/* * Generic process-grouping system. * * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * * Notifications support * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2006 Silicon Graphics, Inc. * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* TODO: replace with more sophisticated array */ #include #include #include /* used in cgroup_attach_task */ #include #include #include /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify * cgroupfs_root of any cgroup hierarchy - subsys list, flags, * release_agent_path and so on. Modifying requires both cgroup_mutex and * cgroup_root_mutex. Readers can acquire either of the two. This is to * break the following locking order cycle. * * A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem * B. namespace_sem -> cgroup_mutex * * B happens only through cgroup_show_options() and using cgroup_root_mutex * breaks it. */ #ifdef CONFIG_PROVE_RCU DEFINE_MUTEX(cgroup_mutex); EXPORT_SYMBOL_GPL(cgroup_mutex); /* only for lockdep */ #else static DEFINE_MUTEX(cgroup_mutex); #endif static DEFINE_MUTEX(cgroup_root_mutex); /* * Generate an array of cgroup subsystem pointers. At boot time, this is * populated with the built in subsystems, and modular subsystems are * registered after that. The mutable section of this array is protected by * cgroup_mutex. */ #define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys, #define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option) static struct cgroup_subsys *cgroup_subsys[CGROUP_SUBSYS_COUNT] = { #include }; /* * The dummy hierarchy, reserved for the subsystems that are otherwise * unattached - it never has more than a single cgroup, and all tasks are * part of that cgroup. */ static struct cgroupfs_root cgroup_dummy_root; /* dummy_top is a shorthand for the dummy hierarchy's top cgroup */ static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup; /* * cgroupfs file entry, pointed to from leaf dentry->d_fsdata. */ struct cfent { struct list_head node; struct dentry *dentry; struct cftype *type; struct cgroup_subsys_state *css; /* file xattrs */ struct simple_xattrs xattrs; }; /* * cgroup_event represents events which userspace want to receive. */ struct cgroup_event { /* * css which the event belongs to. */ struct cgroup_subsys_state *css; /* * Control file which the event associated. */ struct cftype *cft; /* * eventfd to signal userspace about the event. */ struct eventfd_ctx *eventfd; /* * Each of these stored in a list by the cgroup. */ struct list_head list; /* * All fields below needed to unregister event when * userspace closes eventfd. */ poll_table pt; wait_queue_head_t *wqh; wait_queue_t wait; struct work_struct remove; }; /* The list of hierarchy roots */ static LIST_HEAD(cgroup_roots); static int cgroup_root_count; /* * Hierarchy ID allocation and mapping. It follows the same exclusion * rules as other root ops - both cgroup_mutex and cgroup_root_mutex for * writes, either for reads. */ static DEFINE_IDR(cgroup_hierarchy_idr); static struct cgroup_name root_cgroup_name = { .name = "/" }; /* * Assign a monotonically increasing serial number to cgroups. It * guarantees cgroups with bigger numbers are newer than those with smaller * numbers. Also, as cgroups are always appended to the parent's * ->children list, it guarantees that sibling cgroups are always sorted in * the ascending serial number order on the list. Protected by * cgroup_mutex. */ static u64 cgroup_serial_nr_next = 1; /* This flag indicates whether tasks in the fork and exit paths should * check for fork/exit handlers to call. This avoids us having to do * extra work in the fork/exit path if none of the subsystems need to * be called. */ static int need_forkexit_callback __read_mostly; static struct cftype cgroup_base_files[]; static void cgroup_destroy_css_killed(struct cgroup *cgrp); static int cgroup_destroy_locked(struct cgroup *cgrp); static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], bool is_add); /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns the dummy_css) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (ss) return rcu_dereference_check(cgrp->subsys[ss->subsys_id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->dummy_css; } /* convenient tests for these bits */ static inline bool cgroup_is_dead(const struct cgroup *cgrp) { return test_bit(CGRP_DEAD, &cgrp->flags); } /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested * @ancestor: possible ancestor of @cgrp * * Test whether @cgrp is a descendant of @ancestor. It also returns %true * if @cgrp == @ancestor. This function is safe to call as long as @cgrp * and @ancestor are accessible. */ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) { while (cgrp) { if (cgrp == ancestor) return true; cgrp = cgrp->parent; } return false; } EXPORT_SYMBOL_GPL(cgroup_is_descendant); static int cgroup_is_releasable(const struct cgroup *cgrp) { const int bits = (1 << CGRP_RELEASABLE) | (1 << CGRP_NOTIFY_ON_RELEASE); return (cgrp->flags & bits) == bits; } static int notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } /** * for_each_subsys - iterate all loaded cgroup subsystems * @ss: the iteration cursor * @i: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * * Should be called under cgroup_mutex. */ #define for_each_subsys(ss, i) \ for ((i) = 0; (i) < CGROUP_SUBSYS_COUNT; (i)++) \ if (({ lockdep_assert_held(&cgroup_mutex); \ !((ss) = cgroup_subsys[i]); })) { } \ else /** * for_each_builtin_subsys - iterate all built-in cgroup subsystems * @ss: the iteration cursor * @i: the index of @ss, CGROUP_BUILTIN_SUBSYS_COUNT after reaching the end * * Bulit-in subsystems are always present and iteration itself doesn't * require any synchronization. */ #define for_each_builtin_subsys(ss, i) \ for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[i]) || true); (i)++) /* iterate each subsystem attached to a hierarchy */ #define for_each_root_subsys(root, ss) \ list_for_each_entry((ss), &(root)->subsys_list, sibling) /* iterate across the active hierarchies */ #define for_each_active_root(root) \ list_for_each_entry((root), &cgroup_roots, root_list) static inline struct cgroup *__d_cgrp(struct dentry *dentry) { return dentry->d_fsdata; } static inline struct cfent *__d_cfe(struct dentry *dentry) { return dentry->d_fsdata; } static inline struct cftype *__d_cft(struct dentry *dentry) { return __d_cfe(dentry)->type; } /** * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive. * @cgrp: the cgroup to be checked for liveness * * On success, returns true; the mutex should be later unlocked. On * failure returns false with no lock held. */ static bool cgroup_lock_live_group(struct cgroup *cgrp) { mutex_lock(&cgroup_mutex); if (cgroup_is_dead(cgrp)) { mutex_unlock(&cgroup_mutex); return false; } return true; } /* the list of cgroups eligible for automatic release. Protected by * release_list_lock */ static LIST_HEAD(release_list); static DEFINE_RAW_SPINLOCK(release_list_lock); static void cgroup_release_agent(struct work_struct *work); static DECLARE_WORK(release_agent_work, cgroup_release_agent); static void check_for_release(struct cgroup *cgrp); /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. * This M:N relationship is represented by the following link structure * which exists for each association and allows traversing the associations * from both sides. */ struct cgrp_cset_link { /* the cgroup and css_set this link associates */ struct cgroup *cgrp; struct css_set *cset; /* list of cgrp_cset_links anchored at cgrp->cset_links */ struct list_head cset_link; /* list of cgrp_cset_links anchored at css_set->cgrp_links */ struct list_head cgrp_link; }; /* The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ static struct css_set init_css_set; static struct cgrp_cset_link init_cgrp_cset_link; /* * css_set_lock protects the list of css_set objects, and the chain of * tasks off each css_set. Nests outside task->alloc_lock due to * css_task_iter_start(). */ static DEFINE_RWLOCK(css_set_lock); static int css_set_count; /* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) { unsigned long key = 0UL; struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key; return key; } /* * We don't maintain the lists running through each css_set to its task * until after the first call to css_task_iter_start(). This reduces the * fork()/exit() overhead for people who have cgroups compiled into their * kernel but not actually in use. */ static int use_task_css_set_links __read_mostly; static void __put_css_set(struct css_set *cset, int taskexit) { struct cgrp_cset_link *link, *tmp_link; /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an * rwlock */ if (atomic_add_unless(&cset->refcount, -1, 1)) return; write_lock(&css_set_lock); if (!atomic_dec_and_test(&cset->refcount)) { write_unlock(&css_set_lock); return; } /* This css_set is dead. unlink it and release cgroup refcounts */ hash_del(&cset->hlist); css_set_count--; list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { struct cgroup *cgrp = link->cgrp; list_del(&link->cset_link); list_del(&link->cgrp_link); /* @cgrp can't go away while we're holding css_set_lock */ if (list_empty(&cgrp->cset_links) && notify_on_release(cgrp)) { if (taskexit) set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); } kfree(link); } write_unlock(&css_set_lock); kfree_rcu(cset, rcu_head); } /* * refcounted get/put for css_set objects */ static inline void get_css_set(struct css_set *cset) { atomic_inc(&cset->refcount); } static inline void put_css_set(struct css_set *cset) { __put_css_set(cset, 0); } static inline void put_css_set_taskexit(struct css_set *cset) { __put_css_set(cset, 1); } /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */ static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { struct list_head *l1, *l2; if (memcmp(template, cset->subsys, sizeof(cset->subsys))) { /* Not all subsystems matched */ return false; } /* * Compare cgroup pointers in order to distinguish between * different cgroups in heirarchies with no subsystems. We * could get by with just this check alone (and skip the * memcmp above) but on most setups the memcmp check will * avoid the need for this more expensive check on almost all * candidates. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2; l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root); /* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true; } /** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */ static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state *template[]) { struct cgroupfs_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i; /* * Build the set of subsystem state objects that we want to see in the * new css_set. while subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (root->subsys_mask & (1UL << i)) { /* Subsystem is in this hierarchy. So we want * the subsystem state from the new * cgroup */ template[i] = cgroup_css(cgrp, ss); } else { /* Subsystem is not in this hierarchy, so we * don't want to change the subsystem state */ template[i] = old_cset->subsys[i]; } } key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue; /* This css_set matches what we need */ return cset; } /* No existing cgroup group matched */ return NULL; } static void free_cgrp_cset_links(struct list_head *links_to_free) { struct cgrp_cset_link *link, *tmp_link; list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); } } /** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */ static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) { struct cgrp_cset_link *link; int i; INIT_LIST_HEAD(tmp_links); for (i = 0; i < count; i++) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0; } /** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp) { struct cgrp_cset_link *link; BUG_ON(list_empty(tmp_links)); link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp; list_move(&link->cset_link, &cgrp->cset_links); /* * Always add links to the tail of the list so that the list * is sorted by order of hierarchy creation */ list_add_tail(&link->cgrp_link, &cset->cgrp_links); } /** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */ static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp) { struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; unsigned long key; lockdep_assert_held(&cgroup_mutex); /* First see if we already have a cgroup group that matches * the desired set */ read_lock(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); read_unlock(&css_set_lock); if (cset) return cset; cset = kzalloc(sizeof(*cset), GFP_KERNEL); if (!cset) return NULL; /* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; } atomic_set(&cset->refcount, 1); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->tasks); INIT_HLIST_NODE(&cset->hlist); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); write_lock(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); } BUG_ON(!list_empty(&tmp_links)); css_set_count++; /* Add