/* * 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. */ #define pr_fmt(fmt) … #include "cgroup-internal.h" #include <linux/bpf-cgroup.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/init_task.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/mutex.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/hashtable.h> #include <linux/idr.h> #include <linux/kthread.h> #include <linux/atomic.h> #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> #include <linux/sched/deadline.h> #include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS #include <trace/events/cgroup.h> #define CGROUP_FILE_NAME_MAX … /* let's not notify more than 100 times per second */ #define CGROUP_FILE_NOTIFY_MIN_INTV … /* * To avoid confusing the compiler (and generating warnings) with code * that attempts to access what would be a 0-element array (i.e. sized * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this * constant expression can be added. */ #define CGROUP_HAS_SUBSYS_CONFIG … /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * css_set_lock protects task->cgroups pointer, the list of css_set * objects, and the chain of tasks off each css_set. * * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */ DEFINE_MUTEX(…) …; DEFINE_SPINLOCK(…); #ifdef CONFIG_PROVE_RCU EXPORT_SYMBOL_GPL(…); EXPORT_SYMBOL_GPL(…); #endif DEFINE_SPINLOCK(…); char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; static bool cgroup_debug __read_mostly; /* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. */ static DEFINE_SPINLOCK(cgroup_idr_lock); /* * Protects cgroup_file->kn for !self csses. It synchronizes notifications * against file removal/re-creation across css hiding. */ static DEFINE_SPINLOCK(cgroup_file_kn_lock); DEFINE_PERCPU_RWSEM(…); #define cgroup_assert_mutex_or_rcu_locked() … /* * cgroup destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. */ static struct workqueue_struct *cgroup_destroy_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS … struct cgroup_subsys *cgroup_subsys[] = …; #undef SUBSYS /* array of cgroup subsystem names */ #define SUBSYS … static const char *cgroup_subsys_name[] = …; #undef SUBSYS /* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */ #define SUBSYS … #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS … static struct static_key_true *cgroup_subsys_enabled_key[] = …; #undef SUBSYS #define SUBSYS … static struct static_key_true *cgroup_subsys_on_dfl_key[] = …; #undef SUBSYS static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); /* the default hierarchy */ struct cgroup_root cgrp_dfl_root = …; EXPORT_SYMBOL_GPL(…); /* * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */ static bool cgrp_dfl_visible; /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ static u16 cgrp_dfl_implicit_ss_mask; /* some controllers can be threaded on the default hierarchy */ static u16 cgrp_dfl_threaded_ss_mask; /* The list of hierarchy roots */ LIST_HEAD(…); static int cgroup_root_count; /* hierarchy ID allocation and mapping, protected by cgroup_mutex */ static DEFINE_IDR(cgroup_hierarchy_idr); /* * Assign a monotonically increasing serial number to csses. It guarantees * cgroups with bigger numbers are newer than those with smaller numbers. * Also, as csses are always appended to the parent's ->children list, it * guarantees that sibling csses are always sorted in the ascending serial * number order on the list. Protected by cgroup_mutex. */ static u64 css_serial_nr_next = …; /* * These bitmasks identify subsystems with specific features to avoid * having to do iterative checks repeatedly. */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly; static bool have_favordynmods __ro_after_init = … IS_ENABLED(…); /* cgroup namespace for init task */ struct cgroup_namespace init_cgroup_ns = …; static struct file_system_type cgroup2_fs_type; static struct cftype cgroup_base_files[]; static struct cftype cgroup_psi_files[]; /* cgroup optional features */ enum cgroup_opt_features { … }; static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = …; static u16 cgroup_feature_disable_mask __read_mostly; static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); #ifdef CONFIG_DEBUG_CGROUP_REF #define CGROUP_REF_FN_ATTRS … #define CGROUP_REF_EXPORT(fn) … #include <linux/cgroup_refcnt.h> #endif /** * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID * @ssid: subsys ID of interest * * cgroup_subsys_enabled() can only be used with literal subsys names which * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */ bool cgroup_ssid_enabled(int ssid) { … } /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" * and "name" are disallowed. * * - When mounting an existing superblock, mount options should match. * * - rename(2) is disallowed. * * - "tasks" is removed. Everything should be at process granularity. Use * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. * * - "cgroup.clone_children" is removed. * * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup * and its descendants contain no task; otherwise, 1. The file also * generates kernfs notification which can be monitored through poll and * [di]notify when the value of the file changes. * * - cpuset: tasks will be kept in empty cpusets when hotplug happens and * take masks of ancestors with non-empty cpus/mems, instead of being * moved to an ancestor. * * - cpuset: a task can be moved into an empty cpuset, and again it takes * masks of ancestors. * * - blkcg: blk-throttle becomes properly hierarchical. */ bool cgroup_on_dfl(const struct cgroup *cgrp) { … } /* IDR wrappers which synchronize using cgroup_idr_lock */ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) { … } static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) { … } static void cgroup_idr_remove(struct idr *idr, int id) { … } static bool cgroup_has_tasks(struct