/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2014 Facebook. All rights reserved. */ #ifndef BTRFS_QGROUP_H #define BTRFS_QGROUP_H #include <linux/types.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/kobject.h> #include <linux/list.h> #include <uapi/linux/btrfs_tree.h> struct extent_buffer; struct extent_changeset; struct btrfs_delayed_extent_op; struct btrfs_fs_info; struct btrfs_root; struct btrfs_ioctl_quota_ctl_args; struct btrfs_trans_handle; struct btrfs_delayed_ref_root; struct btrfs_inode; /* * Btrfs qgroup overview * * Btrfs qgroup splits into 3 main part: * 1) Reserve * Reserve metadata/data space for incoming operations * Affect how qgroup limit works * * 2) Trace * Tell btrfs qgroup to trace dirty extents. * * Dirty extents including: * - Newly allocated extents * - Extents going to be deleted (in this trans) * - Extents whose owner is going to be modified * * This is the main part affects whether qgroup numbers will stay * consistent. * Btrfs qgroup can trace clean extents and won't cause any problem, * but it will consume extra CPU time, it should be avoided if possible. * * 3) Account * Btrfs qgroup will updates its numbers, based on dirty extents traced * in previous step. * * Normally at qgroup rescan and transaction commit time. */ /* * Special performance optimization for balance. * * For balance, we need to swap subtree of subvolume and reloc trees. * In theory, we need to trace all subtree blocks of both subvolume and reloc * trees, since their owner has changed during such swap. * * However since balance has ensured that both subtrees are containing the * same contents and have the same tree structures, such swap won't cause * qgroup number change. * * But there is a race window between subtree swap and transaction commit, * during that window, if we increase/decrease tree level or merge/split tree * blocks, we still need to trace the original subtrees. * * So for balance, we use a delayed subtree tracing, whose workflow is: * * 1) Record the subtree root block get swapped. * * During subtree swap: * O = Old tree blocks * N = New tree blocks * reloc tree subvolume tree X * Root Root * / \ / \ * NA OB OA OB * / | | \ / | | \ * NC ND OE OF OC OD OE OF * * In this case, NA and OA are going to be swapped, record (NA, OA) into * subvolume tree X. * * 2) After subtree swap. * reloc tree subvolume tree X * Root Root * / \ / \ * OA OB NA OB * / | | \ / | | \ * OC OD OE OF NC ND OE OF * * 3a) COW happens for OB * If we are going to COW tree block OB, we check OB's bytenr against * tree X's swapped_blocks structure. * If it doesn't fit any, nothing will happen. * * 3b) COW happens for NA * Check NA's bytenr against tree X's swapped_blocks, and get a hit. * Then we do subtree scan on both subtrees OA and NA. * Resulting 6 tree blocks to be scanned (OA, OC, OD, NA, NC, ND). * * Then no matter what we do to subvolume tree X, qgroup numbers will * still be correct. * Then NA's record gets removed from X's swapped_blocks. * * 4) Transaction commit * Any record in X's swapped_blocks gets removed, since there is no * modification to the swapped subtrees, no need to trigger heavy qgroup * subtree rescan for them. */ /* * These flags share the flags field of the btrfs_qgroup_status_item with the * persisted flags defined in btrfs_tree.h. * * To minimize the chance of collision with new persisted status flags, these * count backwards from the MSB. */ #define BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN … #define BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING … /* * Record a dirty extent, and info qgroup to update quota on it */ struct btrfs_qgroup_extent_record { … }; struct btrfs_qgroup_swapped_block { … }; /* * Qgroup reservation types: * * DATA: * space reserved for data * * META_PERTRANS: * Space reserved for metadata (per-transaction) * Due to the fact that qgroup data is only updated at transaction commit * time, reserved space for metadata must be kept until transaction * commits. * Any metadata reserved that are used in btrfs_start_transaction() should * be of this type. * * META_PREALLOC: * There are cases where metadata space is reserved before starting * transaction, and then btrfs_join_transaction() to get a trans handle. * Any metadata reserved for such usage should be of this type. * And after join_transaction() part (or all) of such reservation should * be converted into META_PERTRANS. */ enum btrfs_qgroup_rsv_type { … }; /* * Represents how many bytes we have reserved for this qgroup. * * Each type should have different reservation behavior. * E.g, data follows its io_tree flag modification, while * *currently* meta is just reserve-and-clear during transaction. * * TODO: Add new type for reservation which can survive transaction commit. * Current metadata