EINVAL; if (geneveh->proto_type != htons(ETH_P_TEB)) return -EINVAL; gs = rcu_dereference_sk_user_data(sk); if (!gs) return -ENOENT; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph = ip_hdr(skb); __be32 addr4 = 0; if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr4 = iph->daddr; } return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT; } #if IS_ENABLED(CONFIG_IPV6) if (geneve_get_sk_family(gs) == AF_INET6) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct in6_addr addr6; memset(&addr6, 0, sizeof(struct in6_addr)); if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr6 = ip6h->daddr; } return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT; } #endif return -EPFNOSUPPORT; } static struct sock *geneve_create_sock(struct net *net, struct geneve_dev *geneve, bool ipv6) { struct ip_tunnel_info *info = &geneve->cfg.info; struct udp_port_cfg udp_conf; struct socket *sock; int err; memset(&udp_conf, 0, sizeof(udp_conf)); #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { udp_conf.family = AF_INET6; udp_conf.ipv6_v6only = 1; udp_conf.use_udp6_rx_checksums = geneve->cfg.use_udp6_rx_checksums; udp_conf.local_ip6 = info->key.u.ipv6.src; } else #endif { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = info->key.u.ipv4.src; } udp_conf.local_udp_port = info->key.tp_dst; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock->sk; } static bool geneve_hdr_match(struct sk_buff *skb, const struct genevehdr *gh, const struct genevehdr *gh2, unsigned int hint_off) { const struct geneve_opt_gro_hint *gro_hint; void *nested, *nested2, *nh, *nh2; struct udphdr *udp, *udp2; unsigned int gh_len; /* Match the geneve hdr and options */ if (gh->opt_len != gh2->opt_len) return false; gh_len = geneve_hlen(gh); if (memcmp(gh, gh2, gh_len)) return false; if (!hint_off) return true; /* * When gro is present consider the nested headers as part * of the geneve options */ nested = (void *)gh + gh_len; nested2 = (void *)gh2 + gh_len; gro_hint = geneve_opt_gro_hint(gh, hint_off); if (!memcmp(nested, nested2, gro_hint->nested_hdr_len)) return true; /* * The nested headers differ; the packets can still belong to * the same flow when IPs/proto/ports match; if so flushing is * required. */ nh = nested + gro_hint->nested_nh_offset; nh2 = nested2 + gro_hint->nested_nh_offset; if (gro_hint->nested_is_v6) { struct ipv6hdr *iph = nh, *iph2 = nh2; unsigned int nested_nlen; __be32 first_word; first_word = *(__be32 *)iph ^ *(__be32 *)iph2; if ((first_word & htonl(0xF00FFFFF)) || !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || iph->nexthdr != iph2->nexthdr) return false; nested_nlen = gro_hint->nested_tp_offset - gro_hint->nested_nh_offset; if (nested_nlen > sizeof(struct ipv6hdr) && (memcmp(iph + 1, iph2 + 1, nested_nlen - sizeof(struct ipv6hdr)))) return false; } else { struct iphdr *iph = nh, *iph2 = nh2; if ((iph->protocol ^ iph2->protocol) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) return false; } udp = nested + gro_hint->nested_tp_offset; udp2 = nested2 + gro_hint->nested_tp_offset; if (udp->source != udp2->source || udp->dest != udp2->dest || udp->check != udp2->check) return false; NAPI_GRO_CB(skb)->flush = 1; return true; } static struct sk_buff *geneve_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { unsigned int hlen, gh_len, off_gnv, hint_off; const struct geneve_opt_gro_hint *gro_hint; const struct packet_offload *ptype; struct genevehdr *gh, *gh2; struct sk_buff *pp = NULL; struct sk_buff *p; int flush = 1; __be16 type; off_gnv = skb_gro_offset(skb); hlen = off_gnv + sizeof(*gh); gh = skb_gro_header(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; if (gh->ver != GENEVE_VER || gh->oam) goto out; gh_len = geneve_hlen(gh); type = gh->proto_type; hlen = off_gnv + gh_len; if (!skb_gro_may_pull(skb, hlen)) { gh = skb_gro_header_slow(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; } /* The GRO hint/nested hdr could use a different ethernet type. */ hint_off = geneve_sk_gro_hint_off(sk, gh, &type, &gh_len); if (hint_off) { /* * If the hint is present, and nested hdr validation fails, do * not attempt plain GRO: it will ignore inner hdrs and cause * OoO. */ gh = skb_gro_header(skb, off_gnv + gh_len, off_gnv); if (unlikely(!gh)) goto out; gro_hint = geneve_opt_gro_hint(gh, hint_off); if (!geneve_opt_gro_hint_validate_csum(skb, gh, gro_hint)) goto out; } list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; gh2 = (struct genevehdr *)(p->data + off_gnv); if (!geneve_hdr_match(skb, gh, gh2, hint_off)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); if (likely(type == htons(ETH_P_TEB))) return call_gro_receive(eth_gro_receive, head, skb); ptype = gro_find_receive_by_type(type); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final(skb, pp, flush); return pp; } static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct genevehdr *gh; struct packet_offload *ptype; __be16 type; unsigned int gh_len; int err = -ENOSYS; gh = (struct genevehdr *)(skb->data + nhoff); gh_len = geneve_hlen(gh); type = gh->proto_type; geneve_sk_gro_hint_off(sk, gh, &type, &gh_len); /* Bail out if we are about to dispatch past the inner network header * gro_receive() validated. An inner VLAN tag only pushes * inner_network_offset out, so use a lower bound. */ if (skb->encapsulation) { unsigned int inner_nh = nhoff + gh_len; if (type == htons(ETH_P_TEB)) inner_nh += ETH_HLEN; if (unlikely(inner_nh > NAPI_GRO_CB(skb)->inner_network_offset)) return -EINVAL; } /* since skb->encapsulation is set, eth_gro_complete() sets the inner mac header */ if (likely(type == htons(ETH_P_TEB))) return eth_gro_complete(skb, nhoff + gh_len); ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); skb_set_inner_mac_header(skb, nhoff + gh_len); return err; } /* Create new listen socket if needed */ static struct geneve_sock *geneve_socket_create(struct net *net, struct geneve_dev *geneve, bool ipv6) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct udp_tunnel_sock_cfg tunnel_cfg; struct geneve_sock *gs; struct sock *sk; int h; gs = kzalloc_obj(*gs); if (!gs) return ERR_PTR(-ENOMEM); sk = geneve_create_sock(net, geneve, ipv6); if (IS_ERR(sk)) { kfree(gs); return ERR_CAST(sk); } gs->sk = sk; gs->refcnt = 1; for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&gs->vni_list[h]); /* Initialize the geneve udp offloads structure */ udp_tunnel_notify_add_rx_port(sk, UDP_TUNNEL_TYPE_GENEVE); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = gs; tunnel_cfg.encap_type = 1; tunnel_cfg.gro_receive = geneve_gro_receive; tunnel_cfg.gro_complete = geneve_gro_complete; tunnel_cfg.encap_rcv = geneve_udp_encap_recv; tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sk, &tunnel_cfg); list_add(&gs->list, &gn->sock_list); return gs; } static void __geneve_sock_release(struct geneve_sock *gs) { if (!gs || --gs->refcnt) return; list_del(&gs->list); udp_tunnel_notify_del_rx_port(gs->sk, UDP_TUNNEL_TYPE_GENEVE); udp_tunnel_sock_release(gs->sk); kfree_rcu(gs, rcu); } static void geneve_sock_release(struct geneve_dev *geneve) { struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4); #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); #endif rcu_assign_pointer(geneve->sock4, NULL); __geneve_sock_release(gs4); #if IS_ENABLED(CONFIG_IPV6) __geneve_sock_release(gs6); #endif } static struct geneve_sock *geneve_find_sock(struct net *net, struct geneve_dev *geneve, bool ipv6) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct ip_tunnel_info *info = &geneve->cfg.info; sa_family_t family = ipv6 ? AF_INET6 : AF_INET; bool gro_hint = geneve->cfg.gro_hint; __be16 dst_port = info->key.tp_dst; struct geneve_sock *gs; list_for_each_entry(gs, &gn->sock_list, list) { if (inet_sk(gs->sk)->inet_sport != dst_port) continue; if (geneve_get_sk_family(gs) != family) continue; if (gs->gro_hint != gro_hint) continue; if (family == AF_INET && inet_sk(gs->sk)->inet_saddr != info->key.u.ipv4.src) continue; #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6 && !ipv6_addr_equal(&gs->sk->sk_v6_rcv_saddr, &info->key.u.ipv6.src)) continue; #endif return gs; } return NULL; } static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) { struct net *net = geneve->net; struct geneve_dev_node *node; struct geneve_sock *gs; __u8 vni[3]; __u32 hash; gs = geneve_find_sock(net, geneve, ipv6); if (gs) { gs->refcnt++; goto out; } gs = geneve_socket_create(net, geneve, ipv6); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->cfg.collect_md; gs->gro_hint = geneve->cfg.gro_hint; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(geneve->sock6, gs); node = &geneve->hlist6; } else #endif { rcu_assign_pointer(geneve->sock4, gs); node = &geneve->hlist4; } node->geneve = geneve; tunnel_id_to_vni(geneve->cfg.info.key.tun_id, vni); hash = geneve_net_vni_hash(vni); hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]); return 0; } static int geneve_open(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); bool dualstack = geneve->cfg.dualstack; bool ipv4, ipv6; int ret = 0; ipv6 = geneve->cfg.info.mode & IP_TUNNEL_INFO_IPV6 || dualstack; ipv4 = !ipv6 || dualstack; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { ret = geneve_sock_add(geneve, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = geneve_sock_add(geneve, false); if (ret < 0) geneve_sock_release(geneve); return ret; } static int geneve_stop(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); hlist_del_init_rcu(&geneve->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&geneve->hlist6.hlist); #endif geneve_sock_release(geneve); return 0; } static void geneve_build_header(struct genevehdr *geneveh, const struct ip_tunnel_info *info, __be16 inner_proto) { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, info->key.tun_flags); geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, info->key.tun_flags); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) ip_tunnel_info_opts_get(geneveh->options, info); } static int geneve_build_gro_hint_opt(const struct geneve_dev *geneve, struct sk_buff *skb) { struct geneve_skb_cb *cb = GENEVE_SKB_CB(skb); struct geneve_opt_gro_hint *hint; unsigned int nhlen; bool nested_is_v6; int id; BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct geneve_skb_cb)); cb->gro_hint_len = 0; /* Try to add the GRO hint only in case of double encap. */ if (!geneve->cfg.gro_hint || !skb->encapsulation) return 0; /* * The nested headers must fit the geneve opt len fields and the * nested encap must carry a nested transport (UDP) header. */ nhlen = skb_inner_mac_header(skb) - skb->data; if (nhlen > 255 || !skb_transport_header_was_set(skb) || skb->inner_protocol_type != ENCAP_TYPE_ETHER || (skb_transport_offset(skb) + sizeof(struct udphdr) > nhlen)) return 0; id = proto_to_id(skb->inner_protocol); if (id < 0) return 0; nested_is_v6 = skb->protocol == htons(ETH_P_IPV6); if (nested_is_v6) { int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); u8 proto = ipv6_hdr(skb)->nexthdr; __be16 foff; if (ipv6_skip_exthdr(skb, start, &proto, &foff) < 0 || proto != IPPROTO_UDP) return 0; } else { if (ip_hdr(skb)->protocol != IPPROTO_UDP) return 0; } hint = &cb->gro_hint; memset(hint, 0, sizeof(*hint)); hint->inner_proto_id = id; hint->nested_is_v6 = skb->protocol == htons(ETH_P_IPV6); hint->nested_nh_offset = skb_network_offset(skb); hint->nested_tp_offset = skb_transport_offset(skb); hint->nested_hdr_len = nhlen; cb->gro_hint_len = GENEVE_OPT_GRO_HINT_SIZE; return GENEVE_OPT_GRO_HINT_SIZE; } static void geneve_put_gro_hint_opt(struct genevehdr *gnvh, int opt_size, const struct geneve_opt_gro_hint *hint) { struct geneve_opt *gro_opt; /* geneve_build_header() did not took in account the GRO hint. */ gnvh->opt_len = (opt_size + GENEVE_OPT_GRO_HINT_SIZE) >> 2; gro_opt = (void *)(gnvh + 1) + opt_size; memset(gro_opt, 0, sizeof(*gro_opt)); gro_opt->opt_class = htons(GENEVE_OPT_NETDEV_CLASS); gro_opt->type = GENEVE_OPT_GRO_HINT_TYPE; gro_opt->length = GENEVE_OPT_GRO_HINT_LEN; memcpy(gro_opt + 1, hint, sizeof(*hint)); } static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, const struct ip_tunnel_info *info, const struct geneve_dev *geneve, int ip_hdr_len) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_skb_cb *cb = GENEVE_SKB_CB(skb); struct genevehdr *gnvh; __be16 inner_proto; bool double_encap; int min_headroom; int opt_size; int err; skb_reset_mac_header(skb); skb_scrub_packet(skb, xnet); opt_size = info->options_len + cb->gro_hint_len; min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + GENEVE_BASE_HLEN + opt_size + ip_hdr_len; err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; double_encap = udp_tunnel_handle_partial(skb); err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; gnvh = __skb_push(skb, sizeof(*gnvh) + opt_size); inner_proto = inner_proto_inherit ? skb->protocol : htons(ETH_P_TEB); geneve_build_header(gnvh, info, inner_proto); if (cb->gro_hint_len) geneve_put_gro_hint_opt(gnvh, info->options_len, &cb->gro_hint); udp_tunnel_set_inner_protocol(skb, double_encap, inner_proto); return 0; free_dst: dst_release(dst); return err; } static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev, const struct ip_tunnel_info *info, bool *use_cache) { struct geneve_dev *geneve = netdev_priv(dev); u8 dsfield; dsfield = info->key.tos; if (dsfield == 1 && !geneve->cfg.collect_md) { dsfield = ip_tunnel_get_dsfield(ip_hdr(skb), skb); *use_cache = false; } return dsfield; } static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; bool use_cache; __u8 tos, ttl; __be16 df = 0; __be32 saddr; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, geneve->cfg.inner_proto_inherit)) return -EINVAL; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); if (geneve->cfg.info.key.u.ipv4.src && saddr != geneve->cfg.info.key.u.ipv4.src) { dst_release(&rt->dst); return -EADDRNOTAVAIL; } err = skb_tunnel_check_pmtu(skb, &rt->dst, GENEVE_IPV4_HLEN + info->options_len + geneve_build_gro_hint_opt(geneve, skb), netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(&rt->dst); return err; } else if (err) { struct ip_tunnel_info *info; info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(&rt->dst); return -ENOMEM; } unclone->key.u.ipv4.dst = saddr; unclone->key.u.ipv4.src = info->key.u.ipv4.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(&rt->dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(&rt->dst); return -EMSGSIZE; } tos = ip_tunnel_ecn_encap(tos, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); if (geneve->cfg.df == GENEVE_DF_SET) { df = htons(IP_DF); } else if (geneve->cfg.df == GENEVE_DF_INHERIT) { struct ethhdr *eth = skb_eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6) { df = htons(IP_DF); } else if (ntohs(eth->h_proto) == ETH_P_IP) { struct iphdr *iph = ip_hdr(skb); if (iph->frag_off & htons(IP_DF)) df = htons(IP_DF); } } } err = geneve_build_skb(&rt->dst, skb, info, geneve, sizeof(struct iphdr)); if (unlikely(err)) return err; udp_tunnel_xmit_skb(rt, gs4->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), 0); return 0; } #if IS_ENABLED(CONFIG_IPV6) static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr; bool use_cache; __u8 prio, ttl; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, geneve->cfg.inner_proto_inherit)) return -EINVAL; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sk, 0, &saddr, key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); if (!ipv6_addr_any(&geneve->cfg.info.key.u.ipv6.src) && !ipv6_addr_equal(&saddr, &geneve->cfg.info.key.u.ipv6.src)) { dst_release(dst); return -EADDRNOTAVAIL; } err = skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len + geneve_build_gro_hint_opt(geneve, skb), netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(dst); return err; } else if (err) { struct ip_tunnel_info *info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(dst); return -ENOMEM; } unclone->key.u.ipv6.dst = saddr; unclone->key.u.ipv6.src = info->key.u.ipv6.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(dst); return -EMSGSIZE; } prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, geneve, sizeof(struct ipv6hdr)); if (unlikely(err)) return err; udp_tunnel6_xmit_skb(dst, gs6->sk, skb, dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), 0); return 0; } #endif static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (geneve->cfg.collect_md) { info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); dev_kfree_skb(skb); dev_dstats_tx_dropped(dev); return NETDEV_TX_OK; } } else { info = &geneve->cfg.info; } rcu_read_lock(); #if IS_ENABLED(CONFIG_IPV6) if (info->mode & IP_TUNNEL_INFO_IPV6) err = geneve6_xmit_skb(skb, dev, geneve, info); else #endif err = geneve_xmit_skb(skb, dev, geneve, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; if (err != -EMSGSIZE) dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static int geneve_change_mtu(struct net_device *dev, int new_mtu) { if (new_mtu > dev->max_mtu) new_mtu = dev->max_mtu; else if (new_mtu < dev->min_mtu) new_mtu = dev->min_mtu; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct geneve_dev *geneve = netdev_priv(dev); __be16 sport; if (ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); bool use_cache; __be32 saddr; u8 tos; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = saddr; #if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); struct in6_addr saddr; bool use_cache; u8 prio; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sk, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); dst_release(dst); info->key.u.ipv6.src = saddr; #endif } else { return -EINVAL; } info->key.tp_src = sport; info->key.tp_dst = geneve->cfg.info.key.tp_dst; return 0; } static const struct net_device_ops geneve_netdev_ops = { .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fill_metadata_dst = geneve_fill_metadata_dst, }; static void geneve_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver)); } static const struct ethtool_ops geneve_ethtool_ops = { .get_drvinfo = geneve_get_drvinfo, .get_link = ethtool_op_get_link, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type geneve_type = { .name = "geneve", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening GENEVE udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void geneve_offload_rx_ports(struct net_device *dev, bool push) { struct net *net = dev_net(dev); struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; ASSERT_RTNL(); list_for_each_entry(gs, &gn->sock_list, list) { if (push) { udp_tunnel_push_rx_port(dev, gs->sk, UDP_TUNNEL_TYPE_GENEVE); } else { udp_tunnel_drop_rx_port(dev, gs->sk, UDP_TUNNEL_TYPE_GENEVE); } } } /* Initialize the device structure. */ static void geneve_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &geneve_netdev_ops; dev->ethtool_ops = &geneve_ethtool_ops; dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &geneve_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; /* Partial features are disabled by default. */ dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= UDP_TUNNEL_PARTIAL_FEATURES; dev->hw_features |= NETIF_F_GSO_PARTIAL; dev->hw_enc_features = dev->hw_features; dev->gso_partial_features = UDP_TUNNEL_PARTIAL_FEATURES; dev->mangleid_features = NETIF_F_GSO_PARTIAL; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE * options, to avoid excluding potentially valid * configurations. This will be further reduced by IPvX hdr size. */ dev->max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len; netif_keep_dst(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->lltx = true; eth_hw_addr_random(dev); } static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UNSPEC] = { .strict_start_type = IFLA_GENEVE_INNER_PROTO_INHERIT }, [IFLA_GENEVE_ID] = { .type = NLA_U32 }, [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, [IFLA_GENEVE_LABEL] = { .type = NLA_U32 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 }, [IFLA_GENEVE_DF] = { .type = NLA_U8 }, [IFLA_GENEVE_INNER_PROTO_INHERIT] = { .type = NLA_FLAG }, [IFLA_GENEVE_PORT_RANGE] = NLA_POLICY_EXACT_LEN(sizeof(struct ifla_geneve_port_range)), [IFLA_GENEVE_GRO_HINT] = { .type = NLA_FLAG }, [IFLA_GENEVE_LOCAL] = { .type = NLA_BE32 }, [IFLA_GENEVE_LOCAL6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (!data) { NL_SET_ERR_MSG(extack, "Not enough attributes provided to perform the operation"); return -EINVAL; } if (data[IFLA_GENEVE_ID]) { __u32 vni = nla_get_u32(data[IFLA_GENEVE_ID]); if (vni >= GENEVE_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_ID], "Geneve ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_GENEVE_DF]) { enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]); if (df < 0 || df > GENEVE_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF], "Invalid DF attribute"); return -EINVAL; } } if (data[IFLA_GENEVE_PORT_RANGE]) { const struct ifla_geneve_port_range *p; p = nla_data(data[IFLA_GENEVE_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_PORT_RANGE], "Invalid source port range"); return -EINVAL; } } return 0; } static bool geneve_saddr_wildcard(const struct ip_tunnel_info *info) { if (ip_tunnel_info_af(info) == AF_INET) { if (!info->key.u.ipv4.src) return true; #if IS_ENABLED(CONFIG_IPV6) } else { if (ipv6_addr_any(&info->key.u.ipv6.src)) return true; #endif } return false; } static bool geneve_saddr_conflict(const struct ip_tunnel_info *a, const struct ip_tunnel_info *b) { if (ip_tunnel_info_af(a) != ip_tunnel_info_af(b)) return false; if (geneve_saddr_wildcard(a) || geneve_saddr_wildcard(b)) return true; if (ip_tunnel_info_af(a) == AF_INET) { if (a->key.u.ipv4.src == b->key.u.ipv4.src) return true; #if IS_ENABLED(CONFIG_IPV6) } else { if (ipv6_addr_equal(&a->key.u.ipv6.src, &b->key.u.ipv6.src)) return true; #endif } return false; } static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, const struct geneve_config *cfg, const struct ip_tunnel_info *info, bool *tun_on_same_port, bool *tun_collect_md) { struct geneve_dev *geneve, *t = NULL; *tun_on_same_port = false; *tun_collect_md = false; list_for_each_entry(geneve, &gn->geneve_list, next) { if (info->key.tp_dst == geneve->cfg.info.key.tp_dst && (cfg->dualstack || geneve->cfg.dualstack || geneve_saddr_conflict(info, &geneve->cfg.info))) { *tun_collect_md |= geneve->cfg.collect_md; *tun_on_same_port = true; } if (info->key.tun_id == geneve->cfg.info.key.tun_id && info->key.tp_dst == geneve->cfg.info.key.tp_dst && !memcmp(&info->key.u, &geneve->cfg.info.key.u, sizeof(info->key.u))) t = geneve; } return t; } static bool is_tnl_info_zero(const struct ip_tunnel_info *info) { return !