cgroup *cgrp) { … } static bool cgroup_is_threaded(struct cgroup *cgrp) { … } /* can @cgrp host both domain and threaded children? */ static bool cgroup_is_mixable(struct cgroup *cgrp) { … } /* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { … } /* is @cgrp root of a threaded subtree? */ static bool cgroup_is_thread_root(struct cgroup *cgrp) { … } /* a domain which isn't connected to the root w/o brekage can't be used */ static bool cgroup_is_valid_domain(struct cgroup *cgrp) { … } /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { … } /* subsystems enabled on a cgroup */ static u16 cgroup_ss_mask(struct cgroup *cgrp) { … } /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * 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) { … } /** * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, struct cgroup_subsys *ss) { … } /** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { … } /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { … } EXPORT_SYMBOL_GPL(…); static void cgroup_get_live(struct cgroup *cgrp) { … } /** * __cgroup_task_count - count the number of tasks in a cgroup. The caller * is responsible for taking the css_set_lock. * @cgrp: the cgroup in question */ int __cgroup_task_count(const struct cgroup *cgrp) { … } /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question */ int cgroup_task_count(const struct cgroup *cgrp) { … } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { … } EXPORT_SYMBOL_GPL(…); /** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_mutex. */ #define for_each_css(css, ssid, cgrp) … /** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */ #define do_each_subsys_mask(ss, ssid, ss_mask) … #define while_each_subsys_mask() … /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) … /* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) … /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) … /* * 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. */ struct css_set init_css_set = …; static int css_set_count = …; /* 1 for init_css_set */ static bool css_set_threaded(struct css_set *cset) { … } /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set * * css_set_populated() should be the same as !!cset->nr_tasks at steady * state. However, css_set_populated() can be called while a task is being * added to or removed from the linked list before the nr_tasks is * properly updated. Hence, we can't just look at ->nr_tasks here. */ static bool css_set_populated(struct css_set *cset) { … } /** * cgroup_update_populated - update the populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first * task or losing the last. Update @cgrp->nr_populated_* accordingly. The * count is propagated towards root so that a given cgroup's * nr_populated_children is zero iff none of its descendants contain any * tasks. * * @cgrp's interface file "cgroup.populated" is zero if both * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and * 1 otherwise. When the sum changes from or to zero, userland is notified * that the content of the interface file has changed. This can be used to * detect when @cgrp and its descendants become populated or empty. */ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { … } /** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * populated counters of all associated cgroups accordingly. */ static void css_set_update_populated(struct css_set *cset, bool populated) { … } /* * @task is leaving, advance task iterators which are pointing to it so * that they can resume at the next position. Advancing an iterator might * remove it from the list, use safe walk. See css_task_iter_skip() for * details. */ static void css_set_skip_task_iters(struct css_set *cset, struct task_struct *task) { … } /** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */ static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks) { … } /* * 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 … static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); static unsigned long css_set_hash(struct cgroup_subsys_state **css) { … } void put_css_set_locked(struct css_set *cset) { … } /** * 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[]) { … } /** * 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) { … } static void free_cgrp_cset_links(struct list_head *links_to_free) { … } /** * 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) { … } /** * 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) { … } /** * 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_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { … } void cgroup_favor_dynmods(struct cgroup_root *root, bool favor) { … } static int cgroup_init_root_id(struct cgroup_root *root) { … } static void cgroup_exit_root_id(struct cgroup_root *root) { … } void cgroup_free_root(struct cgroup_root *root) { … } static void cgroup_destroy_root(struct cgroup_root *root) { … } /* * Returned cgroup is without refcount but it's valid as long as cset pins it. */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { … } /* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */ static struct cgroup * current_cgns_cgroup_from_root(struct cgroup_root *root) { … } /* * Look up cgroup associated with current task's cgroup namespace on the default * hierarchy. * * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu * pointers. * - css_set_lock is not needed because we just read cset->dfl_cgrp. * - As a bonus returned cgrp is pinned with the current because it cannot * switch cgroup_ns asynchronously. */ static struct cgroup *current_cgns_cgroup_dfl(void) { … } /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { … } /* * Return the cgroup for "task" from the given hierarchy. Must be * called with css_set_lock held to prevent task's groups from being modified. * Must be called with either cgroup_mutex or rcu read lock to prevent the * cgroup root from being destroyed. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) { … } /* * 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. * * 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, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) { … } /** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */ static umode_t cgroup_file_mode(const struct cftype *cft) { … } /** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { … } /** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */ void cgroup_kn_unlock(struct kernfs_node *kn) { … } /** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { … } static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { … } /** * css_clear_dir - remove subsys files in a cgroup directory * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { … } /** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */ static int css_populate_dir(struct cgroup_subsys_state *css) { … } int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { … } int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root) { … } enum cgroup2_param { … }; static const struct fs_parameter_spec cgroup2_fs_parameters[] = …; static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) { … } static void apply_cgroup_root_flags(unsigned int root_flags) { … } static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { … } static int cgroup_reconfigure(struct fs_context *fc) { … } static void init_cgroup_housekeeping(struct cgroup *cgrp) { … } void init_cgroup_root(struct cgroup_fs_context *ctx) { … } int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { … } int cgroup_do_get_tree(struct fs_context *fc) { … } /* * Destroy a cgroup filesystem context. */ static void cgroup_fs_context_free(struct fs_context *fc) { … } static int cgroup_get_tree(struct fs_context *fc) { … } static const struct fs_context_operations cgroup_fs_context_ops = …; static const struct fs_context_operations cgroup1_fs_context_ops = …; /* * Initialise the cgroup filesystem creation/reconfiguration context. Notably, * we select the namespace we're going to use. */ static int cgroup_init_fs_context(struct fs_context *fc) { … } static void cgroup_kill_sb(struct super_block *sb) { … } struct file_system_type cgroup_fs_type = …; static struct file_system_type cgroup2_fs_type = …; #ifdef CONFIG_CPUSETS static const struct fs_context_operations cpuset_fs_context_ops = …; /* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ static int cpuset_init_fs_context(struct fs_context *fc) { … } static struct file_system_type cpuset_fs_type = …; #endif int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { … } int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { … } EXPORT_SYMBOL_GPL(…); /** * cgroup_attach_lock - Lock for ->attach() * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem * * cgroup migration sometimes needs to stabilize threadgroups against forks and * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() * implementations (e.g. cpuset), also need to disable CPU hotplug. * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can * lead to deadlocks. * * Bringing up a CPU may involve creating and destroying tasks which requires * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while * write-locking threadgroup_rwsem, the locking order is reversed and we end up * waiting for an on-going CPU hotplug operation which in turn is waiting for * the threadgroup_rwsem to be released to create new tasks. For more details: * * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu * * Resolve the situation by always acquiring cpus_read_lock() before optionally * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. */ void cgroup_attach_lock(bool lock_threadgroup) { … } /** * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem */ void cgroup_attach_unlock(bool lock_threadgroup) { … } /** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context * * Add @task, which is a migration target, to @mgctx->tset. This function * becomes noop if @task doesn't need to be migrated. @task's css_set * should have been added as a migration source and @task->cg_list will be * moved from the css_set's tasks list to mg_tasks one. */ static void cgroup_migrate_add_task(struct task_struct *task, struct cgroup_mgctx *mgctx) { … } /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { … } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * 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 cgroup_subsys_state **dst_cssp) { … } /** * cgroup_migrate_execute - migrate a taskset * @mgctx: migration context * * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @mgctx are migrated. * @mgctx is consumed regardless of success. */ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) { … } /** * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the mixable, (possible) thread root * and threaded cgroups, subtree_control must be zero for migration * destination cgroups with tasks so that child cgroups don't compete * against tasks. */ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) { … } /** * cgroup_migrate_finish - cleanup after attach * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { … } /** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem * even if the target is a process. Threads may be created and destroyed * but as long as cgroup_mutex is not dropped, no new css_set can be put * into play and the preloaded css_sets are guaranteed to cover all * migrations. */ void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx) { … } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been * preloaded to @mgctx->preloaded_src_csets. This function looks up and * pins all destination css_sets, links each to its source, and append them * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @mgctx. */ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) { … } /** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */ int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx) { … } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) { … } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *threadgroup_locked) { … } void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { … } static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { … } /* show controllers which are enabled from the parent */ static int cgroup_controllers_show(struct seq_file *seq, void *v) { … } /* show controllers which are enabled for a given cgroup's children */ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) { … } /** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { … } /** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex) { … } /** * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { … } /** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */ static void cgroup_propagate_control(struct cgroup *cgrp) { … } /** * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { … } static bool css_visible(struct cgroup_subsys_state *css) { … } /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { … } /** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */ static void cgroup_apply_control_disable(struct cgroup *cgrp) { … } /** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */ static int cgroup_apply_control(struct cgroup *cgrp) { … } /** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */ static void cgroup_finalize_control(struct cgroup *cgrp, int ret) { … } static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) { … } /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } /** * cgroup_enable_threaded - make @cgrp threaded * @cgrp: the target cgroup * * Called when "threaded" is written to the cgroup.type interface file and * tries to make @cgrp threaded and join the parent's resource domain. * This function is never called on the root cgroup as cgroup.type doesn't * exist on it. */ static int cgroup_enable_threaded(struct cgroup *cgrp) { … } static int cgroup_type_show(struct seq_file *seq, void *v) { … } static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static int cgroup_max_descendants_show(struct seq_file *seq, void *v) { … } static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static int cgroup_max_depth_show(struct seq_file *seq, void *v) { … } static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static int cgroup_events_show(struct seq_file *seq, void *v) { … } static int cgroup_stat_show(struct seq_file *seq, void *v) { … } #ifdef CONFIG_CGROUP_SCHED /** * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { … } static int cgroup_extra_stat_show(struct seq_file *seq, int ssid) { … } static int cgroup_local_stat_show(struct seq_file *seq, struct cgroup *cgrp, int ssid) { … } #endif static int cpu_stat_show(struct seq_file *seq, void *v) { … } static int cpu_local_stat_show(struct seq_file *seq, void *v) { … } #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { … } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { … } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { … } static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { … } static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } #ifdef CONFIG_IRQ_TIME_ACCOUNTING static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) { … } static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } #endif static int cgroup_pressure_show(struct seq_file *seq, void *v) { … } static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { … } static void cgroup_pressure_release(struct kernfs_open_file *of) { … } bool cgroup_psi_enabled(void) { … } #else /* CONFIG_PSI */ bool cgroup_psi_enabled(void) { return false; } #endif /* CONFIG_PSI */ static int cgroup_freeze_show(struct seq_file *seq, void *v) { … } static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static void __cgroup_kill(struct cgroup *cgrp) { … } static void cgroup_kill(struct cgroup *cgrp) { … } static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static int cgroup_file_open(struct kernfs_open_file *of) { … } static void cgroup_file_release(struct kernfs_open_file *of) { … } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { … } static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { … } static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { … } static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { … } static int cgroup_seqfile_show(struct seq_file *m, void *arg) { … } static struct kernfs_ops cgroup_kf_single_ops = …; static struct kernfs_ops cgroup_kf_ops = …; static void cgroup_file_notify_timer(struct timer_list *timer) { … } static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { … } /** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */ static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add) { … } static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { … } static void cgroup_exit_cftypes(struct cftype *cfts) { … } static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { … } static void cgroup_rm_cftypes_locked(struct cftype *cfts) { … } /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */ int cgroup_rm_cftypes(struct cftype *cfts) { … } /** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { … } /** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { … } /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { … } /** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */ void cgroup_file_notify(struct cgroup_file *cfile) { … } /** * cgroup_file_show - show or hide a hidden cgroup file * @cfile: target cgroup_file obtained by setting cftype->file_offset * @show: whether to show or hide */ void cgroup_file_show(struct cgroup_file *cfile, bool