diff options
Diffstat (limited to '')
| -rw-r--r-- | kernel/cgroup/Makefile | 9 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup-internal.h | 298 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup-v1.c | 1308 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup.c | 7074 | ||||
| -rw-r--r-- | kernel/cgroup/cpuset.c | 4241 | ||||
| -rw-r--r-- | kernel/cgroup/debug.c | 381 | ||||
| -rw-r--r-- | kernel/cgroup/freezer.c | 323 | ||||
| -rw-r--r-- | kernel/cgroup/legacy_freezer.c | 487 | ||||
| -rw-r--r-- | kernel/cgroup/misc.c | 424 | ||||
| -rw-r--r-- | kernel/cgroup/namespace.c | 151 | ||||
| -rw-r--r-- | kernel/cgroup/pids.c | 387 | ||||
| -rw-r--r-- | kernel/cgroup/rdma.c | 610 | ||||
| -rw-r--r-- | kernel/cgroup/rstat.c | 549 |
13 files changed, 16242 insertions, 0 deletions
diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile new file mode 100644 index 000000000..12f8457ad --- /dev/null +++ b/kernel/cgroup/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o freezer.o + +obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o +obj-$(CONFIG_CGROUP_PIDS) += pids.o +obj-$(CONFIG_CGROUP_RDMA) += rdma.o +obj-$(CONFIG_CPUSETS) += cpuset.o +obj-$(CONFIG_CGROUP_MISC) += misc.o +obj-$(CONFIG_CGROUP_DEBUG) += debug.o diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h new file mode 100644 index 000000000..367b0a42a --- /dev/null +++ b/kernel/cgroup/cgroup-internal.h @@ -0,0 +1,298 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __CGROUP_INTERNAL_H +#define __CGROUP_INTERNAL_H + +#include <linux/cgroup.h> +#include <linux/kernfs.h> +#include <linux/workqueue.h> +#include <linux/list.h> +#include <linux/refcount.h> +#include <linux/fs_parser.h> + +#define TRACE_CGROUP_PATH_LEN 1024 +extern spinlock_t trace_cgroup_path_lock; +extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; +extern void __init enable_debug_cgroup(void); + +/* + * cgroup_path() takes a spin lock. It is good practice not to take + * spin locks within trace point handlers, as they are mostly hidden + * from normal view. As cgroup_path() can take the kernfs_rename_lock + * spin lock, it is best to not call that function from the trace event + * handler. + * + * Note: trace_cgroup_##type##_enabled() is a static branch that will only + * be set when the trace event is enabled. + */ +#define TRACE_CGROUP_PATH(type, cgrp, ...) \ + do { \ + if (trace_cgroup_##type##_enabled()) { \ + unsigned long flags; \ + spin_lock_irqsave(&trace_cgroup_path_lock, \ + flags); \ + cgroup_path(cgrp, trace_cgroup_path, \ + TRACE_CGROUP_PATH_LEN); \ + trace_cgroup_##type(cgrp, trace_cgroup_path, \ + ##__VA_ARGS__); \ + spin_unlock_irqrestore(&trace_cgroup_path_lock, \ + flags); \ + } \ + } while (0) + +/* + * The cgroup filesystem superblock creation/mount context. + */ +struct cgroup_fs_context { + struct kernfs_fs_context kfc; + struct cgroup_root *root; + struct cgroup_namespace *ns; + unsigned int flags; /* CGRP_ROOT_* flags */ + + /* cgroup1 bits */ + bool cpuset_clone_children; + bool none; /* User explicitly requested empty subsystem */ + bool all_ss; /* Seen 'all' option */ + u16 subsys_mask; /* Selected subsystems */ + char *name; /* Hierarchy name */ + char *release_agent; /* Path for release notifications */ +}; + +static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) +{ + struct kernfs_fs_context *kfc = fc->fs_private; + + return container_of(kfc, struct cgroup_fs_context, kfc); +} + +struct cgroup_pidlist; + +struct cgroup_file_ctx { + struct cgroup_namespace *ns; + + struct { + void *trigger; + } psi; + + struct { + bool started; + struct css_task_iter iter; + } procs; + + struct { + struct cgroup_pidlist *pidlist; + } procs1; +}; + +/* + * 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; +}; + +/* used to track tasks and csets during migration */ +struct cgroup_taskset { + /* the src and dst cset list running through cset->mg_node */ + struct list_head src_csets; + struct list_head dst_csets; + + /* the number of tasks in the set */ + int nr_tasks; + + /* the subsys currently being processed */ + int ssid; + + /* + * Fields for cgroup_taskset_*() iteration. + * + * Before migration is committed, the target migration tasks are on + * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of + * the csets on ->dst_csets. ->csets point to either ->src_csets + * or ->dst_csets depending on whether migration is committed. + * + * ->cur_csets and ->cur_task point to the current task position + * during iteration. + */ + struct list_head *csets; + struct css_set *cur_cset; + struct task_struct *cur_task; +}; + +/* migration context also tracks preloading */ +struct cgroup_mgctx { + /* + * Preloaded source and destination csets. Used to guarantee + * atomic success or failure on actual migration. + */ + struct list_head preloaded_src_csets; + struct list_head preloaded_dst_csets; + + /* tasks and csets to migrate */ + struct cgroup_taskset tset; + + /* subsystems affected by migration */ + u16 ss_mask; +}; + +#define CGROUP_TASKSET_INIT(tset) \ +{ \ + .src_csets = LIST_HEAD_INIT(tset.src_csets), \ + .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ + .csets = &tset.src_csets, \ +} + +#define CGROUP_MGCTX_INIT(name) \ +{ \ + LIST_HEAD_INIT(name.preloaded_src_csets), \ + LIST_HEAD_INIT(name.preloaded_dst_csets), \ + CGROUP_TASKSET_INIT(name.tset), \ +} + +#define DEFINE_CGROUP_MGCTX(name) \ + struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) + +extern spinlock_t css_set_lock; +extern struct cgroup_subsys *cgroup_subsys[]; +extern struct list_head cgroup_roots; + +/* iterate across the hierarchies */ +#define for_each_root(root) \ + list_for_each_entry((root), &cgroup_roots, root_list) + +/** + * for_each_subsys - iterate all enabled cgroup subsystems + * @ss: the iteration cursor + * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end + */ +#define for_each_subsys(ss, ssid) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ + (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) + +static inline bool cgroup_is_dead(const struct cgroup *cgrp) +{ + return !(cgrp->self.flags & CSS_ONLINE); +} + +static inline bool notify_on_release(const struct cgroup *cgrp) +{ + return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); +} + +void put_css_set_locked(struct css_set *cset); + +static inline void put_css_set(struct css_set *cset) +{ + unsigned long flags; + + /* + * 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 (refcount_dec_not_one(&cset->refcount)) + return; + + spin_lock_irqsave(&css_set_lock, flags); + put_css_set_locked(cset); + spin_unlock_irqrestore(&css_set_lock, flags); +} + +/* + * refcounted get/put for css_set objects + */ +static inline void get_css_set(struct css_set *cset) +{ + refcount_inc(&cset->refcount); +} + +bool cgroup_ssid_enabled(int ssid); +bool cgroup_on_dfl(const struct cgroup *cgrp); +bool cgroup_is_thread_root(struct cgroup *cgrp); +bool cgroup_is_threaded(struct cgroup *cgrp); + +struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); +struct cgroup *task_cgroup_from_root(struct task_struct *task, + struct cgroup_root *root); +struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline); +void cgroup_kn_unlock(struct kernfs_node *kn); +int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns); + +void cgroup_favor_dynmods(struct cgroup_root *root, bool favor); +void cgroup_free_root(struct cgroup_root *root); +void init_cgroup_root(struct cgroup_fs_context *ctx); +int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask); +int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); +int cgroup_do_get_tree(struct fs_context *fc); + +int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); +void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); +void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, + struct cgroup_mgctx *mgctx); +int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx); +int cgroup_migrate(struct task_struct *leader, bool threadgroup, + struct cgroup_mgctx *mgctx); + +int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, + bool threadgroup); +void cgroup_attach_lock(bool lock_threadgroup); +void cgroup_attach_unlock(bool lock_threadgroup); +struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, + bool *locked) + __acquires(&cgroup_threadgroup_rwsem); +void cgroup_procs_write_finish(struct task_struct *task, bool locked) + __releases(&cgroup_threadgroup_rwsem); + +void cgroup_lock_and_drain_offline(struct cgroup *cgrp); + +int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode); +int cgroup_rmdir(struct kernfs_node *kn); +int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, + struct kernfs_root *kf_root); + +int __cgroup_task_count(const struct cgroup *cgrp); +int cgroup_task_count(const struct cgroup *cgrp); + +/* + * rstat.c + */ +int cgroup_rstat_init(struct cgroup *cgrp); +void cgroup_rstat_exit(struct cgroup *cgrp); +void cgroup_rstat_boot(void); +void cgroup_base_stat_cputime_show(struct seq_file *seq); + +/* + * namespace.c + */ +extern const struct proc_ns_operations cgroupns_operations; + +/* + * cgroup-v1.c + */ +extern struct cftype cgroup1_base_files[]; +extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; +extern const struct fs_parameter_spec cgroup1_fs_parameters[]; + +int proc_cgroupstats_show(struct seq_file *m, void *v); +bool cgroup1_ssid_disabled(int ssid); +void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); +void cgroup1_release_agent(struct work_struct *work); +void cgroup1_check_for_release(struct cgroup *cgrp); +int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param); +int cgroup1_get_tree(struct fs_context *fc); +int cgroup1_reconfigure(struct fs_context *ctx); + +#endif /* __CGROUP_INTERNAL_H */ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c new file mode 100644 index 000000000..289cc873c --- /dev/null +++ b/kernel/cgroup/cgroup-v1.c @@ -0,0 +1,1308 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "cgroup-internal.h" + +#include <linux/ctype.h> +#include <linux/kmod.h> +#include <linux/sort.h> +#include <linux/delay.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/magic.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/delayacct.h> +#include <linux/pid_namespace.h> +#include <linux/cgroupstats.h> +#include <linux/fs_parser.h> + +#include <trace/events/cgroup.h> + +/* + * pidlists linger the following amount before being destroyed. The goal + * is avoiding frequent destruction in the middle of consecutive read calls + * Expiring in the middle is a performance problem not a correctness one. + * 1 sec should be enough. + */ +#define CGROUP_PIDLIST_DESTROY_DELAY HZ + +/* Controllers blocked by the commandline in v1 */ +static u16 cgroup_no_v1_mask; + +/* disable named v1 mounts */ +static bool cgroup_no_v1_named; + +/* + * pidlist destructions need to be flushed on cgroup destruction. Use a + * separate workqueue as flush domain. + */ +static struct workqueue_struct *cgroup_pidlist_destroy_wq; + +/* protects cgroup_subsys->release_agent_path */ +static DEFINE_SPINLOCK(release_agent_path_lock); + +bool cgroup1_ssid_disabled(int ssid) +{ + return cgroup_no_v1_mask & (1 << ssid); +} + +/** + * 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 + * + * Return: %0 on success or a negative errno code on failure + */ +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) +{ + struct cgroup_root *root; + int retval = 0; + + cgroup_lock(); + cgroup_attach_lock(true); + for_each_root(root) { + struct cgroup *from_cgrp; + + spin_lock_irq(&css_set_lock); + from_cgrp = task_cgroup_from_root(from, root); + spin_unlock_irq(&css_set_lock); + + retval = cgroup_attach_task(from_cgrp, tsk, false); + if (retval) + break; + } + cgroup_attach_unlock(true); + cgroup_unlock(); + + return retval; +} +EXPORT_SYMBOL_GPL(cgroup_attach_task_all); + +/** + * cgroup_transfer_tasks - move tasks from one cgroup to another + * @to: cgroup to which the tasks will be moved + * @from: cgroup in which the tasks currently reside + * + * Locking rules between cgroup_post_fork() and the migration path + * guarantee that, if a task is forking while being migrated, the new child + * is guaranteed to be either visible in the source cgroup after the + * parent's migration is complete or put into the target cgroup. No task + * can slip out of migration through forking. + * + * Return: %0 on success or a negative errno code on failure + */ +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) +{ + DEFINE_CGROUP_MGCTX(mgctx); + struct cgrp_cset_link *link; + struct css_task_iter it; + struct task_struct *task; + int ret; + + if (cgroup_on_dfl(to)) + return -EINVAL; + + ret = cgroup_migrate_vet_dst(to); + if (ret) + return ret; + + cgroup_lock(); + + cgroup_attach_lock(true); + + /* all tasks in @from are being moved, all csets are source */ + spin_lock_irq(&css_set_lock); + list_for_each_entry(link, &from->cset_links, cset_link) + cgroup_migrate_add_src(link->cset, to, &mgctx); + spin_unlock_irq(&css_set_lock); + + ret = cgroup_migrate_prepare_dst(&mgctx); + if (ret) + goto out_err; + + /* + * Migrate tasks one-by-one until @from is empty. This fails iff + * ->can_attach() fails. + */ + do { + css_task_iter_start(&from->self, 0, &it); + + do { + task = css_task_iter_next(&it); + } while (task && (task->flags & PF_EXITING)); + + if (task) + get_task_struct(task); + css_task_iter_end(&it); + + if (task) { + ret = cgroup_migrate(task, false, &mgctx); + if (!ret) + TRACE_CGROUP_PATH(transfer_tasks, to, task, false); + put_task_struct(task); + } + } while (task && !ret); +out_err: + cgroup_migrate_finish(&mgctx); + cgroup_attach_unlock(true); + cgroup_unlock(); + return ret; +} + +/* + * Stuff for reading the 'tasks'/'procs' files. + * + * Reading this file can return large amounts of data if a cgroup has + * *lots* of attached tasks. So it may need several calls to read(), + * but we cannot guarantee that the information we produce is correct + * unless we produce it entirely atomically. + * + */ + +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ +struct cgroup_pidlist { + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* for delayed destruction */ + struct delayed_work destroy_dwork; +}; + +/* + * Used to destroy all pidlists lingering waiting for destroy timer. None + * should be left afterwards. + */ +void cgroup1_pidlist_destroy_all(struct cgroup *cgrp) +{ + struct cgroup_pidlist *l, *tmp_l; + + mutex_lock(&cgrp->pidlist_mutex); + list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) + mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); + mutex_unlock(&cgrp->pidlist_mutex); + + flush_workqueue(cgroup_pidlist_destroy_wq); + BUG_ON(!list_empty(&cgrp->pidlists)); +} + +static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, + destroy_dwork); + struct cgroup_pidlist *tofree = NULL; + + mutex_lock(&l->owner->pidlist_mutex); + + /* + * Destroy iff we didn't get queued again. The state won't change + * as destroy_dwork can only be queued while locked. + */ + if (!delayed_work_pending(dwork)) { + list_del(&l->links); + kvfree(l->list); + put_pid_ns(l->key.ns); + tofree = l; + } + + mutex_unlock(&l->owner->pidlist_mutex); + kfree(tofree); +} + +/* + * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries + * Returns the number of unique elements. + */ +static int pidlist_uniq(pid_t *list, int length) +{ + int src, dest = 1; + + /* + * we presume the 0th element is unique, so i starts at 1. trivial + * edge cases first; no work needs to be done for either + */ + if (length == 0 || length == 1) + return length; + /* src and dest walk down the list; dest counts unique elements */ + for (src = 1; src < length; src++) { + /* find next unique element */ + while (list[src] == list[src-1]) { + src++; + if (src == length) + goto after; + } + /* dest always points to where the next unique element goes */ + list[dest] = list[src]; + dest++; + } +after: + return dest; +} + +/* + * The two pid files - task and cgroup.procs - guaranteed that the result + * is sorted, which forced this whole pidlist fiasco. As pid order is + * different per namespace, each namespace needs differently sorted list, + * making it impossible to use, for example, single rbtree of member tasks + * sorted by task pointer. As pidlists can be fairly large, allocating one + * per open file is dangerous, so cgroup had to implement shared pool of + * pidlists keyed by cgroup and namespace. + */ +static int cmppid(const void *a, const void *b) +{ + return *(pid_t *)a - *(pid_t *)b; +} + +static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, + enum cgroup_filetype type) +{ + struct cgroup_pidlist *l; + /* don't need task_nsproxy() if we're looking at ourself */ + struct pid_namespace *ns = task_active_pid_ns(current); + + lockdep_assert_held(&cgrp->pidlist_mutex); + + list_for_each_entry(l, &cgrp->pidlists, links) + if (l->key.type == type && l->key.ns == ns) + return l; + return NULL; +} + +/* + * find the appropriate pidlist for our purpose (given procs vs tasks) + * returns with the lock on that pidlist already held, and takes care + * of the use count, or returns NULL with no locks held if we're out of + * memory. + */ +static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, + enum cgroup_filetype type) +{ + struct cgroup_pidlist *l; + + lockdep_assert_held(&cgrp->pidlist_mutex); + + l = cgroup_pidlist_find(cgrp, type); + if (l) + return l; + + /* entry not found; create a new one */ + l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); + if (!l) + return l; + + INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); + l->key.type = type; + /* don't need task_nsproxy() if we're looking at ourself */ + l->key.ns = get_pid_ns(task_active_pid_ns(current)); + l->owner = cgrp; + list_add(&l->links, &cgrp->pidlists); + return l; +} + +/* + * Load a cgroup's pidarray with either procs' tgids or tasks' pids + */ +static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, + struct cgroup_pidlist **lp) +{ + pid_t *array; + int length; + int pid, n = 0; /* used for populating the array */ + struct css_task_iter it; + struct task_struct *tsk; + struct cgroup_pidlist *l; + + lockdep_assert_held(&cgrp->pidlist_mutex); + + /* + * If cgroup gets more users after we read count, we won't have + * enough space - tough. This race is indistinguishable to the + * caller from the case that the additional cgroup users didn't + * show up until sometime later on. + */ + length = cgroup_task_count(cgrp); + array = kvmalloc_array(length, sizeof(pid_t), GFP_KERNEL); + if (!array) + return -ENOMEM; + /* now, populate the array */ + css_task_iter_start(&cgrp->self, 0, &it); + while ((tsk = css_task_iter_next(&it))) { + if (unlikely(n == length)) + break; + /* get tgid or pid for procs or tasks file respectively */ + if (type == CGROUP_FILE_PROCS) + pid = task_tgid_vnr(tsk); + else + pid = task_pid_vnr(tsk); + if (pid > 0) /* make sure to only use valid results */ + array[n++] = pid; + } + css_task_iter_end(&it); + length = n; + /* now sort & strip out duplicates (tgids or recycled thread PIDs) */ + sort(array, length, sizeof(pid_t), cmppid, NULL); + length = pidlist_uniq(array, length); + + l = cgroup_pidlist_find_create(cgrp, type); + if (!l) { + kvfree(array); + return -ENOMEM; + } + + /* store array, freeing old if necessary */ + kvfree(l->list); + l->list = array; + l->length = length; + *lp = l; + return 0; +} + +/* + * seq_file methods for the tasks/procs files. The seq_file position is the + * next pid to display; the seq_file iterator is a pointer to the pid + * in the cgroup->l->list array. + */ + +static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) +{ + /* + * Initially we receive a position value that corresponds to + * one more than the last pid shown (or 0 on the first call or + * after a seek to the start). Use a binary-search to find the + * next pid to display, if any + */ + struct kernfs_open_file *of = s->private; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup *cgrp = seq_css(s)->cgroup; + struct cgroup_pidlist *l; + enum cgroup_filetype type = seq_cft(s)->private; + int index = 0, pid = *pos; + int *iter, ret; + + mutex_lock(&cgrp->pidlist_mutex); + + /* + * !NULL @ctx->procs1.pidlist indicates that this isn't the first + * start() after open. If the matching pidlist is around, we can use + * that. Look for it. Note that @ctx->procs1.pidlist can't be used + * directly. It could already have been destroyed. + */ + if (ctx->procs1.pidlist) + ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); + + /* + * Either this is the first start() after open or the matching + * pidlist has been destroyed inbetween. Create a new one. + */ + if (!ctx->procs1.pidlist) { + ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); + if (ret) + return ERR_PTR(ret); + } + l = ctx->procs1.pidlist; + + if (pid) { + int end = l->length; + + while (index < end) { + int mid = (index + end) / 2; + if (l->list[mid] == pid) { + index = mid; + break; + } else if (l->list[mid] <= pid) + index = mid + 1; + else + end = mid; + } + } + /* If we're off the end of the array, we're done */ + if (index >= l->length) + return NULL; + /* Update the abstract position to be the actual pid that we found */ + iter = l->list + index; + *pos = *iter; + return iter; +} + +static void cgroup_pidlist_stop(struct seq_file *s, void *v) +{ + struct kernfs_open_file *of = s->private; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist; + + if (l) + mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, + CGROUP_PIDLIST_DESTROY_DELAY); + mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); +} + +static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct kernfs_open_file *of = s->private; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist; + pid_t *p = v; + pid_t *end = l->list + l->length; + /* + * Advance to the next pid in the array. If this goes off the + * end, we're done + */ + p++; + if (p >= end) { + (*pos)++; + return NULL; + } else { + *pos = *p; + return p; + } +} + +static int cgroup_pidlist_show(struct seq_file *s, void *v) +{ + seq_printf(s, "%d\n", *(int *)v); + + return 0; +} + +static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off, + bool threadgroup) +{ + struct cgroup *cgrp; + struct task_struct *task; + const struct cred *cred, *tcred; + ssize_t ret; + bool locked; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + task = cgroup_procs_write_start(buf, threadgroup, &locked); + ret = PTR_ERR_OR_ZERO(task); + if (ret) + goto out_unlock; + + /* + * Even if we're attaching all tasks in the thread group, we only need + * to check permissions on one of them. Check permissions using the + * credentials from file open to protect against inherited fd attacks. + */ + cred = of->file->f_cred; + tcred = get_task_cred(task); + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) + ret = -EACCES; + put_cred(tcred); + if (ret) + goto out_finish; + + ret = cgroup_attach_task(cgrp, task, threadgroup); + +out_finish: + cgroup_procs_write_finish(task, locked); +out_unlock: + cgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +static ssize_t cgroup1_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup1_procs_write(of, buf, nbytes, off, true); +} + +static ssize_t cgroup1_tasks_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup1_procs_write(of, buf, nbytes, off, false); +} + +static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + struct cgroup_file_ctx *ctx; + + BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + ctx = of->priv; + if ((ctx->ns->user_ns != &init_user_ns) || + !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + spin_lock(&release_agent_path_lock); + strlcpy(cgrp->root->release_agent_path, strstrip(buf), + sizeof(cgrp->root->release_agent_path)); + spin_unlock(&release_agent_path_lock); + cgroup_kn_unlock(of->kn); + return nbytes; +} + +static int cgroup_release_agent_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + spin_lock(&release_agent_path_lock); + seq_puts(seq, cgrp->root->release_agent_path); + spin_unlock(&release_agent_path_lock); + seq_putc(seq, '\n'); + return 0; +} + +static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) +{ + seq_puts(seq, "0\n"); + return 0; +} + +static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return notify_on_release(css->cgroup); +} + +static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + if (val) + set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); + else + clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); + return 0; +} + +static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); +} + +static int cgroup_clone_children_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + if (val) + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); + else + clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); + return 0; +} + +/* cgroup core interface files for the legacy hierarchies */ +struct cftype cgroup1_base_files[] = { + { + .name = "cgroup.procs", + .seq_start = cgroup_pidlist_start, + .seq_next = cgroup_pidlist_next, + .seq_stop = cgroup_pidlist_stop, + .seq_show = cgroup_pidlist_show, + .private = CGROUP_FILE_PROCS, + .write = cgroup1_procs_write, + }, + { + .name = "cgroup.clone_children", + .read_u64 = cgroup_clone_children_read, + .write_u64 = cgroup_clone_children_write, + }, + { + .name = "cgroup.sane_behavior", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cgroup_sane_behavior_show, + }, + { + .name = "tasks", + .seq_start = cgroup_pidlist_start, + .seq_next = cgroup_pidlist_next, + .seq_stop = cgroup_pidlist_stop, + .seq_show = cgroup_pidlist_show, + .private = CGROUP_FILE_TASKS, + .write = cgroup1_tasks_write, + }, + { + .name = "notify_on_release", + .read_u64 = cgroup_read_notify_on_release, + .write_u64 = cgroup_write_notify_on_release, + }, + { + .name = "release_agent", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cgroup_release_agent_show, + .write = cgroup_release_agent_write, + .max_write_len = PATH_MAX - 1, + }, + { } /* terminate */ +}; + +/* Display information about each subsystem and each hierarchy */ +int proc_cgroupstats_show(struct seq_file *m, void *v) +{ + struct cgroup_subsys *ss; + int i; + + seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); + /* + * Grab the subsystems state racily. No need to add avenue to + * cgroup_mutex contention. + */ + + for_each_subsys(ss, i) + seq_printf(m, "%s\t%d\t%d\t%d\n", + ss->legacy_name, ss->root->hierarchy_id, + atomic_read(&ss->root->nr_cgrps), + cgroup_ssid_enabled(i)); + + return 0; +} + +/** + * cgroupstats_build - build and fill cgroupstats + * @stats: cgroupstats to fill information into + * @dentry: A dentry entry belonging to the cgroup for which stats have + * been requested. + * + * Build and fill cgroupstats so that taskstats can export it to user + * space. + * + * Return: %0 on success or a negative errno code on failure + */ +int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) +{ + struct kernfs_node *kn = kernfs_node_from_dentry(dentry); + struct cgroup *cgrp; + struct css_task_iter it; + struct task_struct *tsk; + + /* it should be kernfs_node belonging to cgroupfs and is a directory */ + if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || + kernfs_type(kn) != KERNFS_DIR) + return -EINVAL; + + /* + * We aren't being called from kernfs and there's no guarantee on + * @kn->priv's validity. For this and css_tryget_online_from_dir(), + * @kn->priv is RCU safe. Let's do the RCU dancing. + */ + rcu_read_lock(); + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); + if (!cgrp || !cgroup_tryget(cgrp)) { + rcu_read_unlock(); + return -ENOENT; + } + rcu_read_unlock(); + + css_task_iter_start(&cgrp->self, 0, &it); + while ((tsk = css_task_iter_next(&it))) { + switch (READ_ONCE(tsk->__state)) { + case TASK_RUNNING: + stats->nr_running++; + break; + case TASK_INTERRUPTIBLE: + stats->nr_sleeping++; + break; + case TASK_UNINTERRUPTIBLE: + stats->nr_uninterruptible++; + break; + case TASK_STOPPED: + stats->nr_stopped++; + break; + default: + if (tsk->in_iowait) + stats->nr_io_wait++; + break; + } + } + css_task_iter_end(&it); + + cgroup_put(cgrp); + return 0; +} + +void cgroup1_check_for_release(struct cgroup *cgrp) +{ + if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && + !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) + schedule_work(&cgrp->release_agent_work); +} + +/* + * Notify userspace when a cgroup is released, by running the + * configured release agent with the name of the cgroup (path + * relative to the root of cgroup file system) as the argument. + * + * Most likely, this user command will try to rmdir this cgroup. + * + * This races with the possibility that some other task will be + * attached to this cgroup before it is removed, or that some other + * user task will 'mkdir' a child cgroup of this cgroup. That's ok. + * The presumed 'rmdir' will fail quietly if this cgroup is no longer + * unused, and this cgroup will be reprieved from its death sentence, + * to continue to serve a useful existence. Next time it's released, + * we will get notified again, if it still has 'notify_on_release' set. + * + * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which + * means only wait until the task is successfully execve()'d. The + * separate release agent task is forked by call_usermodehelper(), + * then control in this thread returns here, without waiting for the + * release agent task. We don't bother to wait because the caller of + * this routine has no use for the exit status of the release agent + * task, so no sense holding our caller up for that. + */ +void cgroup1_release_agent(struct work_struct *work) +{ + struct cgroup *cgrp = + container_of(work, struct cgroup, release_agent_work); + char *pathbuf, *agentbuf; + char *argv[3], *envp[3]; + int ret; + + /* snoop agent path and exit early if empty */ + if (!cgrp->root->release_agent_path[0]) + return; + + /* prepare argument buffers */ + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + agentbuf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathbuf || !agentbuf) + goto out_free; + + spin_lock(&release_agent_path_lock); + strlcpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX); + spin_unlock(&release_agent_path_lock); + if (!agentbuf[0]) + goto out_free; + + ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); + if (ret < 0 || ret >= PATH_MAX) + goto out_free; + + argv[0] = agentbuf; + argv[1] = pathbuf; + argv[2] = NULL; + + /* minimal command environment */ + envp[0] = "HOME=/"; + envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + envp[2] = NULL; + + call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); +out_free: + kfree(agentbuf); + kfree(pathbuf); +} + +/* + * cgroup_rename - Only allow simple rename of directories in place. + */ +static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, + const char *new_name_str) +{ + struct cgroup *cgrp = kn->priv; + int ret; + + /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ + if (strchr(new_name_str, '\n')) + return -EINVAL; + + if (kernfs_type(kn) != KERNFS_DIR) + return -ENOTDIR; + if (kn->parent != new_parent) + return -EIO; + + /* + * We're gonna grab cgroup_mutex which nests outside kernfs + * active_ref. kernfs_rename() doesn't require active_ref + * protection. Break them before grabbing cgroup_mutex. + */ + kernfs_break_active_protection(new_parent); + kernfs_break_active_protection(kn); + + cgroup_lock(); + + ret = kernfs_rename(kn, new_parent, new_name_str); + if (!ret) + TRACE_CGROUP_PATH(rename, cgrp); + + cgroup_unlock(); + + kernfs_unbreak_active_protection(kn); + kernfs_unbreak_active_protection(new_parent); + return ret; +} + +static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root) +{ + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + struct cgroup_subsys *ss; + int ssid; + + for_each_subsys(ss, ssid) + if (root->subsys_mask & (1 << ssid)) + seq_show_option(seq, ss->legacy_name, NULL); + if (root->flags & CGRP_ROOT_NOPREFIX) + seq_puts(seq, ",noprefix"); + if (root->flags & CGRP_ROOT_XATTR) + seq_puts(seq, ",xattr"); + if (root->flags & CGRP_ROOT_CPUSET_V2_MODE) + seq_puts(seq, ",cpuset_v2_mode"); + if (root->flags & CGRP_ROOT_FAVOR_DYNMODS) + seq_puts(seq, ",favordynmods"); + + spin_lock(&release_agent_path_lock); + if (strlen(root->release_agent_path)) + seq_show_option(seq, "release_agent", + root->release_agent_path); + spin_unlock(&release_agent_path_lock); + + if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) + seq_puts(seq, ",clone_children"); + if (strlen(root->name)) + seq_show_option(seq, "name", root->name); + return 0; +} + +enum cgroup1_param { + Opt_all, + Opt_clone_children, + Opt_cpuset_v2_mode, + Opt_name, + Opt_none, + Opt_noprefix, + Opt_release_agent, + Opt_xattr, + Opt_favordynmods, + Opt_nofavordynmods, +}; + +const struct fs_parameter_spec cgroup1_fs_parameters[] = { + fsparam_flag ("all", Opt_all), + fsparam_flag ("clone_children", Opt_clone_children), + fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), + fsparam_string("name", Opt_name), + fsparam_flag ("none", Opt_none), + fsparam_flag ("noprefix", Opt_noprefix), + fsparam_string("release_agent", Opt_release_agent), + fsparam_flag ("xattr", Opt_xattr), + fsparam_flag ("favordynmods", Opt_favordynmods), + fsparam_flag ("nofavordynmods", Opt_nofavordynmods), + {} +}; + +int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct cgroup_subsys *ss; + struct fs_parse_result result; + int opt, i; + + opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); + if (opt == -ENOPARAM) { + int ret; + + ret = vfs_parse_fs_param_source(fc, param); + if (ret != -ENOPARAM) + return ret; + for_each_subsys(ss, i) { + if (strcmp(param->key, ss->legacy_name)) + continue; + if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i)) + return invalfc(fc, "Disabled controller '%s'", + param->key); + ctx->subsys_mask |= (1 << i); + return 0; + } + return invalfc(fc, "Unknown subsys name '%s'", param->key); + } + if (opt < 0) + return opt; + + switch (opt) { + case Opt_none: + /* Explicitly have no subsystems */ + ctx->none = true; + break; + case Opt_all: + ctx->all_ss = true; + break; + case Opt_noprefix: + ctx->flags |= CGRP_ROOT_NOPREFIX; + break; + case Opt_clone_children: + ctx->cpuset_clone_children = true; + break; + case Opt_cpuset_v2_mode: + ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; + break; + case Opt_xattr: + ctx->flags |= CGRP_ROOT_XATTR; + break; + case Opt_favordynmods: + ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; + break; + case Opt_nofavordynmods: + ctx->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; + break; + case Opt_release_agent: + /* Specifying two release agents is forbidden */ + if (ctx->release_agent) + return invalfc(fc, "release_agent respecified"); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) + return invalfc(fc, "Setting release_agent not allowed"); + ctx->release_agent = param->string; + param->string = NULL; + break; + case Opt_name: + /* blocked by boot param? */ + if (cgroup_no_v1_named) + return -ENOENT; + /* Can't specify an empty name */ + if (!param->size) + return invalfc(fc, "Empty name"); + if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) + return invalfc(fc, "Name too long"); + /* Must match [\w.-]+ */ + for (i = 0; i < param->size; i++) { + char c = param->string[i]; + if (isalnum(c)) + continue; + if ((c == '.') || (c == '-') || (c == '_')) + continue; + return invalfc(fc, "Invalid name"); + } + /* Specifying two names is forbidden */ + if (ctx->name) + return invalfc(fc, "name respecified"); + ctx->name = param->string; + param->string = NULL; + break; + } + return 0; +} + +static int check_cgroupfs_options(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + u16 mask = U16_MAX; + u16 enabled = 0; + struct cgroup_subsys *ss; + int i; + +#ifdef CONFIG_CPUSETS + mask = ~((u16)1 << cpuset_cgrp_id); +#endif + for_each_subsys(ss, i) + if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i)) + enabled |= 1 << i; + + ctx->subsys_mask &= enabled; + + /* + * In absence of 'none', 'name=' and subsystem name options, + * let's default to 'all'. + */ + if (!ctx->subsys_mask && !ctx->none && !ctx->name) + ctx->all_ss = true; + + if (ctx->all_ss) { + /* Mutually exclusive option 'all' + subsystem name */ + if (ctx->subsys_mask) + return invalfc(fc, "subsys name conflicts with all"); + /* 'all' => select all the subsystems */ + ctx->subsys_mask = enabled; + } + + /* + * We either have to specify by name or by subsystems. (So all + * empty hierarchies must have a name). + */ + if (!ctx->subsys_mask && !ctx->name) + return invalfc(fc, "Need name or subsystem set"); + + /* + * Option noprefix was introduced just for backward compatibility + * with the old cpuset, so we allow noprefix only if mounting just + * the cpuset subsystem. + */ + if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) + return invalfc(fc, "noprefix used incorrectly"); + + /* Can't specify "none" and some subsystems */ + if (ctx->subsys_mask && ctx->none) + return invalfc(fc, "none used incorrectly"); + + return 0; +} + +int cgroup1_reconfigure(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb); + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + int ret = 0; + u16 added_mask, removed_mask; + + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); + + /* See what subsystems are wanted */ + ret = check_cgroupfs_options(fc); + if (ret) + goto out_unlock; + + if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent) + pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", + task_tgid_nr(current), current->comm); + + added_mask = ctx->subsys_mask & ~root->subsys_mask; + removed_mask = root->subsys_mask & ~ctx->subsys_mask; + + /* Don't allow flags or name to change at remount */ + if ((ctx->flags ^ root->flags) || + (ctx->name && strcmp(ctx->name, root->name))) { + errorfc(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", + ctx->flags, ctx->name ?: "", root->flags, root->name); + ret = -EINVAL; + goto out_unlock; + } + + /* remounting is not allowed for populated hierarchies */ + if (!list_empty(&root->cgrp.self.children)) { + ret = -EBUSY; + goto out_unlock; + } + + ret = rebind_subsystems(root, added_mask); + if (ret) + goto out_unlock; + + WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); + + if (ctx->release_agent) { + spin_lock(&release_agent_path_lock); + strcpy(root->release_agent_path, ctx->release_agent); + spin_unlock(&release_agent_path_lock); + } + + trace_cgroup_remount(root); + + out_unlock: + cgroup_unlock(); + return ret; +} + +struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { + .rename = cgroup1_rename, + .show_options = cgroup1_show_options, + .mkdir = cgroup_mkdir, + .rmdir = cgroup_rmdir, + .show_path = cgroup_show_path, +}; + +/* + * The guts of cgroup1 mount - find or create cgroup_root to use. + * Called with cgroup_mutex held; returns 0 on success, -E... on + * error and positive - in case when the candidate is busy dying. + * On success it stashes a reference to cgroup_root into given + * cgroup_fs_context; that reference is *NOT* counting towards the + * cgroup_root refcount. + */ +static int cgroup1_root_to_use(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct cgroup_root *root; + struct cgroup_subsys *ss; + int i, ret; + + /* First find the desired set of subsystems */ + ret = check_cgroupfs_options(fc); + if (ret) + return ret; + + /* + * Destruction of cgroup root is asynchronous, so subsystems may + * still be dying after the previous unmount. Let's drain the + * dying subsystems. We just need to ensure that the ones + * unmounted previously finish dying and don't care about new ones + * starting. Testing ref liveliness is good enough. + */ + for_each_subsys(ss, i) { + if (!(ctx->subsys_mask & (1 << i)) || + ss->root == &cgrp_dfl_root) + continue; + + if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) + return 1; /* restart */ + cgroup_put(&ss->root->cgrp); + } + + for_each_root(root) { + bool name_match = false; + + if (root == &cgrp_dfl_root) + continue; + + /* + * If we asked for a name then it must match. Also, if + * name matches but sybsys_mask doesn't, we should fail. + * Remember whether name matched. + */ + if (ctx->name) { + if (strcmp(ctx->name, root->name)) + continue; + name_match = true; + } + + /* + * If we asked for subsystems (or explicitly for no + * subsystems) then they must match. + */ + if ((ctx->subsys_mask || ctx->none) && + (ctx->subsys_mask != root->subsys_mask)) { + if (!name_match) + continue; + return -EBUSY; + } + + if (root->flags ^ ctx->flags) + pr_warn("new mount options do not match the existing superblock, will be ignored\n"); + + ctx->root = root; + return 0; + } + + /* + * No such thing, create a new one. name= matching without subsys + * specification is allowed for already existing hierarchies but we + * can't create new one without subsys specification. + */ + if (!ctx->subsys_mask && !ctx->none) + return invalfc(fc, "No subsys list or none specified"); + + /* Hierarchies may only be created in the initial cgroup namespace. */ + if (ctx->ns != &init_cgroup_ns) + return -EPERM; + + root = kzalloc(sizeof(*root), GFP_KERNEL); + if (!root) + return -ENOMEM; + + ctx->root = root; + init_cgroup_root(ctx); + + ret = cgroup_setup_root(root, ctx->subsys_mask); + if (!ret) + cgroup_favor_dynmods(root, ctx->flags & CGRP_ROOT_FAVOR_DYNMODS); + else + cgroup_free_root(root); + + return ret; +} + +int cgroup1_get_tree(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + int ret; + + /* Check if the caller has permission to mount. */ + if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); + + ret = cgroup1_root_to_use(fc); + if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) + ret = 1; /* restart */ + + cgroup_unlock(); + + if (!ret) + ret = cgroup_do_get_tree(fc); + + if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { + fc_drop_locked(fc); + ret = 1; + } + + if (unlikely(ret > 0)) { + msleep(10); + return restart_syscall(); + } + return ret; +} + +static int __init cgroup1_wq_init(void) +{ + /* + * Used to destroy pidlists and separate to serve as flush domain. + * Cap @max_active to 1 too. + */ + cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", + 0, 1); + BUG_ON(!cgroup_pidlist_destroy_wq); + return 0; +} +core_initcall(cgroup1_wq_init); + +static int __init cgroup_no_v1(char *str) +{ + struct cgroup_subsys *ss; + char *token; + int i; + + while ((token = strsep(&str, ",")) != NULL) { + if (!*token) + continue; + + if (!strcmp(token, "all")) { + cgroup_no_v1_mask = U16_MAX; + continue; + } + + if (!strcmp(token, "named")) { + cgroup_no_v1_named = true; + continue; + } + + for_each_subsys(ss, i) { + if (strcmp(token, ss->name) && + strcmp(token, ss->legacy_name)) + continue; + + cgroup_no_v1_mask |= 1 << i; + } + } + return 1; +} +__setup("cgroup_no_v1=", cgroup_no_v1); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c new file mode 100644 index 000000000..97ecca433 --- /dev/null +++ b/kernel/cgroup/cgroup.c @@ -0,0 +1,7074 @@ +/* + * 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) KBUILD_MODNAME ": " 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 (MAX_CGROUP_TYPE_NAMELEN + \ + MAX_CFTYPE_NAME + 2) +/* let's not notify more than 100 times per second */ +#define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100) + +/* + * 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_SUBSYS_COUNT > 0) + +/* + * 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(cgroup_mutex); +DEFINE_SPINLOCK(css_set_lock); + +#ifdef CONFIG_PROVE_RCU +EXPORT_SYMBOL_GPL(cgroup_mutex); +EXPORT_SYMBOL_GPL(css_set_lock); +#endif + +DEFINE_SPINLOCK(trace_cgroup_path_lock); +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(cgroup_threadgroup_rwsem); + +#define cgroup_assert_mutex_or_rcu_locked() \ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&cgroup_mutex), \ + "cgroup_mutex or RCU read lock required"); + +/* + * 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(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, +struct cgroup_subsys *cgroup_subsys[] = { +#include <linux/cgroup_subsys.h> +}; +#undef SUBSYS + +/* array of cgroup subsystem names */ +#define SUBSYS(_x) [_x ## _cgrp_id] = #_x, +static const char *cgroup_subsys_name[] = { +#include <linux/cgroup_subsys.h> +}; +#undef SUBSYS + +/* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */ +#define SUBSYS(_x) \ + DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \ + DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \ + EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \ + EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key); +#include <linux/cgroup_subsys.h> +#undef SUBSYS + +#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key, +static struct static_key_true *cgroup_subsys_enabled_key[] = { +#include <linux/cgroup_subsys.h> +}; +#undef SUBSYS + +#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key, +static struct static_key_true *cgroup_subsys_on_dfl_key[] = { +#include <linux/cgroup_subsys.h> +}; +#undef SUBSYS + +static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); + +/* the default hierarchy */ +struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu }; +EXPORT_SYMBOL_GPL(cgrp_dfl_root); + +/* + * 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(cgroup_roots); +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 = 1; + +/* + * 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; + +/* cgroup namespace for init task */ +struct cgroup_namespace init_cgroup_ns = { + .ns.count = REFCOUNT_INIT(2), + .user_ns = &init_user_ns, + .ns.ops = &cgroupns_operations, + .ns.inum = PROC_CGROUP_INIT_INO, + .root_cset = &init_css_set, +}; + +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 { +#ifdef CONFIG_PSI + OPT_FEATURE_PRESSURE, +#endif + OPT_FEATURE_COUNT +}; + +static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = { +#ifdef CONFIG_PSI + "pressure", +#endif +}; + +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); + +/** + * 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) +{ + if (!CGROUP_HAS_SUBSYS_CONFIG) + return false; + + return static_key_enabled(cgroup_subsys_enabled_key[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. + * + * - debug: disallowed on the default hierarchy. + */ +bool cgroup_on_dfl(const struct cgroup *cgrp) +{ + return cgrp->root == &cgrp_dfl_root; +} + +/* 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) +{ + int ret; + + idr_preload(gfp_mask); + spin_lock_bh(&cgroup_idr_lock); + ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); + spin_unlock_bh(&cgroup_idr_lock); + idr_preload_end(); + return ret; +} + +static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) +{ + void *ret; + + spin_lock_bh(&cgroup_idr_lock); + ret = idr_replace(idr, ptr, id); + spin_unlock_bh(&cgroup_idr_lock); + return ret; +} + +static void cgroup_idr_remove(struct idr *idr, int id) +{ + spin_lock_bh(&cgroup_idr_lock); + idr_remove(idr, id); + spin_unlock_bh(&cgroup_idr_lock); +} + +static bool cgroup_has_tasks(struct cgroup *cgrp) +{ + return cgrp->nr_populated_csets; +} + +bool cgroup_is_threaded(struct cgroup *cgrp) +{ + return cgrp->dom_cgrp != cgrp; +} + +/* can @cgrp host both domain and threaded children? */ +static bool cgroup_is_mixable(struct cgroup *cgrp) +{ + /* + * Root isn't under domain level resource control exempting it from + * the no-internal-process constraint, so it can serve as a thread + * root and a parent of resource domains at the same time. + */ + return !cgroup_parent(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) +{ + /* mixables don't care */ + if (cgroup_is_mixable(cgrp)) + return true; + + /* domain roots can't be nested under threaded */ + if (cgroup_is_threaded(cgrp)) + return false; + + /* can only have either domain or threaded children */ + if (cgrp->nr_populated_domain_children) + return false; + + /* and no domain controllers can be enabled */ + if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) + return false; + + return true; +} + +/* is @cgrp root of a threaded subtree? */ +bool cgroup_is_thread_root(struct cgroup *cgrp) +{ + /* thread root should be a domain */ + if (cgroup_is_threaded(cgrp)) + return false; + + /* a domain w/ threaded children is a thread root */ + if (cgrp->nr_threaded_children) + return true; + + /* + * A domain which has tasks and explicit threaded controllers + * enabled is a thread root. + */ + if (cgroup_has_tasks(cgrp) && + (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) + return true; + + return false; +} + +/* 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) +{ + /* the cgroup itself can be a thread root */ + if (cgroup_is_threaded(cgrp)) + return false; + + /* but the ancestors can't be unless mixable */ + while ((cgrp = cgroup_parent(cgrp))) { + if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) + return false; + if (cgroup_is_threaded(cgrp)) + return false; + } + + return true; +} + +/* subsystems visibly enabled on a cgroup */ +static u16 cgroup_control(struct cgroup *cgrp) +{ + struct cgroup *parent = cgroup_parent(cgrp); + u16 root_ss_mask = cgrp->root->subsys_mask; + + if (parent) { + u16 ss_mask = parent->subtree_control; + + /* threaded cgroups can only have threaded controllers */ + if (cgroup_is_threaded(cgrp)) + ss_mask &= cgrp_dfl_threaded_ss_mask; + return ss_mask; + } + + if (cgroup_on_dfl(cgrp)) + root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | + cgrp_dfl_implicit_ss_mask); + return root_ss_mask; +} + +/* subsystems enabled on a cgroup */ +static u16 cgroup_ss_mask(struct cgroup *cgrp) +{ + struct cgroup *parent = cgroup_parent(cgrp); + + if (parent) { + u16 ss_mask = parent->subtree_ss_mask; + + /* threaded cgroups can only have threaded controllers */ + if (cgroup_is_threaded(cgrp)) + ss_mask &= cgrp_dfl_threaded_ss_mask; + return ss_mask; + } + + return cgrp->root->subsys_mask; +} + +/** + * 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) +{ + if (CGROUP_HAS_SUBSYS_CONFIG && ss) + return rcu_dereference_check(cgrp->subsys[ss->id], + lockdep_is_held(&cgroup_mutex)); + else + return &cgrp->self; +} + +/** + * 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) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + css = cgroup_css(cgrp, ss); + if (css && !css_tryget_online(css)) + css = NULL; + rcu_read_unlock(); + + return css; +} + +/** + * 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) +{ + lockdep_assert_held(&cgroup_mutex); + + if (!ss) + return &cgrp->self; + + /* + * This function is used while updating css associations and thus + * can't test the csses directly. Test ss_mask. + */ + while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { + cgrp = cgroup_parent(cgrp); + if (!cgrp) + return NULL; + } + + return cgroup_css(cgrp, 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) +{ + struct cgroup_subsys_state *css; + + if (!CGROUP_HAS_SUBSYS_CONFIG) + return NULL; + + do { + css = cgroup_css(cgrp, ss); + + if (css) + return css; + cgrp = cgroup_parent(cgrp); + } while (cgrp); + + return init_css_set.subsys[ss->id]; +} + +/** + * 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) +{ + struct cgroup_subsys_state *css; + + if (!CGROUP_HAS_SUBSYS_CONFIG) + return NULL; + + rcu_read_lock(); + + do { + css = cgroup_css(cgrp, ss); + + if (css && css_tryget_online(css)) + goto out_unlock; + cgrp = cgroup_parent(cgrp); + } while (cgrp); + + css = init_css_set.subsys[ss->id]; + css_get(css); +out_unlock: + rcu_read_unlock(); + return css; +} +EXPORT_SYMBOL_GPL(cgroup_get_e_css); + +static void cgroup_get_live(struct cgroup *cgrp) +{ + WARN_ON_ONCE(cgroup_is_dead(cgrp)); + css_get(&cgrp->self); +} + +/** + * __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) +{ + int count = 0; + struct cgrp_cset_link *link; + + lockdep_assert_held(&css_set_lock); + + list_for_each_entry(link, &cgrp->cset_links, cset_link) + count += link->cset->nr_tasks; + + return count; +} + +/** + * cgroup_task_count - count the number of tasks in a cgroup. + * @cgrp: the cgroup in question + */ +int cgroup_task_count(const struct cgroup *cgrp) +{ + int count; + + spin_lock_irq(&css_set_lock); + count = __cgroup_task_count(cgrp); + spin_unlock_irq(&css_set_lock); + + return count; +} + +struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) +{ + struct cgroup *cgrp = of->kn->parent->priv; + struct cftype *cft = of_cft(of); + + /* + * This is open and unprotected implementation of cgroup_css(). + * seq_css() is only called from a kernfs file operation which has + * an active reference on the file. Because all the subsystem + * files are drained before a css is disassociated with a cgroup, + * the matching css from the cgroup's subsys table is guaranteed to + * be and stay valid until the enclosing operation is complete. + */ + if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss) + return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); + else + return &cgrp->self; +} +EXPORT_SYMBOL_GPL(of_css); + +/** + * 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_[tree_]mutex. + */ +#define for_each_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = rcu_dereference_check( \ + (cgrp)->subsys[(ssid)], \ + lockdep_is_held(&cgroup_mutex)))) { } \ + else + +/** + * for_each_e_css - iterate all effective 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_[tree_]mutex. + */ +#define for_each_e_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = cgroup_e_css_by_mask(cgrp, \ + cgroup_subsys[(ssid)]))) \ + ; \ + else + +/** + * 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) do { \ + unsigned long __ss_mask = (ss_mask); \ + if (!CGROUP_HAS_SUBSYS_CONFIG) { \ + (ssid) = 0; \ + break; \ + } \ + for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ + (ss) = cgroup_subsys[ssid]; \ + { + +#define while_each_subsys_mask() \ + } \ + } \ +} while (false) + +/* iterate over child cgrps, lock should be held throughout iteration */ +#define cgroup_for_each_live_child(child, cgrp) \ + list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ + if (({ lockdep_assert_held(&cgroup_mutex); \ + cgroup_is_dead(child); })) \ + ; \ + else + +/* walk live descendants in pre order */ +#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ + css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ + if (({ lockdep_assert_held(&cgroup_mutex); \ + (dsct) = (d_css)->cgroup; \ + cgroup_is_dead(dsct); })) \ + ; \ + else + +/* walk live descendants in postorder */ +#define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ + css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ + if (({ lockdep_assert_held(&cgroup_mutex); \ + (dsct) = (d_css)->cgroup; \ + cgroup_is_dead(dsct); })) \ + ; \ + else + +/* + * 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 = { + .refcount = REFCOUNT_INIT(1), + .dom_cset = &init_css_set, + .tasks = LIST_HEAD_INIT(init_css_set.tasks), + .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), + .dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks), + .