(info->key.tun_id || info->key.tos || !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || #if IS_ENABLED(CONFIG_IPV6) (ip_tunnel_info_af(info) == AF_INET6 && !ipv6_addr_any(&info->key.u.ipv6.dst)) || #endif (ip_tunnel_info_af(info) == AF_INET && info->key.u.ipv4.dst)); } static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, struct ip_tunnel_info *b) { if (ip_tunnel_info_af(a) == AF_INET) return a->key.u.ipv4.dst == b->key.u.ipv4.dst; else return ipv6_addr_equal(&a->key.u.ipv6.dst, &b->key.u.ipv6.dst); } static int geneve_configure(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack, const struct geneve_config *cfg) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); const struct ip_tunnel_info *info = &cfg->info; bool tun_collect_md, tun_on_same_port; int err, encap_len; if (cfg->collect_md && !is_tnl_info_zero(info)) { NL_SET_ERR_MSG(extack, "Device is externally controlled, so attributes (VNI, Port, and so on) must not be specified"); return -EINVAL; } geneve->net = net; geneve->dev = dev; t = geneve_find_dev(gn, cfg, info, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; /* make enough headroom for basic scenario */ encap_len = GENEVE_BASE_HLEN + ETH_HLEN; if (!cfg->collect_md && ip_tunnel_info_af(info) == AF_INET) { encap_len += sizeof(struct iphdr); dev->max_mtu -= sizeof(struct iphdr); } else { encap_len += sizeof(struct ipv6hdr); dev->max_mtu -= sizeof(struct ipv6hdr); } dev->needed_headroom = encap_len + ETH_HLEN; if (cfg->collect_md) { if (tun_on_same_port) { NL_SET_ERR_MSG(extack, "There can be only one externally controlled device on a destination port and a source address"); return -EPERM; } } else { if (tun_collect_md) { NL_SET_ERR_MSG(extack, "There already exists an externally controlled device on this destination port and the source address"); return -EPERM; } } dst_cache_reset(&geneve->cfg.info.dst_cache); memcpy(&geneve->cfg, cfg, sizeof(*cfg)); if (geneve->cfg.inner_proto_inherit) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP; } err = register_netdevice(dev); if (err) return err; list_add(&geneve->next, &gn->geneve_list); return 0; } static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) { memset(info, 0, sizeof(*info)); info->key.tp_dst = htons(dst_port); } static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack, struct geneve_config *cfg, bool changelink) { struct ip_tunnel_info *info = &cfg->info; int attrtype; if (data[IFLA_GENEVE_COLLECT_METADATA]) { if (changelink) { attrtype = IFLA_GENEVE_COLLECT_METADATA; goto change_notsup; } cfg->collect_md = true; cfg->dualstack = true; } if ((data[IFLA_GENEVE_LOCAL] || data[IFLA_GENEVE_REMOTE]) && (data[IFLA_GENEVE_LOCAL6] || data[IFLA_GENEVE_REMOTE6])) { NL_SET_ERR_MSG(extack, "Cannot specify both IPv4/IPv6 Remote/Local addresses"); return -EINVAL; } if (data[IFLA_GENEVE_REMOTE]) { if (changelink && (ip_tunnel_info_af(info) == AF_INET6)) { attrtype = IFLA_GENEVE_REMOTE; goto change_notsup; } info->key.u.ipv4.dst = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); if (ipv4_is_multicast(info->key.u.ipv4.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE], "Remote IPv4 address cannot be Multicast"); return -EINVAL; } } if (data[IFLA_GENEVE_REMOTE6]) { #if IS_ENABLED(CONFIG_IPV6) int addr_type; if (changelink && (ip_tunnel_info_af(info) == AF_INET)) { attrtype = IFLA_GENEVE_REMOTE6; goto change_notsup; } info->mode = IP_TUNNEL_INFO_IPV6; info->key.u.ipv6.dst = nla_get_in6_addr(data[IFLA_GENEVE_REMOTE6]); addr_type = ipv6_addr_type(&info->key.u.ipv6.dst); if (addr_type & IPV6_ADDR_LINKLOCAL) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be link-local"); return -EINVAL; } if (addr_type & IPV6_ADDR_MULTICAST) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be Multicast"); return -EINVAL; } __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); cfg->use_udp6_rx_checksums = true; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_LOCAL]) { if (changelink) { __be32 src = nla_get_in_addr(data[IFLA_GENEVE_LOCAL]); if (ip_tunnel_info_af(info) == AF_INET6 || src != info->key.u.ipv4.src) { attrtype = IFLA_GENEVE_LOCAL; goto change_notsup; } } else { info->key.u.ipv4.src = nla_get_in_addr(data[IFLA_GENEVE_LOCAL]); if (ipv4_is_multicast(info->key.u.ipv4.src)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL], "Local IPv4 address cannot be Multicast"); return -EINVAL; } cfg->dualstack = false; } } if (data[IFLA_GENEVE_LOCAL6]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { struct in6_addr src = nla_get_in6_addr(data[IFLA_GENEVE_LOCAL6]); if (ip_tunnel_info_af(info) == AF_INET || !ipv6_addr_equal(&src, &info->key.u.ipv6.src)) { attrtype = IFLA_GENEVE_LOCAL6; goto change_notsup; } } else { int addr_type; info->mode = IP_TUNNEL_INFO_IPV6; info->key.u.ipv6.src = nla_get_in6_addr(data[IFLA_GENEVE_LOCAL6]); addr_type = ipv6_addr_type(&info->key.u.ipv6.src); if (addr_type & IPV6_ADDR_LINKLOCAL) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL6], "Local IPv6 address cannot be link-local"); return -EINVAL; } if (addr_type & IPV6_ADDR_MULTICAST) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL6], "Local IPv6 address cannot be Multicast"); return -EINVAL; } cfg->dualstack = false; } #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LOCAL6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_ID]) { __u32 vni; __u8 tvni[3]; __be64 tunid; vni = nla_get_u32(data[IFLA_GENEVE_ID]); tvni[0] = (vni & 0x00ff0000) >> 16; tvni[1] = (vni & 0x0000ff00) >> 8; tvni[2] = vni & 0x000000ff; tunid = vni_to_tunnel_id(tvni); if (changelink && (tunid != info->key.tun_id)) { attrtype = IFLA_GENEVE_ID; goto change_notsup; } info->key.tun_id = tunid; } if (data[IFLA_GENEVE_TTL_INHERIT]) { if (nla_get_u8(data[IFLA_GENEVE_TTL_INHERIT])) cfg->ttl_inherit = true; else cfg->ttl_inherit = false; } else if (data[IFLA_GENEVE_TTL]) { info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); cfg->ttl_inherit = false; } if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); if (data[IFLA_GENEVE_DF]) cfg->df = nla_get_u8(data[IFLA_GENEVE_DF]); if (data[IFLA_GENEVE_LABEL]) { info->key.label = nla_get_be32(data[IFLA_GENEVE_LABEL]) & IPV6_FLOWLABEL_MASK; if (info->key.label && (!(info->mode & IP_TUNNEL_INFO_IPV6))) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LABEL], "Label attribute only applies for IPv6 Geneve devices"); return -EINVAL; } } if (data[IFLA_GENEVE_PORT]) { if (changelink) { attrtype = IFLA_GENEVE_PORT; goto change_notsup; } info->key.tp_dst = nla_get_be16(data[IFLA_GENEVE_PORT]); } if (data[IFLA_GENEVE_PORT_RANGE]) { const struct ifla_geneve_port_range *p; if (changelink) { attrtype = IFLA_GENEVE_PORT_RANGE; goto change_notsup; } p = nla_data(data[IFLA_GENEVE_PORT_RANGE]); cfg->port_min = ntohs(p->low); cfg->port_max = ntohs(p->high); } if (data[IFLA_GENEVE_UDP_CSUM]) { if (changelink) { attrtype = IFLA_GENEVE_UDP_CSUM; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_TX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) __clear_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_RX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) cfg->use_udp6_rx_checksums = false; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_INNER_PROTO_INHERIT]) { if (changelink) { attrtype = IFLA_GENEVE_INNER_PROTO_INHERIT; goto change_notsup; } cfg->inner_proto_inherit = true; } if (data[IFLA_GENEVE_GRO_HINT]) { if (changelink) { attrtype = IFLA_GENEVE_GRO_HINT; goto change_notsup; } cfg->gro_hint = true; } return 0; change_notsup: NL_SET_ERR_MSG_ATTR(extack, data[attrtype], "Changing VNI, Port, endpoint IP address family, external, inner_proto_inherit, gro_hint and UDP checksum attributes are not supported"); return -EOPNOTSUPP; } static void geneve_link_config(struct net_device *dev, struct ip_tunnel_info *info, struct nlattr *tb[]) { struct geneve_dev *geneve = netdev_priv(dev); int ldev_mtu = 0; if (tb[IFLA_MTU]) { geneve_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return; } switch (ip_tunnel_info_af(info)) { case AF_INET: { struct flowi4 fl4 = { .daddr = info->key.u.ipv4.dst }; struct rtable *rt = ip_route_output_key(geneve->net, &fl4); if (!IS_ERR(rt) && rt->dst.dev) { ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV4_HLEN; ip_rt_put(rt); } break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct rt6_info *rt; if (!__in6_dev_get(dev)) break; rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; ip6_rt_put(rt); break; } #endif } if (ldev_mtu <= 0) return; geneve_change_mtu(dev, ldev_mtu - info->options_len); } static int geneve_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = false, .ttl_inherit = false, .collect_md = false, .dualstack = false, .port_min = 1, .port_max = USHRT_MAX, }; int err; init_tnl_info(&cfg.info, GENEVE_UDP_PORT); err = geneve_nl2info(tb, data, extack, &cfg, false); if (err) return err; err = geneve_configure(link_net, dev, extack, &cfg); if (err) return err; geneve_link_config(dev, &cfg.info, tb); return 0; } /* Quiesces the geneve device data path for both TX and RX. * * On transmit geneve checks for non-NULL geneve_sock before it proceeds. * So, if we set that socket to NULL under RCU and wait for synchronize_net() * to complete for the existing set of in-flight packets to be transmitted, * then we would have quiesced the transmit data path. All the future packets * will get dropped until we unquiesce the data path. * * On receive geneve dereference the geneve_sock stashed in the socket. So, * if we set that to NULL under RCU and wait for synchronize_net() to * complete, then we would have quiesced the receive data path. */ static void geneve_quiesce(struct geneve_dev *geneve, struct geneve_sock **gs4, struct geneve_sock **gs6) { *gs4 = rtnl_dereference(geneve->sock4); rcu_assign_pointer(geneve->sock4, NULL); if (*gs4) rcu_assign_sk_user_data((*gs4)->sk, NULL); #if IS_ENABLED(CONFIG_IPV6) *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); if (*gs6) rcu_assign_sk_user_data((*gs6)->sk, NULL); #else *gs6 = NULL; #endif synchronize_net(); } /* Resumes the geneve device data path for both TX and RX. */ static void geneve_unquiesce(struct geneve_dev *geneve, struct geneve_sock *gs4, struct geneve_sock __maybe_unused *gs6) { rcu_assign_pointer(geneve->sock4, gs4); if (gs4) rcu_assign_sk_user_data(gs4->sk, gs4); #if IS_ENABLED(CONFIG_IPV6) rcu_assign_pointer(geneve->sock6, gs6); if (gs6) rcu_assign_sk_user_data(gs6->sk, gs6); #endif } static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4, *gs6; struct geneve_config cfg; int err; /* If the geneve device is configured for metadata (or externally * controlled, for example, OVS), then nothing can be changed. */ if (geneve->cfg.collect_md) return -EOPNOTSUPP; /* Start with the existing info. */ memcpy(&cfg, &geneve->cfg, sizeof(cfg)); err = geneve_nl2info(tb, data, extack, &cfg, true); if (err) return err; if (!geneve_dst_addr_equal(&geneve->cfg.info, &cfg.info)) { dst_cache_reset(&cfg.info.dst_cache); geneve_link_config(dev, &cfg.info, tb); } geneve_quiesce(geneve, &gs4, &gs6); memcpy(&geneve->cfg, &cfg, sizeof(cfg)); geneve_unquiesce(geneve, gs4, gs6); return 0; } static void geneve_dellink(struct net_device *dev, struct list_head *head) { struct geneve_dev *geneve = netdev_priv(dev); list_del(&geneve->next); unregister_netdevice_queue(dev, head); } static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */ nla_total_size(0) + /* IFLA_GENEVE_INNER_PROTO_INHERIT */ nla_total_size(sizeof(struct ifla_geneve_port_range)) + /* IFLA_GENEVE_PORT_RANGE */ nla_total_size(0) + /* IFLA_GENEVE_GRO_HINT */ 0; } static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = &geneve->cfg.info; bool ttl_inherit = geneve->cfg.ttl_inherit; bool metadata = geneve->cfg.collect_md; struct ifla_geneve_port_range ports = { .low = htons(geneve->cfg.port_min), .high = htons(geneve->cfg.port_max), }; __u8 tmp_vni[3]; __u32 vni; tunnel_id_to_vni(info->key.tun_id, tmp_vni); vni = (tmp_vni[0] << 16) | (tmp_vni[1] << 8) | tmp_vni[2]; if (nla_put_u32(skb, IFLA_GENEVE_ID, vni)) goto nla_put_failure; if (!metadata && ip_tunnel_info_af(info) == AF_INET) { if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, info->key.u.ipv4.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else if (!metadata) { if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6, &info->key.u.ipv6.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #endif } if (!geneve->cfg.dualstack) { if (ip_tunnel_info_af(info) == AF_INET) { if ((info->key.u.ipv4.src || geneve->cfg.collect_md) && nla_put_in_addr(skb, IFLA_GENEVE_LOCAL, info->key.u.ipv4.src)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if ((!ipv6_addr_any(&info->key.u.ipv6.src) || geneve->cfg.collect_md) && nla_put_in6_addr(skb, IFLA_GENEVE_LOCAL6, &info->key.u.ipv6.src)) goto nla_put_failure; #endif } } if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) || nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) || nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->cfg.df)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst)) goto nla_put_failure; if (metadata && nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, !geneve->cfg.use_udp6_rx_checksums)) goto nla_put_failure; #endif if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) goto nla_put_failure; if (geneve->cfg.inner_proto_inherit && nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT)) goto nla_put_failure; if (nla_put(skb, IFLA_GENEVE_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; if (geneve->cfg.gro_hint && nla_put_flag(skb, IFLA_GENEVE_GRO_HINT)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops geneve_link_ops __read_mostly = { .kind = "geneve", .maxtype = IFLA_GENEVE_MAX, .policy = geneve_policy, .priv_size = sizeof(struct geneve_dev), .setup = geneve_setup, .validate = geneve_validate, .newlink = geneve_newlink, .changelink = geneve_changelink, .dellink = geneve_dellink, .get_size = geneve_get_size, .fill_info = geneve_fill_info, }; struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); int err; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = true, .ttl_inherit = false, .collect_md = true, .dualstack = true, .port_min = 1, .port_max = USHRT_MAX, }; memset(tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &geneve_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; init_tnl_info(&cfg.info, dst_port); err = geneve_configure(net, dev, NULL, &cfg); if (err) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = geneve_change_mtu(dev, IP_MAX_MTU); if (err) goto err; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto err; return dev; err: geneve_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); static int geneve_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) geneve_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) geneve_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block geneve_notifier_block __read_mostly = { .notifier_call = geneve_netdevice_event, }; static __net_init int geneve_init_net(struct net *net) { struct geneve_net *gn = net_generic(net, geneve_net_id); INIT_LIST_HEAD(&gn->geneve_list); INIT_LIST_HEAD(&gn->sock_list); return 0; } static void __net_exit geneve_exit_rtnl_net(struct net *net, struct list_head *dev_to_kill) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) geneve_dellink(geneve->dev, dev_to_kill); } static void __net_exit geneve_exit_net(struct net *net) { const struct geneve_net *gn = net_generic(net, geneve_net_id); WARN_ON_ONCE(!list_empty(&gn->sock_list)); } static struct pernet_operations geneve_net_ops = { .init = geneve_init_net, .exit_rtnl = geneve_exit_rtnl_net, .exit = geneve_exit_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), }; static int __init geneve_init_module(void) { int rc; rc = register_pernet_subsys(&geneve_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&geneve_notifier_block); if (rc) goto out2; rc = rtnl_link_register(&geneve_link_ops); if (rc) goto out3; return 0; out3: unregister_netdevice_notifier(&geneve_notifier_block); out2: unregister_pernet_subsys(&geneve_net_ops); out1: return rc; } late_initcall(geneve_init_module); static void __exit geneve_cleanup_module(void) { rtnl_link_unregister(&geneve_link_ops); unregister_netdevice_notifier(&geneve_notifier_block); unregister_pernet_subsys(&geneve_net_ops); } module_exit(geneve_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(GENEVE_NETDEV_VER); MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>"); MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("geneve"); |