this cgroup group to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); write_unlock(&css_set_lock); return cset; } /* * Return the cgroup for "task" from the given hierarchy. Must be * called with cgroup_mutex held. */ static struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroupfs_root *root) { struct css_set *cset; struct cgroup *res = NULL; BUG_ON(!mutex_is_locked(&cgroup_mutex)); read_lock(&css_set_lock); /* * No need to lock the task - since we hold cgroup_mutex the * task can't change groups, so the only thing that can happen * is that it exits and its css is set back to init_css_set. */ cset = task_css_set(task); if (cset == &init_css_set) { res = &root->top_cgroup; } else { struct cgrp_cset_link *link; list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res = c; break; } } } read_unlock(&css_set_lock); BUG_ON(!res); return res; } /* * There is one global cgroup mutex. We also require taking * task_lock() when dereferencing a task's cgroup subsys pointers. * See "The task_lock() exception", at the end of this comment. * * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't * (usually) take cgroup_mutex. These are the two most performance * critical pieces of code here. The exception occurs on cgroup_exit(), * when a task in a notify_on_release cgroup exits. Then cgroup_mutex * is taken, and if the cgroup count is zero, a usermode call made * to the release agent with the name of the cgroup (path relative to * the root of cgroup file system) as the argument. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, top_cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that top_cgroup cannot be deleted. * * The task_lock() exception * * The need for this exception arises from the action of * cgroup_attach_task(), which overwrites one task's cgroup pointer with * another. It does so using cgroup_mutex, however there are * several performance critical places that need to reference * task->cgroup without the expense of grabbing a system global * mutex. Therefore except as noted below, when dereferencing or, as * in cgroup_attach_task(), modifying a task's cgroup pointer we use * task_lock(), which acts on a spinlock (task->alloc_lock) already in * the task_struct routinely used for such matters. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ /* * A couple of forward declarations required, due to cyclic reference loop: * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir -> * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations * -> cgroup_mkdir. */ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask); static const struct inode_operations cgroup_dir_inode_operations; static const struct file_operations proc_cgroupstats_operations; static struct backing_dev_info cgroup_backing_dev_info = { .name = "cgroup", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info; } return inode; } static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry) { struct cgroup_name *name; name = kmalloc(sizeof(*name) + dentry->d_name.len + 1, GFP_KERNEL); if (!name) return NULL; strcpy(name->name, dentry->d_name.name); return name; } static void cgroup_free_fn(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work); mutex_lock(&cgroup_mutex); cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); /* * We get a ref to the parent's dentry, and put the ref when * this cgroup is being freed, so it's guaranteed that the * parent won't be destroyed before its children. */ dput(cgrp->parent->dentry); /* * Drop the active superblock reference that we took when we * created the cgroup. This will free cgrp->root, if we are * holding the last reference to @sb. */ deactivate_super(cgrp->root->sb); /* * if we're getting rid of the cgroup, refcount should ensure * that there are no pidlists left. */ BUG_ON(!list_empty(&cgrp->pidlists)); simple_xattrs_free(&cgrp->xattrs); kfree(rcu_dereference_raw(cgrp->name)); kfree(cgrp); } static void cgroup_free_rcu(struct rcu_head *head) { struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head); INIT_WORK(&cgrp->destroy_work, cgroup_free_fn); schedule_work(&cgrp->destroy_work); } static void cgroup_diput(struct dentry *dentry, struct inode *inode) { /* is dentry a directory ? if so, kfree() associated cgroup */ if (S_ISDIR(inode->i_mode)) { struct cgroup *cgrp = dentry->d_fsdata; BUG_ON(!(cgroup_is_dead(cgrp))); call_rcu(&cgrp->rcu_head, cgroup_free_rcu); } else { struct cfent *cfe = __d_cfe(dentry); struct cgroup *cgrp = dentry->d_parent->d_fsdata; WARN_ONCE(!list_empty(&cfe->node) && cgrp != &cgrp->root->top_cgroup, "cfe still linked for %s\n", cfe->type->name); simple_xattrs_free(&cfe->xattrs); kfree(cfe); } iput(inode); } static int cgroup_delete(const struct dentry *d) { return 1; } static void remove_dir(struct dentry *d) { struct dentry *parent = dget(d->d_parent); d_delete(d); simple_rmdir(parent->d_inode, d); dput(parent); } static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { struct cfent *cfe; lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex); lockdep_assert_held(&cgroup_mutex); /* * If we're doing cleanup due to failure of cgroup_create(), * the corresponding @cfe may not exist. */ list_for_each_entry(cfe, &cgrp->files, node) { struct dentry *d = cfe->dentry; if (cft && cfe->type != cft) continue; dget(d); d_delete(d); simple_unlink(cgrp->dentry->d_inode, d); list_del_init(&cfe->node); dput(d); break; } } /** * cgroup_clear_dir - remove subsys files in a cgroup directory * @cgrp: target cgroup * @subsys_mask: mask of the subsystem ids whose files should be removed */ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) { struct cftype_set *set; if (!test_bit(i, &subsys_mask)) continue; list_for_each_entry(set, &ss->cftsets, node) cgroup_addrm_files(cgrp, set->cfts, false); } } /* * NOTE : the dentry must have been dget()'ed */ static void cgroup_d_remove_dir(struct dentry *dentry) { struct dentry *parent; parent = dentry->d_parent; spin_lock(&parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); list_del_init(&dentry->d_u.d_child); spin_unlock(&dentry->d_lock); spin_unlock(&parent->d_lock); remove_dir(dentry); } /* * Call with cgroup_mutex held. Drops reference counts on modules, including * any duplicate ones that parse_cgroupfs_options took. If this function * returns an error, no reference counts are touched. */ static int rebind_subsystems(struct cgroupfs_root *root, unsigned long added_mask, unsigned removed_mask) { struct cgroup *cgrp = &root->top_cgroup; struct cgroup_subsys *ss; unsigned long pinned = 0; int i, ret; BUG_ON(!mutex_is_locked(&cgroup_mutex)); BUG_ON(!mutex_is_locked(&cgroup_root_mutex)); /* Check that any added subsystems are currently free */ for_each_subsys(ss, i) { if (!