show) { … } /** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent) { … } /** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { … } EXPORT_SYMBOL_GPL(…); /** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct rightmost descendant as * long as @pos is accessible. */ struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) { … } static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) { … } /** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant * to visit for post-order traversal of @root's descendants. @root is * included in the iteration and the last node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @cgroup are accessible and @pos is a descendant of * @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { … } /** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */ bool css_has_online_children(struct cgroup_subsys_state *css) { … } static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) { … } /** * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ static void css_task_iter_advance_css_set(struct css_task_iter *it) { … } static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task) { … } static void css_task_iter_advance(struct css_task_iter *it) { … } /** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { … } /** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { … } /** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */ void css_task_iter_end(struct css_task_iter *it) { … } static void cgroup_procs_release(struct kernfs_open_file *of) { … } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { … } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, unsigned int iter_flags) { … } static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) { … } static int cgroup_procs_show(struct seq_file *s, void *v) { … } static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) { … } static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, struct cgroup_namespace *ns) { … } static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, bool threadgroup, struct cgroup_namespace *ns) { … } static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { … } static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) { … } static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { … } /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = …; static struct cftype cgroup_psi_files[] = …; /* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_rwork_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */ static void css_free_rwork_fn(struct work_struct *work) { … } static void css_release_work_fn(struct work_struct *work) { … } static void css_release(struct percpu_ref *ref) { … } static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { … } /* invoke ->css_online() on a new CSS and mark it online if successful */ static int online_css(struct cgroup_subsys_state *css) { … } /* if the CSS is online, invoke ->css_offline() on it and mark it offline */ static void offline_css(struct cgroup_subsys_state *css) { … } /** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss) { … } /* * The returned cgroup is fully initialized including its control mask, but * it doesn't have the control mask applied. */ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, umode_t mode) { … } static bool cgroup_check_hierarchy_limits(struct cgroup *parent) { … } int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { … } /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { … } /* css kill confirmation processing requires process context, bounce */ static void css_killed_ref_fn(struct percpu_ref *ref) { … } /** * kill_css - destroy a css * @css: css to destroy * * This function initiates destruction of @css by removing cgroup interface * files and putting its base reference. ->css_offline() will be invoked * asynchronously once css_tryget_online() is guaranteed to fail and when * the reference count reaches zero, @css will be released. */ static void kill_css(struct cgroup_subsys_state *css) { … } /** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * * css's make use of percpu refcnts whose killing latency shouldn't be * exposed to userland and are RCU protected. Also, cgroup core needs to * guarantee that css_tryget_online() won't succeed by the time * ->css_offline() is invoked. To satisfy all the requirements, * destruction is implemented in the following two steps. * * s1. Verify @cgrp can be destroyed and mark it dying. Remove all * userland visible parts and start killing the percpu refcnts of * css's. Set up so that the next stage will be kicked off once all * the percpu refcnts are confirmed to be killed. * * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the * rest of destruction. Once all cgroup references are gone, the * cgroup is RCU-freed. * * This function implements s1. After this step, @cgrp is gone as far as * the userland is concerned and a new cgroup with the same name may be * created. As cgroup doesn't care about the names internally, this * doesn't cause any problem. */ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); /* * Only migration can raise populated from zero and we're already * holding cgroup_mutex. */ if (cgroup_is_populated(cgrp)) return -EBUSY; /* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY; /* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_kn_lock_live(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn); if (cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; spin_lock_irq(&css_set_lock); for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; /* * If the dying cgroup is frozen, decrease frozen descendants * counters of ancestor cgroups. */ if (test_bit(CGRP_FROZEN, &cgrp->flags)) tcgrp->freezer.nr_frozen_descendants--; } spin_unlock_irq(&css_set_lock); cgroup1_check_for_release(parent); cgroup_bpf_offline(cgrp); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); return 