| 2 2 2 2 2 2 2 2 2 2 2 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 | // SPDX-License-Identifier: GPL-2.0-or-later /* drivers/net/ifb.c: The purpose of this driver is to provide a device that allows for sharing of resources: 1) qdiscs/policies that are per device as opposed to system wide. ifb allows for a device which can be redirected to thus providing an impression of sharing. 2) Allows for queueing incoming traffic for shaping instead of dropping. The original concept is based on what is known as the IMQ driver initially written by Martin Devera, later rewritten by Patrick McHardy and then maintained by Andre Correa. You need the tc action mirror or redirect to feed this device packets. Authors: Jamal Hadi Salim (2005) */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/moduleparam.h> #include <linux/netfilter_netdev.h> #include <net/pkt_sched.h> #include <net/net_namespace.h> #define TX_Q_LIMIT 32 struct ifb_q_stats { u64_stats_t packets; u64_stats_t bytes; struct u64_stats_sync sync; }; struct ifb_q_private { struct net_device *dev; struct tasklet_struct ifb_tasklet; int tasklet_pending; int txqnum; struct sk_buff_head rq; struct sk_buff_head tq; struct ifb_q_stats rx_stats; struct ifb_q_stats tx_stats; } ____cacheline_aligned_in_smp; struct ifb_dev_private { struct ifb_q_private *tx_private; }; /* For ethtools stats. */ struct ifb_q_stats_desc { char desc[ETH_GSTRING_LEN]; size_t offset; }; #define IFB_Q_STAT(m) offsetof(struct ifb_q_stats, m) static const struct ifb_q_stats_desc ifb_q_stats_desc[] = { { "packets", IFB_Q_STAT(packets) }, { "bytes", IFB_Q_STAT(bytes) }, }; #define IFB_Q_STATS_LEN ARRAY_SIZE(ifb_q_stats_desc) static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev); static int ifb_open(struct net_device *dev); static int ifb_close(struct net_device *dev); static void ifb_update_q_stats(struct ifb_q_stats *stats, int len) { u64_stats_update_begin(&stats->sync); u64_stats_inc(&stats->packets); u64_stats_add(&stats->bytes, len); u64_stats_update_end(&stats->sync); } static void ifb_ri_tasklet(struct tasklet_struct *t) { struct ifb_q_private *txp = from_tasklet(txp, t, ifb_tasklet); struct netdev_queue *txq; struct sk_buff *skb; txq = netdev_get_tx_queue(txp->dev, txp->txqnum); skb = skb_peek(&txp->tq); if (!skb) { if (!__netif_tx_trylock(txq)) goto resched; skb_queue_splice_tail_init(&txp->rq, &txp->tq); __netif_tx_unlock(txq); } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { /* Skip tc and netfilter to prevent redirection loop. */ skb->redirected = 0; #ifdef CONFIG_NET_CLS_ACT skb->tc_skip_classify = 1; #endif nf_skip_egress(skb, true); ifb_update_q_stats(&txp->tx_stats, skb->len); rcu_read_lock(); skb->dev = dev_get_by_index_rcu(dev_net(txp->dev), skb->skb_iif); if (!skb->dev) { rcu_read_unlock(); dev_kfree_skb(skb); txp->dev->stats.tx_dropped++; if (skb_queue_len(&txp->tq) != 0) goto resched; break; } rcu_read_unlock(); skb->skb_iif = txp->dev->ifindex; if (!skb->from_ingress) { dev_queue_xmit(skb); } else { skb_pull_rcsum(skb, skb->mac_len); netif_receive_skb(skb); } } if (__netif_tx_trylock(txq)) { skb = skb_peek(&txp->rq); if (!skb) { txp->tasklet_pending = 0; if (netif_tx_queue_stopped(txq)) netif_tx_wake_queue(txq); } else { __netif_tx_unlock(txq); goto resched; } __netif_tx_unlock(txq); } else { resched: txp->tasklet_pending = 1; tasklet_schedule(&txp->ifb_tasklet); } } static void ifb_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp = dp->tx_private; unsigned int start; u64 packets, bytes; int i; for (i = 0; i < dev->num_tx_queues; i++,txp++) { do { start = u64_stats_fetch_begin(&txp->rx_stats.sync); packets = u64_stats_read(&txp->rx_stats.packets); bytes = u64_stats_read(&txp->rx_stats.bytes); } while (u64_stats_fetch_retry(&txp->rx_stats.sync, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; do { start = u64_stats_fetch_begin(&txp->tx_stats.sync); packets = u64_stats_read(&txp->tx_stats.packets); bytes = u64_stats_read(&txp->tx_stats.bytes); } while (u64_stats_fetch_retry(&txp->tx_stats.sync, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; } stats->rx_dropped = dev->stats.rx_dropped; stats->tx_dropped = dev->stats.tx_dropped; } static int ifb_dev_init(struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp; int i; txp = kzalloc_objs(*txp, dev->num_tx_queues); if (!txp) return -ENOMEM; dp->tx_private = txp; for (i = 0; i < dev->num_tx_queues; i++,txp++) { txp->txqnum = i; txp->dev = dev; __skb_queue_head_init(&txp->rq); __skb_queue_head_init(&txp->tq); u64_stats_init(&txp->rx_stats.sync); u64_stats_init(&txp->tx_stats.sync); tasklet_setup(&txp->ifb_tasklet, ifb_ri_tasklet); netif_tx_start_queue(netdev_get_tx_queue(dev, i)); } return 0; } static void ifb_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { u8 *p = buf; int i, j; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < dev->num_tx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "rx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); for (i = 0; i < dev->num_tx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "tx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); break; } } static int ifb_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: return IFB_Q_STATS_LEN * dev->num_tx_queues * 2; default: return -EOPNOTSUPP; } } static void ifb_fill_stats_data(u64 **data, struct ifb_q_stats *q_stats) { void *stats_base = (void *)q_stats; unsigned int start; size_t offset; int j; do { start = u64_stats_fetch_begin(&q_stats->sync); for (j = 0; j < IFB_Q_STATS_LEN; j++) { offset = ifb_q_stats_desc[j].offset; (*data)[j] = u64_stats_read((u64_stats_t *)(stats_base + offset)); } } while (u64_stats_fetch_retry(&q_stats->sync, start)); *data += IFB_Q_STATS_LEN; } static void ifb_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp; int i; for (i = 0; i < dev->num_tx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->rx_stats); } for (i = 0; i < dev->num_tx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->tx_stats); } } static const struct net_device_ops ifb_netdev_ops = { .ndo_open = ifb_open, .ndo_stop = ifb_close, .ndo_get_stats64 = ifb_stats64, .ndo_start_xmit = ifb_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_init = ifb_dev_init, }; static const struct ethtool_ops ifb_ethtool_ops = { .get_strings = ifb_get_strings, .get_sset_count = ifb_get_sset_count, .get_ethtool_stats = ifb_get_ethtool_stats, }; #define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \ NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_TX) static void ifb_dev_free(struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp = dp->tx_private; int i; for (i = 0; i < dev->num_tx_queues; i++,txp++) { tasklet_kill(&txp->ifb_tasklet); __skb_queue_purge(&txp->rq); __skb_queue_purge(&txp->tq); } kfree(dp->tx_private); } static void ifb_setup(struct net_device *dev) { /* Initialize the device structure. */ dev->netdev_ops = &ifb_netdev_ops; dev->ethtool_ops = &ifb_ethtool_ops; /* Fill in device structure with ethernet-generic values. */ ether_setup(dev); dev->tx_queue_len = TX_Q_LIMIT; dev->features |= IFB_FEATURES; dev->hw_features |= dev->features; dev->hw_enc_features |= dev->features; dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); dev->flags |= IFF_NOARP; dev->flags &= ~IFF_MULTICAST; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); eth_hw_addr_random(dev); dev->needs_free_netdev = true; dev->priv_destructor = ifb_dev_free; dev->min_mtu = 0; dev->max_mtu = 0; netif_set_tso_max_size(dev, GSO_MAX_SIZE); } static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp = dp->tx_private + skb_get_queue_mapping(skb); ifb_update_q_stats(&txp->rx_stats, skb->len); if (!skb->redirected || !skb->skb_iif) { dev_kfree_skb(skb); dev->stats.rx_dropped++; return NETDEV_TX_OK; } if (skb_queue_len(&txp->rq) >= dev->tx_queue_len) netif_tx_stop_queue(netdev_get_tx_queue(dev, txp->txqnum)); __skb_queue_tail(&txp->rq, skb); if (!txp->tasklet_pending) { txp->tasklet_pending = 1; tasklet_schedule(&txp->ifb_tasklet); } return NETDEV_TX_OK; } static int ifb_close(struct net_device *dev) { netif_tx_stop_all_queues(dev); return 0; } static int ifb_open(struct net_device *dev) { netif_tx_start_all_queues(dev); return 0; } static int ifb_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static struct rtnl_link_ops ifb_link_ops __read_mostly = { .kind = "ifb", .priv_size = sizeof(struct ifb_dev_private), .setup = ifb_setup, .validate = ifb_validate, }; /* Number of ifb devices to be set up by this module. * Note that these legacy devices have one queue. * Prefer something like : ip link add ifb10 numtxqueues 8 type ifb */ static int numifbs = 2; module_param(numifbs, int, 0); MODULE_PARM_DESC(numifbs, "Number of ifb devices"); static int __init ifb_init_one(int index) { struct net_device *dev_ifb; int err; dev_ifb = alloc_netdev(sizeof(struct ifb_dev_private), "ifb%d", NET_NAME_UNKNOWN, ifb_setup); if (!dev_ifb) return -ENOMEM; dev_ifb->rtnl_link_ops = &ifb_link_ops; err = register_netdevice(dev_ifb); if (err < 0) goto err; return 0; err: free_netdev(dev_ifb); return err; } static int __init ifb_init_module(void) { int i, err; err = rtnl_link_register(&ifb_link_ops); if (err < 0) return err; rtnl_net_lock(&init_net); for (i = 0; i < numifbs && !err; i++) { err = ifb_init_one(i); cond_resched(); } rtnl_net_unlock(&init_net); if (err) rtnl_link_unregister(&ifb_link_ops); return err; } static void __exit ifb_cleanup_module(void) { rtnl_link_unregister(&ifb_link_ops); } module_init(ifb_init_module); module_exit(ifb_cleanup_module); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Intermediate Functional Block (ifb) netdevice driver for sharing of resources and ingress packet queuing"); MODULE_AUTHOR("Jamal Hadi Salim"); MODULE_ALIAS_RTNL_LINK("ifb"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2020 Intel Corporation. */ #ifndef XSK_BUFF_POOL_H_ #define XSK_BUFF_POOL_H_ #include <linux/if_xdp.h> #include <linux/types.h> #include <linux/dma-mapping.h> #include <linux/bpf.h> #include <net/xdp.h> struct xsk_buff_pool; struct xdp_rxq_info; struct xsk_cb_desc; struct xsk_queue; struct xdp_desc; struct xdp_umem; struct xdp_sock; struct device; struct page; #define XSK_PRIV_MAX 24 struct xdp_buff_xsk { struct xdp_buff xdp; u8 cb[XSK_PRIV_MAX]; dma_addr_t dma; dma_addr_t frame_dma; struct xsk_buff_pool *pool; struct list_head list_node; } __aligned_largest; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) #define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t)) struct xsk_dma_map { dma_addr_t *dma_pages; struct device *dev; struct net_device *netdev; refcount_t users; struct list_head list; /* Protected by the RTNL_LOCK */ u32 dma_pages_cnt; }; struct xsk_buff_pool { /* Members only used in the control path first. */ struct device *dev; struct net_device *netdev; struct list_head xsk_tx_list; /* Protects modifications to the xsk_tx_list */ spinlock_t xsk_tx_list_lock; refcount_t users; struct xdp_umem *umem; struct work_struct work; /* Protects generic receive in shared and non-shared umem mode. */ spinlock_t rx_lock; struct list_head free_list; struct list_head xskb_list; u32 heads_cnt; u16 queue_id; /* Data path members as close to free_heads at the end as possible. */ struct xsk_queue *fq ____cacheline_aligned_in_smp; struct xsk_queue *cq; /* For performance reasons, each buff pool has its own array of dma_pages * even when they are identical. */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; struct xdp_desc *tx_descs; u64 chunk_mask; u64 addrs_cnt; u32 free_list_cnt; u32 dma_pages_cnt; u32 free_heads_cnt; u32 headroom; u32 chunk_size; u32 chunk_shift; u32 frame_len; u32 xdp_zc_max_segs; u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; bool unaligned; bool tx_sw_csum; void *addrs; /* Mutual exclusion of the completion ring in the SKB mode. * Protect: NAPI TX thread and sendmsg error paths in the SKB * destructor callback. */ spinlock_t cq_prod_lock; struct xdp_buff_xsk *free_heads[]; }; /* Masks for xdp_umem_page flags. * The low 12-bits of the addr will be 0 since this is the page address, so we * can use them for flags. */ #define XSK_NEXT_PG_CONTIG_SHIFT 0 #define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) /* AF_XDP core. */ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem); int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs, struct net_device *dev, u16 queue_id); int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_destroy(struct xsk_buff_pool *pool); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, u64 addr) { xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; } static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, dma_addr_t *dma_pages, u64 addr) { xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK); xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM; } /* AF_XDP ZC drivers, via xdp_sock_buff.h */ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq); void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc); int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages); void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs); struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool); u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max); bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count); void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr); dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr); struct xdp_desc_ctx { dma_addr_t dma; struct xsk_tx_metadata *meta; }; struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr); static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb) { return xskb->dma; } static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) { return xskb->frame_dma; } static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { dma_sync_single_for_cpu(xskb->pool->dev, xskb->dma, xskb->pool->frame_len, DMA_BIDIRECTIONAL); } static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { dma_sync_single_for_device(pool->dev, dma, size, DMA_BIDIRECTIONAL); } static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, u64 addr, u32 len) { bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE; if (likely(!cross_pg)) return false; return pool->dma_pages && !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } static inline bool xp_mb_desc(const struct xdp_desc *desc) { return desc->options & XDP_PKT_CONTD; } static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) { return addr & pool->chunk_mask; } static inline u64 xp_unaligned_extract_addr(u64 addr) { return addr & XSK_UNALIGNED_BUF_ADDR_MASK; } static inline u64 xp_unaligned_extract_offset(u64 addr) { return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; } static inline u64 xp_unaligned_add_offset_to_addr(u64 addr) { return xp_unaligned_extract_addr(addr) + xp_unaligned_extract_offset(addr); } static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr) { return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift; } static inline void xp_release(struct xdp_buff_xsk *xskb) { if (xskb->pool->unaligned) xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; } static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool) { u64 orig_addr = xskb->xdp.data - pool->addrs; u64 offset; if (!pool->unaligned) return orig_addr; offset = xskb->xdp.data - xskb->xdp.data_hard_start; offset += pool->headroom; orig_addr -= offset; return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); } static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool) { return pool->tx_metadata_len > 0; } #endif /* XSK_BUFF_POOL_H_ */ |
| 118 3 7 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KBD_KERN_H #define _KBD_KERN_H #include <linux/tty.h> #include <linux/interrupt.h> #include <linux/keyboard.h> extern char *func_table[MAX_NR_FUNC]; /* * kbd->xxx contains the VC-local things (flag settings etc..) * * Note: externally visible are LED_SCR, LED_NUM, LED_CAP defined in kd.h * The code in KDGETLED / KDSETLED depends on the internal and * external order being the same. * * Note: lockstate is used as index in the array key_map. */ struct kbd_struct { unsigned char lockstate; /* 8 modifiers - the names do not have any meaning at all; they can be associated to arbitrarily chosen keys */ #define VC_SHIFTLOCK KG_SHIFT /* shift lock mode */ #define VC_ALTGRLOCK KG_ALTGR /* altgr lock mode */ #define VC_CTRLLOCK KG_CTRL /* control lock mode */ #define VC_ALTLOCK KG_ALT /* alt lock mode */ #define VC_SHIFTLLOCK KG_SHIFTL /* shiftl lock mode */ #define VC_SHIFTRLOCK KG_SHIFTR /* shiftr lock mode */ #define VC_CTRLLLOCK KG_CTRLL /* ctrll lock mode */ #define VC_CTRLRLOCK KG_CTRLR /* ctrlr lock mode */ unsigned char slockstate; /* for `sticky' Shift, Ctrl, etc. */ unsigned char ledmode:1; #define LED_SHOW_FLAGS 0 /* traditional state */ #define LED_SHOW_IOCTL 1 /* only change leds upon ioctl */ unsigned char ledflagstate:4; /* flags, not lights */ unsigned char default_ledflagstate:4; #define VC_SCROLLOCK 0 /* scroll-lock mode */ #define VC_NUMLOCK 1 /* numeric lock mode */ #define VC_CAPSLOCK 2 /* capslock mode */ #define VC_KANALOCK 3 /* kanalock mode */ unsigned char kbdmode:3; /* one 3-bit value */ #define VC_XLATE 0 /* translate keycodes using keymap */ #define VC_MEDIUMRAW 1 /* medium raw (keycode) mode */ #define VC_RAW 2 /* raw (scancode) mode */ #define VC_UNICODE 3 /* Unicode mode */ #define VC_OFF 4 /* disabled mode */ unsigned char modeflags:5; #define VC_APPLIC 0 /* application key mode */ #define VC_CKMODE 1 /* cursor key mode */ #define VC_REPEAT 2 /* keyboard repeat */ #define VC_CRLF 3 /* 0 - enter sends CR, 1 - enter sends CRLF */ #define VC_META 4 /* 0 - meta, 1 - meta=prefix with ESC */ }; extern int kbd_init(void); extern void setledstate(struct kbd_struct *kbd, unsigned int led); extern int do_poke_blanked_console; extern void (*kbd_ledfunc)(unsigned int led); extern int set_console(int nr); extern void schedule_console_callback(void); static inline int vc_kbd_mode(struct kbd_struct * kbd, int flag) { return ((kbd->modeflags >> flag) & 1); } static inline int vc_kbd_led(struct kbd_struct * kbd, int flag) { return ((kbd->ledflagstate >> flag) & 1); } static inline void set_vc_kbd_mode(struct kbd_struct * kbd, int flag) { kbd->modeflags |= 1 << flag; } static inline void set_vc_kbd_led(struct kbd_struct * kbd, int flag) { kbd->ledflagstate |= 1 << flag; } static inline void clr_vc_kbd_mode(struct kbd_struct * kbd, int flag) { kbd->modeflags &= ~(1 << flag); } static inline void clr_vc_kbd_led(struct kbd_struct * kbd, int flag) { kbd->ledflagstate &= ~(1 << flag); } static inline void chg_vc_kbd_lock(struct kbd_struct * kbd, int flag) { kbd->lockstate ^= 1 << flag; } static inline void chg_vc_kbd_slock(struct kbd_struct * kbd, int flag) { kbd->slockstate ^= 1 << flag; } static inline void chg_vc_kbd_mode(struct kbd_struct * kbd, int flag) { kbd->modeflags ^= 1 << flag; } static inline void chg_vc_kbd_led(struct kbd_struct * kbd, int flag) { kbd->ledflagstate ^= 1 << flag; } #define U(x) ((x) ^ 0xf000) #define BRL_UC_ROW 0x2800 /* keyboard.c */ struct console; void vt_set_leds_compute_shiftstate(void); /* defkeymap.c */ extern unsigned int keymap_count; #endif |