(added_mask & (1 << i))) continue; /* is the subsystem mounted elsewhere? */ if (ss->root != &cgroup_dummy_root) { ret = -EBUSY; goto out_put; } /* pin the module */ if (!try_module_get(ss->module)) { ret = -ENOENT; goto out_put; } pinned |= 1 << i; } /* subsys could be missing if unloaded between parsing and here */ if (added_mask != pinned) { ret = -ENOENT; goto out_put; } ret = cgroup_populate_dir(cgrp, added_mask); if (ret) goto out_put; /* * Nothing can fail from this point on. Remove files for the * removed subsystems and rebind each subsystem. */ cgroup_clear_dir(cgrp, removed_mask); for_each_subsys(ss, i) { unsigned long bit = 1UL << i; if (bit & added_mask) { /* We're binding this subsystem to this hierarchy */ BUG_ON(cgroup_css(cgrp, ss)); BUG_ON(!cgroup_css(cgroup_dummy_top, ss)); BUG_ON(cgroup_css(cgroup_dummy_top, ss)->cgroup != cgroup_dummy_top); rcu_assign_pointer(cgrp->subsys[i], cgroup_css(cgroup_dummy_top, ss)); cgroup_css(cgrp, ss)->cgroup = cgrp; list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) ss->bind(cgroup_css(cgrp, ss)); /* refcount was already taken, and we're keeping it */ root->subsys_mask |= bit; } else if (bit & removed_mask) { /* We're removing this subsystem */ BUG_ON(cgroup_css(cgrp, ss) != cgroup_css(cgroup_dummy_top, ss)); BUG_ON(cgroup_css(cgrp, ss)->cgroup != cgrp); if (ss->bind) ss->bind(cgroup_css(cgroup_dummy_top, ss)); cgroup_css(cgroup_dummy_top, ss)->cgroup = cgroup_dummy_top; RCU_INIT_POINTER(cgrp->subsys[i], NULL); cgroup_subsys[i]->root = &cgroup_dummy_root; list_move(&ss->sibling, &cgroup_dummy_root.subsys_list); /* subsystem is now free - drop reference on module */ module_put(ss->module); root->subsys_mask &= ~bit; } } /* * Mark @root has finished binding subsystems. @root->subsys_mask * now matches the bound subsystems. */ root->flags |= CGRP_ROOT_SUBSYS_BOUND; return 0; out_put: for_each_subsys(ss, i) if (pinned & (1 << i)) module_put(ss->module); return ret; } static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry) { struct cgroupfs_root *root = dentry->d_sb->s_fs_info; struct cgroup_subsys *ss; mutex_lock(&cgroup_root_mutex); for_each_root_subsys(root, ss) seq_printf(seq, ",%s", ss->name); if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) seq_puts(seq, ",sane_behavior"); if (root->flags & CGRP_ROOT_NOPREFIX) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); if (strlen(root->release_agent_path)) seq_printf(seq, ",release_agent=%s", root->release_agent_path); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_printf(seq, ",name=%s", root->name); mutex_unlock(&cgroup_root_mutex); return 0; } struct cgroup_sb_opts { unsigned long subsys_mask; unsigned long flags; char *release_agent; bool cpuset_clone_children; char *name; /* User explicitly requested empty subsystem */ bool none; struct cgroupfs_root *new_root; }; /* * Convert a hierarchy specifier into a bitmask of subsystems and * flags. Call with cgroup_mutex held to protect the cgroup_subsys[] * array. This function takes refcounts on subsystems to be used, unless it * returns error, in which case no refcounts are taken. */ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { char *token, *o = data; bool all_ss = false, one_ss = false; unsigned long mask = (unsigned long)-1; struct cgroup_subsys *ss; int i; BUG_ON(!mutex_is_locked(&cgroup_mutex)); #ifdef CONFIG_CPUSETS mask = ~(1UL << cpuset_subsys_id); #endif memset(opts, 0, sizeof(*opts)); while ((token = strsep(&o, ",")) != NULL) { if (!*token) return -EINVAL; if (!strcmp(token, "none")) { /* Explicitly have no subsystems */ opts->none = true; continue; } if (!strcmp(token, "all")) { /* Mutually exclusive option 'all' + subsystem name */ if (one_ss) return -EINVAL; all_ss = true; continue; } if (!strcmp(token, "__DEVEL__sane_behavior")) { opts->flags |= CGRP_ROOT_SANE_BEHAVIOR; continue; } if (!strcmp(token, "noprefix")) { opts->flags |= CGRP_ROOT_NOPREFIX; continue; } if (!strcmp(token, "clone_children")) { opts->cpuset_clone_children = true; continue; } if (!strcmp(token, "xattr")) { opts->flags |= CGRP_ROOT_XATTR; continue; } if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) return -EINVAL; opts->release_agent = kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); if (!opts->release_agent) return -ENOMEM; continue; } if (!strncmp(token, "name=", 5)) { const char *name = token + 5; /* Can't specify an empty name */ if (!strlen(name)) return -EINVAL; /* Must match [\w.-]+ */ for (i = 0; i < strlen(name); i++) { char c = name[i]; if (isalnum(c)) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; return -EINVAL; } /* Specifying two names is forbidden */ if (opts->name) return -EINVAL; opts->name = kstrndup(name, MAX_CGROUP_ROOT_NAMELEN - 1, GFP_KERNEL); if (!opts->name) return -ENOMEM; continue; } for_each_subsys(ss, i) { if (strcmp(token, ss->name)) continue; if (ss->disabled) continue; /* Mutually exclusive option 'all' + subsystem name */ if (all_ss) return -EINVAL; set_bit(i, &opts->subsys_mask); one_ss = true; break; } if (i == CGROUP_SUBSYS_COUNT) return -ENOENT; } /* * If the 'all' option was specified select all the subsystems, * otherwise if 'none', 'name=' and a subsystem name options * were not specified, let's default to 'all' */ if (all_ss || (!one_ss && !opts->none && !opts->name)) for_each_subsys(ss, i) if (!ss->disabled) set_bit(i, &opts->subsys_mask); /* Consistency checks */ if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) { pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n"); if (opts->flags & CGRP_ROOT_NOPREFIX) { pr_err("cgroup: sane_behavior: noprefix is not allowed\n"); return -EINVAL; } if (opts->cpuset_clone_children) { pr_err("cgroup: sane_behavior: clone_children is not allowed\n"); return -EINVAL; } } /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask)) return -EINVAL; /* Can't specify "none" and some subsystems */ if (opts->subsys_mask && opts->none) return -EINVAL; /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ if (!opts->subsys_mask && !opts->name) return -EINVAL; return 0; } static int cgroup_remount(struct super_block *sb, int *flags, char *data) { int ret = 0; struct cgroupfs_root *root = sb->s_fs_info; struct cgroup *cgrp = &root->top_cgroup; struct cgroup_sb_opts opts; unsigned long added_mask, removed_mask; if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) { pr_err("cgroup: sane_behavior: remount is not allowed\n"); return -EINVAL; } mutex_lock(&cgrp->dentry->d_inode->i_mutex); mutex_lock(&cgroup_mutex); mutex_lock(&cgroup_root_mutex); /* See what subsystems are wanted */ ret = parse_cgroupfs_options(data, &opts); if (ret) goto out_unlock; if (opts.subsys_mask != root->subsys_mask || opts.release_agent) pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); added_mask = opts.subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~opts.subsys_mask; /* Don't allow flags or name to change at remount */ if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) || (opts.name && strcmp(opts.name, root->name))) { pr_err("cgroup: option or name mismatch, new: 0x%lx \"%s\", old: 0x%lx \"%s\"\n", opts.flags & CGRP_ROOT_OPTION_MASK, opts.name ?: "", root->flags & CGRP_ROOT_OPTION_MASK, root->name); ret = -EINVAL; goto out_unlock; } /* remounting is not allowed for populated hierarchies */ if (root->number_of_cgroups > 1) { ret = -EBUSY; goto out_unlock; } ret = rebind_subsystems(root, added_mask, removed_mask); if (ret) goto out_unlock; if (opts.release_agent) strcpy(root->release_agent_path, opts.release_agent); out_unlock: kfree(opts.release_agent); kfree(opts.name); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); mutex_unlock(&cgrp->dentry->d_inode->i_mutex); return ret; } static const struct super_operations cgroup_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = cgroup_show_options, .remount_fs = cgroup_remount, }; static void init_cgroup_housekeeping(struct cgroup *cgrp) { INIT_LIST_HEAD(&cgrp->sibling); INIT_LIST_HEAD(&cgrp->children); INIT_LIST_HEAD(&cgrp->files); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->dummy_css.cgroup = cgrp; INIT_LIST_HEAD(&cgrp->event_list); spin_lock_init(&cgrp->event_list_lock); simple_xattrs_init(&cgrp->xattrs); } static void init_cgroup_root(struct cgroupfs_root *root) { struct cgroup *cgrp = &root->top_cgroup; INIT_LIST_HEAD(&root->subsys_list); INIT_LIST_HEAD(&root->root_list); root->number_of_cgroups = 1; cgrp->root = root; RCU_INIT_POINTER(cgrp->name, &root_cgroup_name); init_cgroup_housekeeping(cgrp); idr_init(&root->cgroup_idr); } static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end) { int id; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&cgroup_root_mutex); id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, start, end, GFP_KERNEL); if (id < 0) return id; root->hierarchy_id = id; return 0; } static void cgroup_exit_root_id(struct cgroupfs_root *root) { lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&cgroup_root_mutex); if (root->hierarchy_id) { idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); root->hierarchy_id = 0; } } static int cgroup_test_super(struct super_block *sb, void *data) { struct cgroup_sb_opts *opts = data; struct cgroupfs_root *root = sb->s_fs_info; /* If we asked for a name then it must match */ if (opts->name && strcmp(opts->name, root->name)) return 0; /* * If we asked for subsystems (or explicitly for no * subsystems) then they must match */ if ((opts->subsys_mask || opts->none) && (opts->subsys_mask != root->subsys_mask)) return 0; return 1; } static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts) { struct cgroupfs_root *root; if (!opts->subsys_mask && !opts->none) return NULL; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return ERR_PTR(-ENOMEM); init_cgroup_root(root); /* * We need to set @root->subsys_mask now so that @root can be * matched by cgroup_test_super() before it finishes * initialization; otherwise, competing mounts with the same * options may try to bind the same subsystems instead of waiting * for the first one leading to unexpected mount errors. * SUBSYS_BOUND will be set once actual binding is complete. */ root->subsys_mask = opts->subsys_mask; root->flags = opts->flags; if (opts->release_agent) strcpy(root->release_agent_path, opts->release_agent); if (opts->name) strcpy(root->name, opts->name); if (opts->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags); return root; } static void cgroup_free_root(struct cgroupfs_root *root) { if (root) { /* hierarhcy ID shoulid already have been released */ WARN_ON_ONCE(root->hierarchy_id); idr_destroy(&root->cgroup_idr); kfree(root); } } static int cgroup_set_super(struct super_block *sb, void *data) { int ret; struct cgroup_sb_opts *opts = data; /* If we don't have a new root, we can't set up a new sb */ if (!opts->new_root) return -EINVAL; BUG_ON(!opts->subsys_mask && !opts->none); ret = set_anon_super(sb, NULL); if (ret) return ret; sb->s_fs_info = opts->new_root; opts->new_root->sb = sb; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = CGROUP_SUPER_MAGIC; sb->s_op = &cgroup_ops; return 0; } static int cgroup_get_rootdir(struct super_block *sb) { static const struct dentry_operations cgroup_dops = { .d_iput = cgroup_diput, .d_delete = cgroup_delete, }; struct inode *inode = cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb); if (!inode) return -ENOMEM; inode->i_fop = &simple_dir_operations; inode->i_op = &cgroup_dir_inode_operations; /* directories start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); sb->s_root = d_make_root(inode); if (!sb->s_root) return -ENOMEM; /* for everything else we want ->d_op set */ sb->s_d_op = &cgroup_dops; return 0; } static struct dentry *cgroup_mount(struct file_system_type *fs_type, int flags, const char *unused_dev_name, void *data) { struct cgroup_sb_opts opts; struct cgroupfs_root *root; int ret = 0; struct super_block *sb; struct cgroupfs_root *new_root; struct list_head tmp_links; struct inode *inode; const struct cred *cred; /* First find the desired set of subsystems */ mutex_lock(&cgroup_mutex); ret = parse_cgroupfs_options(data, &opts); mutex_unlock(&cgroup_mutex); if (ret) goto out_err; /* * Allocate a new cgroup root. We may not need it if we're * reusing an existing hierarchy. */ new_root = cgroup_root_from_opts(&opts); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); goto out_err; } opts.new_root = new_root; /* Locate an existing or new sb for this hierarchy */ sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts); if (IS_ERR(sb)) { ret = PTR_ERR(sb); cgroup_free_root(opts.new_root); goto