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), + .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), + .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), + .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), + .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), + .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), + + /* + * The following field is re-initialized when this cset gets linked + * in cgroup_init(). However, let's initialize the field + * statically too so that the default cgroup can be accessed safely + * early during boot. + */ + .dfl_cgrp = &cgrp_dfl_root.cgrp, +}; + +static int css_set_count = 1; /* 1 for init_css_set */ + +static bool css_set_threaded(struct css_set *cset) +{ + return cset->dom_cset != 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) +{ + lockdep_assert_held(&css_set_lock); + + return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks); +} + +/** + * 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) +{ + struct cgroup *child = NULL; + int adj = populated ? 1 : -1; + + lockdep_assert_held(&css_set_lock); + + do { + bool was_populated = cgroup_is_populated(cgrp); + + if (!child) { + cgrp->nr_populated_csets += adj; + } else { + if (cgroup_is_threaded(child)) + cgrp->nr_populated_threaded_children += adj; + else + cgrp->nr_populated_domain_children += adj; + } + + if (was_populated == cgroup_is_populated(cgrp)) + break; + + cgroup1_check_for_release(cgrp); + TRACE_CGROUP_PATH(notify_populated, cgrp, + cgroup_is_populated(cgrp)); + cgroup_file_notify(&cgrp->events_file); + + child = cgrp; + cgrp = cgroup_parent(cgrp); + } while (cgrp); +} + +/** + * 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) +{ + struct cgrp_cset_link *link; + + lockdep_assert_held(&css_set_lock); + + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) + cgroup_update_populated(link->cgrp, 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) +{ + struct css_task_iter *it, *pos; + + list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) + css_task_iter_skip(it, 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) +{ + lockdep_assert_held(&css_set_lock); + + if (to_cset && !css_set_populated(to_cset)) + css_set_update_populated(to_cset, true); + + if (from_cset) { + WARN_ON_ONCE(list_empty(&task->cg_list)); + + css_set_skip_task_iters(from_cset, task); + list_del_init(&task->cg_list); + if (!css_set_populated(from_cset)) + css_set_update_populated(from_cset, false); + } else { + WARN_ON_ONCE(!list_empty(&task->cg_list)); + } + + if (to_cset) { + /* + * We are synchronized through cgroup_threadgroup_rwsem + * against PF_EXITING setting such that we can't race + * against cgroup_exit()/cgroup_free() dropping the css_set. + */ + WARN_ON_ONCE(task->flags & PF_EXITING); + + cgroup_move_task(task, to_cset); + list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : + &to_cset->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 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; +} + +void put_css_set_locked(struct css_set *cset) +{ + struct cgrp_cset_link *link, *tmp_link; + struct cgroup_subsys *ss; + int ssid; + + lockdep_assert_held(&css_set_lock); + + if (!refcount_dec_and_test(&cset->refcount)) + return; + + WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); + + /* This css_set is dead. Unlink it and release cgroup and css refs */ + for_each_subsys(ss, ssid) { + list_del(&cset->e_cset_node[ssid]); + css_put(cset->subsys[ssid]); + } + hash_del(&cset->hlist); + css_set_count--; + + list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { + list_del(&link->cset_link); + list_del(&link->cgrp_link); + if (cgroup_parent(link->cgrp)) + cgroup_put(link->cgrp); + kfree(link); + } + + if (css_set_threaded(cset)) { + list_del(&cset->threaded_csets_node); + put_css_set_locked(cset->dom_cset); + } + + kfree_rcu(cset, rcu_head); +} + +/** + * 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 cgroup *new_dfl_cgrp; + struct list_head *l1, *l2; + + /* + * On the default hierarchy, there can be csets which are + * associated with the same set of cgroups but different csses. + * Let's first ensure that csses match. + */ + if (memcmp(template, cset->subsys, sizeof(cset->subsys))) + return false; + + + /* @cset's domain should match the default cgroup's */ + if (cgroup_on_dfl(new_cgrp)) + new_dfl_cgrp = new_cgrp; + else + new_dfl_cgrp = old_cset->dfl_cgrp; + + if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) + return false; + + /* + * Compare cgroup pointers in order to distinguish between + * different cgroups in hierarchies. As different cgroups may + * share the same effective css, this comparison is always + * necessary. + */ + 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 cgroup_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)) { + /* + * @ss is in this hierarchy, so we want the + * effective css from @cgrp. + */ + template[i] = cgroup_e_css_by_mask(cgrp, ss); + } else { + /* + * @ss is not in this hierarchy, so we don't want + * to change the css. + */ + 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)); + + if (cgroup_on_dfl(cgrp)) + cset->dfl_cgrp = cgrp; + + link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); + link->cset = cset; + link->cgrp = cgrp; + + /* + * Always add links to the tail of the lists so that the lists are + * in chronological order. + */ + list_move_tail(&link->cset_link, &cgrp->cset_links); + list_add_tail(&link->cgrp_link, &cset->cgrp_links); + + if (cgroup_parent(cgrp)) + cgroup_get_live(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_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; + struct css_set *cset; + struct list_head tmp_links; + struct cgrp_cset_link *link; + struct cgroup_subsys *ss; + unsigned long key; + int ssid; + + lockdep_assert_held(&cgroup_mutex); + + /* First see if we already have a cgroup group that matches + * the desired set */ + spin_lock_irq(&css_set_lock); + cset = find_existing_css_set(old_cset, cgrp, template); + if (cset) + get_css_set(cset); + spin_unlock_irq(&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; + } + + refcount_set(&cset->refcount, 1); + cset->dom_cset = cset; + INIT_LIST_HEAD(&cset->tasks); + INIT_LIST_HEAD(&cset->mg_tasks); + INIT_LIST_HEAD(&cset->dying_tasks); + INIT_LIST_HEAD(&cset->task_iters); + INIT_LIST_HEAD(&cset->threaded_csets); + INIT_HLIST_NODE(&cset->hlist); + INIT_LIST_HEAD(&cset->cgrp_links); + INIT_LIST_HEAD(&cset->mg_src_preload_node); + INIT_LIST_HEAD(&cset->mg_dst_preload_node); + INIT_LIST_HEAD(&cset->mg_node); + + /* Copy the set of subsystem state objects generated in + * find_existing_css_set() */ + memcpy(cset->subsys, template, sizeof(cset->subsys)); + + spin_lock_irq(&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 @cset to the hash table */ + key = css_set_hash(cset->subsys); + hash_add(css_set_table, &cset->hlist, key); + + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cset->subsys[ssid]; + + list_add_tail(&cset->e_cset_node[ssid], + &css->cgroup->e_csets[ssid]); + css_get(css); + } + + spin_unlock_irq(&css_set_lock); + + /* + * If @cset should be threaded, look up the matching dom_cset and + * link them up. We first fully initialize @cset then look for the + * dom_cset. It's simpler this way and safe as @cset is guaranteed + * to stay empty until we return. + */ + if (cgroup_is_threaded(cset->dfl_cgrp)) { + struct css_set *dcset; + + dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); + if (!dcset) { + put_css_set(cset); + return NULL; + } + + spin_lock_irq(&css_set_lock); + cset->dom_cset = dcset; + list_add_tail(&cset->threaded_csets_node, + &dcset->threaded_csets); + spin_unlock_irq(&css_set_lock); + } + + return cset; +} + +struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) +{ + struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv; + + return root_cgrp->root; +} + +void cgroup_favor_dynmods(struct cgroup_root *root, bool favor) +{ + bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS; + + /* see the comment above CGRP_ROOT_FAVOR_DYNMODS definition */ + if (favor && !favoring) { + rcu_sync_enter(&cgroup_threadgroup_rwsem.rss); + root->flags |= CGRP_ROOT_FAVOR_DYNMODS; + } else if (!favor && favoring) { + rcu_sync_exit(&cgroup_threadgroup_rwsem.rss); + root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; + } +} + +static int cgroup_init_root_id(struct cgroup_root *root) +{ + int id; + + lockdep_assert_held(&cgroup_mutex); + + id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); + if (id < 0) + return id; + + root->hierarchy_id = id; + return 0; +} + +static void cgroup_exit_root_id(struct cgroup_root *root) +{ + lockdep_assert_held(&cgroup_mutex); + + idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); +} + +void cgroup_free_root(struct cgroup_root *root) +{ + kfree(root); +} + +static void cgroup_destroy_root(struct cgroup_root *root) +{ + struct cgroup *cgrp = &root->cgrp; + struct cgrp_cset_link *link, *tmp_link; + + trace_cgroup_destroy_root(root); + + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); + + BUG_ON(atomic_read(&root->nr_cgrps)); + BUG_ON(!list_empty(&cgrp->self.children)); + + /* Rebind all subsystems back to the default hierarchy */ + WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); + + /* + * Release all the links from cset_links to this hierarchy's + * root cgroup + */ + spin_lock_irq(&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); + } + + spin_unlock_irq(&css_set_lock); + + if (!list_empty(&root->root_list)) { + list_del(&root->root_list); + cgroup_root_count--; + } + + cgroup_favor_dynmods(root, false); + cgroup_exit_root_id(root); + + cgroup_unlock(); + + cgroup_rstat_exit(cgrp); + kernfs_destroy_root(root->kf_root); + cgroup_free_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) +{ + struct cgroup *res_cgroup = NULL; + + if (cset == &init_css_set) { + res_cgroup = &root->cgrp; + } else if (root == &cgrp_dfl_root) { + res_cgroup = cset->dfl_cgrp; + } else { + struct cgrp_cset_link *link; + lockdep_assert_held(&css_set_lock); + + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + if (c->root == root) { + res_cgroup = c; + break; + } + } + } + + BUG_ON(!res_cgroup); + return res_cgroup; +} + +/* + * 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) +{ + struct cgroup *res = NULL; + struct css_set *cset; + + lockdep_assert_held(&css_set_lock); + + rcu_read_lock(); + + cset = current->nsproxy->cgroup_ns->root_cset; + res = __cset_cgroup_from_root(cset, root); + + rcu_read_unlock(); + + return res; +} + +/* + * 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) +{ + struct css_set *cset; + + cset = current->nsproxy->cgroup_ns->root_cset; + return __cset_cgroup_from_root(cset, &cgrp_dfl_root); +} + +/* 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) +{ + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_lock); + + return __cset_cgroup_from_root(cset, root); +} + +/* + * Return the cgroup for "task" from the given hierarchy. Must be + * called with cgroup_mutex and css_set_lock held. + */ +struct cgroup *task_cgroup_from_root(struct task_struct *task, + struct cgroup_root *root) +{ + /* + * No need to lock the task - since we hold css_set_lock the + * task can't change groups. + */ + return cset_cgroup_from_root(task_css_set(task), 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) +{ + struct cgroup_subsys *ss = cft->ss; + + if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && + !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { + const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : ""; + + snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s", + dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, + cft->name); + } else { + strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); + } + return 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) +{ + umode_t mode = 0; + + if (cft->read_u64 || cft->read_s64 || cft->seq_show) + mode |= S_IRUGO; + + if (cft->write_u64 || cft->write_s64 || cft->write) { + if (cft->flags & CFTYPE_WORLD_WRITABLE) + mode |= S_IWUGO; + else + mode |= S_IWUSR; + } + + return mode; +} + +/** + * 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) +{ + u16 cur_ss_mask = subtree_control; + struct cgroup_subsys *ss; + int ssid; + + lockdep_assert_held(&cgroup_mutex); + + cur_ss_mask |= cgrp_dfl_implicit_ss_mask; + + while (true) { + u16 new_ss_mask = cur_ss_mask; + + do_each_subsys_mask(ss, ssid, cur_ss_mask) { + new_ss_mask |= ss->depends_on; + } while_each_subsys_mask(); + + /* + * Mask out subsystems which aren't available. This can + * happen only if some depended-upon subsystems were bound + * to non-default hierarchies. + */ + new_ss_mask &= this_ss_mask; + + if (new_ss_mask == cur_ss_mask) + break; + cur_ss_mask = new_ss_mask; + } + + return cur_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) +{ + struct cgroup *cgrp; + + if (kernfs_type(kn) == KERNFS_DIR) + cgrp = kn->priv; + else + cgrp = kn->parent->priv; + + cgroup_unlock(); + + kernfs_unbreak_active_protection(kn); + cgroup_put(cgrp); +} + +/** + * 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) +{ + struct cgroup *cgrp; + + if (kernfs_type(kn) == KERNFS_DIR) + cgrp = kn->priv; + else + cgrp = kn->parent->priv; + + /* + * We're gonna grab cgroup_mutex which nests outside kernfs + * active_ref. cgroup liveliness check alone provides enough + * protection against removal. Ensure @cgrp stays accessible and + * break the active_ref protection. + */ + if (!cgroup_tryget(cgrp)) + return NULL; + kernfs_break_active_protection(kn); + + if (drain_offline) + cgroup_lock_and_drain_offline(cgrp); + else + cgroup_lock(); + + if (!cgroup_is_dead(cgrp)) + return cgrp; + + cgroup_kn_unlock(kn); + return NULL; +} + +static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) +{ + char name[CGROUP_FILE_NAME_MAX]; + + lockdep_assert_held(&cgroup_mutex); + + if (cft->file_offset) { + struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); + struct cgroup_file *cfile = (void *)css + cft->file_offset; + + spin_lock_irq(&cgroup_file_kn_lock); + cfile->kn = NULL; + spin_unlock_irq(&cgroup_file_kn_lock); + + del_timer_sync(&cfile->notify_timer); + } + + kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); +} + +/** + * css_clear_dir - remove subsys files in a cgroup directory + * @css: target css + */ +static void css_clear_dir(struct cgroup_subsys_state *css) +{ + struct cgroup *cgrp = css->cgroup; + struct cftype *cfts; + + if (!(css->flags & CSS_VISIBLE)) + return; + + css->flags &= ~CSS_VISIBLE; + + if (!css->ss) { + if (cgroup_on_dfl(cgrp)) { + cgroup_addrm_files(css, cgrp, + cgroup_base_files, false); + if (cgroup_psi_enabled()) + cgroup_addrm_files(css, cgrp, + cgroup_psi_files, false); + } else { + cgroup_addrm_files(css, cgrp, + cgroup1_base_files, false); + } + } else { + list_for_each_entry(cfts, &css->ss->cfts, node) + cgroup_addrm_files(css, cgrp, cfts, false); + } +} + +/** + * 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) +{ + struct cgroup *cgrp = css->cgroup; + struct cftype *cfts, *failed_cfts; + int ret; + + if ((css->flags & CSS_VISIBLE) || !cgrp->kn) + return 0; + + if (!css->ss) { + if (cgroup_on_dfl(cgrp)) { + ret = cgroup_addrm_files(&cgrp->self, cgrp, + cgroup_base_files, true); + if (ret < 0) + return ret; + + if (cgroup_psi_enabled()) { + ret = cgroup_addrm_files(&cgrp->self, cgrp, + cgroup_psi_files, true); + if (ret < 0) + return ret; + } + } else { + cgroup_addrm_files(css, cgrp, + cgroup1_base_files, true); + } + } else { + list_for_each_entry(cfts, &css->ss->cfts, node) { + ret = cgroup_addrm_files(css, cgrp, cfts, true); + if (ret < 0) { + failed_cfts = cfts; + goto err; + } + } + } + + css->flags |= CSS_VISIBLE; + + return 0; +err: + list_for_each_entry(cfts, &css->ss->cfts, node) { + if (cfts == failed_cfts) + break; + cgroup_addrm_files(css, cgrp, cfts, false); + } + return ret; +} + +int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) +{ + struct cgroup *dcgrp = &dst_root->cgrp; + struct cgroup_subsys *ss; + int ssid, ret; + u16 dfl_disable_ss_mask = 0; + + lockdep_assert_held(&cgroup_mutex); + + do_each_subsys_mask(ss, ssid, ss_mask) { + /* + * If @ss has non-root csses attached to it, can't move. + * If @ss is an implicit controller, it is exempt from this + * rule and can be stolen. + */ + if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && + !ss->implicit_on_dfl) + return -EBUSY; + + /* can't move between two non-dummy roots either */ + if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) + return -EBUSY; + + /* + * Collect ssid's that need to be disabled from default + * hierarchy. + */ + if (ss->root == &cgrp_dfl_root) + dfl_disable_ss_mask |= 1 << ssid; + + } while_each_subsys_mask(); + + if (dfl_disable_ss_mask) { + struct cgroup *scgrp = &cgrp_dfl_root.cgrp; + + /* + * Controllers from default hierarchy that need to be rebound + * are all disabled together in one go. + */ + cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } + + do_each_subsys_mask(ss, ssid, ss_mask) { + struct cgroup_root *src_root = ss->root; + struct cgroup *scgrp = &src_root->cgrp; + struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); + struct css_set *cset, *cset_pos; + struct css_task_iter *it; + + WARN_ON(!css || cgroup_css(dcgrp, ss)); + + if (src_root != &cgrp_dfl_root) { + /* disable from the source */ + src_root->subsys_mask &= ~(1 << ssid); + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } + + /* rebind */ + RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); + rcu_assign_pointer(dcgrp->subsys[ssid], css); + ss->root = dst_root; + css->cgroup = dcgrp; + + spin_lock_irq(&css_set_lock); + WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); + list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], + e_cset_node[ss->id]) { + list_move_tail(&cset->e_cset_node[ss->id], + &dcgrp->e_csets[ss->id]); + /* + * all css_sets of scgrp together in same order to dcgrp, + * patch in-flight iterators to preserve correct iteration. + * since the iterator is always advanced right away and + * finished when it->cset_pos meets it->cset_head, so only + * update it->cset_head is enough here. + */ + list_for_each_entry(it, &cset->task_iters, iters_node) + if (it->cset_head == &scgrp->e_csets[ss->id]) + it->cset_head = &dcgrp->e_csets[ss->id]; + } + spin_unlock_irq(&css_set_lock); + + if (ss->css_rstat_flush) { + list_del_rcu(&css->rstat_css_node); + synchronize_rcu(); + list_add_rcu(&css->rstat_css_node, + &dcgrp->rstat_css_list); + } + + /* default hierarchy doesn't enable controllers by default */ + dst_root->subsys_mask |= 1 << ssid; + if (dst_root == &cgrp_dfl_root) { + static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); + } else { + dcgrp->subtree_control |= 1 << ssid; + static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); + } + + ret = cgroup_apply_control(dcgrp); + if (ret) + pr_warn("partial failure to rebind %s controller (err=%d)\n", + ss->name, ret); + + if (ss->bind) + ss->bind(css); + } while_each_subsys_mask(); + + kernfs_activate(dcgrp->kn); + return 0; +} + +int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, + struct kernfs_root *kf_root) +{ + int len = 0; + char *buf = NULL; + struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); + struct cgroup *ns_cgroup; + + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + spin_lock_irq(&css_set_lock); + ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); + len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); + spin_unlock_irq(&css_set_lock); + + if (len >= PATH_MAX) + len = -ERANGE; + else if (len > 0) { + seq_escape(sf, buf, " \t\n\\"); + len = 0; + } + kfree(buf); + return len; +} + +enum cgroup2_param { + Opt_nsdelegate, + Opt_favordynmods, + Opt_memory_localevents, + Opt_memory_recursiveprot, + nr__cgroup2_params +}; + +static const struct fs_parameter_spec cgroup2_fs_parameters[] = { + fsparam_flag("nsdelegate", Opt_nsdelegate), + fsparam_flag("favordynmods", Opt_favordynmods), + fsparam_flag("memory_localevents", Opt_memory_localevents), + fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), + {} +}; + +static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_nsdelegate: + ctx->flags |= CGRP_ROOT_NS_DELEGATE; + return 0; + case Opt_favordynmods: + ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; + return 0; + case Opt_memory_localevents: + ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; + return 0; + case Opt_memory_recursiveprot: + ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; + return 0; + } + return -EINVAL; +} + +static void apply_cgroup_root_flags(unsigned int root_flags) +{ + if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { + if (root_flags & CGRP_ROOT_NS_DELEGATE) + cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; + else + cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE; + + cgroup_favor_dynmods(&cgrp_dfl_root, + root_flags & CGRP_ROOT_FAVOR_DYNMODS); + + if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) + cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; + else + cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS; + + if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) + cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; + else + cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT; + } +} + +static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) +{ + if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) + seq_puts(seq, ",nsdelegate"); + if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS) + seq_puts(seq, ",favordynmods"); + if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) + seq_puts(seq, ",memory_localevents"); + if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) + seq_puts(seq, ",memory_recursiveprot"); + return 0; +} + +static int cgroup_reconfigure(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + + apply_cgroup_root_flags(ctx->flags); + return 0; +} + +static void init_cgroup_housekeeping(struct cgroup *cgrp) +{ + struct cgroup_subsys *ss; + int ssid; + + INIT_LIST_HEAD(&cgrp->self.sibling); + INIT_LIST_HEAD(&cgrp->self.children); + INIT_LIST_HEAD(&cgrp->cset_links); + INIT_LIST_HEAD(&cgrp->pidlists); + mutex_init(&cgrp->pidlist_mutex); + cgrp->self.cgroup = cgrp; + cgrp->self.flags |= CSS_ONLINE; + cgrp->dom_cgrp = cgrp; + cgrp->max_descendants = INT_MAX; + cgrp->max_depth = INT_MAX; + INIT_LIST_HEAD(&cgrp->rstat_css_list); + prev_cputime_init(&cgrp->prev_cputime); + + for_each_subsys(ss, ssid) + INIT_LIST_HEAD(&cgrp->e_csets[ssid]); + + init_waitqueue_head(&cgrp->offline_waitq); + INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); +} + +void init_cgroup_root(struct cgroup_fs_context *ctx) +{ + struct cgroup_root *root = ctx->root; + struct cgroup *cgrp = &root->cgrp; + + INIT_LIST_HEAD(&root->root_list); + atomic_set(&root->nr_cgrps, 1); + cgrp->root = root; + init_cgroup_housekeeping(cgrp); + + /* DYNMODS must be modified through cgroup_favor_dynmods() */ + root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS; + if (ctx->release_agent) + strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); + if (ctx->name) + strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); + if (ctx->cpuset_clone_children) + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); +} + +int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) +{ + LIST_HEAD(tmp_links); + struct cgroup *root_cgrp = &root->cgrp; + struct kernfs_syscall_ops *kf_sops; + struct css_set *cset; + int i, ret; + + lockdep_assert_held(&cgroup_mutex); + + ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, + 0, GFP_KERNEL); + if (ret) + goto out; + + /* + * 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. Later rebinding may disable + * controllers on the default hierarchy and thus create new csets, + * which can't be more than the existing ones. Allocate 2x. + */ + ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); + if (ret) + goto cancel_ref; + + ret = cgroup_init_root_id(root); + if (ret) + goto cancel_ref; + + kf_sops = root == &cgrp_dfl_root ? + &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; + + root->kf_root = kernfs_create_root(kf_sops, + KERNFS_ROOT_CREATE_DEACTIVATED | + KERNFS_ROOT_SUPPORT_EXPORTOP | + KERNFS_ROOT_SUPPORT_USER_XATTR, + root_cgrp); + if (IS_ERR(root->kf_root)) { + ret = PTR_ERR(root->kf_root); + goto exit_root_id; + } + root_cgrp->kn = kernfs_root_to_node(root->kf_root); + WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1); + root_cgrp->ancestors[0] = root_cgrp; + + ret = css_populate_dir(&root_cgrp->self); + if (ret) + goto destroy_root; + + ret = cgroup_rstat_init(root_cgrp); + if (ret) + goto destroy_root; + + ret = rebind_subsystems(root, ss_mask); + if (ret) + goto exit_stats; + + ret = cgroup_bpf_inherit(root_cgrp); + WARN_ON_ONCE(ret); + + trace_cgroup_setup_root(root); + + /* + * 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 root cgroup in this hierarchy into all the css_set + * objects. + */ + spin_lock_irq(&css_set_lock); + hash_for_each(css_set_table, i, cset, hlist) { + link_css_set(&tmp_links, cset, root_cgrp); + if (css_set_populated(cset)) + cgroup_update_populated(root_cgrp, true); + } + spin_unlock_irq(&css_set_lock); + + BUG_ON(!list_empty(&root_cgrp->self.children)); + BUG_ON(atomic_read(&root->nr_cgrps) != 1); + + ret = 0; + goto out; + +exit_stats: + cgroup_rstat_exit(root_cgrp); +destroy_root: + kernfs_destroy_root(root->kf_root); + root->kf_root = NULL; +exit_root_id: + cgroup_exit_root_id(root); +cancel_ref: + percpu_ref_exit(&root_cgrp->self.refcnt); +out: + free_cgrp_cset_links(&tmp_links); + return ret; +} + +int cgroup_do_get_tree(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + int ret; + + ctx->kfc.root = ctx->root->kf_root; + if (fc->fs_type == &cgroup2_fs_type) + ctx->kfc.magic = CGROUP2_SUPER_MAGIC; + else + ctx->kfc.magic = CGROUP_SUPER_MAGIC; + ret = kernfs_get_tree(fc); + + /* + * In non-init cgroup namespace, instead of root cgroup's dentry, + * we return the dentry corresponding to the cgroupns->root_cgrp. + */ + if (!ret && ctx->ns != &init_cgroup_ns) { + struct dentry *nsdentry; + struct super_block *sb = fc->root->d_sb; + struct cgroup *cgrp; + + cgroup_lock(); + spin_lock_irq(&css_set_lock); + + cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); + + spin_unlock_irq(&css_set_lock); + cgroup_unlock(); + + nsdentry = kernfs_node_dentry(cgrp->kn, sb); + dput(fc->root); + if (IS_ERR(nsdentry)) { + deactivate_locked_super(sb); + ret = PTR_ERR(nsdentry); + nsdentry = NULL; + } + fc->root = nsdentry; + } + + if (!ctx->kfc.new_sb_created) + cgroup_put(&ctx->root->cgrp); + + return ret; +} + +/* + * Destroy a cgroup filesystem context. + */ +static void cgroup_fs_context_free(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + + kfree(ctx->name); + kfree(ctx->release_agent); + put_cgroup_ns(ctx->ns); + kernfs_free_fs_context(fc); + kfree(ctx); +} + +static int cgroup_get_tree(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + int ret; + + WRITE_ONCE(cgrp_dfl_visible, true); + cgroup_get_live(&cgrp_dfl_root.cgrp); + ctx->root = &cgrp_dfl_root; + + ret = cgroup_do_get_tree(fc); + if (!ret) + apply_cgroup_root_flags(ctx->flags); + return ret; +} + +static const struct fs_context_operations cgroup_fs_context_ops = { + .free = cgroup_fs_context_free, + .parse_param = cgroup2_parse_param, + .get_tree = cgroup_get_tree, + .reconfigure = cgroup_reconfigure, +}; + +static const struct fs_context_operations cgroup1_fs_context_ops = { + .free = cgroup_fs_context_free, + .parse_param = cgroup1_parse_param, + .get_tree = cgroup1_get_tree, + .reconfigure = cgroup1_reconfigure, +}; + +/* + * 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) +{ + struct cgroup_fs_context *ctx; + + ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->ns = current->nsproxy->cgroup_ns; + get_cgroup_ns(ctx->ns); + fc->fs_private = &ctx->kfc; + if (fc->fs_type == &cgroup2_fs_type) + fc->ops = &cgroup_fs_context_ops; + else + fc->ops = &cgroup1_fs_context_ops; + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(ctx->ns->user_ns); + fc->global = true; + +#ifdef CONFIG_CGROUP_FAVOR_DYNMODS + ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; +#endif + return 0; +} + +static void cgroup_kill_sb(struct super_block *sb) +{ + struct kernfs_root *kf_root = kernfs_root_from_sb(sb); + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + + /* + * If @root doesn't have any children, start killing it. + * This prevents new mounts by disabling percpu_ref_tryget_live(). + * + * And don't kill the default root. + */ + if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && + !percpu_ref_is_dying(&root->cgrp.self.refcnt)) { + cgroup_bpf_offline(&root->cgrp); + percpu_ref_kill(&root->cgrp.self.refcnt); + } + cgroup_put(&root->cgrp); + kernfs_kill_sb(sb); +} + +struct file_system_type cgroup_fs_type = { + .name = "cgroup", + .init_fs_context = cgroup_init_fs_context, + .parameters = cgroup1_fs_parameters, + .