| 1 1 1 4 4 2 3 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 | /* * Equalizer Load-balancer for serial network interfaces. * * (c) Copyright 1995 Simon "Guru Aleph-Null" Janes * NCM: Network and Communications Management, Inc. * * (c) Copyright 2002 David S. Miller (davem@redhat.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. * * The author may be reached as simon@ncm.com, or C/O * NCM * Attn: Simon Janes * 6803 Whittier Ave * McLean VA 22101 * Phone: 1-703-847-0040 ext 103 */ /* * Sources: * skeleton.c by Donald Becker. * Inspirations: * The Harried and Overworked Alan Cox * Conspiracies: * The Alan Cox and Mike McLagan plot to get someone else to do the code, * which turned out to be me. */ /* * $Log: eql.c,v $ * Revision 1.2 1996/04/11 17:51:52 guru * Added one-line eql_remove_slave patch. * * Revision 1.1 1996/04/11 17:44:17 guru * Initial revision * * Revision 3.13 1996/01/21 15:17:18 alan * tx_queue_len changes. * reformatted. * * Revision 3.12 1995/03/22 21:07:51 anarchy * Added capable() checks on configuration. * Moved header file. * * Revision 3.11 1995/01/19 23:14:31 guru * slave_load = (ULONG_MAX - (ULONG_MAX / 2)) - * (priority_Bps) + bytes_queued * 8; * * Revision 3.10 1995/01/19 23:07:53 guru * back to * slave_load = (ULONG_MAX - (ULONG_MAX / 2)) - * (priority_Bps) + bytes_queued; * * Revision 3.9 1995/01/19 22:38:20 guru * slave_load = (ULONG_MAX - (ULONG_MAX / 2)) - * (priority_Bps) + bytes_queued * 4; * * Revision 3.8 1995/01/19 22:30:55 guru * slave_load = (ULONG_MAX - (ULONG_MAX / 2)) - * (priority_Bps) + bytes_queued * 2; * * Revision 3.7 1995/01/19 21:52:35 guru * printk's trimmed out. * * Revision 3.6 1995/01/19 21:49:56 guru * This is working pretty well. I gained 1 K/s in speed.. now it's just * robustness and printk's to be diked out. * * Revision 3.5 1995/01/18 22:29:59 guru * still crashes the kernel when the lock_wait thing is woken up. * * Revision 3.4 1995/01/18 21:59:47 guru * Broken set-bit locking snapshot * * Revision 3.3 1995/01/17 22:09:18 guru * infinite sleep in a lock somewhere.. * * Revision 3.2 1995/01/15 16:46:06 guru * Log trimmed of non-pertinent 1.x branch messages * * Revision 3.1 1995/01/15 14:41:45 guru * New Scheduler and timer stuff... * * Revision 1.15 1995/01/15 14:29:02 guru * Will make 1.14 (now 1.15) the 3.0 branch, and the 1.12 the 2.0 branch, the one * with the dumber scheduler * * Revision 1.14 1995/01/15 02:37:08 guru * shock.. the kept-new-versions could have zonked working * stuff.. shudder * * Revision 1.13 1995/01/15 02:36:31 guru * big changes * * scheduler was torn out and replaced with something smarter * * global names not prefixed with eql_ were renamed to protect * against namespace collisions * * a few more abstract interfaces were added to facilitate any * potential change of datastructure. the driver is still using * a linked list of slaves. going to a heap would be a bit of * an overkill. * * this compiles fine with no warnings. * * the locking mechanism and timer stuff must be written however, * this version will not work otherwise * * Sorry, I had to rewrite most of this for 2.5.x -DaveM */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/compat.h> #include <linux/capability.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/netdevice.h> #include <net/net_namespace.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_eql.h> #include <linux/pkt_sched.h> #include <linux/uaccess.h> static int eql_open(struct net_device *dev); static int eql_close(struct net_device *dev); static int eql_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); static netdev_tx_t eql_slave_xmit(struct sk_buff *skb, struct net_device *dev); #define eql_is_slave(dev) ((dev->flags & IFF_SLAVE) == IFF_SLAVE) #define eql_is_master(dev) ((dev->flags & IFF_MASTER) == IFF_MASTER) static void eql_kill_one_slave(slave_queue_t *queue, slave_t *slave); static void eql_timer(struct timer_list *t) { equalizer_t *eql = timer_container_of(eql, t, timer); struct list_head *this, *tmp, *head; spin_lock(&eql->queue.lock); head = &eql->queue.all_slaves; list_for_each_safe(this, tmp, head) { slave_t *slave = list_entry(this, slave_t, list); if ((slave->dev->flags & IFF_UP) == IFF_UP) { slave->bytes_queued -= slave->priority_Bps; if (slave->bytes_queued < 0) slave->bytes_queued = 0; } else { eql_kill_one_slave(&eql->queue, slave); } } spin_unlock(&eql->queue.lock); eql->timer.expires = jiffies + EQL_DEFAULT_RESCHED_IVAL; add_timer(&eql->timer); } static const char version[] __initconst = "Equalizer2002: Simon Janes (simon@ncm.com) and David S. Miller (davem@redhat.com)"; static const struct net_device_ops eql_netdev_ops = { .ndo_open = eql_open, .ndo_stop = eql_close, .ndo_siocdevprivate = eql_siocdevprivate, .ndo_start_xmit = eql_slave_xmit, }; static void __init eql_setup(struct net_device *dev) { equalizer_t *eql = netdev_priv(dev); timer_setup(&eql->timer, eql_timer, 0); eql->timer.expires = jiffies + EQL_DEFAULT_RESCHED_IVAL; spin_lock_init(&eql->queue.lock); INIT_LIST_HEAD(&eql->queue.all_slaves); eql->queue.master_dev = dev; dev->netdev_ops = &eql_netdev_ops; /* * Now we undo some of the things that eth_setup does * that we don't like */ dev->mtu = EQL_DEFAULT_MTU; /* set to 576 in if_eql.h */ dev->flags = IFF_MASTER; dev->type = ARPHRD_SLIP; dev->tx_queue_len = 5; /* Hands them off fast */ netif_keep_dst(dev); } static int eql_open(struct net_device *dev) { equalizer_t *eql = netdev_priv(dev); /* XXX We should force this off automatically for the user. */ netdev_info(dev, "remember to turn off Van-Jacobson compression on your slave devices\n"); BUG_ON(!list_empty(&eql->queue.all_slaves)); eql->min_slaves = 1; eql->max_slaves = EQL_DEFAULT_MAX_SLAVES; /* 4 usually... */ add_timer(&eql->timer); return 0; } static void eql_kill_one_slave(slave_queue_t *queue, slave_t *slave) { list_del(&slave->list); queue->num_slaves--; slave->dev->flags &= ~IFF_SLAVE; netdev_put(slave->dev, &slave->dev_tracker); kfree(slave); } static void eql_kill_slave_queue(slave_queue_t *queue) { struct list_head *head, *tmp, *this; spin_lock_bh(&queue->lock); head = &queue->all_slaves; list_for_each_safe(this, tmp, head) { slave_t *s = list_entry(this, slave_t, list); eql_kill_one_slave(queue, s); } spin_unlock_bh(&queue->lock); } static int eql_close(struct net_device *dev) { equalizer_t *eql = netdev_priv(dev); /* * The timer has to be stopped first before we start hacking away * at the data structure it scans every so often... */ timer_delete_sync(&eql->timer); eql_kill_slave_queue(&eql->queue); return 0; } static int eql_enslave(struct net_device *dev, slaving_request_t __user *srq); static int eql_emancipate(struct net_device *dev, slaving_request_t __user *srq); static int eql_g_slave_cfg(struct net_device *dev, slave_config_t __user *sc); static int eql_s_slave_cfg(struct net_device *dev, slave_config_t __user *sc); static int eql_g_master_cfg(struct net_device *dev, master_config_t __user *mc); static int eql_s_master_cfg(struct net_device *dev, master_config_t __user *mc); static int eql_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { if (cmd != EQL_GETMASTRCFG && cmd != EQL_GETSLAVECFG && !capable(CAP_NET_ADMIN)) return -EPERM; if (in_compat_syscall()) /* to be implemented */ return -EOPNOTSUPP; switch (cmd) { case EQL_ENSLAVE: return eql_enslave(dev, data); case EQL_EMANCIPATE: return eql_emancipate(dev, data); case EQL_GETSLAVECFG: return eql_g_slave_cfg(dev, data); case EQL_SETSLAVECFG: return eql_s_slave_cfg(dev, data); case EQL_GETMASTRCFG: return eql_g_master_cfg(dev, data); case EQL_SETMASTRCFG: return eql_s_master_cfg(dev, data); default: return -EOPNOTSUPP; } } /* queue->lock must be held */ static slave_t *__eql_schedule_slaves(slave_queue_t *queue) { unsigned long best_load = ~0UL; struct list_head *this, *tmp, *head; slave_t *best_slave; best_slave = NULL; /* Make a pass to set the best slave. */ head = &queue->all_slaves; list_for_each_safe(this, tmp, head) { slave_t *slave = list_entry(this, slave_t, list); unsigned long slave_load, bytes_queued, priority_Bps; /* Go through the slave list once, updating best_slave * whenever a new best_load is found. */ bytes_queued = slave->bytes_queued; priority_Bps = slave->priority_Bps; if ((slave->dev->flags & IFF_UP) == IFF_UP) { slave_load = (~0UL - (~0UL / 2)) - (priority_Bps) + bytes_queued * 8; if (slave_load < best_load) { best_load = slave_load; best_slave = slave; } } else { /* We found a dead slave, kill it. */ eql_kill_one_slave(queue, slave); } } return best_slave; } static netdev_tx_t eql_slave_xmit(struct sk_buff *skb, struct net_device *dev) { equalizer_t *eql = netdev_priv(dev); slave_t *slave; spin_lock(&eql->queue.lock); slave = __eql_schedule_slaves(&eql->queue); if (slave) { struct net_device *slave_dev = slave->dev; skb->dev = slave_dev; skb->priority = TC_PRIO_FILLER; slave->bytes_queued += skb->len; dev_queue_xmit(skb); dev->stats.tx_packets++; } else { dev->stats.tx_dropped++; dev_kfree_skb(skb); } spin_unlock(&eql->queue.lock); return NETDEV_TX_OK; } /* * Private ioctl functions */ /* queue->lock must be held */ static slave_t *__eql_find_slave_dev(slave_queue_t *queue, struct net_device *dev) { struct list_head *this, *head; head = &queue->all_slaves; list_for_each(this, head) { slave_t *slave = list_entry(this, slave_t, list); if (slave->dev == dev) return slave; } return NULL; } static inline int eql_is_full(slave_queue_t *queue) { equalizer_t *eql = netdev_priv(queue->master_dev); if (queue->num_slaves >= eql->max_slaves) return 1; return 0; } /* queue->lock must be held */ static int __eql_insert_slave(slave_queue_t *queue, slave_t *slave) { if (!eql_is_full(queue)) { slave_t *duplicate_slave = NULL; duplicate_slave = __eql_find_slave_dev(queue, slave->dev); if (duplicate_slave) eql_kill_one_slave(queue, duplicate_slave); netdev_hold(slave->dev, &slave->dev_tracker, GFP_ATOMIC); list_add(&slave->list, &queue->all_slaves); queue->num_slaves++; slave->dev->flags |= IFF_SLAVE; return 0; } return -ENOSPC; } static int eql_enslave(struct net_device *master_dev, slaving_request_t __user *srqp) { struct net_device *slave_dev; slaving_request_t srq; if (copy_from_user(&srq, srqp, sizeof (slaving_request_t))) return -EFAULT; slave_dev = __dev_get_by_name(&init_net, srq.slave_name); if (!slave_dev) return -ENODEV; if ((master_dev->flags & IFF_UP) == IFF_UP) { /* slave is not a master & not already a slave: */ if (!eql_is_master(slave_dev) && !eql_is_slave(slave_dev)) { slave_t *s = kzalloc_obj(*s); equalizer_t *eql = netdev_priv(master_dev); int ret; if (!s) return -ENOMEM; s->dev = slave_dev; s->priority = srq.priority; s->priority_bps = srq.priority; s->priority_Bps = srq.priority / 8; spin_lock_bh(&eql->queue.lock); ret = __eql_insert_slave(&eql->queue, s); if (ret) kfree(s); spin_unlock_bh(&eql->queue.lock); return ret; } } return -EINVAL; } static int eql_emancipate(struct net_device *master_dev, slaving_request_t __user *srqp) { equalizer_t *eql = netdev_priv(master_dev); struct net_device *slave_dev; slaving_request_t srq; int ret; if (copy_from_user(&srq, srqp, sizeof (slaving_request_t))) return -EFAULT; slave_dev = __dev_get_by_name(&init_net, srq.slave_name); if (!slave_dev) return -ENODEV; ret = -EINVAL; spin_lock_bh(&eql->queue.lock); if (eql_is_slave(slave_dev)) { slave_t *slave = __eql_find_slave_dev(&eql->queue, slave_dev); if (slave) { eql_kill_one_slave(&eql->queue, slave); ret = 0; } } spin_unlock_bh(&eql->queue.lock); return ret; } static int eql_g_slave_cfg(struct net_device *dev, slave_config_t __user *scp) { equalizer_t *eql = netdev_priv(dev); slave_t *slave; struct net_device *slave_dev; slave_config_t sc; int ret; if (copy_from_user(&sc, scp, sizeof (slave_config_t))) return -EFAULT; slave_dev = __dev_get_by_name(&init_net, sc.slave_name); if (!slave_dev) return -ENODEV; ret = -EINVAL; spin_lock_bh(&eql->queue.lock); if (eql_is_slave(slave_dev)) { slave = __eql_find_slave_dev(&eql->queue, slave_dev); if (slave) { sc.priority = slave->priority; ret = 0; } } spin_unlock_bh(&eql->queue.lock); if (!ret && copy_to_user(scp, &sc, sizeof (slave_config_t))) ret = -EFAULT; return ret; } static int eql_s_slave_cfg(struct net_device *dev, slave_config_t __user *scp) { slave_t *slave; equalizer_t *eql; struct net_device *slave_dev; slave_config_t sc; int ret; if (copy_from_user(&sc, scp, sizeof (slave_config_t))) return -EFAULT; slave_dev = __dev_get_by_name(&init_net, sc.slave_name); if (!slave_dev) return -ENODEV; ret = -EINVAL; eql = netdev_priv(dev); spin_lock_bh(&eql->queue.lock); if (eql_is_slave(slave_dev)) { slave = __eql_find_slave_dev(&eql->queue, slave_dev); if (slave) { slave->priority = sc.priority; slave->priority_bps = sc.priority; slave->priority_Bps = sc.priority / 8; ret = 0; } } spin_unlock_bh(&eql->queue.lock); return ret; } static int eql_g_master_cfg(struct net_device *dev, master_config_t __user *mcp) { equalizer_t *eql; master_config_t mc; memset(&mc, 0, sizeof(master_config_t)); if (eql_is_master(dev)) { eql = netdev_priv(dev); mc.max_slaves = eql->max_slaves; mc.min_slaves = eql->min_slaves; if (copy_to_user(mcp, &mc, sizeof (master_config_t))) return -EFAULT; return 0; } return -EINVAL; } static int eql_s_master_cfg(struct net_device *dev, master_config_t __user *mcp) { equalizer_t *eql; master_config_t mc; if (copy_from_user(&mc, mcp, sizeof (master_config_t))) return -EFAULT; if (eql_is_master(dev)) { eql = netdev_priv(dev); eql->max_slaves = mc.max_slaves; eql->min_slaves = mc.min_slaves; return 0; } return -EINVAL; } static struct net_device *dev_eql; static int __init eql_init_module(void) { int err; pr_info("%s\n", version); dev_eql = alloc_netdev(sizeof(equalizer_t), "eql", NET_NAME_UNKNOWN, eql_setup); if (!dev_eql) return -ENOMEM; err = register_netdev(dev_eql); if (err) free_netdev(dev_eql); return err; } static void __exit eql_cleanup_module(void) { unregister_netdev(dev_eql); free_netdev(dev_eql); } module_init(eql_init_module); module_exit(eql_cleanup_module); MODULE_DESCRIPTION("Equalizer Load-balancer for serial network interfaces"); MODULE_LICENSE("GPL"); |
| 152 152 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/bug.h> #include <linux/export.h> #include <linux/limits.h> #include <linux/math.h> #include <linux/minmax.h> #include <linux/types.h> #include <linux/reciprocal_div.h> /* * For a description of the algorithm please have a look at * include/linux/reciprocal_div.h */ struct reciprocal_value reciprocal_value(u32 d) { struct reciprocal_value R; u64 m; int l; l = fls(d - 1); m = ((1ULL << 32) * ((1ULL << l) - d)); do_div(m, d); ++m; R.m = (u32)m; R.sh1 = min(l, 1); R.sh2 = max(l - 1, 0); return R; } EXPORT_SYMBOL(reciprocal_value); struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec) { struct reciprocal_value_adv R; u32 l, post_shift; u64 mhigh, mlow; /* ceil(log2(d)) */ l = fls(d - 1); /* NOTE: mlow/mhigh could overflow u64 when l == 32. This case needs to * be handled before calling "reciprocal_value_adv", please see the * comment at include/linux/reciprocal_div.h. */ WARN(l == 32, "ceil(log2(0x%08x)) == 32, %s doesn't support such divisor", d, __func__); post_shift = l; mlow = 1ULL << (32 + l); do_div(mlow, d); mhigh = (1ULL << (32 + l)) + (1ULL << (32 + l - prec)); do_div(mhigh, d); for (; post_shift > 0; post_shift--) { u64 lo = mlow >> 1, hi = mhigh >> 1; if (lo >= hi) break; mlow = lo; mhigh = hi; } R.m = (u32)mhigh; R.sh = post_shift; R.exp = l; R.is_wide_m = mhigh > U32_MAX; return R; } EXPORT_SYMBOL(reciprocal_value_adv); |
| 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 14 14 21 21 21 1 21 21 21 21 21 21 21 21 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - Domain management * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2024-2025 Microsoft Corporation */ #include <kunit/test.h> #include <linux/bitops.h> #include <linux/bits.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/path.h> #include <linux/pid.h> #include <linux/sched.h> #include <linux/signal.h> #include <linux/uidgid.h> #include "access.h" #include "common.h" #include "domain.h" #include "id.h" #ifdef CONFIG_AUDIT /** * get_current_exe - Get the current's executable path, if any * * @exe_str: Returned pointer to a path string with a lifetime tied to the * returned buffer, if any. * @exe_size: Returned size of @exe_str (including the trailing null * character), if any. * * Return: A pointer to an allocated buffer where @exe_str point to, %NULL if * there is no executable path, or an error otherwise. */ static const void *get_current_exe(const char **const exe_str, size_t *const exe_size) { const size_t buffer_size = LANDLOCK_PATH_MAX_SIZE; struct mm_struct *mm = current->mm; struct file *file __free(fput) = NULL; char *buffer __free(kfree) = NULL; const char *exe; ssize_t size; if (!mm) return NULL; file = get_mm_exe_file(mm); if (!file) return NULL; buffer = kmalloc(buffer_size, GFP_KERNEL); if (!buffer) return ERR_PTR(-ENOMEM); exe = d_path(&file->f_path, buffer, buffer_size); if (WARN_ON_ONCE(IS_ERR(exe))) /* Should never happen according to LANDLOCK_PATH_MAX_SIZE. */ return ERR_CAST(exe); size = buffer + buffer_size - exe; if (WARN_ON_ONCE(size <= 0)) return ERR_PTR(-ENAMETOOLONG); *exe_size = size; *exe_str = exe; return no_free_ptr(buffer); } /* * Return: A newly allocated object describing a domain, or an error * otherwise. */ static struct landlock_details *get_current_details(void) { /* Cf. audit_log_d_path_exe() */ static const char null_path[] = "(null)"; const char *path_str = null_path; size_t path_size = sizeof(null_path); const void *buffer __free(kfree) = NULL; struct landlock_details *details; buffer = get_current_exe(&path_str, &path_size); if (IS_ERR(buffer)) return ERR_CAST(buffer); /* * Create the new details according to the path's length. Account to * the calling task's memcg, like the other Landlock per-domain * allocations, even if it may not control the related size. */ details = kzalloc_flex(*details, exe_path, path_size, GFP_KERNEL_ACCOUNT); if (!details) return ERR_PTR(-ENOMEM); memcpy(details->exe_path, path_str, path_size); details->pid = get_pid(task_tgid(current)); details->uid = from_kuid(&init_user_ns, current_uid()); get_task_comm(details->comm, current); return details; } /** * landlock_init_hierarchy_log - Partially initialize landlock_hierarchy * * @hierarchy: The hierarchy to initialize. * * The current task is referenced as the domain that is enforcing the * restriction. The subjective credentials must not be in an overridden state. * * @hierarchy->parent and @hierarchy->usage should already be set. * * Return: 0 on success, -errno on failure. */ int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy) { struct landlock_details *details; details = get_current_details(); if (IS_ERR(details)) return PTR_ERR(details); hierarchy->details = details; hierarchy->id = landlock_get_id_range(1); hierarchy->log_status = LANDLOCK_LOG_PENDING; hierarchy->log_same_exec = true; hierarchy->log_new_exec = false; atomic64_set(&hierarchy->num_denials, 0); return 0; } static deny_masks_t get_layer_deny_mask(const access_mask_t all_existing_optional_access, const unsigned long access_bit, const size_t layer) { unsigned long access_weight; /* This may require change with new object types. */ WARN_ON_ONCE(all_existing_optional_access != _LANDLOCK_ACCESS_FS_OPTIONAL); if (WARN_ON_ONCE(layer >= LANDLOCK_MAX_NUM_LAYERS)) return 0; access_weight = hweight_long(all_existing_optional_access & GENMASK(access_bit, 0)); if (WARN_ON_ONCE(access_weight < 1)) return 0; return layer << ((access_weight - 1) * HWEIGHT(LANDLOCK_MAX_NUM_LAYERS - 1)); } /** * landlock_get_quiet_optional_accesses - Get optional accesses which are * covered by quiet rule flags. * * @all_existing_optional_access: Bitmask of valid optional accesses. * @deny_masks: Domain layer levels that denied each optional access (the * deny_masks field on struct landlock_file_security). * @masks: The struct layer_masks collected during the path walk. * * Return: a bitmask of which optional accesses are denied by layers for which * the quiet flag was collected during the path walk. */ optional_access_t landlock_get_quiet_optional_accesses( const access_mask_t all_existing_optional_access, const deny_masks_t deny_masks, const struct layer_masks *const masks) { const unsigned long access_opt = all_existing_optional_access; size_t access_index = 0; unsigned long access_bit; optional_access_t quiet_optional_accesses = 0; /* This will require change with new object types. */ WARN_ON_ONCE(access_opt != _LANDLOCK_ACCESS_FS_OPTIONAL); for_each_set_bit(access_bit, &access_opt, BITS_PER_TYPE(access_mask_t)) { const u8 layer = (deny_masks >> (access_index * HWEIGHT(LANDLOCK_MAX_NUM_LAYERS - 1))) & (LANDLOCK_MAX_NUM_LAYERS - 1); if (masks->layers[layer].quiet) quiet_optional_accesses |= BIT(access_index); access_index++; } return quiet_optional_accesses; } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_get_layer_deny_mask(struct kunit *const test) { const unsigned long truncate = BIT_INDEX(LANDLOCK_ACCESS_FS_TRUNCATE); const unsigned long ioctl_dev = BIT_INDEX(LANDLOCK_ACCESS_FS_IOCTL_DEV); KUNIT_EXPECT_EQ(test, 0, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, truncate, 0)); KUNIT_EXPECT_EQ(test, 0x3, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, truncate, 3)); KUNIT_EXPECT_EQ(test, 0, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, ioctl_dev, 0)); KUNIT_EXPECT_EQ(test, 0xf0, get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL, ioctl_dev, 15)); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ deny_masks_t landlock_get_deny_masks(const access_mask_t all_existing_optional_access, const access_mask_t optional_access, const struct layer_masks *const masks) { const unsigned long access_opt = optional_access; unsigned long access_bit; deny_masks_t deny_masks = 0; access_mask_t all_denied = 0; /* This may require change with new object types. */ WARN_ON_ONCE(!access_mask_subset(optional_access, all_existing_optional_access)); if (WARN_ON_ONCE(!masks)) return 0; if (WARN_ON_ONCE(!access_opt)) return 0; for (ssize_t i = ARRAY_SIZE(masks->layers) - 1; i >= 0; i--) { const access_mask_t denied = masks->layers[i].access & optional_access; const unsigned long newly_denied = denied & ~all_denied; if (!newly_denied) continue; for_each_set_bit(access_bit, &newly_denied, 8 * sizeof(access_mask_t)) { deny_masks |= get_layer_deny_mask( all_existing_optional_access, access_bit, i); } all_denied |= denied; } return deny_masks; } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_landlock_get_deny_masks(struct kunit *const test) { const struct layer_masks layers1 = { .layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE | LANDLOCK_ACCESS_FS_IOCTL_DEV, .layers[1].access = LANDLOCK_ACCESS_FS_TRUNCATE, .layers[2].access = LANDLOCK_ACCESS_FS_IOCTL_DEV, .layers[9].access = LANDLOCK_ACCESS_FS_EXECUTE, }; KUNIT_EXPECT_EQ(test, 0x1, landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL, LANDLOCK_ACCESS_FS_TRUNCATE, &layers1)); KUNIT_EXPECT_EQ(test, 0x20, landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL, LANDLOCK_ACCESS_FS_IOCTL_DEV, &layers1)); KUNIT_EXPECT_EQ( test, 0x21, landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL, LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV, &layers1)); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static struct kunit_case test_cases[] = { /* clang-format off */ KUNIT_CASE(test_get_layer_deny_mask), KUNIT_CASE(test_landlock_get_deny_masks), {} /* clang-format on */ }; static struct kunit_suite test_suite = { .name = "landlock_domain", .test_cases = test_cases, }; kunit_test_suite(test_suite); #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #endif /* CONFIG_AUDIT */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 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; } |