0; }; int cgroup_rmdir(struct kernfs_node *kn) { … } static struct kernfs_syscall_ops cgroup_kf_syscall_ops = …; static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) { … } /** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */ int __init cgroup_init_early(void) { … } /** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */ int __init cgroup_init(void) { … } static int __init cgroup_wq_init(void) { … } core_initcall(cgroup_wq_init); void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { … } /* * cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * Only cgroups within current task's cgroup NS are valid. */ struct cgroup *cgroup_get_from_id(u64 id) { … } EXPORT_SYMBOL_GPL(…); /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { … } /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the target css_set. */ void cgroup_fork(struct task_struct *child) { … } /** * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer * @f: file corresponding to cgroup_dir * * Find the cgroup from a file pointer associated with a cgroup directory. * Returns a pointer to the cgroup on success. ERR_PTR is returned if the * cgroup cannot be found. */ static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { … } /** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. * @f: file corresponding to cgroup2_dir */ static struct cgroup *cgroup_get_from_file(struct file *f) { … } /** * cgroup_css_set_fork - find or create a css_set for a child process * @kargs: the arguments passed to create the child process * * This functions finds or creates a new css_set which the child * process will be attached to in cgroup_post_fork(). By default, * the child process will be given the same css_set as its parent. * * If CLONE_INTO_CGROUP is specified this function will try to find an * existing css_set which includes the requested cgroup and if not create * a new css_set that the child will be attached to later. If this function * succeeds it will hold cgroup_threadgroup_rwsem on return. If * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex * before grabbing cgroup_threadgroup_rwsem and will hold a reference * to the target cgroup. */ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem) { … } /** * cgroup_css_set_put_fork - drop references we took during fork * @kargs: the arguments passed to create the child process * * Drop references to the prepared css_set and target cgroup if * CLONE_INTO_CGROUP was requested. */ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { … } /** * cgroup_can_fork - called on a new task before the process is exposed * @child: the child process * @kargs: the arguments passed to create the child process * * This prepares a new css_set for the child process which the child will * be attached to in cgroup_post_fork(). * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() * callback returns an error, the fork aborts with that error code. This * allows for a cgroup subsystem to conditionally allow or deny new forks. */ int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs) { … } /** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the child process * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, struct kernel_clone_args *kargs) { … } /** * cgroup_post_fork - finalize cgroup setup for the child process * @child: the child process * @kargs: the arguments passed to create the child process * * Attach the child process to its css_set calling the subsystem fork() * callbacks. */ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { … } /** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk. * */ void cgroup_exit(struct task_struct *tsk) { … } void cgroup_release(struct task_struct *task) { … } void cgroup_free(struct task_struct *task) { … } static int __init cgroup_disable(char *str) { … } __setup(…); void __init __weak enable_debug_cgroup(void) { … } static int __init enable_cgroup_debug(char *str) { … } __setup(…); static int __init cgroup_favordynmods_setup(char *str) { … } __setup(…); /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { … } /** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { … } /** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) { … } EXPORT_SYMBOL_GPL(…); /** * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ struct cgroup *cgroup_v1v2_get_from_fd(int fd) { … } /** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. * @fd: fd obtained by open(cgroup2_dir) */ struct cgroup *cgroup_get_from_fd(int fd) { … } EXPORT_SYMBOL_GPL(…); static u64 power_of_ten(int power) { … } /** * cgroup_parse_float - parse a floating number * @input: input string * @dec_shift: number of decimal digits to shift * @v: output * * Parse a decimal floating point number in @input and store the result in * @v with decimal point right shifted @dec_shift times. For example, if * @input is "12.3456" and @dec_shift is 3, *@v will be set to 12345. * Returns 0 on success, -errno otherwise. * * There's nothing cgroup specific about this function except that it's * currently the only user. */ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) { … } /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { … } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { … } void cgroup_sk_free(struct sock_cgroup_data *skcd) { … } #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) { … } static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { … } static struct kobj_attribute cgroup_delegate_attr = …; static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { … } static struct kobj_attribute cgroup_features_attr = …; static struct attribute *cgroup_sysfs_attrs[] = …; static const struct attribute_group cgroup_sysfs_attr_group = …; static int __init cgroup_sysfs_init(void) { … } subsys_initcall(cgroup_sysfs_init); #endif /* CONFIG_SYSFS */
Codebase Browser
linux