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, +}; + +static struct file_system_type cgroup2_fs_type = { + .name = "cgroup2", + .init_fs_context = cgroup_init_fs_context, + .parameters = cgroup2_fs_parameters, + .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, +}; + +#ifdef CONFIG_CPUSETS +static const struct fs_context_operations cpuset_fs_context_ops = { + .get_tree = cgroup1_get_tree, + .free = cgroup_fs_context_free, +}; + +/* + * 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) +{ + char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); + struct cgroup_fs_context *ctx; + int err; + + err = cgroup_init_fs_context(fc); + if (err) { + kfree(agent); + return err; + } + + fc->ops = &cpuset_fs_context_ops; + + ctx = cgroup_fc2context(fc); + ctx->subsys_mask = 1 << cpuset_cgrp_id; + ctx->flags |= CGRP_ROOT_NOPREFIX; + ctx->release_agent = agent; + + get_filesystem(&cgroup_fs_type); + put_filesystem(fc->fs_type); + fc->fs_type = &cgroup_fs_type; + + return 0; +} + +static struct file_system_type cpuset_fs_type = { + .name = "cpuset", + .init_fs_context = cpuset_init_fs_context, + .fs_flags = FS_USERNS_MOUNT, +}; +#endif + +int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) +{ + struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); + + return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); +} + +int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) +{ + int ret; + + cgroup_lock(); + spin_lock_irq(&css_set_lock); + + ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); + + spin_unlock_irq(&css_set_lock); + cgroup_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(cgroup_path_ns); + +/** + * 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. + * + * Return value is the same as kernfs_path(). + */ +int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) +{ + struct cgroup_root *root; + struct cgroup *cgrp; + int hierarchy_id = 1; + int ret; + + cgroup_lock(); + spin_lock_irq(&css_set_lock); + + root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); + + if (root) { + cgrp = task_cgroup_from_root(task, root); + ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); + } else { + /* if no hierarchy exists, everyone is in "/" */ + ret = strscpy(buf, "/", buflen); + } + + spin_unlock_irq(&css_set_lock); + cgroup_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(task_cgroup_path); + +/** + * 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) +{ + cpus_read_lock(); + if (lock_threadgroup) + percpu_down_write(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_attach_unlock - Undo cgroup_attach_lock() + * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem + */ +void cgroup_attach_unlock(bool lock_threadgroup) +{ + if (lock_threadgroup) + percpu_up_write(&cgroup_threadgroup_rwsem); + cpus_read_unlock(); +} + +/** + * 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) +{ + struct css_set *cset; + + lockdep_assert_held(&css_set_lock); + + /* @task either already exited or can't exit until the end */ + if (task->flags & PF_EXITING) + return; + + /* cgroup_threadgroup_rwsem protects racing against forks */ + WARN_ON_ONCE(list_empty(&task->cg_list)); + + cset = task_css_set(task); + if (!cset->mg_src_cgrp) + return; + + mgctx->tset.nr_tasks++; + + list_move_tail(&task->cg_list, &cset->mg_tasks); + if (list_empty(&cset->mg_node)) + list_add_tail(&cset->mg_node, + &mgctx->tset.src_csets); + if (list_empty(&cset->mg_dst_cset->mg_node)) + list_add_tail(&cset->mg_dst_cset->mg_node, + &mgctx->tset.dst_csets); +} + +/** + * 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) +{ + tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); + tset->cur_task = NULL; + + return cgroup_taskset_next(tset, 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) +{ + struct css_set *cset = tset->cur_cset; + struct task_struct *task = tset->cur_task; + + while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) { + if (!task) + task = list_first_entry(&cset->mg_tasks, + struct task_struct, cg_list); + else + task = list_next_entry(task, cg_list); + + if (&task->cg_list != &cset->mg_tasks) { + tset->cur_cset = cset; + tset->cur_task = task; + + /* + * This function may be called both before and + * after cgroup_taskset_migrate(). The two cases + * can be distinguished by looking at whether @cset + * has its ->mg_dst_cset set. + */ + if (cset->mg_dst_cset) + *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; + else + *dst_cssp = cset->subsys[tset->ssid]; + + return task; + } + + cset = list_next_entry(cset, mg_node); + task = NULL; + } + + return NULL; +} + +/** + * 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) +{ + struct cgroup_taskset *tset = &mgctx->tset; + struct cgroup_subsys *ss; + struct task_struct *task, *tmp_task; + struct css_set *cset, *tmp_cset; + int ssid, failed_ssid, ret; + + /* check that we can legitimately attach to the cgroup */ + if (tset->nr_tasks) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { + if (ss->can_attach) { + tset->ssid = ssid; + ret = ss->can_attach(tset); + if (ret) { + failed_ssid = ssid; + goto out_cancel_attach; + } + } + } while_each_subsys_mask(); + } + + /* + * Now that we're guaranteed success, proceed to move all tasks to + * the new cgroup. There are no failure cases after here, so this + * is the commit point. + */ + spin_lock_irq(&css_set_lock); + list_for_each_entry(cset, &tset->src_csets, mg_node) { + list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { + struct css_set *from_cset = task_css_set(task); + struct css_set *to_cset = cset->mg_dst_cset; + + get_css_set(to_cset); + to_cset->nr_tasks++; + css_set_move_task(task, from_cset, to_cset, true); + from_cset->nr_tasks--; + /* + * If the source or destination cgroup is frozen, + * the task might require to change its state. + */ + cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp, + to_cset->dfl_cgrp); + put_css_set_locked(from_cset); + + } + } + spin_unlock_irq(&css_set_lock); + + /* + * Migration is committed, all target tasks are now on dst_csets. + * Nothing is sensitive to fork() after this point. Notify + * controllers that migration is complete. + */ + tset->csets = &tset->dst_csets; + + if (tset->nr_tasks) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { + if (ss->attach) { + tset->ssid = ssid; + ss->attach(tset); + } + } while_each_subsys_mask(); + } + + ret = 0; + goto out_release_tset; + +out_cancel_attach: + if (tset->nr_tasks) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { + if (ssid == failed_ssid) + break; + if (ss->cancel_attach) { + tset->ssid = ssid; + ss->cancel_attach(tset); + } + } while_each_subsys_mask(); + } +out_release_tset: + spin_lock_irq(&css_set_lock); + list_splice_init(&tset->dst_csets, &tset->src_csets); + list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { + list_splice_tail_init(&cset->mg_tasks, &cset->tasks); + list_del_init(&cset->mg_node); + } + spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; + return ret; +} + +/** + * 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) +{ + /* v1 doesn't have any restriction */ + if (!cgroup_on_dfl(dst_cgrp)) + return 0; + + /* verify @dst_cgrp can host resources */ + if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) + return -EOPNOTSUPP; + + /* + * If @dst_cgrp is already or can become a thread root or is + * threaded, it doesn't matter. + */ + if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) + return 0; + + /* apply no-internal-process constraint */ + if (dst_cgrp->subtree_control) + return -EBUSY; + + return 0; +} + +/** + * 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) +{ + struct css_set *cset, *tmp_cset; + + lockdep_assert_held(&cgroup_mutex); + + spin_lock_irq(&css_set_lock); + + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, + mg_src_preload_node) { + cset->mg_src_cgrp = NULL; + cset->mg_dst_cgrp = NULL; + cset->mg_dst_cset = NULL; + list_del_init(&cset->mg_src_preload_node); + put_css_set_locked(cset); + } + + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, + mg_dst_preload_node) { + cset->mg_src_cgrp = NULL; + cset->mg_dst_cgrp = NULL; + cset->mg_dst_cset = NULL; + list_del_init(&cset->mg_dst_preload_node); + put_css_set_locked(cset); + } + + spin_unlock_irq(&css_set_lock); +} + +/** + * 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) +{ + struct cgroup *src_cgrp; + + lockdep_assert_held(&cgroup_mutex); + lockdep_assert_held(&css_set_lock); + + /* + * If ->dead, @src_set is associated with one or more dead cgroups + * and doesn't contain any migratable tasks. Ignore it early so + * that the rest of migration path doesn't get confused by it. + */ + if (src_cset->dead) + return; + + if (!list_empty(&src_cset->mg_src_preload_node)) + return; + + src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); + + WARN_ON(src_cset->mg_src_cgrp); + WARN_ON(src_cset->mg_dst_cgrp); + WARN_ON(!list_empty(&src_cset->mg_tasks)); + WARN_ON(!list_empty(&src_cset->mg_node)); + + src_cset->mg_src_cgrp = src_cgrp; + src_cset->mg_dst_cgrp = dst_cgrp; + get_css_set(src_cset); + list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); +} + +/** + * 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) +{ + struct css_set *src_cset, *tmp_cset; + + lockdep_assert_held(&cgroup_mutex); + + /* look up the dst cset for each src cset and link it to src */ + list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, + mg_src_preload_node) { + struct css_set *dst_cset; + struct cgroup_subsys *ss; + int ssid; + + dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); + if (!dst_cset) + return -ENOMEM; + + WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); + + /* + * If src cset equals dst, it's noop. Drop the src. + * cgroup_migrate() will skip the cset too. Note that we + * can't handle src == dst as some nodes are used by both. + */ + if (src_cset == dst_cset) { + src_cset->mg_src_cgrp = NULL; + src_cset->mg_dst_cgrp = NULL; + list_del_init(&src_cset->mg_src_preload_node); + put_css_set(src_cset); + put_css_set(dst_cset); + continue; + } + + src_cset->mg_dst_cset = dst_cset; + + if (list_empty(&dst_cset->mg_dst_preload_node)) + list_add_tail(&dst_cset->mg_dst_preload_node, + &mgctx->preloaded_dst_csets); + else + put_css_set(dst_cset); + + for_each_subsys(ss, ssid) + if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) + mgctx->ss_mask |= 1 << ssid; + } + + return 0; +} + +/** + * 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) +{ + struct task_struct *task; + + /* + * 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. + */ + spin_lock_irq(&css_set_lock); + rcu_read_lock(); + task = leader; + do { + cgroup_migrate_add_task(task, mgctx); + if (!threadgroup) + break; + } while_each_thread(leader, task); + rcu_read_unlock(); + spin_unlock_irq(&css_set_lock); + + return cgroup_migrate_execute(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) +{ + DEFINE_CGROUP_MGCTX(mgctx); + struct task_struct *task; + int ret = 0; + + /* look up all src csets */ + spin_lock_irq(&css_set_lock); + rcu_read_lock(); + task = leader; + do { + cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); + if (!threadgroup) + break; + } while_each_thread(leader, task); + rcu_read_unlock(); + spin_unlock_irq(&css_set_lock); + + /* prepare dst csets and commit */ + ret = cgroup_migrate_prepare_dst(&mgctx); + if (!ret) + ret = cgroup_migrate(leader, threadgroup, &mgctx); + + cgroup_migrate_finish(&mgctx); + + if (!ret) + TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); + + return ret; +} + +struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, + bool *threadgroup_locked) +{ + struct task_struct *tsk; + pid_t pid; + + if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) + return ERR_PTR(-EINVAL); + + /* + * If we migrate a single thread, we don't care about threadgroup + * stability. If the thread is `current`, it won't exit(2) under our + * hands or change PID through exec(2). We exclude + * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write + * callers by cgroup_mutex. + * Therefore, we can skip the global lock. + */ + lockdep_assert_held(&cgroup_mutex); + *threadgroup_locked = pid || threadgroup; + cgroup_attach_lock(*threadgroup_locked); + + rcu_read_lock(); + if (pid) { + tsk = find_task_by_vpid(pid); + if (!tsk) { + tsk = ERR_PTR(-ESRCH); + goto out_unlock_threadgroup; + } + } else { + tsk = current; + } + + if (threadgroup) + tsk = tsk->group_leader; + + /* + * kthreads may acquire PF_NO_SETAFFINITY during initialization. + * If userland migrates such a kthread to a non-root cgroup, it can + * become trapped in a cpuset, or RT kthread may be born in a + * cgroup with no rt_runtime allocated. Just say no. + */ + if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { + tsk = ERR_PTR(-EINVAL); + goto out_unlock_threadgroup; + } + + get_task_struct(tsk); + goto out_unlock_rcu; + +out_unlock_threadgroup: + cgroup_attach_unlock(*threadgroup_locked); + *threadgroup_locked = false; +out_unlock_rcu: + rcu_read_unlock(); + return tsk; +} + +void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) +{ + struct cgroup_subsys *ss; + int ssid; + + /* release reference from cgroup_procs_write_start() */ + put_task_struct(task); + + cgroup_attach_unlock(threadgroup_locked); + + for_each_subsys(ss, ssid) + if (ss->post_attach) + ss->post_attach(); +} + +static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) +{ + struct cgroup_subsys *ss; + bool printed = false; + int ssid; + + do_each_subsys_mask(ss, ssid, ss_mask) { + if (printed) + seq_putc(seq, ' '); + seq_puts(seq, ss->name); + printed = true; + } while_each_subsys_mask(); + if (printed) + seq_putc(seq, '\n'); +} + +/* show controllers which are enabled from the parent */ +static int cgroup_controllers_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + cgroup_print_ss_mask(seq, cgroup_control(cgrp)); + return 0; +} + +/* show controllers which are enabled for a given cgroup's children */ +static int cgroup_subtree_control_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + cgroup_print_ss_mask(seq, cgrp->subtree_control); + return 0; +} + +/** + * 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) +{ + DEFINE_CGROUP_MGCTX(mgctx); + struct cgroup_subsys_state *d_css; + struct cgroup *dsct; + struct css_set *src_cset; + bool has_tasks; + int ret; + + lockdep_assert_held(&cgroup_mutex); + + /* look up all csses currently attached to @cgrp's subtree */ + spin_lock_irq(&css_set_lock); + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { + struct cgrp_cset_link *link; + + /* + * As cgroup_update_dfl_csses() is only called by + * cgroup_apply_control(). The csses associated with the + * given cgrp will not be affected by changes made to + * its subtree_control file. We can skip them. + */ + if (dsct == cgrp) + continue; + + list_for_each_entry(link, &dsct->cset_links, cset_link) + cgroup_migrate_add_src(link->cset, dsct, &mgctx); + } + spin_unlock_irq(&css_set_lock); + + /* + * We need to write-lock threadgroup_rwsem while migrating tasks. + * However, if there are no source csets for @cgrp, changing its + * controllers isn't gonna produce any task migrations and the + * write-locking can be skipped safely. + */ + has_tasks = !list_empty(&mgctx.preloaded_src_csets); + cgroup_attach_lock(has_tasks); + + /* NULL dst indicates self on default hierarchy */ + ret = cgroup_migrate_prepare_dst(&mgctx); + if (ret) + goto out_finish; + + spin_lock_irq(&css_set_lock); + list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, + mg_src_preload_node) { + struct task_struct *task, *ntask; + + /* all tasks in src_csets need to be migrated */ + list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) + cgroup_migrate_add_task(task, &mgctx); + } + spin_unlock_irq(&css_set_lock); + + ret = cgroup_migrate_execute(&mgctx); +out_finish: + cgroup_migrate_finish(&mgctx); + cgroup_attach_unlock(has_tasks); + return ret; +} + +/** + * 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) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + struct cgroup_subsys *ss; + int ssid; + +restart: + cgroup_lock(); + + cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + DEFINE_WAIT(wait); + + if (!css || !percpu_ref_is_dying(&css->refcnt)) + continue; + + cgroup_get_live(dsct); + prepare_to_wait(&dsct->offline_waitq, &wait, + TASK_UNINTERRUPTIBLE); + + cgroup_unlock(); + schedule(); + finish_wait(&dsct->offline_waitq, &wait); + + cgroup_put(dsct); + goto restart; + } + } +} + +/** + * 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) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { + dsct->old_subtree_control = dsct->subtree_control; + dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; + dsct->old_dom_cgrp = dsct->dom_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) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { + dsct->subtree_control &= cgroup_control(dsct); + dsct->subtree_ss_mask = + cgroup_calc_subtree_ss_mask(dsct->subtree_control, + cgroup_ss_mask(dsct)); + } +} + +/** + * 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) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + + cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { + dsct->subtree_control = dsct->old_subtree_control; + dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; + dsct->dom_cgrp = dsct->old_dom_cgrp; + } +} + +static bool css_visible(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + + if (cgroup_control(cgrp) & (1 << ss->id)) + return true; + if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) + return false; + return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; +} + +/** + * 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) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + struct cgroup_subsys *ss; + int ssid, ret; + + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + + if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) + continue; + + if (!css) { + css = css_create(dsct, ss); + if (IS_ERR(css)) + return PTR_ERR(css); + } + + WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); + + if (css_visible(css)) { + ret = css_populate_dir(css); + if (ret) + return ret; + } + } + } + + return 0; +} + +/** + * 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) +{ + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + struct cgroup_subsys *ss; + int ssid; + + cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cgroup_css(dsct, ss); + + if (!css) + continue; + + WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); + + if (css->parent && + !(cgroup_ss_mask(dsct) & (1 << ss->id))) { + kill_css(css); + } else if (!css_visible(css)) { + css_clear_dir(css); + if (ss->css_reset) + ss->css_reset(css); + } + } + } +} + +/** + * 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) +{ + int ret; + + cgroup_propagate_control(cgrp); + + ret = cgroup_apply_control_enable(cgrp); + if (ret) + return ret; + + /* + * At this point, cgroup_e_css_by_mask() results reflect the new csses + * making the following cgroup_update_dfl_csses() properly update + * css associations of all tasks in the subtree. + */ + return cgroup_update_dfl_csses(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) +{ + if (ret) { + cgroup_restore_control(cgrp); + cgroup_propagate_control(cgrp); + } + + cgroup_apply_control_disable(cgrp); +} + +static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) +{ + u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask; + + /* if nothing is getting enabled, nothing to worry about */ + if (!enable) + return 0; + + /* can @cgrp host any resources? */ + if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) + return -EOPNOTSUPP; + + /* mixables don't care */ + if (cgroup_is_mixable(cgrp)) + return 0; + + if (domain_enable) { + /* can't enable domain controllers inside a thread subtree */ + if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) + return -EOPNOTSUPP; + } else { + /* + * Threaded controllers can handle internal competitions + * and are always allowed inside a (prospective) thread + * subtree. + */ + if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) + return 0; + } + + /* + * Controllers can't be enabled for a cgroup with tasks to avoid + * child cgroups competing against tasks. + */ + if (cgroup_has_tasks(cgrp)) + return -EBUSY; + + return 0; +} + +/* 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) +{ + u16 enable = 0, disable = 0; + struct cgroup *cgrp, *child; + struct cgroup_subsys *ss; + char *tok; + int ssid, ret; + + /* + * Parse input - space separated list of subsystem names prefixed + * with either + or -. + */ + buf = strstrip(buf); + while ((tok = strsep(&buf, " "))) { + if (tok[0] == '\0') + continue; + do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { + if (!cgroup_ssid_enabled(ssid) || + strcmp(tok + 1, ss->name)) + continue; + + if (*tok == '+') { + enable |= 1 << ssid; + disable &= ~(1 << ssid); + } else if (*tok == '-') { + disable |= 1 << ssid; + enable &= ~(1 << ssid); + } else { + return -EINVAL; + } + break; + } while_each_subsys_mask(); + if (ssid == CGROUP_SUBSYS_COUNT) + return -EINVAL; + } + + cgrp = cgroup_kn_lock_live(of->kn, true); + if (!cgrp) + return -ENODEV; + + for_each_subsys(ss, ssid) { + if (enable & (1 << ssid)) { + if (cgrp->subtree_control & (1 << ssid)) { + enable &= ~(1 << ssid); + continue; + } + + if (!(cgroup_control(cgrp) & (1 << ssid))) { + ret = -ENOENT; + goto out_unlock; + } + } else if (disable & (1 << ssid)) { + if (!(cgrp->subtree_control & (1 << ssid))) { + disable &= ~(1 << ssid); + continue; + } + + /* a child has it enabled? */ + cgroup_for_each_live_child(child, cgrp) { + if (child->subtree_control & (1 << ssid)) { + ret = -EBUSY; + goto out_unlock; + } + } + } + } + + if (!enable && !disable) { + ret = 0; + goto out_unlock; + } + + ret = cgroup_vet_subtree_control_enable(cgrp, enable); + if (ret) + goto out_unlock; + + /* save and update control masks and prepare csses */ + cgroup_save_control(cgrp); + + cgrp->subtree_control |= enable; + cgrp->subtree_control &= ~disable; + + ret = cgroup_apply_control(cgrp); + cgroup_finalize_control(cgrp, ret); + if (ret) + goto out_unlock; + + kernfs_activate(cgrp->kn); +out_unlock: + cgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +/** + * 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) +{ + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup *dom_cgrp = parent->dom_cgrp; + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; + int ret; + + lockdep_assert_held(&cgroup_mutex); + + /* noop if already threaded */ + if (cgroup_is_threaded(cgrp)) + return 0; + + /* + * If @cgroup is populated or has domain controllers enabled, it + * can't be switched. While the below cgroup_can_be_thread_root() + * test can catch the same conditions, that's only when @parent is + * not mixable, so let's check it explicitly. + */ + if (cgroup_is_populated(cgrp) || + cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) + return -EOPNOTSUPP; + + /* we're joining the parent's domain, ensure its validity */ + if (!cgroup_is_valid_domain(dom_cgrp) || + !cgroup_can_be_thread_root(dom_cgrp)) + return -EOPNOTSUPP; + + /* + * The following shouldn't cause actual migrations and should + * always succeed. + */ + cgroup_save_control(cgrp); + + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) + if (dsct == cgrp || cgroup_is_threaded(dsct)) + dsct->dom_cgrp = dom_cgrp; + + ret = cgroup_apply_control(cgrp); + if (!ret) + parent->nr_threaded_children++; + + cgroup_finalize_control(cgrp, ret); + return ret; +} + +static int cgroup_type_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + if (cgroup_is_threaded(cgrp)) + seq_puts(seq, "threaded\n"); + else if (!cgroup_is_valid_domain(cgrp)) + seq_puts(seq, "domain invalid\n"); + else if (cgroup_is_thread_root(cgrp)) + seq_puts(seq, "domain threaded\n"); + else + seq_puts(seq, "domain\n"); + + return 0; +} + +static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + int ret; + + /* only switching to threaded mode is supported */ + if (strcmp(strstrip(buf), "threaded")) + return -EINVAL; + + /* drain dying csses before we re-apply (threaded) subtree control */ + cgrp = cgroup_kn_lock_live(of->kn, true); + if (!cgrp) + return -ENOENT; + + /* threaded can only be enabled */ + ret = cgroup_enable_threaded(cgrp); + + cgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +static int cgroup_max_descendants_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + int descendants = READ_ONCE(cgrp->max_descendants); + + if (descendants == INT_MAX) + seq_puts(seq, "max\n"); + else + seq_printf(seq, "%d\n", descendants); + + return 0; +} + +static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + int descendants; + ssize_t ret; + + buf = strstrip(buf); + if (!strcmp(buf, "max")) { + descendants = INT_MAX; + } else { + ret = kstrtoint(buf, 0, &descendants); + if (ret) + return ret; + } + + if (descendants < 0) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + cgrp->max_descendants = descendants; + + cgroup_kn_unlock(of->kn); + + return nbytes; +} + +static int cgroup_max_depth_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + int depth = READ_ONCE(cgrp->max_depth); + + if (depth == INT_MAX) + seq_puts(seq, "max\n"); + else + seq_printf(seq, "%d\n", depth); + + return 0; +} + +static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + ssize_t ret; + int depth; + + buf = strstrip(buf); + if (!strcmp(buf, "max")) { + depth = INT_MAX; + } else { + ret = kstrtoint(buf, 0, &depth); + if (ret) + return ret; + } + + if (depth < 0) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + cgrp->max_depth = depth; + + cgroup_kn_unlock(of->kn); + + return nbytes; +} + +static int cgroup_events_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp)); + seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags)); + + return 0; +} + +static int cgroup_stat_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgroup = seq_css(seq)->cgroup; + + seq_printf(seq, "nr_descendants %d\n", + cgroup->nr_descendants); + seq_printf(seq, "nr_dying_descendants %d\n", + cgroup->nr_dying_descendants); + + return 0; +} + +static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq, + struct cgroup *cgrp, int ssid) +{ + struct cgroup_subsys *ss = cgroup_subsys[ssid]; + struct cgroup_subsys_state *css; + int ret; + + if (!ss->css_extra_stat_show) + return 0; + + css = cgroup_tryget_css(cgrp, ss); + if (!css) + return 0; + + ret = ss->css_extra_stat_show(seq, css); + css_put(css); + return ret; +} + +static int cpu_stat_show(struct seq_file *seq, void *v) +{ + struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; + int ret = 0; + + cgroup_base_stat_cputime_show(seq); +#ifdef CONFIG_CGROUP_SCHED + ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id); +#endif + return ret; +} + +#ifdef CONFIG_PSI +static int cgroup_io_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + return psi_show(seq, psi, PSI_IO); +} +static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + return psi_show(seq, psi, PSI_MEM); +} +static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + return psi_show(seq, psi, PSI_CPU); +} + +static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, enum psi_res res) +{ + struct cgroup_file_ctx *ctx = of->priv; + struct psi_trigger *new; + struct cgroup *cgrp; + struct psi_group *psi; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + cgroup_get(cgrp); + cgroup_kn_unlock(of->kn); + + /* Allow only one trigger per file descriptor */ + if (ctx->psi.trigger) { + cgroup_put(cgrp); + return -EBUSY; + } + + psi = cgroup_psi(cgrp); + new = psi_trigger_create(psi, buf, res, of->file, of); + if (IS_ERR(new)) { + cgroup_put(cgrp); + return PTR_ERR(new); + } + + smp_store_release(&ctx->psi.trigger, new); + cgroup_put(cgrp); + + return nbytes; +} + +static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return pressure_write(of, buf, nbytes, PSI_IO); +} + +static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return pressure_write(of, buf, nbytes, PSI_MEM); +} + +static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return pressure_write(of, buf, nbytes, PSI_CPU); +} + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + return psi_show(seq, psi, PSI_IRQ); +} + +static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return pressure_write(of, buf, nbytes, PSI_IRQ); +} +#endif + +static int cgroup_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + seq_printf(seq, "%d\n", psi->enabled); + + return 0; +} + +static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + ssize_t ret; + int enable; + struct cgroup *cgrp; + struct psi_group *psi; + + ret = kstrtoint(strstrip(buf), 0, &enable); + if (ret) + return ret; + + if (enable < 0 || enable > 1) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + psi = cgroup_psi(cgrp); + if (psi->enabled != enable) { + int i; + + /* show or hide {cpu,memory,io,irq}.pressure files */ + for (i = 0; i < NR_PSI_RESOURCES; i++) + cgroup_file_show(&cgrp->psi_files[i], enable); + + psi->enabled = enable; + if (enable) + psi_cgroup_restart(psi); + } + + cgroup_kn_unlock(of->kn); + + return nbytes; +} + +static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, + poll_table *pt) +{ + struct cgroup_file_ctx *ctx = of->priv; + + return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); +} + +static void cgroup_pressure_release(struct kernfs_open_file *of) +{ + struct cgroup_file_ctx *ctx = of->priv; + + psi_trigger_destroy(ctx->psi.trigger); +} + +bool cgroup_psi_enabled(void) +{ + if (static_branch_likely(&psi_disabled)) + return false; + + return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; +} + +#else /* CONFIG_PSI */ +bool cgroup_psi_enabled(void) +{ + return false; +} + +#endif /* CONFIG_PSI */ + +static int cgroup_freeze_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + seq_printf(seq, "%d\n", cgrp->freezer.freeze); + + return 0; +} + +static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + ssize_t ret; + int freeze; + + ret = kstrtoint(strstrip(buf), 0, &freeze); + if (ret) + return ret; + + if (freeze < 0 || freeze > 1) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + cgroup_freeze(cgrp, freeze); + + cgroup_kn_unlock(of->kn); + + return nbytes; +} + +static void __cgroup_kill(struct cgroup *cgrp) +{ + struct css_task_iter it; + struct task_struct *task; + + lockdep_assert_held(&cgroup_mutex); + + spin_lock_irq(&css_set_lock); + set_bit(CGRP_KILL, &cgrp->flags); + spin_unlock_irq(&css_set_lock); + + css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); + while ((task = css_task_iter_next(&it))) { + /* Ignore kernel threads here. */ + if (task->flags & PF_KTHREAD) + continue; + + /* Skip tasks that are already dying. */ + if (__fatal_signal_pending(task)) + continue; + + send_sig(SIGKILL, task, 0); + } + css_task_iter_end(&it); + + spin_lock_irq(&css_set_lock); + clear_bit(CGRP_KILL, &cgrp->flags); + spin_unlock_irq(&css_set_lock); +} + +static void cgroup_kill(struct cgroup *cgrp) +{ + struct cgroup_subsys_state *css; + struct cgroup *dsct; + + lockdep_assert_held(&cgroup_mutex); + + cgroup_for_each_live_descendant_pre(dsct, css, cgrp) + __cgroup_kill(dsct); +} + +static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + ssize_t ret = 0; + int kill; + struct cgroup *cgrp; + + ret = kstrtoint(strstrip(buf), 0, &kill); + if (ret) + return ret; + + if (kill != 1) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + /* + * Killing is a process directed operation, i.e. the whole thread-group + * is taken down so act like we do for cgroup.procs and only make this + * writable in non-threaded cgroups. + */ + if (cgroup_is_threaded(cgrp)) + ret = -EOPNOTSUPP; + else + cgroup_kill(cgrp); + + cgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +static int cgroup_file_open(struct kernfs_open_file *of) +{ + struct cftype *cft = of_cft(of); + struct cgroup_file_ctx *ctx; + int ret; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->ns = current->nsproxy->cgroup_ns; + get_cgroup_ns(ctx->ns); + of->priv = ctx; + + if (!cft->open) + return 0; + + ret = cft->open(of); + if (ret) { + put_cgroup_ns(ctx->ns); + kfree(ctx); + } + return ret; +} + +static void cgroup_file_release(struct kernfs_open_file *of) +{ + struct cftype *cft = of_cft(of); + struct cgroup_file_ctx *ctx = of->priv; + + if (cft->release) + cft->release(of); + put_cgroup_ns(ctx->ns); + kfree(ctx); +} + +static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup *cgrp = of->kn->parent->priv; + struct cftype *cft = of_cft(of); + struct cgroup_subsys_state *css; + int ret; + + if (!nbytes) + return 0; + + /* + * If namespaces are delegation boundaries, disallow writes to + * files in an non-init namespace root from inside the namespace + * except for the files explicitly marked delegatable - + * cgroup.procs and cgroup.subtree_control. + */ + if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && + !(cft->flags & CFTYPE_NS_DELEGATABLE) && + ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) + return -EPERM; + + if (cft->write) + return cft->write(of, buf, nbytes, off); + + /* + * kernfs guarantees that a file isn't deleted with operations in + * flight, which means that the matching css is and stays alive and + * doesn't need to be pinned. The RCU locking is not necessary + * either. It's just for the convenience of using cgroup_css(). + */ + rcu_read_lock(); + css = cgroup_css(cgrp, cft->ss); + rcu_read_unlock(); + + if (cft->write_u64) { + unsigned long long v; + ret = kstrtoull(buf, 0, &v); + if (!ret) + ret = cft->write_u64(css, cft, v); + } else if (cft->write_s64) { + long long v; + ret = kstrtoll(buf, 0, &v); + if (!ret) + ret = cft->write_s64(css, cft, v); + } else { + ret = -EINVAL; + } + + return ret ?: nbytes; +} + +static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) +{ + struct cftype *cft = of_cft(of); + + if (cft->poll) + return cft->poll(of, pt); + + return kernfs_generic_poll(of, pt); +} + +static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) +{ + return seq_cft(seq)->seq_start(seq, ppos); +} + +static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) +{ + return seq_cft(seq)->seq_next(seq, v, ppos); +} + +static void cgroup_seqfile_stop(struct seq_file *seq, void *v) +{ + if (seq_cft(seq)->seq_stop) + seq_cft(seq)->seq_stop(seq, v); +} + +static int cgroup_seqfile_show(struct seq_file *m, void *arg) +{ + struct cftype *cft = seq_cft(m); + struct cgroup_subsys_state *css = seq_css(m); + + if (cft->seq_show) + return cft->seq_show(m, arg); + + if (cft->read_u64) + seq_printf(m, "%llu\n", cft->read_u64(css, cft)); + else if (cft->read_s64) + seq_printf(m, "%lld\n", cft->read_s64(css, cft)); + else + return -EINVAL; + return 0; +} + +static struct kernfs_ops cgroup_kf_single_ops = { + .atomic_write_len = PAGE_SIZE, + .open = cgroup_file_open, + .release = cgroup_file_release, + .write = cgroup_file_write, + .poll = cgroup_file_poll, + .seq_show = cgroup_seqfile_show, +}; + +static struct kernfs_ops cgroup_kf_ops = { + .atomic_write_len = PAGE_SIZE, + .open = cgroup_file_open, + .release = cgroup_file_release, + .write = cgroup_file_write, + .poll = cgroup_file_poll, + .seq_start = cgroup_seqfile_start, + .seq_next = cgroup_seqfile_next, + .seq_stop = cgroup_seqfile_stop, + .seq_show = cgroup_seqfile_show, +}; + +/* set uid and gid of cgroup dirs and files to that of the creator */ +static int cgroup_kn_set_ugid(struct kernfs_node *kn) +{ + struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = current_fsuid(), + .ia_gid = current_fsgid(), }; + + if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && + gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) + return 0; + + return kernfs_setattr(kn, &iattr); +} + +static void cgroup_file_notify_timer(struct timer_list *timer) +{ + cgroup_file_notify(container_of(timer, struct cgroup_file, + notify_timer)); +} + +static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, + struct cftype *cft) +{ + char name[CGROUP_FILE_NAME_MAX]; + struct kernfs_node *kn; + struct lock_class_key *key = NULL; + int ret; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + key = &cft->lockdep_key; +#endif + kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), + cgroup_file_mode(cft), + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + 0, cft->kf_ops, cft, + NULL, key); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = cgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } + + if (cft->file_offset) { + struct cgroup_file *cfile = (void *)css + cft->file_offset; + + timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); + + spin_lock_irq(&cgroup_file_kn_lock); + cfile->kn = kn; + spin_unlock_irq(&cgroup_file_kn_lock); + } + + return 0; +} + +/** + * 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) +{ + struct cftype *cft, *cft_end = NULL; + int ret = 0; + + lockdep_assert_held(&cgroup_mutex); + +restart: + for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { + /* does cft->flags tell us to skip this file on @cgrp? */ + if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) + continue; + if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) + continue; + if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) + continue; + if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) + continue; + if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug) + continue; + if (is_add) { + ret = cgroup_add_file(css, cgrp, cft); + if (ret) { + pr_warn("%s: failed to add %s, err=%d\n", + __func__, cft->name, ret); + cft_end = cft; + is_add = false; + goto restart; + } + } else { + cgroup_rm_file(cgrp, cft); + } + } + return ret; +} + +static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) +{ + struct cgroup_subsys *ss = cfts[0].ss; + struct cgroup *root = &ss->root->cgrp; + struct cgroup_subsys_state *css; + int ret = 0; + + lockdep_assert_held(&cgroup_mutex); + + /* add/rm files for all cgroups created before */ + css_for_each_descendant_pre(css, cgroup_css(root, ss)) { + struct cgroup *cgrp = css->cgroup; + + if (!(css->flags & CSS_VISIBLE)) + continue; + + ret = cgroup_addrm_files(css, cgrp, cfts, is_add); + if (ret) + break; + } + + if (is_add && !ret) + kernfs_activate(root->kn); + return ret; +} + +static void cgroup_exit_cftypes(struct cftype *cfts) +{ + struct cftype *cft; + + for (cft = cfts; cft->name[0] != '\0'; cft++) { + /* free copy for custom atomic_write_len, see init_cftypes() */ + if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) + kfree(cft->kf_ops); + cft->kf_ops = NULL; + cft->ss = NULL; + + /* revert flags set by cgroup core while adding @cfts */ + cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL | + __CFTYPE_ADDED); + } +} + +static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +{ + struct cftype *cft; + int ret = 0; + + for (cft = cfts; cft->name[0] != '\0'; cft++) { + struct kernfs_ops *kf_ops; + + WARN_ON(cft->ss || cft->kf_ops); + + if (cft->flags & __CFTYPE_ADDED) { + ret = -EBUSY; + break; + } + + if (cft->seq_start) + kf_ops = &cgroup_kf_ops; + else + kf_ops = &cgroup_kf_single_ops; + + /* + * Ugh... if @cft wants a custom max_write_len, we need to + * make a copy of kf_ops to set its atomic_write_len. + */ + if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { + kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); + if (!kf_ops) { + ret = -ENOMEM; + break; + } + kf_ops->atomic_write_len = cft->max_write_len; + } + + cft->kf_ops = kf_ops; + cft->ss = ss; + cft->flags |= __CFTYPE_ADDED; + } + + if (ret) + cgroup_exit_cftypes(cfts); + return ret; +} + +static int cgroup_rm_cftypes_locked(struct cftype *cfts) +{ + lockdep_assert_held(&cgroup_mutex); + + list_del(&cfts->node); + cgroup_apply_cftypes(cfts, false); + cgroup_exit_cftypes(cfts); + return 0; +} + +/** + * 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) +{ + int ret; + + if (!cfts || cfts[0].name[0] == '\0') + return 0; + + if (!(cfts[0].flags & __CFTYPE_ADDED)) + return -ENOENT; + + cgroup_lock(); + ret = cgroup_rm_cftypes_locked(cfts); + cgroup_unlock(); + return ret; +} + +/** + * 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) +{ + int ret; + + if (!cgroup_ssid_enabled(ss->id)) + return 0; + + if (!cfts || cfts[0].name[0] == '\0') + return 0; + + ret = cgroup_init_cftypes(ss, cfts); + if (ret) + return ret; + + cgroup_lock(); + + list_add_tail(&cfts->node, &ss->cfts); + ret = cgroup_apply_cftypes(cfts, true); + if (ret) + cgroup_rm_cftypes_locked(cfts); + + cgroup_unlock(); + return ret; +} + +/** + * 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) +{ + struct cftype *cft; + + for (cft = cfts; cft && cft->name[0] != '\0'; cft++) + cft->flags |= __CFTYPE_ONLY_ON_DFL; + return cgroup_add_cftypes(ss, 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) +{ + struct cftype *cft; + + for (cft = cfts; cft && cft->name[0] != '\0'; cft++) + cft->flags |= __CFTYPE_NOT_ON_DFL; + return cgroup_add_cftypes(ss, 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) +{ + unsigned long flags; + + spin_lock_irqsave(&cgroup_file_kn_lock, flags); + if (cfile->kn) { + unsigned long last = cfile->notified_at; + unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV; + + if (time_in_range(jiffies, last, next)) { + timer_reduce(&cfile->notify_timer, next); + } else { + kernfs_notify(cfile->kn); + cfile->notified_at = jiffies; + } + } + spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); +} + +/** + * 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) +{ + struct kernfs_node *kn; + + spin_lock_irq(&cgroup_file_kn_lock); + kn = cfile->kn; + kernfs_get(kn); + spin_unlock_irq(&cgroup_file_kn_lock); + + if (kn) + kernfs_show(kn, show); + + kernfs_put(kn); +} + +/** + * 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) +{ + struct cgroup_subsys_state *next; + + cgroup_assert_mutex_or_rcu_locked(); + + /* + * @pos could already have been unlinked from the sibling list. + * Once a cgroup is removed, its ->sibling.next is no longer + * updated when its next sibling changes. CSS_RELEASED is set when + * @pos is taken off list, at which time its next pointer is valid, + * and, as releases are serialized, the one pointed to by the next + * pointer is guaranteed to not have started release yet. This + * implies that if we observe !CSS_RELEASED on @pos in this RCU + * critical section, the one pointed to by its next pointer is + * guaranteed to not have finished its RCU grace period even if we + * have dropped rcu_read_lock() in-between iterations. + * + * If @pos has CSS_RELEASED set, its next pointer can't be + * dereferenced; however, as each css is given a monotonically + * increasing unique serial number and always appended to the + * sibling list, the next one can be found by walking the parent's + * children until the first css with higher serial number than + * @pos's. While this path can be slower, it happens iff iteration + * races against release and the race window is very small. + */ + if (!pos) { + next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); + } else if (likely(!(pos->flags & CSS_RELEASED))) { + next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); + } else { + list_for_each_entry_rcu(next, &parent->children, sibling, + lockdep_is_held(&cgroup_mutex)) + if (next->serial_nr > pos->serial_nr) + break; + } + + /* + * @next, if not pointing to the head, can be dereferenced and is + * the next sibling. + */ + if (&next->sibling != &parent->children) + return next; + return NULL; +} + +/** + * 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) +{ + struct cgroup_subsys_state *next; + + cgroup_assert_mutex_or_rcu_locked(); + + /* if first iteration, visit @root */ + if (!pos) + return root; + + /* visit the first child if exists */ + next = css_next_child(NULL, pos); + if (next) + return next; + + /* no child, visit my or the closest ancestor's next sibling */ + while (pos != root) { + next = css_next_child(pos, pos->parent); + if (next) + return next; + pos = pos->parent; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(css_next_descendant_pre); + +/** + * 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) +{ + struct cgroup_subsys_state *last, *tmp; + + cgroup_assert_mutex_or_rcu_locked(); + + do { + last = pos; + /* ->prev isn't RCU safe, walk ->next till the end */ + pos = NULL; + css_for_each_child(tmp, last) + pos = tmp; + } while (pos); + + return last; +} + +static struct cgroup_subsys_state * +css_leftmost_descendant(struct cgroup_subsys_state *pos) +{ + struct cgroup_subsys_state *last; + + do { + last = pos; + pos = css_next_child(NULL, pos); + } while (pos); + + return last; +} + +/** + * 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) +{ + struct cgroup_subsys_state *next; + + cgroup_assert_mutex_or_rcu_locked(); + + /* if first iteration, visit leftmost descendant which may be @root */ + if (!pos) + return css_leftmost_descendant(root); + + /* if we visited @root, we're done */ + if (pos == root) + return NULL; + + /* if there's an unvisited sibling, visit its leftmost descendant */ + next = css_next_child(pos, pos->parent); + if (next) + return css_leftmost_descendant(next); + + /* no sibling left, visit parent */ + return pos->parent; +} + +/** + * 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) +{ + struct cgroup_subsys_state *child; + bool ret = false; + + rcu_read_lock(); + css_for_each_child(child, css) { + if (child->flags & CSS_ONLINE) { + ret = true; + break; + } + } + rcu_read_unlock(); + return ret; +} + +static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) +{ + struct list_head *l; + struct cgrp_cset_link *link; + struct css_set *cset; + + lockdep_assert_held(&css_set_lock); + + /* find the next threaded cset */ + if (it->tcset_pos) { + l = it->tcset_pos->next; + + if (l != it->tcset_head) { + it->tcset_pos = l; + return container_of(l, struct css_set, + threaded_csets_node); + } + + it->tcset_pos = NULL; + } + + /* find the next cset */ + l = it->cset_pos; + l = l->next; + if (l == it->cset_head) { + it->cset_pos = NULL; + return NULL; + } + + if (it->ss) { + cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); + } else { + link = list_entry(l, struct cgrp_cset_link, cset_link); + cset = link->cset; + } + + it->cset_pos = l; + + /* initialize threaded css_set walking */ + if (it->flags & CSS_TASK_ITER_THREADED) { + if (it->cur_dcset) + put_css_set_locked(it->cur_dcset); + it->cur_dcset = cset; + get_css_set(cset); + + it->tcset_head = &cset->threaded_csets; + it->tcset_pos = &cset->threaded_csets; + } + + return cset; +} + +/** + * 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) +{ + struct css_set *cset; + + lockdep_assert_held(&css_set_lock); + + /* Advance to the next non-empty css_set and find first non-empty tasks list*/ + while ((cset = css_task_iter_next_css_set(it))) { + if (!list_empty(&cset->tasks)) { + it->cur_tasks_head = &cset->tasks; + break; + } else if (!list_empty(&cset->mg_tasks)) { + it->cur_tasks_head = &cset->mg_tasks; + break; + } else if (!list_empty(&cset->dying_tasks)) { + it->cur_tasks_head = &cset->dying_tasks; + break; + } + } + if (!cset) { + it->task_pos = NULL; + return; + } + it->task_pos = it->cur_tasks_head->next; + + /* + * We don't keep css_sets locked across iteration steps and thus + * need to take steps to ensure that iteration can be resumed after + * the lock is re-acquired. Iteration is performed at two levels - + * css_sets and tasks in them. + * + * Once created, a css_set never leaves its cgroup lists, so a + * pinned css_set is guaranteed to stay put and we can resume + * iteration afterwards. + * + * Tasks may leave @cset across iteration steps. This is resolved + * by registering each iterator with the css_set currently being + * walked and making css_set_move_task() advance iterators whose + * next task is leaving. + */ + if (it->cur_cset) { + list_del(&it->iters_node); + put_css_set_locked(it->cur_cset); + } + get_css_set(cset); + it->cur_cset = cset; + list_add(&it->iters_node, &cset->task_iters); +} + +static void css_task_iter_skip(struct css_task_iter *it, + struct task_struct *task) +{ + lockdep_assert_held(&css_set_lock); + + if (it->task_pos == &task->cg_list) { + it->task_pos = it->task_pos->next; + it->flags |= CSS_TASK_ITER_SKIPPED; + } +} + +static void css_task_iter_advance(struct css_task_iter *it) +{ + struct task_struct *task; + + lockdep_assert_held(&css_set_lock); +repeat: + if (it->task_pos) { + /* + * Advance iterator to find next entry. We go through cset + * tasks, mg_tasks and dying_tasks, when consumed we move onto + * the next cset. + */ + if (it->flags & CSS_TASK_ITER_SKIPPED) + it->flags &= ~CSS_TASK_ITER_SKIPPED; + else + it->task_pos = it->task_pos->next; + + if (it->task_pos == &it->cur_cset->tasks) { + it->cur_tasks_head = &it->cur_cset->mg_tasks; + it->task_pos = it->cur_tasks_head->next; + } + if (it->task_pos == &it->cur_cset->mg_tasks) { + it->cur_tasks_head = &it->cur_cset->dying_tasks; + it->task_pos = it->cur_tasks_head->next; + } + if (it->task_pos == &it->cur_cset->dying_tasks) + css_task_iter_advance_css_set(it); + } else { + /* called from start, proceed to the first cset */ + css_task_iter_advance_css_set(it); + } + + if (!it->task_pos) + return; + + task = list_entry(it->task_pos, struct task_struct, cg_list); + + if (it->flags & CSS_TASK_ITER_PROCS) { + /* if PROCS, skip over tasks which aren't group leaders */ + if (!thread_group_leader(task)) + goto repeat; + + /* and dying leaders w/o live member threads */ + if (it->cur_tasks_head == &it->cur_cset->dying_tasks && + !atomic_read(&task->signal->live)) + goto repeat; + } else { + /* skip all dying ones */ + if (it->cur_tasks_head == &it->cur_cset->dying_tasks) + goto repeat; + } +} + +/** + * 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) +{ + memset(it, 0, sizeof(*it)); + + spin_lock_irq(&css_set_lock); + + it->ss = css->ss; + it->flags = flags; + + if (CGROUP_HAS_SUBSYS_CONFIG && it->ss) + it->cset_pos = &css->cgroup->e_csets[css->ss->id]; + else + it->cset_pos = &css->cgroup->cset_links; + + it->cset_head = it->cset_pos; + + css_task_iter_advance(it); + + spin_unlock_irq(&css_set_lock); +} + +/** + * 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) +{ + if (it->cur_task) { + put_task_struct(it->cur_task); + it->cur_task = NULL; + } + + spin_lock_irq(&css_set_lock); + + /* @it may be half-advanced by skips, finish advancing */ + if (it->flags & CSS_TASK_ITER_SKIPPED) + css_task_iter_advance(it); + + if (it->task_pos) { + it->cur_task = list_entry(it->task_pos, struct task_struct, + cg_list); + get_task_struct(it->cur_task); + css_task_iter_advance(it); + } + + spin_unlock_irq(&css_set_lock); + + return it->cur_task; +} + +/** + * 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) +{ + if (it->cur_cset) { + spin_lock_irq(&css_set_lock); + list_del(&it->iters_node); + put_css_set_locked(it->cur_cset); + spin_unlock_irq(&css_set_lock); + } + + if (it->cur_dcset) + put_css_set(it->cur_dcset); + + if (it->cur_task) + put_task_struct(it->cur_task); +} + +static void cgroup_procs_release(struct kernfs_open_file *of) +{ + struct cgroup_file_ctx *ctx = of->priv; + + if (ctx->procs.started) + css_task_iter_end(&ctx->procs.iter); +} + +static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct kernfs_open_file *of = s->private; + struct cgroup_file_ctx *ctx = of->priv; + + if (pos) + (*pos)++; + + return css_task_iter_next(&ctx->procs.iter); +} + +static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, + unsigned int iter_flags) +{ + struct kernfs_open_file *of = s->private; + struct cgroup *cgrp = seq_css(s)->cgroup; + struct cgroup_file_ctx *ctx = of->priv; + struct css_task_iter *it = &ctx->procs.iter; + + /* + * When a seq_file is seeked, it's always traversed sequentially + * from position 0, so we can simply keep iterating on !0 *pos. + */ + if (!ctx->procs.started) { + if (WARN_ON_ONCE((*pos))) + return ERR_PTR(-EINVAL); + css_task_iter_start(&cgrp->self, iter_flags, it); + ctx->procs.started = true; + } else if (!(*pos)) { + css_task_iter_end(it); + css_task_iter_start(&cgrp->self, iter_flags, it); + } else + return it->cur_task; + + return cgroup_procs_next(s, NULL, NULL); +} + +static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) +{ + struct cgroup *cgrp = seq_css(s)->cgroup; + + /* + * All processes of a threaded subtree belong to the domain cgroup + * of the subtree. Only threads can be distributed across the + * subtree. Reject reads on cgroup.procs in the subtree proper. + * They're always empty anyway. + */ + if (cgroup_is_threaded(cgrp)) + return ERR_PTR(-EOPNOTSUPP); + + return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | + CSS_TASK_ITER_THREADED); +} + +static int cgroup_procs_show(struct seq_file *s, void *v) +{ + seq_printf(s, "%d\n", task_pid_vnr(v)); + return 0; +} + +static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) +{ + int ret; + struct inode *inode; + + lockdep_assert_held(&cgroup_mutex); + + inode = kernfs_get_inode(sb, cgrp->procs_file.kn); + if (!inode) + return -ENOMEM; + + ret = inode_permission(&init_user_ns, inode, MAY_WRITE); + iput(inode); + return ret; +} + +static int cgroup_procs_write_permission(struct cgroup *src_cgrp, + struct cgroup *dst_cgrp, + struct super_block *sb, + struct cgroup_namespace *ns) +{ + struct cgroup *com_cgrp = src_cgrp; + int ret; + + lockdep_assert_held(&cgroup_mutex); + + /* find the common ancestor */ + while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) + com_cgrp = cgroup_parent(com_cgrp); + + /* %current should be authorized to migrate to the common ancestor */ + ret = cgroup_may_write(com_cgrp, sb); + if (ret) + return ret; + + /* + * If namespaces are delegation boundaries, %current must be able + * to see both source and destination cgroups from its namespace. + */ + if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && + (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || + !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) + return -ENOENT; + + return 0; +} + +static int cgroup_attach_permissions(struct cgroup *src_cgrp, + struct cgroup *dst_cgrp, + struct super_block *sb, bool threadgroup, + struct cgroup_namespace *ns) +{ + int ret = 0; + + ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); + if (ret) + return ret; + + ret = cgroup_migrate_vet_dst(dst_cgrp); + if (ret) + return ret; + + if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) + ret = -EOPNOTSUPP; + + return ret; +} + +static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, + bool threadgroup) +{ + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup *src_cgrp, *dst_cgrp; + struct task_struct *task; + const struct cred *saved_cred; + ssize_t ret; + bool threadgroup_locked; + + dst_cgrp = cgroup_kn_lock_live(of->kn, false); + if (!dst_cgrp) + return -ENODEV; + + task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); + ret = PTR_ERR_OR_ZERO(task); + if (ret) + goto out_unlock; + + /* find the source cgroup */ + spin_lock_irq(&css_set_lock); + src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); + spin_unlock_irq(&css_set_lock); + + /* + * Process and thread migrations follow same delegation rule. Check + * permissions using the credentials from file open to protect against + * inherited fd attacks. + */ + saved_cred = override_creds(of->file->f_cred); + ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, + of->file->f_path.dentry->d_sb, + threadgroup, ctx->ns); + revert_creds(saved_cred); + if (ret) + goto out_finish; + + ret = cgroup_attach_task(dst_cgrp, task, threadgroup); + +out_finish: + cgroup_procs_write_finish(task, threadgroup_locked); +out_unlock: + cgroup_kn_unlock(of->kn); + + return ret; +} + +static ssize_t cgroup_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup_procs_write(of, buf, true) ?: nbytes; +} + +static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) +{ + return __cgroup_procs_start(s, pos, 0); +} + +static ssize_t cgroup_threads_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup_procs_write(of, buf, false) ?: nbytes; +} + +/* cgroup core interface files for the default hierarchy */ +static struct cftype cgroup_base_files[] = { + { + .name = "cgroup.type", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_type_show, + .write = cgroup_type_write, + }, + { + .name = "cgroup.procs", + .flags = CFTYPE_NS_DELEGATABLE, + .file_offset = offsetof(struct cgroup, procs_file), + .release = cgroup_procs_release, + .seq_start = cgroup_procs_start, + .seq_next = cgroup_procs_next, + .seq_show = cgroup_procs_show, + .write = cgroup_procs_write, + }, + { + .name = "cgroup.threads", + .flags = CFTYPE_NS_DELEGATABLE, + .release = cgroup_procs_release, + .seq_start = cgroup_threads_start, + .seq_next = cgroup_procs_next, + .seq_show = cgroup_procs_show, + .write = cgroup_threads_write, + }, + { + .name = "cgroup.controllers", + .seq_show = cgroup_controllers_show, + }, + { + .name = "cgroup.subtree_control", + .flags = CFTYPE_NS_DELEGATABLE, + .seq_show = cgroup_subtree_control_show, + .write = cgroup_subtree_control_write, + }, + { + .name = "cgroup.events", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct cgroup, events_file), + .seq_show = cgroup_events_show, + }, + { + .name = "cgroup.max.descendants", + .seq_show = cgroup_max_descendants_show, + .write = cgroup_max_descendants_write, + }, + { + .name = "cgroup.max.depth", + .seq_show = cgroup_max_depth_show, + .write = cgroup_max_depth_write, + }, + { + .name = "cgroup.stat", + .seq_show = cgroup_stat_show, + }, + { + .name = "cgroup.freeze", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_freeze_show, + .write = cgroup_freeze_write, + }, + { + .name = "cgroup.kill", + .flags = CFTYPE_NOT_ON_ROOT, + .write = cgroup_kill_write, + }, + { + .name = "cpu.stat", + .seq_show = cpu_stat_show, + }, + { } /* terminate */ +}; + +static struct cftype cgroup_psi_files[] = { +#ifdef CONFIG_PSI + { + .name = "io.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), + .seq_show = cgroup_io_pressure_show, + .write = cgroup_io_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, + { + .name = "memory.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), + .seq_show = cgroup_memory_pressure_show, + .write = cgroup_memory_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, + { + .name = "cpu.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), + .seq_show = cgroup_cpu_pressure_show, + .write = cgroup_cpu_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + { + .name = "irq.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), + .seq_show = cgroup_irq_pressure_show, + .write = cgroup_irq_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, +#endif + { + .name = "cgroup.pressure", + .seq_show = cgroup_pressure_show, + .write = cgroup_pressure_write, + }, +#endif /* CONFIG_PSI */ + { } /* terminate */ +}; + +/* + * 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_work_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) +{ + struct cgroup_subsys_state *css = container_of(to_rcu_work(work), + struct cgroup_subsys_state, destroy_rwork); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + + percpu_ref_exit(&css->refcnt); + + if (ss) { + /* css free path */ + struct cgroup_subsys_state *parent = css->parent; + int id = css->id; + + ss->css_free(css); + cgroup_idr_remove(&ss->css_idr, id); + cgroup_put(cgrp); + + if (parent) + css_put(parent); + } else { + /* cgroup free path */ + atomic_dec(&cgrp->root->nr_cgrps); + cgroup1_pidlist_destroy_all(cgrp); + cancel_work_sync(&cgrp->release_agent_work); + + if (cgroup_parent(cgrp)) { + /* + * We get a ref to the parent, and put the ref when + * this cgroup is being freed, so it's guaranteed + * that the parent won't be destroyed before its + * children. + */ + cgroup_put(cgroup_parent(cgrp)); + kernfs_put(cgrp->kn); + psi_cgroup_free(cgrp); + cgroup_rstat_exit(cgrp); + kfree(cgrp); + } else { + /* + * This is root cgroup's refcnt reaching zero, + * which indicates that the root should be + * released. + */ + cgroup_destroy_root(cgrp->root); + } + } +} + +static void css_release_work_fn(struct work_struct *work) +{ + struct cgroup_subsys_state *css = + container_of(work, struct cgroup_subsys_state, destroy_work); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + + cgroup_lock(); + + css->flags |= CSS_RELEASED; + list_del_rcu(&css->sibling); + + if (ss) { + /* css release path */ + if (!list_empty(&css->rstat_css_node)) { + cgroup_rstat_flush(cgrp); + list_del_rcu(&css->rstat_css_node); + } + + cgroup_idr_replace(&ss->css_idr, NULL, css->id); + if (ss->css_released) + ss->css_released(css); + } else { + struct cgroup *tcgrp; + + /* cgroup release path */ + TRACE_CGROUP_PATH(release, cgrp); + + cgroup_rstat_flush(cgrp); + + spin_lock_irq(&css_set_lock); + for (tcgrp = cgroup_parent(cgrp); tcgrp; + tcgrp = cgroup_parent(tcgrp)) + tcgrp->nr_dying_descendants--; + spin_unlock_irq(&css_set_lock); + + /* + * There are two control paths which try to determine + * cgroup from dentry without going through kernfs - + * cgroupstats_build() and css_tryget_online_from_dir(). + * Those are supported by RCU protecting clearing of + * cgrp->kn->priv backpointer. + */ + if (cgrp->kn) + RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, + NULL); + } + + cgroup_unlock(); + + INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); + queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); +} + +static void css_release(struct percpu_ref *ref) +{ + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + + INIT_WORK(&css->destroy_work, css_release_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); +} + +static void init_and_link_css(struct cgroup_subsys_state *css, + struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + lockdep_assert_held(&cgroup_mutex); + + cgroup_get_live(cgrp); + + memset(css, 0, sizeof(*css)); + css->cgroup = cgrp; + css->ss = ss; + css->id = -1; + INIT_LIST_HEAD(&css->sibling); + INIT_LIST_HEAD(&css->children); + INIT_LIST_HEAD(&css->rstat_css_node); + css->serial_nr = css_serial_nr_next++; + atomic_set(&css->online_cnt, 0); + + if (cgroup_parent(cgrp)) { + css->parent = cgroup_css(cgroup_parent(cgrp), ss); + css_get(css->parent); + } + + if (ss->css_rstat_flush) + list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list); + + BUG_ON(cgroup_css(cgrp, ss)); +} + +/* invoke ->css_online() on a new CSS and mark it online if successful */ +static int online_css(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys *ss = css->ss; + int ret = 0; + + lockdep_assert_held(&cgroup_mutex); + + if (ss->css_online) + ret = ss->css_online(css); + if (!ret) { + css->flags |= CSS_ONLINE; + rcu_assign_pointer(css->cgroup->subsys[ss->id], css); + + atomic_inc(&css->online_cnt); + if (css->parent) + atomic_inc(&css->parent->online_cnt); + } + return ret; +} + +/* if the CSS is online, invoke ->css_offline() on it and mark it offline */ +static void offline_css(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys *ss = css->ss; + + lockdep_assert_held(&cgroup_mutex); + + if (!(css->flags & CSS_ONLINE)) + return; + + if (ss->css_offline) + ss->css_offline(css); + + css->flags &= ~CSS_ONLINE; + RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); + + wake_up_all(&css->cgroup->offline_waitq); +} + +/** + * 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) +{ + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); + struct cgroup_subsys_state *css; + int err; + + lockdep_assert_held(&cgroup_mutex); + + css = ss->css_alloc(parent_css); + if (!css) + css = ERR_PTR(-ENOMEM); + if (IS_ERR(css)) + return css; + + init_and_link_css(css, ss, cgrp); + + err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); + if (err) + goto err_free_css; + + err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); + if (err < 0) + goto err_free_css; + css->id = err; + + /* @css is ready to be brought online now, make it visible */ + list_add_tail_rcu(&css->sibling, &parent_css->children); + cgroup_idr_replace(&ss->css_idr, css, css->id); + + err = online_css(css); + if (err) + goto err_list_del; + + return css; + +err_list_del: + list_del_rcu(&css->sibling); +err_free_css: + list_del_rcu(&css->rstat_css_node); + INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); + queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); + return ERR_PTR(err); +} + +/* + * The returned cgroup is fully initialized including its control mask, but + * it isn't associated with its kernfs_node and doesn't have the control + * mask applied. + */ +static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, + umode_t mode) +{ + struct cgroup_root *root = parent->root; + struct cgroup *cgrp, *tcgrp; + struct kernfs_node *kn; + int level = parent->level + 1; + int ret; + + /* allocate the cgroup and its ID, 0 is reserved for the root */ + cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); + if (!cgrp) + return ERR_PTR(-ENOMEM); + + ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); + if (ret) + goto out_free_cgrp; + + ret = cgroup_rstat_init(cgrp); + if (ret) + goto out_cancel_ref; + + /* create the directory */ + kn = kernfs_create_dir(parent->kn, name, mode, cgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); + goto out_stat_exit; + } + cgrp->kn = kn; + + init_cgroup_housekeeping(cgrp); + + cgrp->self.parent = &parent->self; + cgrp->root = root; + cgrp->level = level; + + ret = psi_cgroup_alloc(cgrp); + if (ret) + goto out_kernfs_remove; + + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_psi_free; + + /* + * New cgroup inherits effective freeze counter, and + * if the parent has to be frozen, the child has too. + */ + cgrp->freezer.e_freeze = parent->freezer.e_freeze; + if (cgrp->freezer.e_freeze) { + /* + * Set the CGRP_FREEZE flag, so when a process will be + * attached to the child cgroup, it will become frozen. + * At this point the new cgroup is unpopulated, so we can + * consider it frozen immediately. + */ + set_bit(CGRP_FREEZE, &cgrp->flags); + set_bit(CGRP_FROZEN, &cgrp->flags); + } + + spin_lock_irq(&css_set_lock); + for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { + cgrp->ancestors[tcgrp->level] = tcgrp; + + if (tcgrp != cgrp) { + tcgrp->nr_descendants++; + + /* + * If the new cgroup is frozen, all ancestor cgroups + * get a new frozen descendant, but their state can't + * change because of this. + */ + if (cgrp->freezer.e_freeze) + tcgrp->freezer.nr_frozen_descendants++; + } + } + spin_unlock_irq(&css_set_lock); + + if (notify_on_release(parent)) + set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); + + if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); + + cgrp->self.serial_nr = css_serial_nr_next++; + + /* allocation complete, commit to creation */ + list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); + atomic_inc(&root->nr_cgrps); + cgroup_get_live(parent); + + /* + * On the default hierarchy, a child doesn't automatically inherit + * subtree_control from the parent. Each is configured manually. + */ + if (!cgroup_on_dfl(cgrp)) + cgrp->subtree_control = cgroup_control(cgrp); + + cgroup_propagate_control(cgrp); + + return cgrp; + +out_psi_free: + psi_cgroup_free(cgrp); +out_kernfs_remove: + kernfs_remove(cgrp->kn); +out_stat_exit: + cgroup_rstat_exit(cgrp); +out_cancel_ref: + percpu_ref_exit(&cgrp->self.refcnt); +out_free_cgrp: + kfree(cgrp); + return ERR_PTR(ret); +} + +static bool cgroup_check_hierarchy_limits(struct cgroup *parent) +{ + struct cgroup *cgroup; + int ret = false; + int level = 1; + + lockdep_assert_held(&cgroup_mutex); + + for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { + if (cgroup->nr_descendants >= cgroup->max_descendants) + goto fail; + + if (level > cgroup->max_depth) + goto fail; + + level++; + } + + ret = true; +fail: + return ret; +} + +int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) +{ + struct cgroup *parent, *cgrp; + int ret; + + /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ + if (strchr(name, '\n')) + return -EINVAL; + + parent = cgroup_kn_lock_live(parent_kn, false); + if (!parent) + return -ENODEV; + + if (!cgroup_check_hierarchy_limits(parent)) { + ret = -EAGAIN; + goto out_unlock; + } + + cgrp = cgroup_create(parent, name, mode); + if (IS_ERR(cgrp)) { + ret = PTR_ERR(cgrp); + goto out_unlock; + } + + /* + * This extra ref will be put in cgroup_free_fn() and guarantees + * that @cgrp->kn is always accessible. + */ + kernfs_get(cgrp->kn); + + ret = cgroup_kn_set_ugid(cgrp->kn); + if (ret) + goto out_destroy; + + ret = css_populate_dir(&cgrp->self); + if (ret) + goto out_destroy; + + ret = cgroup_apply_control_enable(cgrp); + if (ret) + goto out_destroy; + + TRACE_CGROUP_PATH(mkdir, cgrp); + + /* let's create and online css's */ + kernfs_activate(cgrp->kn); + + ret = 0; + goto out_unlock; + +out_destroy: + cgroup_destroy_locked(cgrp); +out_unlock: + cgroup_kn_unlock(parent_kn); + return ret; +} + +/* + * 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) +{ + struct cgroup_subsys_state *css = + container_of(work, struct cgroup_subsys_state, destroy_work); + + cgroup_lock(); + + do { + offline_css(css); + css_put(css); + /* @css can't go away while we're holding cgroup_mutex */ + css = css->parent; + } while (css && atomic_dec_and_test(&css->online_cnt)); + + cgroup_unlock(); +} + +/* css kill confirmation processing requires process context, bounce */ +static void css_killed_ref_fn(struct percpu_ref *ref) +{ + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + + if (atomic_dec_and_test(&css->online_cnt)) { + INIT_WORK(&css->destroy_work, css_killed_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); + } +} + +/** + * 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) +{ + lockdep_assert_held(&cgroup_mutex); + + if (css->flags & CSS_DYING) + return; + + css->flags |= CSS_DYING; + + /* + * This must happen before css is disassociated with its cgroup. + * See seq_css() for details. + */ + css_clear_dir(css); + + /* + * Killing would put the base ref, but we need to keep it alive + * until after ->css_offline(). + */ + css_get(css); + + /* + * cgroup core guarantees that, by the time ->css_offline() is + * invoked, no new css reference will be given out via + * css_tryget_online(). We can't simply call percpu_ref_kill() and + * proceed to offlining css's because percpu_ref_kill() doesn't + * guarantee that the ref is seen as killed on all CPUs on return. + * + * Use percpu_ref_kill_and_confirm() to get notifications as each + * css is confirmed to be seen as killed on all CPUs. + */ + percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); +} + +/** + * 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_lock_live_group(). 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 = cgroup_parent(cgrp); 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) +{ + struct cgroup *cgrp; + int ret = 0; + + cgrp = cgroup_kn_lock_live(kn, false); + if (!cgrp) + return 0; + + ret = cgroup_destroy_locked(cgrp); + if (!ret) + TRACE_CGROUP_PATH(rmdir, cgrp); + + cgroup_kn_unlock(kn); + return ret; +} + +static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { + .show_options = cgroup_show_options, + .mkdir = cgroup_mkdir, + .rmdir = cgroup_rmdir, + .show_path = cgroup_show_path, +}; + +static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) +{ + struct cgroup_subsys_state *css; + + pr_debug("Initializing cgroup subsys %s\n", ss->name); + + cgroup_lock(); + + idr_init(&ss->css_idr); + INIT_LIST_HEAD(&ss->cfts); + + /* Create the root cgroup state for this subsystem */ + ss->root = &cgrp_dfl_root; + css = ss->css_alloc(NULL); + /* We don't handle early failures gracefully */ + BUG_ON(IS_ERR(css)); + init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); + + /* + * Root csses are never destroyed and we can't initialize + * percpu_ref during early init. Disable refcnting. + */ + css->flags |= CSS_NO_REF; + + if (early) { + /* allocation can't be done safely during early init */ + css->id = 1; + } else { + css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); + BUG_ON(css->id < 0); + } + + /* Update the init_css_set to contain a subsys + * pointer to this state - since the subsystem is + * newly registered, all tasks and hence the + * init_css_set is in the subsystem's root cgroup. */ + init_css_set.subsys[ss->id] = css; + + have_fork_callback |= (bool)ss->fork << ss->id; + have_exit_callback |= (bool)ss->exit << ss->id; + have_release_callback |= (bool)ss->release << ss->id; + have_canfork_callback |= (bool)ss->can_fork << ss->id; + + /* At system boot, before all subsystems have been + * registered, no tasks have been forked, so we don't + * need to invoke fork callbacks here. */ + BUG_ON(!list_empty(&init_task.tasks)); + + BUG_ON(online_css(css)); + + cgroup_unlock(); +} + +/** + * 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) +{ + static struct cgroup_fs_context __initdata ctx; + struct cgroup_subsys *ss; + int i; + + ctx.root = &cgrp_dfl_root; + init_cgroup_root(&ctx); + cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; + + RCU_INIT_POINTER(init_task.cgroups, &init_css_set); + + for_each_subsys(ss, i) { + WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, + "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", + i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, + ss->id, ss->name); + WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, + "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); + + ss->id = i; + ss->name = cgroup_subsys_name[i]; + if (!ss->legacy_name) + ss->legacy_name = cgroup_subsys_name[i]; + + if (ss->early_init) + cgroup_init_subsys(ss, true); + } + return 0; +} + +/** + * 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) +{ + struct cgroup_subsys *ss; + int ssid; + + BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); + BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); + BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files)); + BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); + + cgroup_rstat_boot(); + + get_user_ns(init_cgroup_ns.user_ns); + + cgroup_lock(); + + /* + * Add init_css_set to the hash table so that dfl_root can link to + * it during init. + */ + hash_add(css_set_table, &init_css_set.hlist, + css_set_hash(init_css_set.subsys)); + + BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); + + cgroup_unlock(); + + for_each_subsys(ss, ssid) { + if (ss->early_init) { + struct cgroup_subsys_state *css = + init_css_set.subsys[ss->id]; + + css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, + GFP_KERNEL); + BUG_ON(css->id < 0); + } else { + cgroup_init_subsys(ss, false); + } + + list_add_tail(&init_css_set.e_cset_node[ssid], + &cgrp_dfl_root.cgrp.e_csets[ssid]); + + /* + * Setting dfl_root subsys_mask needs to consider the + * disabled flag and cftype registration needs kmalloc, + * both of which aren't available during early_init. + */ + if (!cgroup_ssid_enabled(ssid)) + continue; + + if (cgroup1_ssid_disabled(ssid)) + printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", + ss->name); + + cgrp_dfl_root.subsys_mask |= 1 << ss->id; + + /* implicit controllers must be threaded too */ + WARN_ON(ss->implicit_on_dfl && !ss->threaded); + + if (ss->implicit_on_dfl) + cgrp_dfl_implicit_ss_mask |= 1 << ss->id; + else if (!ss->dfl_cftypes) + cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; + + if (ss->threaded) + cgrp_dfl_threaded_ss_mask |= 1 << ss->id; + + if (ss->dfl_cftypes == ss->legacy_cftypes) { + WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); + } else { + WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); + WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); + } + + if (ss->bind) + ss->bind(init_css_set.subsys[ssid]); + + cgroup_lock(); + css_populate_dir(init_css_set.subsys[ssid]); + cgroup_unlock(); + } + + /* init_css_set.subsys[] has been updated, re-hash */ + hash_del(&init_css_set.hlist); + hash_add(css_set_table, &init_css_set.hlist, + css_set_hash(init_css_set.subsys)); + + WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); + WARN_ON(register_filesystem(&cgroup_fs_type)); + WARN_ON(register_filesystem(&cgroup2_fs_type)); + WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); +#ifdef CONFIG_CPUSETS + WARN_ON(register_filesystem(&cpuset_fs_type)); +#endif + + return 0; +} + +static int __init cgroup_wq_init(void) +{ + /* + * There isn't much point in executing destruction path in + * parallel. Good chunk is serialized with cgroup_mutex anyway. + * Use 1 for @max_active. + * + * We would prefer to do this in cgroup_init() above, but that + * is called before init_workqueues(): so leave this until after. + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); + return 0; +} +core_initcall(cgroup_wq_init); + +void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) +{ + struct kernfs_node *kn; + + kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); + if (!kn) + return; + kernfs_path(kn, buf, buflen); + kernfs_put(kn); +} + +/* + * 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) +{ + struct kernfs_node *kn; + struct cgroup *cgrp, *root_cgrp; + + kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); + if (!kn) + return ERR_PTR(-ENOENT); + + if (kernfs_type(kn) != KERNFS_DIR) { + kernfs_put(kn); + return ERR_PTR(-ENOENT); + } + + rcu_read_lock(); + + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); + if (cgrp && !cgroup_tryget(cgrp)) + cgrp = NULL; + + rcu_read_unlock(); + kernfs_put(kn); + + if (!cgrp) + return ERR_PTR(-ENOENT); + + root_cgrp = current_cgns_cgroup_dfl(); + if (!cgroup_is_descendant(cgrp, root_cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-ENOENT); + } + + return cgrp; +} +EXPORT_SYMBOL_GPL(cgroup_get_from_id); + +/* + * 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) +{ + char *buf; + int retval; + struct cgroup_root *root; + + retval = -ENOMEM; + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) + goto out; + + cgroup_lock(); + spin_lock_irq(&css_set_lock); + + for_each_root(root) { + struct cgroup_subsys *ss; + struct cgroup *cgrp; + int ssid, count = 0; + + if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) + continue; + + seq_printf(m, "%d:", root->hierarchy_id); + if (root != &cgrp_dfl_root) + for_each_subsys(ss, ssid) + if (root->subsys_mask & (1 << ssid)) + seq_printf(m, "%s%s", count++ ? "," : "", + ss->legacy_name); + if (strlen(root->name)) + seq_printf(m, "%sname=%s", count ? "," : "", + root->name); + seq_putc(m, ':'); + + cgrp = task_cgroup_from_root(tsk, root); + + /* + * On traditional hierarchies, all zombie tasks show up as + * belonging to the root cgroup. On the default hierarchy, + * while a zombie doesn't show up in "cgroup.procs" and + * thus can't be migrated, its /proc/PID/cgroup keeps + * reporting the cgroup it belonged to before exiting. If + * the cgroup is removed before the zombie is reaped, + * " (deleted)" is appended to the cgroup path. + */ + if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { + retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, + current->nsproxy->cgroup_ns); + if (retval >= PATH_MAX) + retval = -ENAMETOOLONG; + if (retval < 0) + goto out_unlock; + + seq_puts(m, buf); + } else { + seq_puts(m, "/"); + } + + if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) + seq_puts(m, " (deleted)\n"); + else + seq_putc(m, '\n'); + } + + retval = 0; +out_unlock: + spin_unlock_irq(&css_set_lock); + cgroup_unlock(); + kfree(buf); +out: + return retval; +} + +/** + * 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) +{ + RCU_INIT_POINTER(child->cgroups, &init_css_set); + INIT_LIST_HEAD(&child->cg_list); +} + +/** + * 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) +{ + struct cgroup_subsys_state *css; + + css = css_tryget_online_from_dir(f->f_path.dentry, NULL); + if (IS_ERR(css)) + return ERR_CAST(css); + + return css->cgroup; +} + +/** + * 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) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + + return cgrp; +} + +/** + * 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) +{ + int ret; + struct cgroup *dst_cgrp = NULL; + struct css_set *cset; + struct super_block *sb; + struct file *f; + + if (kargs->flags & CLONE_INTO_CGROUP) + cgroup_lock(); + + cgroup_threadgroup_change_begin(current); + + spin_lock_irq(&css_set_lock); + cset = task_css_set(current); + get_css_set(cset); + spin_unlock_irq(&css_set_lock); + + if (!