| 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PROCFS_FD_H__ #define __PROCFS_FD_H__ #include <linux/fs.h> extern const struct file_operations proc_fd_operations; extern const struct inode_operations proc_fd_inode_operations; extern const struct file_operations proc_fdinfo_operations; extern const struct inode_operations proc_fdinfo_inode_operations; extern int proc_fd_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); static inline unsigned int proc_fd(struct inode *inode) { return PROC_I(inode)->fd; } #endif /* __PROCFS_FD_H__ */ |
| 70 199 1650 5553 1831 146 213 16 107 5 92 9 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/userfaultfd_k.h * * Copyright (C) 2015 Red Hat, Inc. * */ #ifndef _LINUX_USERFAULTFD_K_H #define _LINUX_USERFAULTFD_K_H #ifdef CONFIG_USERFAULTFD #include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */ #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/leafops.h> #include <asm-generic/pgtable_uffd.h> #include <linux/hugetlb_inline.h> /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) #define __VMA_UFFD_FLAGS mk_vma_flags_from_masks(VMA_UFFD_MISSING, VMA_UFFD_WP, \ VMA_UFFD_MINOR) /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want * to re-use O_* flags that couldn't possibly have a meaning * from userfaultfd, in order to leave a free define-space for * shared O_* flags. */ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. * * Locking order: * fd_wqh.lock * fault_pending_wqh.lock * fault_wqh.lock * event_wqh.lock * * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's * also taken in IRQ context. */ struct userfaultfd_ctx { /* waitqueue head for the pending (i.e. not read) userfaults */ wait_queue_head_t fault_pending_wqh; /* waitqueue head for the userfaults */ wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ seqcount_spinlock_t refile_seq; /* pseudo fd refcounting */ refcount_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* released */ bool released; /* * Prevents userfaultfd operations (fill/move/wp) from happening while * some non-cooperative event(s) is taking place. Increments are done * in write-mode. Whereas, userfaultfd operations, which includes * reading mmap_changing, is done under read-mode. */ struct rw_semaphore map_changing_lock; /* memory mappings are changing because of non-cooperative event */ atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; }; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* VMA userfaultfd operations */ struct vm_uffd_ops { /* Checks if a VMA can support userfaultfd */ bool (*can_userfault)(struct vm_area_struct *vma, vm_flags_t vm_flags); /* * Called to resolve UFFDIO_CONTINUE request. * Should return the folio found at pgoff in the VMA's pagecache if it * exists or ERR_PTR otherwise. * The returned folio is locked and with reference held. */ struct folio *(*get_folio_noalloc)(struct inode *inode, pgoff_t pgoff); /* * Called during resolution of UFFDIO_COPY request. * Should allocate and return a folio or NULL if allocation fails. */ struct folio *(*alloc_folio)(struct vm_area_struct *vma, unsigned long addr); /* * Called during resolution of UFFDIO_COPY request. * Should only be called with a folio returned by alloc_folio() above. * The folio will be set to locked. * Returns 0 on success, error code on failure. */ int (*filemap_add)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr); /* * Called during resolution of UFFDIO_COPY request on the error * handling path. * Should revert the operation of ->filemap_add(). */ void (*filemap_remove)(struct folio *folio, struct vm_area_struct *vma); }; /* A combined operation mode + behavior flags. */ typedef unsigned int __bitwise uffd_flags_t; /* Mutually exclusive modes of operation. */ enum mfill_atomic_mode { MFILL_ATOMIC_COPY, MFILL_ATOMIC_ZEROPAGE, MFILL_ATOMIC_CONTINUE, MFILL_ATOMIC_POISON, NR_MFILL_ATOMIC_MODES, }; #define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1) #define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr)) #define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr)) #define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1)) static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected) { return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected); } static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode) { flags &= ~MFILL_ATOMIC_MODE_MASK; return flags | ((__force uffd_flags_t) mode); } /* Flags controlling behavior. These behavior changes are mode-independent. */ #define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0) extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* move_pages */ void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2); void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2); int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx; } /* * Never enable huge pmd sharing on some uffd registered vmas: * * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry. * * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for * VMAs which share huge pmds. (If you have two mappings to the same * underlying pages, and fault in the non-UFFD-registered one with a write, * with huge pmd sharing this would *also* setup the second UFFD-registered * mapping, and we'd not get minor faults.) */ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } /* * Don't do fault around for either WP or MINOR registered uffd range. For * MINOR registered range, fault around will be a total disaster and ptes can * be installed without notifications; for WP it should mostly be fine as long * as the fault around checks for pte_none() before the installation, however * to be super safe we just forbid it. */ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_WP; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MINOR; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return userfaultfd_wp(vma) && pte_uffd_wp(pte); } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return userfaultfd_wp(vma) && pmd_uffd_wp(pmd); } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return vma->vm_flags & __VM_UFFD_FLAGS; } static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) { struct userfaultfd_ctx *uffd_ctx = vma->vm_userfaultfd_ctx.ctx; return uffd_ctx && (uffd_ctx->features & UFFD_FEATURE_EVENT_REMAP) == 0; } extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *, unsigned long from, unsigned long to, unsigned long len); void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *); extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); extern bool userfaultfd_wp_async(struct vm_area_struct *vma); static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) { /* Only wr-protect mode uses pte markers */ if (!userfaultfd_wp(vma)) return false; /* File-based uffd-wp always need markers */ if (!vma_is_anonymous(vma)) return true; /* * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED * enabled (to apply markers on zero pages). */ return userfaultfd_wp_unpopulated(vma); } /* * Returns true if this is a swap pte and was uffd-wp wr-protected in either * forms (pte marker or a normal swap pte), false otherwise. */ static inline bool pte_swp_uffd_wp_any(pte_t pte) { if (!uffd_supports_wp_marker()) return false; if (pte_present(pte)) return false; if (pte_swp_uffd_wp(pte)) return true; if (pte_is_uffd_wp_marker(pte)) return true; return false; } #else /* CONFIG_USERFAULTFD */ /* mm helpers */ static inline vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { return VM_FAULT_SIGBUS; } static inline long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp) { return false; } static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return true; } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return false; } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return false; } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return false; } static inline int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *l) { return 0; } static inline void dup_userfaultfd_complete(struct list_head *l) { } static inline void dup_userfaultfd_fail(struct list_head *l) { } static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { } static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx, unsigned long from, unsigned long to, unsigned long len) { } static inline void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *ctx) { } static inline bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return true; } static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf) { return 0; } static inline void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { } static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) { return false; } static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) { return false; } /* * Returns true if this is a swap pte and was uffd-wp wr-protected in either * forms (pte marker or a normal swap pte), false otherwise. */ static inline bool pte_swp_uffd_wp_any(pte_t pte) { return false; } #endif /* CONFIG_USERFAULTFD */ #endif /* _LINUX_USERFAULTFD_K_H */ |
| 64 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 | #ifndef __NET_SCHED_CODEL_H #define __NET_SCHED_CODEL_H /* * Codel - The Controlled-Delay Active Queue Management algorithm * * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions, and the following disclaimer, * without modification. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. The names of the authors may not be used to endorse or promote products * derived from this software without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/types.h> #include <linux/ktime.h> #include <linux/skbuff.h> /* Controlling Queue Delay (CoDel) algorithm * ========================================= * Source : Kathleen Nichols and Van Jacobson * http://queue.acm.org/detail.cfm?id=2209336 * * Implemented on linux by Dave Taht and Eric Dumazet */ /* CoDel uses a 1024 nsec clock, encoded in u32 * This gives a range of 2199 seconds, because of signed compares */ typedef u32 codel_time_t; typedef s32 codel_tdiff_t; #define CODEL_SHIFT 10 #define MS2TIME(a) ((a * NSEC_PER_MSEC) >> CODEL_SHIFT) static inline codel_time_t codel_get_time(void) { u64 ns = ktime_get_ns(); return ns >> CODEL_SHIFT; } /* Dealing with timer wrapping, according to RFC 1982, as desc in wikipedia: * https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution * codel_time_after(a,b) returns true if the time a is after time b. */ #define codel_time_after(a, b) \ (typecheck(codel_time_t, a) && \ typecheck(codel_time_t, b) && \ ((s32)((a) - (b)) > 0)) #define codel_time_before(a, b) codel_time_after(b, a) #define codel_time_after_eq(a, b) \ (typecheck(codel_time_t, a) && \ typecheck(codel_time_t, b) && \ ((s32)((a) - (b)) >= 0)) #define codel_time_before_eq(a, b) codel_time_after_eq(b, a) static inline u32 codel_time_to_us(codel_time_t val) { u64 valns = ((u64)val << CODEL_SHIFT); do_div(valns, NSEC_PER_USEC); return (u32)valns; } /** * struct codel_params - contains codel parameters * @target: target queue size (in time units) * @ce_threshold: threshold for marking packets with ECN CE * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled * @ce_threshold_selector: apply ce_threshold to packets matching this value * in the diffserv/ECN byte of the IP header * @ce_threshold_mask: mask to apply to ce_threshold_selector comparison */ struct codel_params { codel_time_t target; codel_time_t ce_threshold; codel_time_t interval; u32 mtu; bool ecn; u8 ce_threshold_selector; u8 ce_threshold_mask; }; /** * struct codel_vars - contains codel variables * @count: how many drops we've done since the last time we * entered dropping state * @lastcount: count at entry to dropping state * @dropping: set to true if in dropping state * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 * @first_above_time: when we went (or will go) continuously above target * for interval * @drop_next: time to drop next packet, or when we dropped last * @ldelay: sojourn time of last dequeued packet */ struct codel_vars { u32 count; u32 lastcount; bool dropping; u16 rec_inv_sqrt; codel_time_t first_above_time; codel_time_t drop_next; codel_time_t ldelay; }; #define REC_INV_SQRT_BITS (8 * sizeof(u16)) /* or sizeof_in_bits(rec_inv_sqrt) */ /* needed shift to get a Q0.32 number from rec_inv_sqrt */ #define REC_INV_SQRT_SHIFT (32 - REC_INV_SQRT_BITS) /** * struct codel_stats - contains codel shared variables and stats * @maxpacket: largest packet we've seen so far * @drop_count: temp count of dropped packets in dequeue() * @drop_len: bytes of dropped packets in dequeue() * @ecn_mark: number of packets we ECN marked instead of dropping * @ce_mark: number of packets CE marked because sojourn time was above ce_threshold */ struct codel_stats { u32 maxpacket; u32 drop_count; u32 drop_len; u32 ecn_mark; u32 ce_mark; }; #define CODEL_DISABLED_THRESHOLD INT_MAX typedef u32 (*codel_skb_len_t)(const struct sk_buff *skb); typedef codel_time_t (*codel_skb_time_t)(const struct sk_buff *skb); typedef void (*codel_skb_drop_t)(struct sk_buff *skb, void *ctx); typedef struct sk_buff * (*codel_skb_dequeue_t)(struct codel_vars *vars, void *ctx); #endif |
| 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | /* 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. * * Definitions for the ICMP module. * * Version: @(#)icmp.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _ICMP_H #define _ICMP_H #include <linux/icmp.h> #include <net/inet_sock.h> #include <net/snmp.h> #include <net/ip.h> struct icmp_err { int errno; unsigned int fatal:1; }; extern const struct icmp_err icmp_err_convert[]; #define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define __ICMP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256) #define ICMPMSGIN_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field) struct dst_entry; struct net_proto_family; struct sk_buff; struct net; void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, const struct inet_skb_parm *parm); static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { __icmp_send(skb_in, type, code, info, IPCB(skb_in)); } #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct inet_skb_parm parm; memset(&parm, 0, sizeof(parm)); __icmp_send(skb_in, type, code, info, &parm); } #endif int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr); #endif /* _ICMP_H */ |
| 73 73 73 73 73 73 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2019 Hammerspace Inc */ #include <linux/module.h> #include <linux/kobject.h> #include <linux/sysfs.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/string.h> #include <linux/nfs_fs.h> #include <net/net_namespace.h> #include <linux/rcupdate.h> #include <linux/lockd/bind.h> #include "internal.h" #include "nfs4_fs.h" #include "netns.h" #include "sysfs.h" static struct kset *nfs_kset; static void nfs_kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); kfree(kset); } static const struct kobj_ns_type_operations *nfs_netns_object_child_ns_type( const struct kobject *kobj) { return &net_ns_type_operations; } static struct kobj_type nfs_kset_type = { .release = nfs_kset_release, .sysfs_ops = &kobj_sysfs_ops, .child_ns_type = nfs_netns_object_child_ns_type, }; int nfs_sysfs_init(void) { int ret; nfs_kset = kzalloc_obj(*nfs_kset); if (!nfs_kset) return -ENOMEM; ret = kobject_set_name(&nfs_kset->kobj, "nfs"); if (ret) { kfree(nfs_kset); return ret; } nfs_kset->kobj.parent = fs_kobj; nfs_kset->kobj.ktype = &nfs_kset_type; nfs_kset->kobj.kset = NULL; ret = kset_register(nfs_kset); if (ret) { kfree(nfs_kset); return ret; } return 0; } void nfs_sysfs_exit(void) { kset_unregister(nfs_kset); } static ssize_t nfs_netns_identifier_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, kobject); ssize_t ret; rcu_read_lock(); ret = sysfs_emit(buf, "%s\n", rcu_dereference(c->identifier)); rcu_read_unlock(); return ret; } /* Strip trailing '\n' */ static size_t nfs_string_strip(const char *c, size_t len) { while (len > 0 && c[len-1] == '\n') --len; return len; } static ssize_t nfs_netns_identifier_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, kobject); const char *old; char *p; size_t len; len = nfs_string_strip(buf, min_t(size_t, count, CONTAINER_ID_MAXLEN)); if (!len) return 0; p = kmemdup_nul(buf, len, GFP_KERNEL); if (!p) return -ENOMEM; old = rcu_dereference_protected(xchg(&c->identifier, (char __rcu *)p), 1); if (old) { synchronize_rcu(); kfree(old); } return count; } static void nfs_netns_client_release(struct kobject *kobj) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, kobject); kfree(rcu_dereference_raw(c->identifier)); } static const struct ns_common *nfs_netns_client_namespace(const struct kobject *kobj) { return to_ns_common(container_of(kobj, struct nfs_netns_client, kobject)->net); } static struct kobj_attribute nfs_netns_client_id = __ATTR(identifier, 0644, nfs_netns_identifier_show, nfs_netns_identifier_store); static struct attribute *nfs_netns_client_attrs[] = { &nfs_netns_client_id.attr, NULL, }; ATTRIBUTE_GROUPS(nfs_netns_client); static struct kobj_type nfs_netns_client_type = { .release = nfs_netns_client_release, .default_groups = nfs_netns_client_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_client_namespace, }; static void nfs_netns_object_release(struct kobject *kobj) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, nfs_net_kobj); kfree(c); } static const struct ns_common *nfs_netns_namespace(const struct kobject *kobj) { return to_ns_common(container_of(kobj, struct nfs_netns_client, nfs_net_kobj)->net); } static struct kobj_type nfs_netns_object_type = { .release = nfs_netns_object_release, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_namespace, }; static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent, struct net *net) { struct nfs_netns_client *p; p = kzalloc_obj(*p); if (p) { p->net = net; p->kobject.kset = nfs_kset; p->nfs_net_kobj.kset = nfs_kset; if (kobject_init_and_add(&p->nfs_net_kobj, &nfs_netns_object_type, parent, "net") != 0) { kobject_put(&p->nfs_net_kobj); return NULL; } if (kobject_init_and_add(&p->kobject, &nfs_netns_client_type, &p->nfs_net_kobj, "nfs_client") == 0) return p; kobject_put(&p->kobject); kobject_put(&p->nfs_net_kobj); } return NULL; } void nfs_netns_sysfs_setup(struct nfs_net *netns, struct net *net) { struct nfs_netns_client *clp; clp = nfs_netns_client_alloc(&nfs_kset->kobj, net); if (clp) { netns->nfs_client = clp; kobject_uevent(&clp->kobject, KOBJ_ADD); } } void nfs_netns_sysfs_destroy(struct nfs_net *netns) { struct nfs_netns_client *clp = netns->nfs_client; if (clp) { kobject_uevent(&clp->kobject, KOBJ_REMOVE); kobject_del(&clp->kobject); kobject_put(&clp->kobject); kobject_del(&clp->nfs_net_kobj); kobject_put(&clp->nfs_net_kobj); netns->nfs_client = NULL; } } static bool shutdown_match_client(const struct rpc_task *task, const void *data) { return true; } static void shutdown_client(struct rpc_clnt *clnt) { clnt->cl_shutdown = 1; rpc_cancel_tasks(clnt, -EIO, shutdown_match_client, NULL); } /* * Shut down the nfs_client only once all the superblocks * have been shut down. */ static void shutdown_nfs_client(struct nfs_client *clp) { struct nfs_server *server; rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { if (!