out_err; } root = sb->s_fs_info; BUG_ON(!root); if (root == opts.new_root) { /* We used the new root structure, so this is a new hierarchy */ struct cgroup *root_cgrp = &root->top_cgroup; struct cgroupfs_root *existing_root; int i; struct css_set *cset; BUG_ON(sb->s_root != NULL); ret = cgroup_get_rootdir(sb); if (ret) goto drop_new_super; inode = sb->s_root->d_inode; mutex_lock(&inode->i_mutex); mutex_lock(&cgroup_mutex); mutex_lock(&cgroup_root_mutex); root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL); if (root_cgrp->id < 0) goto unlock_drop; /* Check for name clashes with existing mounts */ ret = -EBUSY; if (strlen(root->name)) for_each_active_root(existing_root) if (!strcmp(existing_root->name, root->name)) goto unlock_drop; /* * We're accessing css_set_count without locking * css_set_lock here, but that's OK - it can only be * increased by someone holding cgroup_lock, and * that's us. The worst that can happen is that we * have some link structures left over */ ret = allocate_cgrp_cset_links(css_set_count, &tmp_links); if (ret) goto unlock_drop; /* ID 0 is reserved for dummy root, 1 for unified hierarchy */ ret = cgroup_init_root_id(root, 2, 0); if (ret) goto unlock_drop; sb->s_root->d_fsdata = root_cgrp; root_cgrp->dentry = sb->s_root; /* * We're inside get_sb() and will call lookup_one_len() to * create the root files, which doesn't work if SELinux is * in use. The following cred dancing somehow works around * it. See 2ce9738ba ("cgroupfs: use init_cred when * populating new cgroupfs mount") for more details. */ cred = override_creds(&init_cred); ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true); if (ret) goto rm_base_files; ret = rebind_subsystems(root, root->subsys_mask, 0); if (ret) goto rm_base_files; revert_creds(cred); /* * There must be no failure case after here, since rebinding * takes care of subsystems' refcounts, which are explicitly * dropped in the failure exit path. */ list_add(&root->root_list, &cgroup_roots); cgroup_root_count++; /* Link the top cgroup in this hierarchy into all * the css_set objects */ write_lock(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) link_css_set(&tmp_links, cset, root_cgrp); write_unlock(&css_set_lock); free_cgrp_cset_links(&tmp_links); BUG_ON(!list_empty(&root_cgrp->children)); BUG_ON(root->number_of_cgroups != 1); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); } else { /* * We re-used an existing hierarchy - the new root (if * any) is not needed */ cgroup_free_root(opts.new_root); if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) { if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) { pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n"); ret = -EINVAL; goto drop_new_super; } else { pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n"); } } } kfree(opts.release_agent); kfree(opts.name); return dget(sb->s_root); rm_base_files: free_cgrp_cset_links(&tmp_links); cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false); revert_creds(cred); unlock_drop: cgroup_exit_root_id(root); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); drop_new_super: deactivate_locked_super(sb); out_err: kfree(opts.release_agent); kfree(opts.name); return ERR_PTR(ret); } static void cgroup_kill_sb(struct super_block *sb) { struct cgroupfs_root *root = sb->s_fs_info; struct cgroup *cgrp = &root->top_cgroup; struct cgrp_cset_link *link, *tmp_link; int ret; BUG_ON(!root); BUG_ON(root->number_of_cgroups != 1); BUG_ON(!list_empty(&cgrp->children)); mutex_lock(&cgrp->dentry->d_inode->i_mutex); mutex_lock(&cgroup_mutex); mutex_lock(&cgroup_root_mutex); /* Rebind all subsystems back to the default hierarchy */ if (root->flags & CGRP_ROOT_SUBSYS_BOUND) { ret = rebind_subsystems(root, 0, root->subsys_mask); /* Shouldn't be able to fail ... */ BUG_ON(ret); } /* * Release all the links from cset_links to this hierarchy's * root cgroup */ write_lock(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); } write_unlock(&css_set_lock); if (!list_empty(&root->root_list)) { list_del(&root->root_list); cgroup_root_count--; } cgroup_exit_root_id(root); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); mutex_unlock(&cgrp->dentry->d_inode->i_mutex); simple_xattrs_free(&cgrp->xattrs); kill_litter_super(sb); cgroup_free_root(root); } static struct file_system_type cgroup_fs_type = { .name = "cgroup", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, }; static struct kobject *cgroup_kobj; /** * cgroup_path - generate the path of a cgroup * @cgrp: the cgroup in question * @buf: the buffer to write the path into * @buflen: the length of the buffer * * Writes path of cgroup into buf. Returns 0 on success, -errno on error. * * We can't generate cgroup path using dentry->d_name, as accessing * dentry->name must be protected by irq-unsafe dentry->d_lock or parent * inode's i_mutex, while on the other hand cgroup_path() can be called * with some irq-safe spinlocks held. */ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) { int ret = -ENAMETOOLONG; char *start; if (!cgrp->parent) { if (strlcpy(buf, "/", buflen) >= buflen) return -ENAMETOOLONG; return 0; } start = buf + buflen - 1; *start = '\0'; rcu_read_lock(); do { const char *name = cgroup_name(cgrp); int len; len = strlen(name); if ((start -= len) < buf) goto out; memcpy(start, name, len); if (--start < buf) goto out; *start = '/'; cgrp = cgrp->parent; } while (cgrp->parent); ret = 0; memmove(buf, start, buf + buflen - start); out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(cgroup_path); /** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task * @buf: the buffer to write the path into * @buflen: the length of the buffer * * Determine @task's cgroup on the first (the one with the lowest non-zero * hierarchy_id) cgroup hierarchy and copy its path into @buf. This * function grabs cgroup_mutex and shouldn't be used inside locks used by * cgroup controller callbacks. * * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short. */ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { struct cgroupfs_root *root; struct cgroup *cgrp; int hierarchy_id = 1, ret = 0; if (buflen < 2) return -ENAMETOOLONG; mutex_lock(&cgroup_mutex); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); if (root) { cgrp = task_cgroup_from_root(task, root); ret = cgroup_path(cgrp, buf, buflen); } else { /* if no hierarchy exists, everyone is in "/" */ memcpy(buf, "/", 2); } mutex_unlock(&cgroup_mutex); return