(kargs->flags & CLONE_INTO_CGROUP)) { + kargs->cset = cset; + return 0; + } + + f = fget_raw(kargs->cgroup); + if (!f) { + ret = -EBADF; + goto err; + } + sb = f->f_path.dentry->d_sb; + + dst_cgrp = cgroup_get_from_file(f); + if (IS_ERR(dst_cgrp)) { + ret = PTR_ERR(dst_cgrp); + dst_cgrp = NULL; + goto err; + } + + if (cgroup_is_dead(dst_cgrp)) { + ret = -ENODEV; + goto err; + } + + /* + * Verify that we the target cgroup is writable for us. This is + * usually done by the vfs layer but since we're not going through + * the vfs layer here we need to do it "manually". + */ + ret = cgroup_may_write(dst_cgrp, sb); + if (ret) + goto err; + + /* + * Spawning a task directly into a cgroup works by passing a file + * descriptor to the target cgroup directory. This can even be an O_PATH + * file descriptor. But it can never be a cgroup.procs file descriptor. + * This was done on purpose so spawning into a cgroup could be + * conceptualized as an atomic + * + * fd = openat(dfd_cgroup, "cgroup.procs", ...); + * write(fd, <child-pid>, ...); + * + * sequence, i.e. it's a shorthand for the caller opening and writing + * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us + * to always use the caller's credentials. + */ + ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, + !(kargs->flags & CLONE_THREAD), + current->nsproxy->cgroup_ns); + if (ret) + goto err; + + kargs->cset = find_css_set(cset, dst_cgrp); + if (!kargs->cset) { + ret = -ENOMEM; + goto err; + } + + put_css_set(cset); + fput(f); + kargs->cgrp = dst_cgrp; + return ret; + +err: + cgroup_threadgroup_change_end(current); + cgroup_unlock(); + if (f) + fput(f); + if (dst_cgrp) + cgroup_put(dst_cgrp); + put_css_set(cset); + if (kargs->cset) + put_css_set(kargs->cset); + return ret; +} + +/** + * 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) +{ + struct cgroup *cgrp = kargs->cgrp; + struct css_set *cset = kargs->cset; + + cgroup_threadgroup_change_end(current); + + if (cset) { + put_css_set(cset); + kargs->cset = NULL; + } + + if (kargs->flags & CLONE_INTO_CGROUP) { + cgroup_unlock(); + if (cgrp) { + cgroup_put(cgrp); + kargs->cgrp = NULL; + } + } +} + +/** + * 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) +{ + struct cgroup_subsys *ss; + int i, j, ret; + + ret = cgroup_css_set_fork(kargs); + if (ret) + return ret; + + do_each_subsys_mask(ss, i, have_canfork_callback) { + ret = ss->can_fork(child, kargs->cset); + if (ret) + goto out_revert; + } while_each_subsys_mask(); + + return 0; + +out_revert: + for_each_subsys(ss, j) { + if (j >= i) + break; + if (ss->cancel_fork) + ss->cancel_fork(child, kargs->cset); + } + + cgroup_css_set_put_fork(kargs); + + return ret; +} + +/** + * 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) +{ + struct cgroup_subsys *ss; + int i; + + for_each_subsys(ss, i) + if (ss->cancel_fork) + ss->cancel_fork(child, kargs->cset); + + cgroup_css_set_put_fork(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) +{ + unsigned long cgrp_flags = 0; + bool kill = false; + struct cgroup_subsys *ss; + struct css_set *cset; + int i; + + cset = kargs->cset; + kargs->cset = NULL; + + spin_lock_irq(&css_set_lock); + + /* init tasks are special, only link regular threads */ + if (likely(child->pid)) { + if (kargs->cgrp) + cgrp_flags = kargs->cgrp->flags; + else + cgrp_flags = cset->dfl_cgrp->flags; + + WARN_ON_ONCE(!list_empty(&child->cg_list)); + cset->nr_tasks++; + css_set_move_task(child, NULL, cset, false); + } else { + put_css_set(cset); + cset = NULL; + } + + if (!(child->flags & PF_KTHREAD)) { + if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) { + /* + * If the cgroup has to be frozen, the new task has + * too. Let's set the JOBCTL_TRAP_FREEZE jobctl bit to + * get the task into the frozen state. + */ + spin_lock(&child->sighand->siglock); + WARN_ON_ONCE(child->frozen); + child->jobctl |= JOBCTL_TRAP_FREEZE; + spin_unlock(&child->sighand->siglock); + + /* + * Calling cgroup_update_frozen() isn't required here, + * because it will be called anyway a bit later from + * do_freezer_trap(). So we avoid cgroup's transient + * switch from the frozen state and back. + */ + } + + /* + * If the cgroup is to be killed notice it now and take the + * child down right after we finished preparing it for + * userspace. + */ + kill = test_bit(CGRP_KILL, &cgrp_flags); + } + + spin_unlock_irq(&css_set_lock); + + /* + * Call ss->fork(). This must happen after @child is linked on + * css_set; otherwise, @child might change state between ->fork() + * and addition to css_set. + */ + do_each_subsys_mask(ss, i, have_fork_callback) { + ss->fork(child); + } while_each_subsys_mask(); + + /* Make the new cset the root_cset of the new cgroup namespace. */ + if (kargs->flags & CLONE_NEWCGROUP) { + struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset; + + get_css_set(cset); + child->nsproxy->cgroup_ns->root_cset = cset; + put_css_set(rcset); + } + + /* Cgroup has to be killed so take down child immediately. */ + if (unlikely(kill)) + do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID); + + cgroup_css_set_put_fork(kargs); +} + +/** + * 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) +{ + struct cgroup_subsys *ss; + struct css_set *cset; + int i; + + spin_lock_irq(&css_set_lock); + + WARN_ON_ONCE(list_empty(&tsk->cg_list)); + cset = task_css_set(tsk); + css_set_move_task(tsk, cset, NULL, false); + list_add_tail(&tsk->cg_list, &cset->dying_tasks); + cset->nr_tasks--; + + if (dl_task(tsk)) + dec_dl_tasks_cs(tsk); + + WARN_ON_ONCE(cgroup_task_frozen(tsk)); + if (unlikely(!(tsk->flags & PF_KTHREAD) && + test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) + cgroup_update_frozen(task_dfl_cgroup(tsk)); + + spin_unlock_irq(&css_set_lock); + + /* see cgroup_post_fork() for details */ + do_each_subsys_mask(ss, i, have_exit_callback) { + ss->exit(tsk); + } while_each_subsys_mask(); +} + +void cgroup_release(struct task_struct *task) +{ + struct cgroup_subsys *ss; + int ssid; + + do_each_subsys_mask(ss, ssid, have_release_callback) { + ss->release(task); + } while_each_subsys_mask(); + + spin_lock_irq(&css_set_lock); + css_set_skip_task_iters(task_css_set(task), task); + list_del_init(&task->cg_list); + spin_unlock_irq(&css_set_lock); +} + +void cgroup_free(struct task_struct *task) +{ + struct css_set *cset = task_css_set(task); + put_css_set(cset); +} + +static int __init cgroup_disable(char *str) +{ + struct cgroup_subsys *ss; + char *token; + int i; + + while ((token = strsep(&str, ",")) != NULL) { + if (!*token) + continue; + + for_each_subsys(ss, i) { + if (strcmp(token, ss->name) && + strcmp(token, ss->legacy_name)) + continue; + + static_branch_disable(cgroup_subsys_enabled_key[i]); + pr_info("Disabling %s control group subsystem\n", + ss->name); + } + + for (i = 0; i < OPT_FEATURE_COUNT; i++) { + if (strcmp(token, cgroup_opt_feature_names[i])) + continue; + cgroup_feature_disable_mask |= 1 << i; + pr_info("Disabling %s control group feature\n", + cgroup_opt_feature_names[i]); + break; + } + } + return 1; +} +__setup("cgroup_disable=", cgroup_disable); + +void __init __weak enable_debug_cgroup(void) { } + +static int __init enable_cgroup_debug(char *str) +{ + cgroup_debug = true; + enable_debug_cgroup(); + return 1; +} +__setup("cgroup_debug", enable_cgroup_debug); + +/** + * 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) +{ + struct kernfs_node *kn = kernfs_node_from_dentry(dentry); + struct file_system_type *s_type = dentry->d_sb->s_type; + struct cgroup_subsys_state *css = NULL; + struct cgroup *cgrp; + + /* is @dentry a cgroup dir? */ + if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || + !kn || kernfs_type(kn) != KERNFS_DIR) + return ERR_PTR(-EBADF); + + rcu_read_lock(); + + /* + * This path doesn't originate from kernfs and @kn could already + * have been or be removed at any point. @kn->priv is RCU + * protected for this access. See css_release_work_fn() for details. + */ + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); + if (cgrp) + css = cgroup_css(cgrp, ss); + + if (!css || !css_tryget_online(css)) + css = ERR_PTR(-ENOENT); + + rcu_read_unlock(); + return css; +} + +/** + * 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) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return idr_find(&ss->css_idr, id); +} + +/** + * 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) +{ + struct kernfs_node *kn; + struct cgroup *cgrp = ERR_PTR(-ENOENT); + struct cgroup *root_cgrp; + + root_cgrp = current_cgns_cgroup_dfl(); + kn = kernfs_walk_and_get(root_cgrp->kn, path); + if (!kn) + goto out; + + if (kernfs_type(kn) != KERNFS_DIR) { + cgrp = ERR_PTR(-ENOTDIR); + goto out_kernfs; + } + + rcu_read_lock(); + + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); + if (!cgrp || !cgroup_tryget(cgrp)) + cgrp = ERR_PTR(-ENOENT); + + rcu_read_unlock(); + +out_kernfs: + kernfs_put(kn); +out: + return cgrp; +} +EXPORT_SYMBOL_GPL(cgroup_get_from_path); + +/** + * 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) +{ + struct cgroup *cgrp; + struct file *f; + + f = fget_raw(fd); + if (!f) + return ERR_PTR(-EBADF); + + cgrp = cgroup_v1v2_get_from_file(f); + fput(f); + return cgrp; +} + +/** + * 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) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + return cgrp; +} +EXPORT_SYMBOL_GPL(cgroup_get_from_fd); + +static u64 power_of_ten(int power) +{ + u64 v = 1; + while (power--) + v *= 10; + return v; +} + +/** + * 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) +{ + s64 whole, frac = 0; + int fstart = 0, fend = 0, flen; + + if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend)) + return -EINVAL; + if (frac < 0) + return -EINVAL; + + flen = fend > fstart ? fend - fstart : 0; + if (flen < dec_shift) + frac *= power_of_ten(dec_shift - flen); + else + frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift)); + + *v = whole * power_of_ten(dec_shift) + frac; + return 0; +} + +/* + * 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) +{ + struct cgroup *cgroup; + + rcu_read_lock(); + /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) { + cgroup = &cgrp_dfl_root.cgrp; + cgroup_get(cgroup); + goto out; + } + + while (true) { + struct css_set *cset; + + cset = task_css_set(current); + if (likely(cgroup_tryget(cset->dfl_cgrp))) { + cgroup = cset->dfl_cgrp; + break; + } + cpu_relax(); + } +out: + skcd->cgroup = cgroup; + cgroup_bpf_get(cgroup); + rcu_read_unlock(); +} + +void cgroup_sk_clone(struct sock_cgroup_data *skcd) +{ + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(cgrp); + cgroup_bpf_get(cgrp); +} + +void cgroup_sk_free(struct sock_cgroup_data *skcd) +{ + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + cgroup_bpf_put(cgrp); + cgroup_put(cgrp); +} + +#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) +{ + struct cftype *cft; + ssize_t ret = 0; + + for (cft = files; cft && cft->name[0] != '\0'; cft++) { + if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) + continue; + + if (prefix) + ret += snprintf(buf + ret, size - ret, "%s.", prefix); + + ret += snprintf(buf + ret, size - ret, "%s\n", cft->name); + + if (WARN_ON(ret >= size)) + break; + } + + return ret; +} + +static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct cgroup_subsys *ss; + int ssid; + ssize_t ret = 0; + + ret = show_delegatable_files(cgroup_base_files, buf + ret, + PAGE_SIZE - ret, NULL); + if (cgroup_psi_enabled()) + ret += show_delegatable_files(cgroup_psi_files, buf + ret, + PAGE_SIZE - ret, NULL); + + for_each_subsys(ss, ssid) + ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, + PAGE_SIZE - ret, + cgroup_subsys_name[ssid]); + + return ret; +} +static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); + +static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, + "nsdelegate\n" + "favordynmods\n" + "memory_localevents\n" + "memory_recursiveprot\n"); +} +static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); + +static struct attribute *cgroup_sysfs_attrs[] = { + &cgroup_delegate_attr.attr, + &cgroup_features_attr.attr, + NULL, +}; + +static const struct attribute_group cgroup_sysfs_attr_group = { + .attrs = cgroup_sysfs_attrs, + .name = "cgroup", +}; + +static int __init cgroup_sysfs_init(void) +{ + return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group); +} +subsys_initcall(cgroup_sysfs_init); + +#endif /* CONFIG_SYSFS */ diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c new file mode 100644 index 000000000..79e6a5d4c --- /dev/null +++ b/kernel/cgroup/cpuset.c @@ -0,0 +1,4241 @@ +/* + * kernel/cpuset.c + * + * Processor and Memory placement constraints for sets of tasks. + * + * Copyright (C) 2003 BULL SA. + * Copyright (C) 2004-2007 Silicon Graphics, Inc. + * Copyright (C) 2006 Google, 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. + * 2006 Rework by Paul Menage to use generic cgroups + * 2008 Rework of the scheduler domains and CPU hotplug handling + * by Max Krasnyansky + * + * 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 <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/cpuset.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kmod.h> +#include <linux/kthread.h> +#include <linux/list.h> +#include <linux/mempolicy.h> +#include <linux/mm.h> +#include <linux/memory.h> +#include <linux/export.h> +#include <linux/mount.h> +#include <linux/fs_context.h> +#include <linux/namei.h> +#include <linux/pagemap.h> +#include <linux/proc_fs.h> +#include <linux/rcupdate.h> +#include <linux/sched.h> +#include <linux/sched/deadline.h> +#include <linux/sched/mm.h> +#include <linux/sched/task.h> +#include <linux/seq_file.h> +#include <linux/security.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/stat.h> +#include <linux/string.h> +#include <linux/time.h> +#include <linux/time64.h> +#include <linux/backing-dev.h> +#include <linux/sort.h> +#include <linux/oom.h> +#include <linux/sched/isolation.h> +#include <linux/uaccess.h> +#include <linux/atomic.h> +#include <linux/mutex.h> +#include <linux/cgroup.h> +#include <linux/wait.h> + +DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); +DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); + +/* + * There could be abnormal cpuset configurations for cpu or memory + * node binding, add this key to provide a quick low-cost judgment + * of the situation. + */ +DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key); + +/* See "Frequency meter" comments, below. */ + +struct fmeter { + int cnt; /* unprocessed events count */ + int val; /* most recent output value */ + time64_t time; /* clock (secs) when val computed */ + spinlock_t lock; /* guards read or write of above */ +}; + +/* + * Invalid partition error code + */ +enum prs_errcode { + PERR_NONE = 0, + PERR_INVCPUS, + PERR_INVPARENT, + PERR_NOTPART, + PERR_NOTEXCL, + PERR_NOCPUS, + PERR_HOTPLUG, + PERR_CPUSEMPTY, +}; + +static const char * const perr_strings[] = { + [PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus", + [PERR_INVPARENT] = "Parent is an invalid partition root", + [PERR_NOTPART] = "Parent is not a partition root", + [PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive", + [PERR_NOCPUS] = "Parent unable to distribute cpu downstream", + [PERR_HOTPLUG] = "No cpu available due to hotplug", + [PERR_CPUSEMPTY] = "cpuset.cpus is empty", +}; + +struct cpuset { + struct cgroup_subsys_state css; + + unsigned long flags; /* "unsigned long" so bitops work */ + + /* + * On default hierarchy: + * + * The user-configured masks can only be changed by writing to + * cpuset.cpus and cpuset.mems, and won't be limited by the + * parent masks. + * + * The effective masks is the real masks that apply to the tasks + * in the cpuset. They may be changed if the configured masks are + * changed or hotplug happens. + * + * effective_mask == configured_mask & parent's effective_mask, + * and if it ends up empty, it will inherit the parent's mask. + * + * + * On legacy hierarchy: + * + * The user-configured masks are always the same with effective masks. + */ + + /* user-configured CPUs and Memory Nodes allow to tasks */ + cpumask_var_t cpus_allowed; + nodemask_t mems_allowed; + + /* effective CPUs and Memory Nodes allow to tasks */ + cpumask_var_t effective_cpus; + nodemask_t effective_mems; + + /* + * CPUs allocated to child sub-partitions (default hierarchy only) + * - CPUs granted by the parent = effective_cpus U subparts_cpus + * - effective_cpus and subparts_cpus are mutually exclusive. + * + * effective_cpus contains only onlined CPUs, but subparts_cpus + * may have offlined ones. + */ + cpumask_var_t subparts_cpus; + + /* + * This is old Memory Nodes tasks took on. + * + * - top_cpuset.old_mems_allowed is initialized to mems_allowed. + * - A new cpuset's old_mems_allowed is initialized when some + * task is moved into it. + * - old_mems_allowed is used in cpuset_migrate_mm() when we change + * cpuset.mems_allowed and have tasks' nodemask updated, and + * then old_mems_allowed is updated to mems_allowed. + */ + nodemask_t old_mems_allowed; + + struct fmeter fmeter; /* memory_pressure filter */ + + /* + * Tasks are being attached to this cpuset. Used to prevent + * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). + */ + int attach_in_progress; + + /* partition number for rebuild_sched_domains() */ + int pn; + + /* for custom sched domain */ + int relax_domain_level; + + /* number of CPUs in subparts_cpus */ + int nr_subparts_cpus; + + /* partition root state */ + int partition_root_state; + + /* + * Default hierarchy only: + * use_parent_ecpus - set if using parent's effective_cpus + * child_ecpus_count - # of children with use_parent_ecpus set + */ + int use_parent_ecpus; + int child_ecpus_count; + + /* + * number of SCHED_DEADLINE tasks attached to this cpuset, so that we + * know when to rebuild associated root domain bandwidth information. + */ + int nr_deadline_tasks; + int nr_migrate_dl_tasks; + u64 sum_migrate_dl_bw; + + /* Invalid partition error code, not lock protected */ + enum prs_errcode prs_err; + + /* Handle for cpuset.cpus.partition */ + struct cgroup_file partition_file; +}; + +/* + * Partition root states: + * + * 0 - member (not a partition root) + * 1 - partition root + * 2 - partition root without load balancing (isolated) + * -1 - invalid partition root + * -2 - invalid isolated partition root + */ +#define PRS_MEMBER 0 +#define PRS_ROOT 1 +#define PRS_ISOLATED 2 +#define PRS_INVALID_ROOT -1 +#define PRS_INVALID_ISOLATED -2 + +static inline bool is_prs_invalid(int prs_state) +{ + return prs_state < 0; +} + +/* + * Temporary cpumasks for working with partitions that are passed among + * functions to avoid memory allocation in inner functions. + */ +struct tmpmasks { + cpumask_var_t addmask, delmask; /* For partition root */ + cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ +}; + +static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cpuset, css) : NULL; +} + +/* Retrieve the cpuset for a task */ +static inline struct cpuset *task_cs(struct task_struct *task) +{ + return css_cs(task_css(task, cpuset_cgrp_id)); +} + +static inline struct cpuset *parent_cs(struct cpuset *cs) +{ + return css_cs(cs->css.parent); +} + +void inc_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks++; +} + +void dec_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks--; +} + +/* bits in struct cpuset flags field */ +typedef enum { + CS_ONLINE, + CS_CPU_EXCLUSIVE, + CS_MEM_EXCLUSIVE, + CS_MEM_HARDWALL, + CS_MEMORY_MIGRATE, + CS_SCHED_LOAD_BALANCE, + CS_SPREAD_PAGE, + CS_SPREAD_SLAB, +} cpuset_flagbits_t; + +/* convenient tests for these bits */ +static inline bool is_cpuset_online(struct cpuset *cs) +{ + return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); +} + +static inline int is_cpu_exclusive(const struct cpuset *cs) +{ + return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); +} + +static inline int is_mem_exclusive(const struct cpuset *cs) +{ + return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); +} + +static inline int is_mem_hardwall(const struct cpuset *cs) +{ + return test_bit(CS_MEM_HARDWALL, &cs->flags); +} + +static inline int is_sched_load_balance(const struct cpuset *cs) +{ + return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); +} + +static inline int is_memory_migrate(const struct cpuset *cs) +{ + return test_bit(CS_MEMORY_MIGRATE, &cs->flags); +} + +static inline int is_spread_page(const struct cpuset *cs) +{ + return test_bit(CS_SPREAD_PAGE, &cs->flags); +} + +static inline int is_spread_slab(const struct cpuset *cs) +{ + return test_bit(CS_SPREAD_SLAB, &cs->flags); +} + +static inline int is_partition_valid(const struct cpuset *cs) +{ + return cs->partition_root_state > 0; +} + +static inline int is_partition_invalid(const struct cpuset *cs) +{ + return cs->partition_root_state < 0; +} + +/* + * Callers should hold callback_lock to modify partition_root_state. + */ +static inline void make_partition_invalid(struct cpuset *cs) +{ + if (is_partition_valid(cs)) + cs->partition_root_state = -cs->partition_root_state; +} + +/* + * Send notification event of whenever partition_root_state changes. + */ +static inline void notify_partition_change(struct cpuset *cs, int old_prs) +{ + if (old_prs == cs->partition_root_state) + return; + cgroup_file_notify(&cs->partition_file); + + /* Reset prs_err if not invalid */ + if (is_partition_valid(cs)) + WRITE_ONCE(cs->prs_err, PERR_NONE); +} + +static struct cpuset top_cpuset = { + .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | + (1 << CS_MEM_EXCLUSIVE)), + .partition_root_state = PRS_ROOT, +}; + +/** + * cpuset_for_each_child - traverse online children of a cpuset + * @child_cs: loop cursor pointing to the current child + * @pos_css: used for iteration + * @parent_cs: target cpuset to walk children of + * + * Walk @child_cs through the online children of @parent_cs. Must be used + * with RCU read locked. + */ +#define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ + css_for_each_child((pos_css), &(parent_cs)->css) \ + if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) + +/** + * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants + * @des_cs: loop cursor pointing to the current descendant + * @pos_css: used for iteration + * @root_cs: target cpuset to walk ancestor of + * + * Walk @des_cs through the online descendants of @root_cs. Must be used + * with RCU read locked. The caller may modify @pos_css by calling + * css_rightmost_descendant() to skip subtree. @root_cs is included in the + * iteration and the first node to be visited. + */ +#define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ + css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ + if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) + +/* + * There are two global locks guarding cpuset structures - cpuset_mutex and + * callback_lock. We also require taking task_lock() when dereferencing a + * task's cpuset pointer. See "The task_lock() exception", at the end of this + * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems + * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * structures. Note that cpuset_mutex needs to be a mutex as it is used in + * paths that rely on priority inheritance (e.g. scheduler - on RT) for + * correctness. + * + * A task must hold both locks to modify cpusets. If a task holds + * cpuset_mutex, it blocks others, ensuring that it is the only task able to + * also acquire callback_lock and be able to modify cpusets. It can perform + * various checks on the cpuset structure first, knowing nothing will change. + * It can also allocate memory while just holding cpuset_mutex. While it is + * performing these checks, various callback routines can briefly acquire + * callback_lock to query cpusets. Once it is ready to make the changes, it + * takes callback_lock, blocking everyone else. + * + * Calls to the kernel memory allocator can not be made while holding + * callback_lock, as that would risk double tripping on callback_lock + * from one of the callbacks into the cpuset code from within + * __alloc_pages(). + * + * If a task is only holding callback_lock, then it has read-only + * access to cpusets. + * + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. + * + * The cpuset_common_file_read() handlers only hold callback_lock across + * small pieces of code, such as when reading out possibly multi-word + * cpumasks and nodemasks. + * + * Accessing a task's cpuset should be done in accordance with the + * guidelines for accessing subsystem state in kernel/cgroup.c + */ + +static DEFINE_MUTEX(cpuset_mutex); + +void cpuset_lock(void) +{ + mutex_lock(&cpuset_mutex); +} + +void cpuset_unlock(void) +{ + mutex_unlock(&cpuset_mutex); +} + +static DEFINE_SPINLOCK(callback_lock); + +static struct workqueue_struct *cpuset_migrate_mm_wq; + +/* + * CPU / memory hotplug is handled asynchronously. + */ +static void cpuset_hotplug_workfn(struct work_struct *work); +static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); + +static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); + +static inline void check_insane_mems_config(nodemask_t *nodes) +{ + if (!cpusets_insane_config() && + movable_only_nodes(nodes)) { + static_branch_enable(&cpusets_insane_config_key); + pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" + "Cpuset allocations might fail even with a lot of memory available.