(server->flags & NFS_MOUNT_SHUTDOWN)) { rcu_read_unlock(); return; } } rcu_read_unlock(); nfs_mark_client_ready(clp, -EIO); shutdown_client(clp->cl_rpcclient); } static ssize_t shutdown_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct nfs_server *server = container_of(kobj, struct nfs_server, kobj); bool shutdown = server->flags & NFS_MOUNT_SHUTDOWN; return sysfs_emit(buf, "%d\n", shutdown); } static ssize_t shutdown_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct nfs_server *server; int ret, val; server = container_of(kobj, struct nfs_server, kobj); ret = kstrtoint(buf, 0, &val); if (ret) return ret; if (val != 1) return -EINVAL; /* already shut down? */ if (server->flags & NFS_MOUNT_SHUTDOWN) goto out; server->flags |= NFS_MOUNT_SHUTDOWN; shutdown_client(server->client); if (!IS_ERR(server->client_acl)) shutdown_client(server->client_acl); if (server->nlm_host) nlmclnt_shutdown_rpc_clnt(server->nlm_host); out: shutdown_nfs_client(server->nfs_client); return count; } static struct kobj_attribute nfs_sysfs_attr_shutdown = __ATTR_RW(shutdown); #if IS_ENABLED(CONFIG_NFS_V4) static ssize_t implid_domain_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct nfs_server *server = container_of(kobj, struct nfs_server, kobj); struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid; if (!impl_id || strlen(impl_id->domain) == 0) return 0; //sysfs_emit(buf, ""); return sysfs_emit(buf, "%s\n", impl_id->domain); } static struct kobj_attribute nfs_sysfs_attr_implid_domain = __ATTR_RO(implid_domain); static ssize_t implid_name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct nfs_server *server = container_of(kobj, struct nfs_server, kobj); struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid; if (!impl_id || strlen(impl_id->name) == 0) return 0; //sysfs_emit(buf, ""); return sysfs_emit(buf, "%s\n", impl_id->name); } static struct kobj_attribute nfs_sysfs_attr_implid_name = __ATTR_RO(implid_name); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ #define RPC_CLIENT_NAME_SIZE 64 void nfs_sysfs_link_rpc_client(struct nfs_server *server, struct rpc_clnt *clnt, const char *uniq) { char name[RPC_CLIENT_NAME_SIZE]; int ret; strscpy(name, clnt->cl_program->name, sizeof(name)); strncat(name, uniq ? uniq : "", sizeof(name) - strlen(name) - 1); strncat(name, "_client", sizeof(name) - strlen(name) - 1); ret = sysfs_create_link_nowarn(&server->kobj, &clnt->cl_sysfs->kobject, name); if (ret < 0) pr_warn("NFS: can't create link to %s in sysfs (%d)\n", name, ret); } EXPORT_SYMBOL_GPL(nfs_sysfs_link_rpc_client); static void nfs_sysfs_sb_release(struct kobject *kobj) { /* no-op: why? see lib/kobject.c kobject_cleanup() */ } static const struct ns_common *nfs_netns_server_namespace(const struct kobject *kobj) { return to_ns_common(container_of(kobj, struct nfs_server, kobj)->nfs_client->cl_net); } static struct kobj_type nfs_sb_ktype = { .release = nfs_sysfs_sb_release, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_server_namespace, .child_ns_type = nfs_netns_object_child_ns_type, }; #if IS_ENABLED(CONFIG_NFS_V4) static void nfs_sysfs_add_nfsv41_server(struct nfs_server *server) { int ret; if (!server->nfs_client->cl_implid) return; ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_domain.attr, nfs_netns_server_namespace(&server->kobj)); if (ret < 0) pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n", server->s_sysfs_id, ret); ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_name.attr, nfs_netns_server_namespace(&server->kobj)); if (ret < 0) pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n", server->s_sysfs_id, ret); } #else /* CONFIG_NFS_V4 */ static inline void nfs_sysfs_add_nfsv41_server(struct nfs_server *server) { } #endif /* CONFIG_NFS_V4 */ #if IS_ENABLED(CONFIG_NFS_LOCALIO) static ssize_t localio_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct nfs_server *server = container_of(kobj, struct nfs_server, kobj); bool localio = nfs_server_is_local(server->nfs_client); return sysfs_emit(buf, "%d\n", localio); } static struct kobj_attribute nfs_sysfs_attr_localio = __ATTR_RO(localio); static void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server) { int ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_localio.attr, nfs_netns_server_namespace(&server->kobj)); if (ret < 0) pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n", server->s_sysfs_id, ret); } #else static inline void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server) { } #endif /* IS_ENABLED(CONFIG_NFS_LOCALIO) */ void nfs_sysfs_add_server(struct nfs_server *server) { int ret; ret = kobject_init_and_add(&server->kobj, &nfs_sb_ktype, &nfs_kset->kobj, "server-%d", server->s_sysfs_id); if (ret < 0) { pr_warn("NFS: nfs sysfs add server-%d failed (%d)\n", server->s_sysfs_id, ret); return; } ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_shutdown.attr, nfs_netns_server_namespace(&server->kobj)); if (ret < 0) pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n", server->s_sysfs_id, ret); nfs_sysfs_add_nfsv41_server(server); nfs_sysfs_add_nfs_localio_server(server); } EXPORT_SYMBOL_GPL(nfs_sysfs_add_server); void nfs_sysfs_move_server_to_sb(struct super_block *s) { struct nfs_server *server = s->s_fs_info; int ret; ret = kobject_rename(&server->kobj, s->s_id); if (ret < 0) pr_warn("NFS: rename sysfs %s failed (%d)\n", server->kobj.name, ret); } void nfs_sysfs_move_sb_to_server(struct nfs_server *server) { const char *s; int ret = -ENOMEM; s = kasprintf(GFP_KERNEL, "server-%d", server->s_sysfs_id); if (s) { ret = kobject_rename(&server->kobj, s); kfree(s); } if (ret < 0) pr_warn("NFS: rename sysfs %s failed (%d)\n", server->kobj.name, ret); } /* unlink, not dec-ref */ void nfs_sysfs_remove_server(struct nfs_server *server) { kobject_del(&server->kobj); } |
| 596 596 595 596 595 720 720 717 703 700 703 244 21 12 479 6 702 720 596 596 359 1 359 359 232 232 230 205 65 232 134 135 135 131 134 132 2 135 135 135 135 136 135 134 135 22 118 135 133 378 376 3 374 11 11 11 287 287 282 74 70 284 98 5 5 1 1 1 1 1 1 1 1 207 205 207 33 29 29 17 10 366 16 15 16 15 2 2 2 2 2 15 324 369 366 168 164 314 364 7 7 6 51 5 5 5 51 55 54 35 34 21 51 637 170 637 637 637 637 636 636 171 635 635 635 119 28 97 97 635 97 2 2 2 2 96 97 637 636 528 527 16 635 636 637 636 28 28 526 527 528 528 528 28 28 526 525 96 525 454 524 524 522 180 253 129 129 129 68 68 129 129 132 4 131 131 70 189 23 180 151 4 4 179 124 180 70 70 179 180 179 177 179 48 180 177 177 177 67 67 129 4 4 130 177 120 68 68 68 68 68 68 68 68 68 68 68 68 36 49 8 4751 4752 127 4741 190 190 190 7 189 4 4 52 52 52 52 4 52 3 52 52 52 52 52 52 65 10 9 7 7 7 7 3 1 2 9 8 8 8 8 8 4 4 4 4 4 4 1 2219 2221 2220 2215 2221 815 814 1 2222 781 746 417 159 159 159 159 417 122 297 50 417 50 660 292 57 296 29 295 296 297 3 295 16 297 296 297 215 295 294 5 297 296 296 297 16 783 276 656 213 710 709 482 482 2 120 410 410 410 44 410 44 43 4 44 410 556 555 557 385 372 371 368 366 362 362 362 40 39 377 362 4 32 557 62 9 9 9 9 9 9 9 9 9 9 1 9 9 9 9 9 276 277 277 99 100 277 272 270 277 8 96 97 97 87 87 87 87 87 85 87 79 79 97 103 1 103 103 102 102 19 8 3 7 6 4 46 1 45 46 42 41 41 10 10 7 7 1 12 12 12 12 12 12 12 2 2 34 34 34 34 97 96 97 83 82 1 83 82 1 83 97 12 2 96 86 87 34 87 47 46 7 81 5 10 10 56 56 56 63 63 62 62 63 63 62 63 60 54 56 56 56 56 56 56 55 56 22 56 56 56 56 56 56 39 62 62 6 48 8 8 40 3 1 31 3 28 29 29 37 35 36 35 78 78 78 78 78 77 40 41 41 41 40 40 40 40 40 40 39 38 41 41 41 16 3 3 3 16 3 15 23 21 21 19 6 16 16 16 9 7 6 1 5 6 9 21 16 15 23 76 9 9 9 1 113 9 8 105 102 93 2 2 91 76 76 8 8 8 8 8 19 19 74 91 91 68 27 26 27 21 21 16 8 21 19 19 113 8 8 8 8 8 124 121 121 31 27 31 11 113 113 113 113 68 68 76 76 1 76 76 19 57 23 10 23 23 19 8 3 3 15 68 68 68 68 68 79 132 1447 1269 20 20 8 126 126 1646 1645 1646 1457 1456 1454 1454 1451 1452 1449 1449 1449 2 55 152 17 29 29 17 16 16 29 16 4 16 29 29 28 29 11 1439 958 601 1645 1646 1646 1449 1447 1444 1 1445 1446 1447 1445 1439 29 29 737 960 962 946 535 499 27 1446 1445 1447 1447 1646 16 16 16 16 16 1 16 16 16 1 1 1 1 25 25 25 27 7 7 74 74 73 67 67 1 1 61 16 8 13 13 66 14 14 14 61 73 69 2 5 3 2 17 11 17 3 3 3 3 3 334 334 334 16 29 334 334 334 193 334 334 139 135 139 139 325 325 261 252 262 16 13 16 16 16 17 16 2 12 14 317 315 317 227 227 317 202 22 7 22 7 7 7 7 7 22 12 12 12 7 7 6 6 1 7 1 7 3 3 3 3 3 3 7 7 7 3 3 12 14 3 2 17 16 15 15 14 13 12 6 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/folio_batch.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <linux/migrate.h> #include <linux/pipe_fs_i.h> #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <linux/sched/mm.h> #include <linux/sysctl.h> #include <linux/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> #include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_rwsem * ->invalidate_lock (acquired by fs in truncate path) * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->invalidate_lock (filemap_fault) * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_merge) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->folio_isolate_lru) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) */ static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { XA_STATE(xas, &mapping->i_pages, folio->index); long nr = 1; mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } static void filemap_unaccount_folio(struct address_space *mapping, struct folio *folio) { long nr; VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, folio_pfn(folio)); dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped * and we'd rather not leak it: if we're wrong, * another bad page check should catch it later. */ atomic_set(&folio->_mapcount, -1); folio_ref_sub(folio, mapcount); } } } /* hugetlb folios do not participate in page cache accounting. */ if (folio_test_hugetlb(folio)) return; nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); if (folio_test_swapbacked(folio)) { lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); if (folio_test_pmd_mappable(folio)) lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); } if (test_bit(AS_KERNEL_FILE, &folio->mapping->flags)) mod_node_page_state(folio_pgdat(folio), NR_KERNEL_FILE_PAGES, -nr); /* * At this point folio must be either written or cleaned by * truncate. Dirty folio here signals a bug and loss of * unwritten data - on ordinary filesystems. * * But it's harmless on in-memory filesystems like tmpfs; and can * occur when a driver which did get_user_pages() sets page dirty * before putting it, while the inode is being finally evicted. * * Below fixes dirty accounting after removing the folio entirely * but leaves the dirty flag set: it has no effect for truncated * folio and anyway will be cleared before returning folio to * buddy allocator. */ if (WARN_ON_ONCE(folio_test_dirty(folio) && mapping_can_writeback(mapping))) folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __filemap_remove_folio(struct folio *folio, void *shadow) { struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } static void filemap_free_folio(const struct address_space *mapping, struct folio *folio) { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; if (free_folio) free_folio(folio); folio_put_refs(folio, folio_nr_pages(folio)); } /** * filemap_remove_folio - Remove folio from page cache. * @folio: The folio. * * This must be called only on folios that are locked and have been * verified to be in the page cache. It will never put the folio into * the free list because the caller has a reference on the page. */ void filemap_remove_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_lru_list_add(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); } /* * page_cache_delete_batch - delete several folios from page cache * @mapping: the mapping to which folios belong * @fbatch: batch of folios to delete * * The function walks over mapping->i_pages and removes folios passed in * @fbatch from the mapping. The function expects @fbatch to be sorted * by page index and is optimised for it to be dense. * It tolerates holes in @fbatch (mapping entries at those indices are not * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); long total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > fbatch->folios[i]->index, folio); continue; } WARN_ON_ONCE(!folio_test_locked(folio)); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ i++; xas_store(&xas, NULL); total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch) { int i; if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_lru_list_add(mapping->host); spin_unlock(&mapping->host->i_lock); for (i = 0; i < folio_batch_count(fbatch); i++) filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } static int filemap_writeback(struct address_space *mapping, loff_t start, loff_t end, enum writeback_sync_modes sync_mode, long *nr_to_write) { struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = nr_to_write ? *nr_to_write : LONG_MAX, .range_start = start, .range_end = end, }; int ret; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); wbc_detach_inode(&wbc); if (!ret && nr_to_write) *nr_to_write = wbc.nr_to_write; return ret; } /** * filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * This is a data integrity operation that waits upon dirty or in writeback * pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return filemap_writeback(mapping, start, end, WB_SYNC_ALL, NULL); } EXPORT_SYMBOL(filemap_fdatawrite_range); int filemap_fdatawrite(struct address_space *mapping) { return filemap_fdatawrite_range(mapping, 0, LLONG_MAX); } EXPORT_SYMBOL(filemap_fdatawrite); /** * filemap_flush_range - start writeback on a range * @mapping: target address_space * @start: index to start writeback on * @end: last (inclusive) index for writeback * * This is a non-integrity writeback helper, to start writing back folios * for the indicated range. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush_range(struct address_space *mapping, loff_t start, loff_t end) { return filemap_writeback(mapping, start, end, WB_SYNC_NONE, NULL); } EXPORT_SYMBOL_GPL(filemap_flush_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return filemap_flush_range(mapping, 0, LLONG_MAX); } EXPORT_SYMBOL(filemap_flush); /* * Start writeback on @nr_to_write pages from @mapping. No one but the existing * btrfs caller should be using this. Talk to linux-mm if you think adding a * new caller is a good idea. */ int filemap_flush_nr(struct address_space *mapping, long *nr_to_write) { return filemap_writeback(mapping, 0, LLONG_MAX, WB_SYNC_NONE, nr_to_write); } EXPORT_SYMBOL_FOR_MODULES(filemap_flush_nr, "btrfs"); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct folio *folio; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { folio = xas_find(&xas, max); if (xas_retry(&xas, folio)) continue; /* Shadow entries don't count */ if (xa_is_value(folio)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct folio_batch fbatch; unsigned nr_folios; folio_batch_init(&fbatch); while (index <= end) { unsigned i; nr_folios = filemap_get_folios_tag(mapping, &index, end, PAGECACHE_TAG_WRITEBACK, &fbatch); if (!nr_folios) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; folio_wait_writeback(folio); } folio_batch_release(&fbatch); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { return mapping->nrpages; } bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; struct folio *folio; if (end_byte < start_byte) return false; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_dirty(folio) || folio_test_locked(folio) || folio_test_writeback(folio)) break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0, err2; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = filemap_fdatawrite_range(mapping, lstart, lend); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = filemap_check_errors(mapping); if (!err) err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = filemap_fdatawrite_range(mapping, lstart, lend); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_folio - replace a pagecache folio with a new one * @old: folio to be replaced * @new: folio to replace with * * This function replaces a folio in the pagecache with a new one. On * success it acquires the pagecache reference for the new folio and * drops it for the old folio. Both the old and new folios must be * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ void replace_page_cache_folio(struct folio *old, struct folio *new) { struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); VM_BUG_ON_FOLIO(!folio_test_locked(old), old); VM_BUG_ON_FOLIO(!folio_test_locked(new), new); VM_BUG_ON_FOLIO(new->mapping, new); folio_get(new); new->mapping = mapping; new->index = offset; mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!folio_test_hugetlb(old)) lruvec_stat_sub_folio(old, NR_FILE_PAGES); if (!folio_test_hugetlb(new)) lruvec_stat_add_folio(new, NR_FILE_PAGES); if (folio_test_swapbacked(old)) lruvec_stat_sub_folio(old, NR_SHMEM); if (folio_test_swapbacked(new)) lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) free_folio(old); folio_put(old); } EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); bool huge; long nr; unsigned int forder = folio_order(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping), folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = xas.xa_index; for (;;) { int order = -1; void *entry, *old = NULL; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } /* * If a larger entry exists, * it will be the first and only entry iterated. */ if (order == -1) order = xas_get_order(&xas); } if (old) { if (order > 0 && order > forder) { unsigned int split_order = max(forder, xas_try_split_min_order(order)); /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); while (order > forder) { xas_set_order(&xas, index, split_order); xas_try_split(&xas, old, order); if (xas_error(&xas)) goto unlock; order = split_order; split_order = max(xas_try_split_min_order( split_order), forder); } xas_reset(&xas); } if (shadowp) *shadowp = old; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ if (!huge) { lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); if (folio_test_pmd_mappable(folio)) lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } unlock: xas_unlock_irq(&xas); if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) goto error; trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; /* Leave folio->index set: truncation relies upon it */ folio_put_refs(folio, nr); return xas_error(&xas); } ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; struct mem_cgroup *tmp; bool kernel_file = test_bit(AS_KERNEL_FILE, &mapping->flags); if (kernel_file) tmp = set_active_memcg(root_mem_cgroup); ret = mem_cgroup_charge(folio, NULL, gfp); if (kernel_file) set_active_memcg(tmp); if (ret) return ret; __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) { mem_cgroup_uncharge(folio); __folio_clear_locked(folio); } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed folio. * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow); folio_add_lru(folio); if (kernel_file) mod_node_page_state(folio_pgdat(folio), NR_KERNEL_FILE_PAGES, folio_nr_pages(folio)); } return ret; } EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy) { int n; struct folio *folio; if (policy) return folio_alloc_mpol_noprof(gfp, order, policy, NO_INTERLEAVE_INDEX, numa_node_id()); if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; } return folio_alloc_noprof(gfp, order); } EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* * filemap_invalidate_lock_two - lock invalidate_lock for two mappings * * Lock exclusively invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to lock * @mapping2: the second mapping to lock */ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1 > mapping2) swap(mapping1, mapping2); if (mapping1) down_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) down_write_nested(&mapping2->invalidate_lock, 1); } EXPORT_SYMBOL(filemap_invalidate_lock_two); /* * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings * * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to unlock * @mapping2: the second mapping to unlock */ void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1) up_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) up_write(&mapping2->invalidate_lock); } EXPORT_SYMBOL(filemap_invalidate_unlock_two); /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *folio_waitqueue(struct folio *folio) { return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } /* How many times do we accept lock stealing from under a waiter? */ static int sysctl_page_lock_unfairness = 5; static const struct ctl_table filemap_sysctl_table[] = { { .procname = "page_lock_unfairness", .data = &sysctl_page_lock_unfairness, .maxlen = sizeof(sysctl_page_lock_unfairness), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, } }; void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); register_sysctl_init("vm", filemap_sysctl_table); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags.f)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags.f)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void folio_wake_bit(struct folio *folio, int bit_nr) { wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page * waiters, but the hashed waitqueue has waiters for other pages on it. * That's okay, it's a rare case. The next waker will clear it. * * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, * other), the flag may be cleared in the course of freeing the page; * but that is not required for correctness. */ if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } /* * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like folio_put_wait_locked() on PG_locked. */ }; /* * Attempt to check (or get) the folio flag, and mark us done * if successful. */ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &folio->flags.f)) return false; } else if (test_bit(bit_nr, &folio->flags.f)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the folio. */ if (behavior == DROP) folio_put(folio); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } #ifdef CONFIG_MIGRATION /** * softleaf_entry_wait_on_locked - Wait for a migration entry or * device_private entry to be removed. * @entry: migration or device_private swap entry. * @ptl: already locked ptl. This function will drop the lock. * * Wait for a migration entry referencing the given page, or device_private * entry referencing a dvice_private page to be unlocked. This is * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this * should be called while holding the ptl for @entry referencing * the page. * * Returns after unlocking the ptl. * * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; wait_queue_head_t *q; struct folio *folio = softleaf_to_folio(entry); q = folio_waitqueue(folio); if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = PG_locked; wait->flags = 0; spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, PG_locked, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. * Similarly any path attempting to drop the last reference to a * device-private page needs to grab the ptl to remove the device-private * entry. */ spin_unlock(ptl); for (;;) { unsigned int flags; set_current_state(TASK_UNINTERRUPTIBLE); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) break; io_schedule(); continue; } break; } finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } } #endif void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit); int folio_wait_bit_killable(struct folio *folio, int bit_nr) { return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit_killable); /** * folio_put_wait_locked - Drop a reference and wait for it to be unlocked * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not * dereference @folio. * * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ static int folio_put_wait_locked(struct folio *folio, int state) { return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** * folio_unlock - Unlock a locked folio. * @folio: The folio. * * Unlocks the folio and wakes up any thread sleeping on the page lock. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_unlock(struct folio *folio) { /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** * folio_end_read - End read on a folio. * @folio: The folio. * @success: True if all reads completed successfully. * * When all reads against a folio have completed, filesystems should * call this function to let the pagecache know that no more reads * are outstanding. This will unlock the folio and wake up any thread * sleeping on the lock. The folio will also be marked uptodate if all * reads succeeded. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_end_read(struct folio *folio, bool success) { unsigned long mask = 1 << PG_locked; /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_end_read); /** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for * it. The folio reference held for PG_private_2 being set is released. * * This is, for example, used when a netfs folio is being written to a local * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ void folio_end_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } EXPORT_SYMBOL(folio_end_private_2); /** * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(folio_wait_private_2); /** * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is * received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; while (folio_test_private_2(folio)) { ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } EXPORT_SYMBOL(folio_wait_private_2_killable); static void filemap_end_dropbehind(struct folio *folio) { struct address_space *mapping = folio->mapping; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) return; if (!folio_test_clear_dropbehind(folio)) return; if (mapping) folio_unmap_invalidate(mapping, folio, 0); } /* * If folio was marked as dropbehind, then pages should be dropped when writeback * completes. Do that now. If we fail, it's likely because of a big folio - * just reset dropbehind for that case and latter completions should invalidate. */ void folio_end_dropbehind(struct folio *folio) { if (!folio_test_dropbehind(folio)) return; /* * Hitting !in_task() should not happen off RWF_DONTCACHE writeback, * but can happen if normal writeback just happens to find dirty folios * that were created as part of uncached writeback, and that writeback * would otherwise not need non-IRQ handling. Just skip the * invalidation in that case. */ if (in_task() && folio_trylock(folio)) { filemap_end_dropbehind(folio); folio_unlock(folio); } } EXPORT_SYMBOL_GPL(folio_end_dropbehind); /** * folio_end_writeback_no_dropbehind - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * This call is intended for filesystems that need to defer dropbehind. * * Context: May be called from process or interrupt context. */ void folio_end_writeback_no_dropbehind(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing * to shuffle a folio marked for immediate reclaim is too mild * a gain to justify taking an atomic operation penalty at the * end of every folio writeback. */ if (folio_test_reclaim(folio)) { folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); } EXPORT_SYMBOL_GPL(folio_end_writeback_no_dropbehind); /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and * reused before the folio_wake_bit(). */ folio_get(folio); folio_end_writeback_no_dropbehind(folio); folio_end_dropbehind(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); /** * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. * @folio: The folio to lock */ void __folio_lock(struct folio *folio) { folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); int ret; wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); folio_set_waiters(folio); ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } /* * Return values: * 0 - folio is locked. * non-zero - folio is not locked. * mmap_lock or per-VMA lock has been released (mmap_read_unlock() or * vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0 * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed. */ vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { unsigned int flags = vmf->flags; if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock/per-VMA lock is not * released even though returning VM_FAULT_RETRY. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; release_fault_lock(vmf); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); return VM_FAULT_RETRY; } if (flags & FAULT_FLAG_KILLABLE) { bool ret; ret = __folio_lock_killable(folio); if (ret) { release_fault_lock(vmf); return VM_FAULT_RETRY; } } else { __folio_lock(folio); } return 0; } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == 0) return 0; } /* Return end of the range + 1 when no hole is found */ return xas.xa_index + 1; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == ULONG_MAX) return ULONG_MAX; } /* Return start of the range - 1 when no hole is found */ return xas.xa_index - 1; } EXPORT_SYMBOL(page_cache_prev_miss); /* * Lockless page cache protocol: * On the lookup side: * 1. Load the folio from i_pages * 2. Increment the refcount if it's not zero * 3. If the folio is not found by xas_reload(), put the refcount and retry * * On the removal side: * A. Freeze the page (by zeroing the refcount if nobody else has a reference) * B. Remove the page from i_pages * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by * folio_put(). */ /* * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache entry at @mapping & @index. If it is a folio, * it is returned with an increased refcount. If it is a shadow entry * of a previously evicted folio, or a swap entry from shmem/tmpfs, * it is returned without further action. * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); folio = xas_load(&xas); if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!folio || xa_is_value(folio)) goto out; if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); goto repeat; } out: rcu_read_unlock(); return folio; } /** * __filemap_get_folio_mpol - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * @policy: NUMA memory allocation policy to follow. * * Looks up the page cache entry at @mapping & @index. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio_mpol(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp, struct mempolicy *policy) { struct folio *folio; repeat: folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) folio = NULL; if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); } /* Has the page been truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (folio_test_idle(folio)) folio_clear_idle(folio); } if (fgp_flags & FGP_STABLE) folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { unsigned int min_order = mapping_min_folio_order(mapping); unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags)); int err; index = mapping_align_index(mapping, index); if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp &= ~__GFP_FS; if (fgp_flags & FGP_NOWAIT) { gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT; } if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; if (order > mapping_max_folio_order(mapping)) order = mapping_max_folio_order(mapping); /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); do { gfp_t alloc_gfp = gfp; err = -ENOMEM; if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order, policy); if (!folio) continue; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); if (fgp_flags & FGP_DONTCACHE) __folio_set_dropbehind(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) break; folio_put(folio); folio = NULL; } while (order-- > min_order); if (err == -EEXIST) goto repeat; if (err) { /* * When NOWAIT I/O fails to allocate folios this could * be due to a nonblocking memory allocation and not * because the system actually is out of memory. * Return -EAGAIN so that there caller retries in a * blocking fashion instead of propagating -ENOMEM * to the application. */ if ((fgp_flags & FGP_NOWAIT) && err == -ENOMEM) err = -EAGAIN; return ERR_PTR(err); } /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. */ if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio); } if (!folio) return ERR_PTR(-ENOENT); /* not an uncached lookup, clear uncached if set */ if (!(fgp_flags & FGP_DONTCACHE) && folio_test_clear_dropbehind(folio)) { if (folio_test_dirty(folio) && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; long nr = folio_nr_pages(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); wb_stat_mod(wb, WB_DONTCACHE_DIRTY, -nr); unlocked_inode_to_wb_end(inode, &cookie); } } return folio; } EXPORT_SYMBOL(__filemap_get_folio_mpol); static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { struct folio *folio; retry: if (mark == XA_PRESENT) folio = xas_find(xas, max); else folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (!folio || xa_is_value(folio)) return folio; if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { folio_put(folio); goto reset; } return folio; reset: xas_reset(xas); goto retry; } /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in * the mapping. The entries are placed in @fbatch. find_get_entries() * takes a reference on any actual folios it returns. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries or large folios. * * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; } if (folio_batch_count(fbatch)) { unsigned long nr; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); else nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]); *start = round_down(indices[idx] + nr, nr); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * find_lock_entries - Find a batch of pagecache entries. * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned * locked and with an incremented refcount. Folios which are locked * by somebody else or under writeback are skipped. Folios which are * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries, large folios, folios which could not be * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { unsigned long base; unsigned long nr; if (!xa_is_value(folio)) { nr = folio_nr_pages(folio); base = folio->index; /* Omit large folio which begins before the start */ if (base < *start) goto put; /* Omit large folio which extends beyond the end */ if (base + nr - 1 > end) goto put; if (!folio_trylock(folio)) goto put; if (folio->mapping != mapping || folio_test_writeback(folio)) goto unlock; VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } else { nr = 1 << xas_get_order(&xas); base = xas.xa_index & ~(nr - 1); /* Omit order>0 value which begins before the start */ if (base < *start) continue; /* Omit order>0 value which extends beyond the end */ if (base + nr - 1 > end) break; } /* Update start now so that last update is correct on return */ *start = base + nr; indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; continue; unlock: folio_unlock(folio); put: folio_put(folio); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill. * * Search for and return a batch of folios in the mapping starting at * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); /** * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_contig() works exactly like filemap_get_folios(), * except the returned folios are guaranteed to be contiguous. This may * not return all contiguous folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); unsigned long nr; struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio && xas.xa_index <= end; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(folio)) goto update_start; /* If we landed in the middle of a THP, continue at its end. */ if (xa_is_sibling(folio)) goto update_start; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) { *start = folio_next_index(folio); goto out; } xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } update_start: nr = folio_batch_count(fbatch); if (nr) { folio = fbatch->folios[nr - 1]; *start = folio_next_index(folio); } out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_contig); /** * filemap_get_folios_tag - Get a batch of folios matching @tag * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @tag: The tag index * @fbatch: The batch to fill * * The first folio may start before @start; if it does, it will contain * @start. The final folio may extend beyond @end; if it does, it will * contain @end. The folios have ascending indices. There may be gaps * between the folios if there are indices which have no folio in the * page cache. If folios are added to or removed from the page cache * while this is running, they may or may not be found by this call. * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. */ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(folio)) continue; if (!folio_batch_add(fbatch, folio)) { *start = folio_next_index(folio); goto out; } } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_tag); /** * filemap_get_folios_dirty - Get a batch of dirty folios * @mapping: The address_space to search * @start: The starting folio index * @end: The final folio index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_dirty() works exactly like filemap_get_folios(), except * the returned folios are presumed to be dirty or undergoing writeback. Dirty * state is presumed because we don't block on folio lock nor want to miss * folios. Callers that need to can recheck state upon locking the folio. * * This may not return all dirty folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_dirty(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { if (xa_is_value(folio)) continue; if (folio_trylock(folio)) { bool clean = !folio_test_dirty(folio) && !folio_test_writeback(folio); folio_unlock(folio); if (clean) { folio_put(folio); continue; } } if (!folio_batch_add(fbatch, folio)) { *start = folio_next_index(folio); goto out; } } /* * We come here when there is no folio beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a folio at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /* * filemap_get_read_batch - Get a batch of folios for read * * Get a batch of folios which represent a contiguous range of bytes in * the file. No exceptional entries will be returned. If @index is in * the middle of a folio, the entire folio will be returned. The last * folio in the batch may have the readahead flag set or the uptodate flag * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; if (xas.xa_index > max || xa_is_value(folio)) break; if (xa_is_sibling(folio)) break; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) break; if (!folio_test_uptodate(folio)) break; if (folio_test_readahead(folio)) break; xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { bool workingset = folio_test_workingset(folio); unsigned long pflags; int error; /* Start the actual read. The read will unlock the page. */ if (unlikely(workingset)) psi_memstall_enter(&pflags); error = filler(file, folio); if (unlikely(workingset)) psi_memstall_leave(&pflags); if (error) return error; error = folio_wait_locked_killable(folio); if (error) return error; if (folio_test_uptodate(folio)) return 0; if (file) shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, loff_t pos, size_t count, struct folio *folio, bool need_uptodate) { if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (need_uptodate) return false; if (!mapping->a_ops->is_partially_uptodate) return false; if (mapping->host->i_blkbits >= folio_shift(folio)) return false; if (folio_pos(folio) > pos) { count -= folio_pos(folio) - pos; pos = 0; } else { pos -= folio_pos(folio); } if (pos == 0 && count >= folio_size(folio)) return false; return mapping->a_ops->is_partially_uptodate(folio, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, size_t count, struct folio *folio, bool need_uptodate) { int error; if (iocb->ki_flags & IOCB_NOWAIT) { if (!filemap_invalidate_trylock_shared(mapping)) return -EAGAIN; } else { filemap_invalidate_lock_shared(mapping); } if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); /* * This is where we usually end up waiting for a * previously submitted readahead to finish. */ folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; if (!folio->mapping) goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio, need_uptodate)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); goto unlock_mapping; unlock: folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) folio_put(folio); return error; } static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order, NULL); if (!folio) return -ENOMEM; if (iocb->ki_flags & IOCB_DONTCACHE) __folio_set_dropbehind(folio); /* * Protect against truncate / hole punch. Grabbing invalidate_lock * here assures we cannot instantiate and bring uptodate new * pagecache folios after evicting page cache during truncate * and before actually freeing blocks. Note that we could * release invalidate_lock after inserting the folio into * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, struct address_space *mapping, struct folio *folio, pgoff_t last_index) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_DONTCACHE) ractl.dropbehind = 1; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, size_t count, struct folio_batch *fbatch, bool need_uptodate) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; unsigned int flags; int err = 0; /* "last_index" is the index of the folio beyond the end of the read */ last_index = round_up(iocb->ki_pos + count, mapping_min_folio_nrbytes(mapping)) >> PAGE_SHIFT; retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); if (iocb->ki_flags & IOCB_DONTCACHE) ractl.dropbehind = 1; page_cache_sync_ra(&ractl, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { err = filemap_create_folio(iocb, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } folio = fbatch->folios[folio_batch_count(fbatch) - 1]; if (folio_test_readahead(folio)) { err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } if (!folio_test_uptodate(folio)) { if (folio_batch_count(fbatch) > 1) { err = -EAGAIN; goto err; } err = filemap_update_page(iocb, mapping, count, folio, need_uptodate); if (err) goto err; } trace_mm_filemap_get_pages(mapping, index, last_index - 1); return 0; err: if (err < 0) folio_put(folio); if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) { unsigned int shift = folio_shift(folio); return (pos1 >> shift == pos2 >> shift); } static void filemap_end_dropbehind_read(struct folio *folio) { if (!folio_test_dropbehind(folio)) return; if (folio_test_writeback(folio) || folio_test_dirty(folio)) return; if (folio_trylock(folio)) { filemap_end_dropbehind(folio); folio_unlock(folio); } } /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. * @iter: Destination for the data. * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns * a negative error number. */ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; loff_t last_pos = ra->prev_pos; if (unlikely(iocb->ki_pos < 0)) return -EINVAL; if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos); folio_batch_init(&fbatch); do { cond_resched(); /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(mapping); /* * When a read accesses the same folio several times, only * mark it as accessed the first time. */ if (!pos_same_folio(iocb->ki_pos, last_pos - 1, fbatch.folios[0])) folio_mark_accessed(fbatch.folios[0]); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t fsize = folio_size(folio); size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); size_t copied; if (end_offset < folio_pos(folio)) break; if (i > 0) folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; last_pos = iocb->ki_pos; if (copied < bytes) { error = -EFAULT; break; } } put_folios: for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; filemap_end_dropbehind_read(folio); folio_put(folio); } folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); ra->prev_pos = last_pos; return already_read ? already_read : error; } EXPORT_SYMBOL_GPL(filemap_read); int kiocb_write_and_wait(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, pos, end)) return -EAGAIN; return 0; } return filemap_write_and_wait_range(mapping, pos, end); } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait) { int ret; if (nowait) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; } else { ret = filemap_write_and_wait_range(mapping, pos, end); if (ret) return ret; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; return filemap_invalidate_pages(mapping, iocb->ki_pos, iocb->ki_pos + count - 1, iocb->ki_flags & IOCB_NOWAIT); } EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; retval = kiocb_write_and_wait(iocb, count); if (retval < 0) return retval; file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } if (retval != -EIOCBQUEUED) iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || IS_DAX(inode)) return retval; if (iocb->ki_pos >= i_size_read(inode)) return retval; } return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); /* * Splice subpages from a folio into a pipe. */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size) { struct page *page; size_t spliced = 0, offset = offset_in_folio(folio, fpos); page = folio_page(folio, offset / PAGE_SIZE); size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; while (spliced < size && !pipe_is_full(pipe)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); *buf = (struct pipe_buffer) { .ops = &page_cache_pipe_buf_ops, .page = page, .offset = offset, .len = part, }; folio_get(folio); pipe->head++; page++; spliced += part; offset = 0; } return spliced; } /** * filemap_splice_read - Splice data from a file's pagecache into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function gets folios from a file's pagecache and splices them into the * pipe. Readahead will be called as necessary to fill more folios. This may * be used for blockdevs also. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct folio_batch fbatch; struct kiocb iocb; size_t total_spliced = 0, used, npages; loff_t isize, end_offset; bool writably_mapped; int i, error = 0; if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) return 0; init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ used = pipe_buf_usage(pipe); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); folio_batch_init(&fbatch); do { cond_resched(); if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; error = filemap_get_pages(&iocb, len, &fbatch, true); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(in->f_mapping); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t n; if (folio_pos(folio) >= end_offset) goto out; folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); n = min_t(loff_t, len, isize - *ppos); n = splice_folio_into_pipe(pipe, folio, *ppos, n); if (!n) goto out; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_is_full(pipe)) goto out; } folio_batch_release(&fbatch); } while (len); out: folio_batch_release(&fbatch); file_accessed(in); return total_spliced ? total_spliced : error; } EXPORT_SYMBOL(filemap_splice_read); static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); folio_lock(folio); if (unlikely(folio->mapping != mapping)) goto unlock; offset = offset_in_folio(folio, start) & ~(bsz - 1); do { if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: folio_unlock(folio); rcu_read_lock(); return start; } static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { if (xa_is_value(folio)) return PAGE_SIZE << xas_get_order(xas); return folio_size(folio); } /** * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. * @mapping: Address space to search. * @start: First byte to consider. * @end: Limit of search (exclusive). * @whence: Either SEEK_HOLE or SEEK_DATA. * * If the page cache knows which blocks contain holes and which blocks * contain data, your filesystem can use this function to implement * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. */ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; size_t seek_size; if (start < pos) { if (!seek_data) goto unlock; start = pos; } seek_size = seek_folio_size(&xas, folio); pos = round_up((u64)pos + 1, seek_size); start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; if (start >= end) break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(folio)) folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); if (folio && !xa_is_value(folio)) folio_put(folio); if (start > end) return end; return start; } #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_folio_or_retry in that it can drop the * mmap_lock. It differs in that it actually returns the folio locked * if it returns 1 and 0 if it couldn't lock the folio. If we did have * to drop the mmap_lock then fpin will point to the pinned file and * needs to be fput()'ed at a later point. */ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the * fault lock, but all fault_handlers only check * for fatal signals if we return VM_FAULT_RETRY, * so we need to drop the fault lock here and * return 0 if we don't have a fpin. */ if (*fpin == NULL) release_fault_lock(vmf); return 0; } } else __folio_lock(folio); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; vm_flags_t vm_flags = vmf->vma->vm_flags; bool force_thp_readahead = false; unsigned int thp_order = 0; unsigned short mmap_miss; /* Use the readahead code, even if readahead is disabled */ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && (vm_flags & VM_HUGEPAGE)) { /* * Cap max THP order at 2MB: this is the common PMD-sized * hugepage size, and it avoids memory pressure from very * large forced readahead when mapping_max_folio_order() is * high (for example, 128MB with 64K base pages on arm64). */ if (mapping_large_folio_support(mapping)) { force_thp_readahead = true; thp_order = min_t(unsigned int, mapping_max_folio_order(mapping), get_order(SZ_2M)); } } if (!force_thp_readahead) { /* * If we don't want any read-ahead, don't bother. * VM_EXEC case below is already intended for random access. */ if ((vm_flags & (VM_RAND_READ | VM_EXEC)) == VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } } if (!(vm_flags & (VM_SEQ_READ | VM_EXEC))) { /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; } if (force_thp_readahead) { unsigned long folio_nr_pages = 1UL << thp_order; fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~(folio_nr_pages - 1); ra->size = folio_nr_pages; /* * Fetch two folios so we get the chance to actually * readahead, unless we've been told not to. */ if (!(vm_flags & VM_RAND_READ)) ra->size *= 2; ra->async_size = folio_nr_pages; ra->order = thp_order; page_cache_ra_order(&ractl, ra); return fpin; } if (vm_flags & VM_EXEC) { /* * Allow arch to request a preferred minimum folio order for * executable memory. This can often be beneficial to * performance if (e.g.) arm64 can contpte-map the folio. * Executable memory rarely benefits from readahead, due to its * random access nature, so set async_size to 0. * * Limit to the boundaries of the VMA to avoid reading in any * pad that might exist between sections, which would be a waste * of memory. */ struct vm_area_struct *vma = vmf->vma; unsigned long start = vma->vm_pgoff; unsigned long end = start + vma_pages(vma); unsigned long ra_end; ra->order = exec_folio_order(); ra->start = round_down(vmf->pgoff, 1UL << ra->order); ra->start = max(ra->start, start); ra_end = round_up(ra->start + ra->ra_pages, 1UL << ra->order); ra_end = min(ra_end, end); ra->size = ra_end - ra->start; ra->async_size = 0; } else { /* * mmap read-around */ ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ra->order = 0; } fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index = ra->start; page_cache_ra_order(&ractl, ra); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned short mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; /* * If the folio is locked, we're likely racing against another fault. * Don't touch the mmap_miss counter to avoid decreasing it multiple * times for a single folio and break the balance with mmap_miss * increase in do_sync_mmap_readahead(). * * VM_SEQ_READ and VM_EXEC mappings skip the mmap_miss increment in * do_sync_mmap_readahead(), so skip the decrement here as well to * keep the counter symmetric. */ if (likely(!folio_test_locked(folio)) && !(vmf->vma->vm_flags & (VM_SEQ_READ | VM_EXEC))) { mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); } if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; pte_t *ptep; /* * We might have COW'ed a pagecache folio and might now have an mlocked * anon folio mapped. The original pagecache folio is not mlocked and * might have been evicted. During a read+clear/modify/write update of * the PTE, such as done in do_numa_page()/change_pte_range(), we * temporarily clear the PTE under PT lock and might detect it here as * "none" when not holding the PT lock. * * Not rechecking the PTE under PT lock could result in an unexpected * major fault in an mlock'ed region. Recheck only for this special * scenario while holding the PT lock, to not degrade non-mlocked * scenarios. Recheck the PTE without PT lock firstly, thereby reducing * the number of times we hold PT lock. */ if (!(vma->vm_flags & VM_LOCKED)) return 0; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; ptep = pte_offset_map_ro_nolock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; if (unlikely(!pte_none(ptep_get_lockless(ptep)))) { ret = VM_FAULT_NOPAGE; } else { spin_lock(vmf->ptl); if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE; spin_unlock(vmf->ptl); } pte_unmap(ptep); return ret; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t max_idx, index = vmf->pgoff; struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; trace_mm_filemap_fault(mapping, index); /* * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } } else { ret = filemap_fault_recheck_pte_none(vmf); if (unlikely(ret)) return ret; /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: /* * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto retry_find; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked folio in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error, * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } /* * OK, the folio is really not uptodate. This can be because the * VMA has the VM_RAND_READ flag set, or because an error * arose. Let's read it in directly. */ goto page_not_uptodate; } /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { folio_unlock(folio); goto out_retry; } if (mapping_locked) filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) { folio_unlock(folio); folio_put(folio); return VM_FAULT_SIGBUS; } vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, pgoff_t start) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { folio_unlock(folio); folio_put(folio); return true; } if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start); vm_fault_t ret = do_set_pmd(vmf, folio, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ folio_unlock(folio); return true; } } if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; } static struct folio *next_uptodate_folio(struct xa_state *xas, struct address_space *mapping, pgoff_t end_pgoff) { struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { if (!folio) return NULL; if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) continue; if (!folio_try_get(folio)) continue; if (folio_test_locked(folio)) goto skip; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; if (!folio_trylock(folio)) goto skip; if (folio->mapping != mapping) goto unlock; if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return folio; unlock: folio_unlock(folio); skip: folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } /* * Map page range [start_page, start_page + nr_pages) of folio. * start_page is gotten from start by folio_page(folio, start) */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, pgoff_t file_end) { struct address_space *mapping = folio->mapping; unsigned int ref_from_caller = 1; vm_fault_t ret = 0; struct page *page = folio_page(folio, start); unsigned int count = 0; pte_t *old_ptep = vmf->pte; unsigned long addr0; /* * Map the large folio fully where possible: * * - The folio is fully within size of the file or belong * to shmem/tmpfs; * - The folio doesn't cross VMA boundary; * - The folio doesn't cross page table boundary; */ addr0 = addr - start * PAGE_SIZE; if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) && folio_within_vma(folio, vmf->vma) && (addr0 & PMD_MASK) == ((addr0 + folio_size(folio) - 1) & PMD_MASK)) { vmf->pte -= start; page -= start; addr = addr0; nr_pages = folio_nr_pages(folio); } do { if (PageHWPoison(page + count)) goto skip; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; continue; skip: if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count - ref_from_caller); ref_from_caller = 0; if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } count++; page += count; vmf->pte += count; addr += count * PAGE_SIZE; count = 0; } while (--nr_pages > 0); if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count - ref_from_caller); ref_from_caller = 0; if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; if (ref_from_caller) /* Locked folios cannot get truncated. */ folio_ref_dec(folio); return ret; } static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, unsigned long *rss) { vm_fault_t ret = 0; struct page *page = &folio->page; if (PageHWPoison(page)) goto out; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit * the fault-around logic. */ if (!pte_none(ptep_get(vmf->pte))) goto out; if (vmf->address == addr) ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); (*rss)++; return ret; out: /* Locked folios cannot get truncated. */ folio_ref_dec(folio); return ret; } vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t file_end, last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; unsigned long rss = 0; unsigned int nr_pages = 0, folio_type; /* * Recalculate end_pgoff based on file_end before calling * next_uptodate_folio() to avoid races with concurrent * truncation. */ file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; end_pgoff = min(end_pgoff, file_end); rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; /* * Do not allow to map with PMD across i_size to preserve * SIGBUS semantics. * * Make an exception for shmem/tmpfs that for long time * intentionally mapped with PMDs across i_size. */ if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) && filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) { folio_unlock(folio); folio_put(folio); goto out; } folio_type = mm_counter_file(folio); do { unsigned long end; vm_fault_t map_ret; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) { map_ret = filemap_map_order0_folio(vmf, folio, addr, &rss); } else { unsigned long start = xas.xa_index - folio->index; map_ret = filemap_map_folio_range(vmf, folio, start, addr, nr_pages, &rss, file_end); } ret |= map_ret; /* * If there are too many folios that are recently evicted * in a file, they will probably continue to be evicted. * In such situation, read-ahead is only a waste of IO. * Don't decrease mmap_miss in this scenario to make sure * we can stop read-ahead. * * VM_SEQ_READ and VM_EXEC mappings skip the mmap_miss * increment in do_sync_mmap_readahead(), so skip the * decrement here as well to keep the counter symmetric. */ if ((map_ret & VM_FAULT_NOPAGE) && !(vmf->flags & FAULT_FLAG_TRIED) && !folio_test_workingset(folio) && !(vma->vm_flags & (VM_SEQ_READ | VM_EXEC))) { unsigned short mmap_miss; mmap_miss = READ_ONCE(file->f_ra.mmap_miss); if (mmap_miss) WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss - 1); } folio_unlock(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); trace_mm_filemap_map_pages(mapping, start_pgoff, end_pgoff); out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); folio_lock(folio); if (folio->mapping != mapping) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty folio and writeprotect it again. */ folio_mark_dirty(folio); folio_wait_stable(folio); out: sb_end_pagefault(mapping->host->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } int generic_file_mmap_prepare(struct vm_area_desc *desc) { struct file *file = desc->file; struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); desc->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc) { if (is_shared_maywrite(&desc->vma_flags)) return -EINVAL; return generic_file_mmap_prepare(desc); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_mmap_prepare(struct vm_area_desc *desc) { return -ENOSYS; } int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_mmap_prepare); EXPORT_SYMBOL(generic_file_readonly_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap_prepare); static struct folio *do_read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { struct folio *folio; int err; if (!filler) filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { folio = filemap_alloc_folio(gfp, mapping_min_folio_order(mapping), NULL); if (!folio) return ERR_PTR(-ENOMEM); index = mapping_align_index(mapping, index); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } goto filler; } if (folio_test_uptodate(folio)) goto out; if (!folio_trylock(folio)) { folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); goto repeat; } /* Folio was truncated from mapping */ if (!folio->mapping) { folio_unlock(folio); folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (folio_test_uptodate(folio)) { folio_unlock(folio); goto out; } filler: e |