reservation behavior is not suitable for such case. */ struct btrfs_qgroup_rsv { … }; /* * one struct for each qgroup, organized in fs_info->qgroup_tree. */ struct btrfs_qgroup { … }; /* Glue structure to represent the relations between qgroups. */ struct btrfs_qgroup_list { … }; struct btrfs_squota_delta { … }; static inline u64 btrfs_qgroup_subvolid(u64 qgroupid) { … } /* * For qgroup event trace points only */ enum { … }; enum btrfs_qgroup_mode { … }; enum btrfs_qgroup_mode btrfs_qgroup_mode(const struct btrfs_fs_info *fs_info); bool btrfs_qgroup_enabled(const struct btrfs_fs_info *fs_info); bool btrfs_qgroup_full_accounting(const struct btrfs_fs_info *fs_info); int btrfs_quota_enable(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_quota_ctl_args *quota_ctl_args); int btrfs_quota_disable(struct btrfs_fs_info *fs_info); int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info); void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info); int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, bool interruptible); int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst, struct btrfs_qgroup_list *prealloc); int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst); int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid); int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid); int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 subvolid); int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid, struct btrfs_qgroup_limit *limit); int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info); void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); int btrfs_qgroup_trace_extent_nolock( struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_qgroup_extent_record *record); int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans, struct btrfs_qgroup_extent_record *qrecord); int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes); int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, struct extent_buffer *eb); int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, struct extent_buffer *root_eb, u64 root_gen, int root_level); int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct ulist *old_roots, struct ulist *new_roots); int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans); int btrfs_run_qgroups(struct btrfs_trans_handle *trans); int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, struct btrfs_qgroup_inherit *inherit, size_t size); int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, u64 objectid, u64 inode_rootid, struct btrfs_qgroup_inherit *inherit); void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, u64 ref_root, u64 num_bytes, enum btrfs_qgroup_rsv_type type); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int btrfs_verify_qgroup_counts(const struct btrfs_fs_info *fs_info, u64 qgroupid, u64 rfer, u64 excl); #endif /* New io_tree based accurate qgroup reserve API */ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released); int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, u64 *freed); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce, bool noflush); /* Reserve metadata space for pertrans and prealloc type */ static inline int btrfs_qgroup_reserve_meta_pertrans(struct btrfs_root *root, int num_bytes, bool enforce) { … } static inline int btrfs_qgroup_reserve_meta_prealloc(struct btrfs_root *root, int num_bytes, bool enforce, bool noflush) { … } void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type); /* Free per-transaction meta reservation for error handling */ static inline void btrfs_qgroup_free_meta_pertrans(struct btrfs_root *root, int num_bytes) { … } /* Pre-allocated meta reservation can be freed at need */ static inline void btrfs_qgroup_free_meta_prealloc(struct btrfs_root *root, int num_bytes) { … } void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root); void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes); void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode); /* btrfs_qgroup_swapped_blocks related functions */ void btrfs_qgroup_init_swapped_blocks( struct btrfs_qgroup_swapped_blocks *swapped_blocks); void btrfs_qgroup_clean_swapped_blocks(struct btrfs_root *root); int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *subvol_root, struct btrfs_block_group *bg, struct extent_buffer *subvol_parent, int subvol_slot, struct extent_buffer *reloc_parent, int reloc_slot, u64 last_snapshot); int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb); void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans); bool btrfs_check_quota_leak(const struct btrfs_fs_info *fs_info); void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes); int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, const struct btrfs_squota_delta *delta); #endif
Codebase Browser
linux