ret; } EXPORT_SYMBOL_GPL(task_cgroup_path); /* * Control Group taskset */ struct task_and_cgroup { struct task_struct *task; struct cgroup *cgrp; struct css_set *cset; }; struct cgroup_taskset { struct task_and_cgroup single; struct flex_array *tc_array; int tc_array_len; int idx; struct cgroup *cur_cgrp; }; /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * * @tset iteration is initialized and the first task is returned. */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) { if (tset->tc_array) { tset->idx = 0; return cgroup_taskset_next(tset); } else { tset->cur_cgrp = tset->single.cgrp; return tset->single.task; } } EXPORT_SYMBOL_GPL(cgroup_taskset_first); /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) { struct task_and_cgroup *tc; if (!tset->tc_array || tset->idx >= tset->tc_array_len) return NULL; tc = flex_array_get(tset->tc_array, tset->idx++); tset->cur_cgrp = tc->cgrp; return tc->task; } EXPORT_SYMBOL_GPL(cgroup_taskset_next); /** * cgroup_taskset_cur_css - return the matching css for the current task * @tset: taskset of interest * @subsys_id: the ID of the target subsystem * * Return the css for the current (last returned) task of @tset for * subsystem specified by @subsys_id. This function must be preceded by * either cgroup_taskset_first() or cgroup_taskset_next(). */ struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset, int subsys_id) { return cgroup_css(tset->cur_cgrp, cgroup_subsys[subsys_id]); } EXPORT_SYMBOL_GPL(cgroup_taskset_cur_css); /** * cgroup_taskset_size - return the number of tasks in taskset * @tset: taskset of interest */ int cgroup_taskset_size(struct cgroup_taskset *tset) { return tset->tc_array ? tset->tc_array_len : 1; } EXPORT_SYMBOL_GPL(cgroup_taskset_size); /* * cgroup_task_migrate - move a task from one cgroup to another. * * Must be called with cgroup_mutex and threadgroup locked. */ static void cgroup_task_migrate(struct cgroup *old_cgrp, struct task_struct *tsk, struct css_set *new_cset) { struct css_set *old_cset; /* * We are synchronized through threadgroup_lock() against PF_EXITING * setting such that we can't race against cgroup_exit() changing the * css_set to init_css_set and dropping the old one. */ WARN_ON_ONCE(tsk->flags & PF_EXITING); old_cset = task_css_set(tsk); task_lock(tsk); rcu_assign_pointer(tsk->cgroups, new_cset); task_unlock(tsk); /* Update the css_set linked lists if we're using them */ write_lock(&css_set_lock); if (!list_empty(&tsk->cg_list)) list_move(&tsk->cg_list, &new_cset->tasks); write_unlock(&css_set_lock); /* * We just gained a reference on old_cset by taking it from the * task. As trading it for new_cset is protected by cgroup_mutex, * we're safe to drop it here; it will be freed under RCU. */ set_bit(CGRP_RELEASABLE, &old_cgrp->flags); put_css_set(old_cset); } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @cgrp: the cgroup to attach to * @tsk: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and the group_rwsem of the leader. Will take * task_lock of @tsk or each thread in the threadgroup individually in turn. */ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, bool threadgroup) { int retval, i, group_size; struct cgroup_subsys *ss, *failed_ss = NULL; struct cgroupfs_root *root = cgrp->root; /* threadgroup list cursor and array */ struct task_struct *leader = tsk; struct task_and_cgroup *tc; struct flex_array *group; struct cgroup_taskset tset = { }; /* * step 0: in order to do expensive, possibly blocking operations for * every thread, we cannot iterate the thread group list, since it needs * rcu or tasklist locked. instead, build an array of all threads in the * group - group_rwsem prevents new threads from appearing, and if * threads exit, this will just be an over-estimate. */ if (threadgroup) group_size = get_nr_threads(tsk); else group_size = 1; /* flex_array supports very large thread-groups better than kmalloc. */ group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL); if (!group) return -ENOMEM; /* pre-allocate to guarantee space while iterating in rcu read-side. */ retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL); if (retval) goto out_free_group_list; i = 0; /* * Prevent freeing of tasks while we take a snapshot. Tasks that are * already PF_EXITING could be freed from underneath us unless we * take an rcu_read_lock. */ rcu_read_lock(); do { struct task_and_cgroup ent; /* @tsk either already exited or can't exit until the end */ if (tsk->flags & PF_EXITING) goto next; /* as per above, nr_threads may decrease, but not increase. */ BUG_ON(i >= group_size); ent.task = tsk; ent.cgrp = task_cgroup_from_root(tsk, root); /* nothing to do if this task is already in the cgroup */ if (ent.cgrp == cgrp) goto next; /* * saying GFP_ATOMIC has no effect here because we did prealloc * earlier, but it's good form to communicate our expectations. */ retval = flex_array_put(group, i, &ent, GFP_ATOMIC); BUG_ON(retval != 0); i++; next: if (!threadgroup) break; } while_each_thread(leader, tsk); rcu_read_unlock(); /* remember the number of threads in the array for later. */ group_size = i; tset.tc_array = group; tset.tc_array_len = group_size; /* methods shouldn't be called if no task is actually migrating */ retval = 0; if (!group_size) goto out_free_group_list; /* * step 1: check that we can legitimately attach to the cgroup. */ for_each_root_subsys(root, ss) { struct cgroup_subsys_state *css = cgroup_css(cgrp, ss); if (ss->can_attach) { retval = ss->can_attach(css, &tset); if (retval) { failed_ss = ss; goto out_cancel_attach; } } } /* * step 2: make sure css_sets exist for all threads to be migrated. * we use find_css_set, which allocates a new one if necessary. */ for (i = 0; i < group_size; i++) { struct css_set *old_cset; tc = flex_array_get(group, i); old_cset = task_css_set(tc->task); tc->cset = find_css_set(old_cset, cgrp); if (!tc->cset) { retval = -ENOMEM; goto out_put_css_set_refs; } } /* * step 3: now that we're guaranteed success wrt the css_sets, * proceed to move all tasks to the new cgroup. There are no * failure cases after here, so this is the commit point. */ for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); cgroup_task_migrate(tc->cgrp, tc->task, tc->cset); } /* nothing is sensitive to fork() after this point. */ /* * step 4: do subsystem attach callbacks. */ for_each_root_subsys(root, ss) { struct cgroup_subsys_state *css = cgroup_css(cgrp, ss); if (ss->attach) ss->attach(css, &tset); } /* * step 5: success! and cleanup */ retval = 0; out_put_css_set_refs: if (retval) { for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); if (!tc->cset) break; put_css_set(tc->cset); } } out_cancel_attach: if (retval) { for_each_root_subsys(root, ss) { struct cgroup_subsys_state *css = cgroup_css(cgrp, ss); if (ss == failed_ss) break; if (ss->cancel_attach) ss->cancel_attach(css, &tset); } } out_free_group_list: flex_array_free(group); return retval; } /* * Find the task_struct of the task to attach by vpid and pass it along to the * function to attach either it or all tasks in its threadgroup. Will lock * cgroup_mutex and threadgroup; may take task_lock of task. */ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) { struct task_struct *tsk; const struct cred *cred = current_cred(), *tcred; int ret; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; retry_find_task: rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { rcu_read_unlock(); ret= -ESRCH; goto out_unlock_cgroup; } /* * even if we're attaching all tasks in the thread group, we * only need to check permissions on one of them. */ tcred = __task_cred(tsk); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->euid, tcred->suid)) { rcu_read_unlock(); ret = -EACCES; goto out_unlock_cgroup; } } else tsk = current; if (threadgroup) tsk = tsk->group_leader; /* * Workqueue threads may acquire PF_NO_SETAFFINITY and become * trapped in a cpuset, or RT worker may be born in a cgroup * with no rt_runtime allocated. Just say no. */ if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; rcu_read_unlock(); goto out_unlock_cgroup; } get_task_struct(tsk); rcu_read_unlock(); threadgroup_lock(tsk); if (threadgroup) { if (!thread_group_leader(tsk)) { /* * a race with de_thread from another thread's exec() * may strip us of our leadership, if this happens, * there is no choice but to throw this task away and * try again; this is * "double-double-toil-and-trouble-check locking". */ threadgroup_unlock(tsk); put_task_struct(tsk); goto retry_find_task; } } ret = cgroup_attach_task(cgrp, tsk, threadgroup); threadgroup_unlock(tsk); put_task_struct(tsk); out_unlock_cgroup: mutex_unlock(&cgroup_mutex); return ret; } /** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached */ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroupfs_root *root; int retval = 0; mutex_lock(&cgroup_mutex); for_each_active_root(root) { struct cgroup *from_cgrp = task_cgroup_from_root(from, root); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } mutex_unlock(&cgroup_mutex); return retval; } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); static int cgroup_tasks_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 pid) { return attach_task_by_pid(css->cgroup, pid, false); } static int cgroup_procs_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 tgid) { return attach_task_by_pid(css->cgroup, tgid, true); } static int cgroup_release_agent_write(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer) { BUILD_BUG_ON(sizeof(css->cgroup->root->release_agent_path) < PATH_MAX); if (strlen(buffer) >= PATH_MAX) return -EINVAL; if (!cgroup_lock_live_group(css->cgroup)) return -ENODEV; mutex_lock(&cgroup_root_mutex); strcpy(css->cgroup->root->release_agent_path, buffer); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); return 0; } static int cgroup_release_agent_show(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *seq) { struct cgroup *cgrp = css->cgroup; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; seq_puts(seq, cgrp->root->release_agent_path); seq_putc(seq, '\n'); mutex_unlock(&cgroup_mutex); return 0; } static int cgroup_sane_behavior_show(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *seq) { seq_printf(seq, "%d\n", cgroup_sane_behavior(css->cgroup)); return 0; } /* A buffer size big enough for numbers or short strings */ #define CGROUP_LOCAL_BUFFER_SIZE 64 static ssize_t cgroup_write_X64(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, const char __user *userbuf, size_t nbytes, loff_t *unused_ppos) { char buffer[CGROUP_LOCAL_BUFFER_SIZE]; int retval = 0; char *end; if (!nbytes) return -EINVAL; if (nbytes >= sizeof(buffer)) return -E2BIG; if (copy_from_user(buffer, userbuf, nbytes)) return -EFAULT; buffer[nbytes] = 0; /* nul-terminate */ if (cft->write_u64) { u64 val = simple_strtoull(strstrip(buffer), &end, 0); if (*end) return -EINVAL; retval = cft->write_u64(css, cft, val); } else { s64 val = simple_strtoll(strstrip(buffer), &end, 0); if (*end) return -EINVAL; retval = cft->write_s64(css, cft, val); } if (!retval) retval = nbytes; return retval; } static ssize_t cgroup_write_string(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, const char __user *userbuf, size_t nbytes, loff_t *unused_ppos) { char local_buffer[CGROUP_LOCAL_BUFFER_SIZE]; int retval = 0; size_t max_bytes = cft->max_write_len; char *buffer = local_buffer; if (!max_bytes) max_bytes = sizeof(local_buffer) - 1; if (nbytes >= max_bytes) return -E2BIG; /* Allocate a dynamic buffer if we need one */ if (nbytes >= sizeof(local_buffer)) { buffer = kmalloc(nbytes + 1, GFP_KERNEL); if (buffer == NULL) return -ENOMEM; } if (nbytes && copy_from_user(buffer, userbuf, nbytes)) { retval = -EFAULT; goto out; } buffer[nbytes] = 0; /* nul-terminate */ retval = cft->write_string(css, cft, strstrip(buffer)); if (!retval) retval = nbytes; out: if (buffer != local_buffer) kfree(buffer); return retval; } static ssize_t cgroup_file_write(struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos) { struct cfent *cfe = __d_cfe(file->f_dentry); struct cftype *cft = __d_cft(file->f_dentry); struct cgroup_subsys_state *css = cfe->css; if (cft->write) return cft->write(css, cft, file, buf, nbytes, ppos); if (cft->write_u64 || cft->write_s64) return cgroup_write_X64(css, cft, file, buf, nbytes, ppos); if (cft->write_string) return cgroup_write_string(css, cft, file, buf, nbytes, ppos); if (cft->trigger) { int ret = cft->trigger(css, (unsigned int)cft->private); return ret ? ret : nbytes; } return -EINVAL; } static ssize_t cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { char tmp[CGROUP_LOCAL_BUFFER_SIZE]; u64 val = cft->read_u64(css, cft); int len = sprintf(tmp, "%llu\n", (unsigned long long) val); return simple_read_from_buffer(buf, nbytes, ppos, tmp, len); } static ssize_t cgroup_read_s64(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, char __user *buf, size_t nbytes