// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <[email protected]> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY … struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { … } static fsnotify_connp_t *fsnotify_object_connp(void *obj, enum fsnotify_obj_type obj_type) { … } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { … } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { … } static void fsnotify_get_sb_watched_objects(struct super_block *sb) { … } static void fsnotify_put_sb_watched_objects(struct super_block *sb) { … } static void fsnotify_get_inode_ref(struct inode *inode) { … } static void fsnotify_put_inode_ref(struct inode *inode) { … } /* * Grab or drop watched objects reference depending on whether the connector * is attached and has any marks attached. */ static void fsnotify_update_sb_watchers(struct super_block *sb, struct fsnotify_mark_connector *conn) { … } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { … } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { … } static bool fsnotify_conn_watches_children( struct fsnotify_mark_connector *conn) { … } static void fsnotify_conn_set_children_dentry_flags( struct fsnotify_mark_connector *conn) { … } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { … } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { … } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { … } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { … } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { … } void fsnotify_put_mark(struct fsnotify_mark *mark) { … } EXPORT_SYMBOL_GPL(…); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { … } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { … } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { … } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { … } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { … } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { … } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { … } EXPORT_SYMBOL_GPL(…); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { … } static int fsnotify_attach_info_to_sb(struct super_block *sb) { … } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, void *obj, unsigned int obj_type) { … } /* * Get mark connector, make sure it is alive and return with its lock held. * This is for users that get connector pointer from inode or mount. Users that * hold reference to a mark on the list may directly lock connector->lock as * they are sure list cannot go away under them. */ static struct fsnotify_mark_connector *fsnotify_grab_connector( fsnotify_connp_t *connp) { … } /* * Add mark into proper place in given list of marks. These marks may be used * for the fsnotify backend to determine which event types should be delivered * to which group and for which inodes. These marks are ordered according to * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { … } /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { … } int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { … } EXPORT_SYMBOL_GPL(…); /* * Given a list of marks, find the mark associated with given group. If found * take a reference to that mark and return it, else return NULL. */ struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, struct fsnotify_group *group) { … } EXPORT_SYMBOL_GPL(…); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type) { … } /* Destroy all marks attached to an object via connector */ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { … } /* * Nothing fancy, just initialize lists and locks and counters. */ void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { … } EXPORT_SYMBOL_GPL(…); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before * actually freeing marks. */ static void fsnotify_mark_destroy_workfn(struct work_struct *work) { … } /* Wait for all marks queued for destruction to be actually destroyed */ void fsnotify_wait_marks_destroyed(void) { … } EXPORT_SYMBOL_GPL(…);