\n", + nodemask_pr_args(nodes)); + } +} + +/* + * Cgroup v2 behavior is used on the "cpus" and "mems" control files when + * on default hierarchy or when the cpuset_v2_mode flag is set by mounting + * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. + * With v2 behavior, "cpus" and "mems" are always what the users have + * requested and won't be changed by hotplug events. Only the effective + * cpus or mems will be affected. + */ +static inline bool is_in_v2_mode(void) +{ + return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || + (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); +} + +/** + * partition_is_populated - check if partition has tasks + * @cs: partition root to be checked + * @excluded_child: a child cpuset to be excluded in task checking + * Return: true if there are tasks, false otherwise + * + * It is assumed that @cs is a valid partition root. @excluded_child should + * be non-NULL when this cpuset is going to become a partition itself. + */ +static inline bool partition_is_populated(struct cpuset *cs, + struct cpuset *excluded_child) +{ + struct cgroup_subsys_state *css; + struct cpuset *child; + + if (cs->css.cgroup->nr_populated_csets) + return true; + if (!excluded_child && !cs->nr_subparts_cpus) + return cgroup_is_populated(cs->css.cgroup); + + rcu_read_lock(); + cpuset_for_each_child(child, css, cs) { + if (child == excluded_child) + continue; + if (is_partition_valid(child)) + continue; + if (cgroup_is_populated(child->css.cgroup)) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + return false; +} + +/* + * Return in pmask the portion of a task's cpusets's cpus_allowed that + * are online and are capable of running the task. If none are found, + * walk up the cpuset hierarchy until we find one that does have some + * appropriate cpus. + * + * One way or another, we guarantee to return some non-empty subset + * of cpu_online_mask. + * + * Call with callback_lock or cpuset_mutex held. + */ +static void guarantee_online_cpus(struct task_struct *tsk, + struct cpumask *pmask) +{ + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + struct cpuset *cs; + + if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask))) + cpumask_copy(pmask, cpu_online_mask); + + rcu_read_lock(); + cs = task_cs(tsk); + + while (!cpumask_intersects(cs->effective_cpus, pmask)) { + cs = parent_cs(cs); + if (unlikely(!cs)) { + /* + * The top cpuset doesn't have any online cpu as a + * consequence of a race between cpuset_hotplug_work + * and cpu hotplug notifier. But we know the top + * cpuset's effective_cpus is on its way to be + * identical to cpu_online_mask. + */ + goto out_unlock; + } + } + cpumask_and(pmask, pmask, cs->effective_cpus); + +out_unlock: + rcu_read_unlock(); +} + +/* + * Return in *pmask the portion of a cpusets's mems_allowed that + * are online, with memory. If none are online with memory, walk + * up the cpuset hierarchy until we find one that does have some + * online mems. The top cpuset always has some mems online. + * + * One way or another, we guarantee to return some non-empty subset + * of node_states[N_MEMORY]. + * + * Call with callback_lock or cpuset_mutex held. + */ +static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) +{ + while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) + cs = parent_cs(cs); + nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); +} + +/* + * update task's spread flag if cpuset's page/slab spread flag is set + * + * Call with callback_lock or cpuset_mutex held. The check can be skipped + * if on default hierarchy. + */ +static void cpuset_update_task_spread_flags(struct cpuset *cs, + struct task_struct *tsk) +{ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) + return; + + if (is_spread_page(cs)) + task_set_spread_page(tsk); + else + task_clear_spread_page(tsk); + + if (is_spread_slab(cs)) + task_set_spread_slab(tsk); + else + task_clear_spread_slab(tsk); +} + +/* + * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? + * + * One cpuset is a subset of another if all its allowed CPUs and + * Memory Nodes are a subset of the other, and its exclusive flags + * are only set if the other's are set. Call holding cpuset_mutex. + */ + +static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) +{ + return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && + nodes_subset(p->mems_allowed, q->mems_allowed) && + is_cpu_exclusive(p) <= is_cpu_exclusive(q) && + is_mem_exclusive(p) <= is_mem_exclusive(q); +} + +/** + * alloc_cpumasks - allocate three cpumasks for cpuset + * @cs: the cpuset that have cpumasks to be allocated. + * @tmp: the tmpmasks structure pointer + * Return: 0 if successful, -ENOMEM otherwise. + * + * Only one of the two input arguments should be non-NULL. + */ +static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) +{ + cpumask_var_t *pmask1, *pmask2, *pmask3; + + if (cs) { + pmask1 = &cs->cpus_allowed; + pmask2 = &cs->effective_cpus; + pmask3 = &cs->subparts_cpus; + } else { + pmask1 = &tmp->new_cpus; + pmask2 = &tmp->addmask; + pmask3 = &tmp->delmask; + } + + if (!zalloc_cpumask_var(pmask1, GFP_KERNEL)) + return -ENOMEM; + + if (!zalloc_cpumask_var(pmask2, GFP_KERNEL)) + goto free_one; + + if (!zalloc_cpumask_var(pmask3, GFP_KERNEL)) + goto free_two; + + return 0; + +free_two: + free_cpumask_var(*pmask2); +free_one: + free_cpumask_var(*pmask1); + return -ENOMEM; +} + +/** + * free_cpumasks - free cpumasks in a tmpmasks structure + * @cs: the cpuset that have cpumasks to be free. + * @tmp: the tmpmasks structure pointer + */ +static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) +{ + if (cs) { + free_cpumask_var(cs->cpus_allowed); + free_cpumask_var(cs->effective_cpus); + free_cpumask_var(cs->subparts_cpus); + } + if (tmp) { + free_cpumask_var(tmp->new_cpus); + free_cpumask_var(tmp->addmask); + free_cpumask_var(tmp->delmask); + } +} + +/** + * alloc_trial_cpuset - allocate a trial cpuset + * @cs: the cpuset that the trial cpuset duplicates + */ +static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) +{ + struct cpuset *trial; + + trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); + if (!trial) + return NULL; + + if (alloc_cpumasks(trial, NULL)) { + kfree(trial); + return NULL; + } + + cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); + cpumask_copy(trial->effective_cpus, cs->effective_cpus); + return trial; +} + +/** + * free_cpuset - free the cpuset + * @cs: the cpuset to be freed + */ +static inline void free_cpuset(struct cpuset *cs) +{ + free_cpumasks(cs, NULL); + kfree(cs); +} + +/* + * validate_change_legacy() - Validate conditions specific to legacy (v1) + * behavior. + */ +static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial) +{ + struct cgroup_subsys_state *css; + struct cpuset *c, *par; + int ret; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + /* Each of our child cpusets must be a subset of us */ + ret = -EBUSY; + cpuset_for_each_child(c, css, cur) + if (!is_cpuset_subset(c, trial)) + goto out; + + /* On legacy hierarchy, we must be a subset of our parent cpuset. */ + ret = -EACCES; + par = parent_cs(cur); + if (par && !is_cpuset_subset(trial, par)) + goto out; + + ret = 0; +out: + return ret; +} + +/* + * validate_change() - Used to validate that any proposed cpuset change + * follows the structural rules for cpusets. + * + * If we replaced the flag and mask values of the current cpuset + * (cur) with those values in the trial cpuset (trial), would + * our various subset and exclusive rules still be valid? Presumes + * cpuset_mutex held. + * + * 'cur' is the address of an actual, in-use cpuset. Operations + * such as list traversal that depend on the actual address of the + * cpuset in the list must use cur below, not trial. + * + * 'trial' is the address of bulk structure copy of cur, with + * perhaps one or more of the fields cpus_allowed, mems_allowed, + * or flags changed to new, trial values. + * + * Return 0 if valid, -errno if not. + */ + +static int validate_change(struct cpuset *cur, struct cpuset *trial) +{ + struct cgroup_subsys_state *css; + struct cpuset *c, *par; + int ret = 0; + + rcu_read_lock(); + + if (!is_in_v2_mode()) + ret = validate_change_legacy(cur, trial); + if (ret) + goto out; + + /* Remaining checks don't apply to root cpuset */ + if (cur == &top_cpuset) + goto out; + + par = parent_cs(cur); + + /* + * Cpusets with tasks - existing or newly being attached - can't + * be changed to have empty cpus_allowed or mems_allowed. + */ + ret = -ENOSPC; + if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { + if (!cpumask_empty(cur->cpus_allowed) && + cpumask_empty(trial->cpus_allowed)) + goto out; + if (!nodes_empty(cur->mems_allowed) && + nodes_empty(trial->mems_allowed)) + goto out; + } + + /* + * We can't shrink if we won't have enough room for SCHED_DEADLINE + * tasks. + */ + ret = -EBUSY; + if (is_cpu_exclusive(cur) && + !cpuset_cpumask_can_shrink(cur->cpus_allowed, + trial->cpus_allowed)) + goto out; + + /* + * If either I or some sibling (!= me) is exclusive, we can't + * overlap + */ + ret = -EINVAL; + cpuset_for_each_child(c, css, par) { + if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && + c != cur && + cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) + goto out; + if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && + c != cur && + nodes_intersects(trial->mems_allowed, c->mems_allowed)) + goto out; + } + + ret = 0; +out: + rcu_read_unlock(); + return ret; +} + +#ifdef CONFIG_SMP +/* + * Helper routine for generate_sched_domains(). + * Do cpusets a, b have overlapping effective cpus_allowed masks? + */ +static int cpusets_overlap(struct cpuset *a, struct cpuset *b) +{ + return cpumask_intersects(a->effective_cpus, b->effective_cpus); +} + +static void +update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) +{ + if (dattr->relax_domain_level < c->relax_domain_level) + dattr->relax_domain_level = c->relax_domain_level; + return; +} + +static void update_domain_attr_tree(struct sched_domain_attr *dattr, + struct cpuset *root_cs) +{ + struct cpuset *cp; + struct cgroup_subsys_state *pos_css; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { + /* skip the whole subtree if @cp doesn't have any CPU */ + if (cpumask_empty(cp->cpus_allowed)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + if (is_sched_load_balance(cp)) + update_domain_attr(dattr, cp); + } + rcu_read_unlock(); +} + +/* Must be called with cpuset_mutex held. */ +static inline int nr_cpusets(void) +{ + /* jump label reference count + the top-level cpuset */ + return static_key_count(&cpusets_enabled_key.key) + 1; +} + +/* + * generate_sched_domains() + * + * This function builds a partial partition of the systems CPUs + * A 'partial partition' is a set of non-overlapping subsets whose + * union is a subset of that set. + * The output of this function needs to be passed to kernel/sched/core.c + * partition_sched_domains() routine, which will rebuild the scheduler's + * load balancing domains (sched domains) as specified by that partial + * partition. + * + * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst + * for a background explanation of this. + * + * Does not return errors, on the theory that the callers of this + * routine would rather not worry about failures to rebuild sched + * domains when operating in the severe memory shortage situations + * that could cause allocation failures below. + * + * Must be called with cpuset_mutex held. + * + * The three key local variables below are: + * cp - cpuset pointer, used (together with pos_css) to perform a + * top-down scan of all cpusets. For our purposes, rebuilding + * the schedulers sched domains, we can ignore !is_sched_load_ + * balance cpusets. + * csa - (for CpuSet Array) Array of pointers to all the cpusets + * that need to be load balanced, for convenient iterative + * access by the subsequent code that finds the best partition, + * i.e the set of domains (subsets) of CPUs such that the + * cpus_allowed of every cpuset marked is_sched_load_balance + * is a subset of one of these domains, while there are as + * many such domains as possible, each as small as possible. + * doms - Conversion of 'csa' to an array of cpumasks, for passing to + * the kernel/sched/core.c routine partition_sched_domains() in a + * convenient format, that can be easily compared to the prior + * value to determine what partition elements (sched domains) + * were changed (added or removed.) + * + * Finding the best partition (set of domains): + * The triple nested loops below over i, j, k scan over the + * load balanced cpusets (using the array of cpuset pointers in + * csa[]) looking for pairs of cpusets that have overlapping + * cpus_allowed, but which don't have the same 'pn' partition + * number and gives them in the same partition number. It keeps + * looping on the 'restart' label until it can no longer find + * any such pairs. + * + * The union of the cpus_allowed masks from the set of + * all cpusets having the same 'pn' value then form the one + * element of the partition (one sched domain) to be passed to + * partition_sched_domains(). + */ +static int generate_sched_domains(cpumask_var_t **domains, + struct sched_domain_attr **attributes) +{ + struct cpuset *cp; /* top-down scan of cpusets */ + struct cpuset **csa; /* array of all cpuset ptrs */ + int csn; /* how many cpuset ptrs in csa so far */ + int i, j, k; /* indices for partition finding loops */ + cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ + struct sched_domain_attr *dattr; /* attributes for custom domains */ + int ndoms = 0; /* number of sched domains in result */ + int nslot; /* next empty doms[] struct cpumask slot */ + struct cgroup_subsys_state *pos_css; + bool root_load_balance = is_sched_load_balance(&top_cpuset); + + doms = NULL; + dattr = NULL; + csa = NULL; + + /* Special case for the 99% of systems with one, full, sched domain */ + if (root_load_balance && !top_cpuset.nr_subparts_cpus) { + ndoms = 1; + doms = alloc_sched_domains(ndoms); + if (!doms) + goto done; + + dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); + if (dattr) { + *dattr = SD_ATTR_INIT; + update_domain_attr_tree(dattr, &top_cpuset); + } + cpumask_and(doms[0], top_cpuset.effective_cpus, + housekeeping_cpumask(HK_TYPE_DOMAIN)); + + goto done; + } + + csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); + if (!csa) + goto done; + csn = 0; + + rcu_read_lock(); + if (root_load_balance) + csa[csn++] = &top_cpuset; + cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { + if (cp == &top_cpuset) + continue; + /* + * Continue traversing beyond @cp iff @cp has some CPUs and + * isn't load balancing. The former is obvious. The + * latter: All child cpusets contain a subset of the + * parent's cpus, so just skip them, and then we call + * update_domain_attr_tree() to calc relax_domain_level of + * the corresponding sched domain. + * + * If root is load-balancing, we can skip @cp if it + * is a subset of the root's effective_cpus. + */ + if (!cpumask_empty(cp->cpus_allowed) && + !(is_sched_load_balance(cp) && + cpumask_intersects(cp->cpus_allowed, + housekeeping_cpumask(HK_TYPE_DOMAIN)))) + continue; + + if (root_load_balance && + cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) + continue; + + if (is_sched_load_balance(cp) && + !cpumask_empty(cp->effective_cpus)) + csa[csn++] = cp; + + /* skip @cp's subtree if not a partition root */ + if (!is_partition_valid(cp)) + pos_css = css_rightmost_descendant(pos_css); + } + rcu_read_unlock(); + + for (i = 0; i < csn; i++) + csa[i]->pn = i; + ndoms = csn; + +restart: + /* Find the best partition (set of sched domains) */ + for (i = 0; i < csn; i++) { + struct cpuset *a = csa[i]; + int apn = a->pn; + + for (j = 0; j < csn; j++) { + struct cpuset *b = csa[j]; + int bpn = b->pn; + + if (apn != bpn && cpusets_overlap(a, b)) { + for (k = 0; k < csn; k++) { + struct cpuset *c = csa[k]; + + if (c->pn == bpn) + c->pn = apn; + } + ndoms--; /* one less element */ + goto restart; + } + } + } + + /* + * Now we know how many domains to create. + * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. + */ + doms = alloc_sched_domains(ndoms); + if (!doms) + goto done; + + /* + * The rest of the code, including the scheduler, can deal with + * dattr==NULL case. No need to abort if alloc fails. + */ + dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), + GFP_KERNEL); + + for (nslot = 0, i = 0; i < csn; i++) { + struct cpuset *a = csa[i]; + struct cpumask *dp; + int apn = a->pn; + + if (apn < 0) { + /* Skip completed partitions */ + continue; + } + + dp = doms[nslot]; + + if (nslot == ndoms) { + static int warnings = 10; + if (warnings) { + pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", + nslot, ndoms, csn, i, apn); + warnings--; + } + continue; + } + + cpumask_clear(dp); + if (dattr) + *(dattr + nslot) = SD_ATTR_INIT; + for (j = i; j < csn; j++) { + struct cpuset *b = csa[j]; + + if (apn == b->pn) { + cpumask_or(dp, dp, b->effective_cpus); + cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN)); + if (dattr) + update_domain_attr_tree(dattr + nslot, b); + + /* Done with this partition */ + b->pn = -1; + } + } + nslot++; + } + BUG_ON(nslot != ndoms); + +done: + kfree(csa); + + /* + * Fallback to the default domain if kmalloc() failed. + * See comments in partition_sched_domains(). + */ + if (doms == NULL) + ndoms = 1; + + *domains = doms; + *attributes = dattr; + return ndoms; +} + +static void dl_update_tasks_root_domain(struct cpuset *cs) +{ + struct css_task_iter it; + struct task_struct *task; + + if (cs->nr_deadline_tasks == 0) + return; + + css_task_iter_start(&cs->css, 0, &it); + + while ((task = css_task_iter_next(&it))) + dl_add_task_root_domain(task); + + css_task_iter_end(&it); +} + +static void dl_rebuild_rd_accounting(void) +{ + struct cpuset *cs = NULL; + struct cgroup_subsys_state *pos_css; + + lockdep_assert_held(&cpuset_mutex); + lockdep_assert_cpus_held(); + lockdep_assert_held(&sched_domains_mutex); + + rcu_read_lock(); + + /* + * Clear default root domain DL accounting, it will be computed again + * if a task belongs to it. + */ + dl_clear_root_domain(&def_root_domain); + + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { + + if (cpumask_empty(cs->effective_cpus)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + css_get(&cs->css); + + rcu_read_unlock(); + + dl_update_tasks_root_domain(cs); + + rcu_read_lock(); + css_put(&cs->css); + } + rcu_read_unlock(); +} + +static void +partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + mutex_lock(&sched_domains_mutex); + partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); + dl_rebuild_rd_accounting(); + mutex_unlock(&sched_domains_mutex); +} + +/* + * Rebuild scheduler domains. + * + * If the flag 'sched_load_balance' of any cpuset with non-empty + * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset + * which has that flag enabled, or if any cpuset with a non-empty + * 'cpus' is removed, then call this routine to rebuild the + * scheduler's dynamic sched domains. + * + * Call with cpuset_mutex held. Takes cpus_read_lock(). + */ +static void rebuild_sched_domains_locked(void) +{ + struct cgroup_subsys_state *pos_css; + struct sched_domain_attr *attr; + cpumask_var_t *doms; + struct cpuset *cs; + int ndoms; + + lockdep_assert_cpus_held(); + lockdep_assert_held(&cpuset_mutex); + + /* + * If we have raced with CPU hotplug, return early to avoid + * passing doms with offlined cpu to partition_sched_domains(). + * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. + * + * With no CPUs in any subpartitions, top_cpuset's effective CPUs + * should be the same as the active CPUs, so checking only top_cpuset + * is enough to detect racing CPU offlines. + */ + if (!top_cpuset.nr_subparts_cpus && + !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) + return; + + /* + * With subpartition CPUs, however, the effective CPUs of a partition + * root should be only a subset of the active CPUs. Since a CPU in any + * partition root could be offlined, all must be checked. + */ + if (top_cpuset.nr_subparts_cpus) { + rcu_read_lock(); + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { + if (!is_partition_valid(cs)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + if (!cpumask_subset(cs->effective_cpus, + cpu_active_mask)) { + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + } + + /* Generate domain masks and attrs */ + ndoms = generate_sched_domains(&doms, &attr); + + /* Have scheduler rebuild the domains */ + partition_and_rebuild_sched_domains(ndoms, doms, attr); +} +#else /* !CONFIG_SMP */ +static void rebuild_sched_domains_locked(void) +{ +} +#endif /* CONFIG_SMP */ + +void rebuild_sched_domains(void) +{ + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + rebuild_sched_domains_locked(); + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); +} + +/** + * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. + * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed + * @new_cpus: the temp variable for the new effective_cpus mask + * + * Iterate through each task of @cs updating its cpus_allowed to the + * effective cpuset's. As this function is called with cpuset_mutex held, + * cpuset membership stays stable. + */ +static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) +{ + struct css_task_iter it; + struct task_struct *task; + bool top_cs = cs == &top_cpuset; + + css_task_iter_start(&cs->css, 0, &it); + while ((task = css_task_iter_next(&it))) { + /* + * Percpu kthreads in top_cpuset are ignored + */ + if (top_cs && (task->flags & PF_KTHREAD) && + kthread_is_per_cpu(task)) + continue; + + cpumask_and(new_cpus, cs->effective_cpus, + task_cpu_possible_mask(task)); + set_cpus_allowed_ptr(task, new_cpus); + } + css_task_iter_end(&it); +} + +/** + * compute_effective_cpumask - Compute the effective cpumask of the cpuset + * @new_cpus: the temp variable for the new effective_cpus mask + * @cs: the cpuset the need to recompute the new effective_cpus mask + * @parent: the parent cpuset + * + * If the parent has subpartition CPUs, include them in the list of + * allowable CPUs in computing the new effective_cpus mask. Since offlined + * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask + * to mask those out. + */ +static void compute_effective_cpumask(struct cpumask *new_cpus, + struct cpuset *cs, struct cpuset *parent) +{ + if (parent->nr_subparts_cpus) { + cpumask_or(new_cpus, parent->effective_cpus, + parent->subparts_cpus); + cpumask_and(new_cpus, new_cpus, cs->cpus_allowed); + cpumask_and(new_cpus, new_cpus, cpu_active_mask); + } else { + cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus); + } +} + +/* + * Commands for update_parent_subparts_cpumask + */ +enum subparts_cmd { + partcmd_enable, /* Enable partition root */ + partcmd_disable, /* Disable partition root */ + partcmd_update, /* Update parent's subparts_cpus */ + partcmd_invalidate, /* Make partition invalid */ +}; + +static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, + int turning_on); +/** + * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset + * @cpuset: The cpuset that requests change in partition root state + * @cmd: Partition root state change command + * @newmask: Optional new cpumask for partcmd_update + * @tmp: Temporary addmask and delmask + * Return: 0 or a partition root state error code + * + * For partcmd_enable, the cpuset is being transformed from a non-partition + * root to a partition root. The cpus_allowed mask of the given cpuset will + * be put into parent's subparts_cpus and taken away from parent's + * effective_cpus. The function will return 0 if all the CPUs listed in + * cpus_allowed can be granted or an error code will be returned. + * + * For partcmd_disable, the cpuset is being transformed from a partition + * root back to a non-partition root. Any CPUs in cpus_allowed that are in + * parent's subparts_cpus will be taken away from that cpumask and put back + * into parent's effective_cpus. 0 will always be returned. + * + * For partcmd_update, if the optional newmask is specified, the cpu list is + * to be changed from cpus_allowed to newmask. Otherwise, cpus_allowed is + * assumed to remain the same. The cpuset should either be a valid or invalid + * partition root. The partition root state may change from valid to invalid + * or vice versa. An error code will only be returned if transitioning from + * invalid to valid violates the exclusivity rule. + * + * For partcmd_invalidate, the current partition will be made invalid. + * + * The partcmd_enable and partcmd_disable commands are used by + * update_prstate(). An error code may be returned and the caller will check + * for error. + * + * The partcmd_update command is used by update_cpumasks_hier() with newmask + * NULL and update_cpumask() with newmask set. The partcmd_invalidate is used + * by update_cpumask() with NULL newmask. In both cases, the callers won't + * check for error and so partition_root_state and prs_error will be updated + * directly. + */ +static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, + struct cpumask *newmask, + struct tmpmasks *tmp) +{ + struct cpuset *parent = parent_cs(cs); + int adding; /* Moving cpus from effective_cpus to subparts_cpus */ + int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ + int old_prs, new_prs; + int part_error = PERR_NONE; /* Partition error? */ + + lockdep_assert_held(&cpuset_mutex); + + /* + * The parent must be a partition root. + * The new cpumask, if present, or the current cpus_allowed must + * not be empty. + */ + if (!is_partition_valid(parent)) { + return is_partition_invalid(parent) + ? PERR_INVPARENT : PERR_NOTPART; + } + if ((newmask && cpumask_empty(newmask)) || + (!newmask && cpumask_empty(cs->cpus_allowed))) + return PERR_CPUSEMPTY; + + /* + * new_prs will only be changed for the partcmd_update and + * partcmd_invalidate commands. + */ + adding = deleting = false; + old_prs = new_prs = cs->partition_root_state; + if (cmd == partcmd_enable) { + /* + * Enabling partition root is not allowed if cpus_allowed + * doesn't overlap parent's cpus_allowed. + */ + if (!cpumask_intersects(cs->cpus_allowed, parent->cpus_allowed)) + return PERR_INVCPUS; + + /* + * A parent can be left with no CPU as long as there is no + * task directly associated with the parent partition. + */ + if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) && + partition_is_populated(parent, cs)) + return PERR_NOCPUS; + + cpumask_copy(tmp->addmask, cs->cpus_allowed); + adding = true; + } else if (cmd == partcmd_disable) { + /* + * Need to remove cpus from parent's subparts_cpus for valid + * partition root. + */ + deleting = !is_prs_invalid(old_prs) && + cpumask_and(tmp->delmask, cs->cpus_allowed, + parent->subparts_cpus); + } else if (cmd == partcmd_invalidate) { + if (is_prs_invalid(old_prs)) + return 0; + + /* + * Make the current partition invalid. It is assumed that + * invalidation is caused by violating cpu exclusivity rule. + */ + deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, + parent->subparts_cpus); + if (old_prs > 0) { + new_prs = -old_prs; + part_error = PERR_NOTEXCL; + } + } else if (newmask) { + /* + * partcmd_update with newmask: + * + * Compute add/delete mask to/from subparts_cpus + * + * delmask = cpus_allowed & ~newmask & parent->subparts_cpus + * addmask = newmask & parent->cpus_allowed + * & ~parent->subparts_cpus + */ + cpumask_andnot(tmp->delmask, cs->cpus_allowed, newmask); + deleting = cpumask_and(tmp->delmask, tmp->delmask, + parent->subparts_cpus); + + cpumask_and(tmp->addmask, newmask, parent->cpus_allowed); + adding = cpumask_andnot(tmp->addmask, tmp->addmask, + parent->subparts_cpus); + /* + * Make partition invalid if parent's effective_cpus could + * become empty and there are tasks in the parent. + */ + if (adding && + cpumask_subset(parent->effective_cpus, tmp->addmask) && + !cpumask_intersects(tmp->delmask, cpu_active_mask) && + partition_is_populated(parent, cs)) { + part_error = PERR_NOCPUS; + adding = false; + deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, + parent->subparts_cpus); + } + } else { + /* + * partcmd_update w/o newmask: + * + * delmask = cpus_allowed & parent->subparts_cpus + * addmask = cpus_allowed & parent->cpus_allowed + * & ~parent->subparts_cpus + * + * This gets invoked either due to a hotplug event or from + * update_cpumasks_hier(). This can cause the state of a + * partition root to transition from valid to invalid or vice + * versa. So we still need to compute the addmask and delmask. + + * A partition error happens when: + * 1) Cpuset is valid partition, but parent does not distribute + * out any CPUs. + * 2) Parent has tasks and all its effective CPUs will have + * to be distributed out. + */ + cpumask_and(tmp->addmask, cs->cpus_allowed, + parent->cpus_allowed); + adding = cpumask_andnot(tmp->addmask, tmp->addmask, + parent->subparts_cpus); + + if ((is_partition_valid(cs) && !parent->nr_subparts_cpus) || + (adding && + cpumask_subset(parent->effective_cpus, tmp->addmask) && + partition_is_populated(parent, cs))) { + part_error = PERR_NOCPUS; + adding = false; + } + + if (part_error && is_partition_valid(cs) && + parent->nr_subparts_cpus) + deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, + parent->subparts_cpus); + } + if (part_error) + WRITE_ONCE(cs->prs_err, part_error); + + if (cmd == partcmd_update) { + /* + * Check for possible transition between valid and invalid + * partition root. + */ + switch (cs->partition_root_state) { + case PRS_ROOT: + case PRS_ISOLATED: + if (part_error) + new_prs = -old_prs; + break; + case PRS_INVALID_ROOT: + case PRS_INVALID_ISOLATED: + if (!part_error) + new_prs = -old_prs; + break; + } + } + + if (!adding && !deleting && (new_prs == old_prs)) + return 0; + + /* + * Transitioning between invalid to valid or vice versa may require + * changing CS_CPU_EXCLUSIVE and CS_SCHED_LOAD_BALANCE. + */ + if (old_prs != new_prs) { + if (is_prs_invalid(old_prs) && !is_cpu_exclusive(cs) && + (update_flag(CS_CPU_EXCLUSIVE, cs, 1) < 0)) + return PERR_NOTEXCL; + if (is_prs_invalid(new_prs) && is_cpu_exclusive(cs)) + update_flag(CS_CPU_EXCLUSIVE, cs, 0); + } + + /* + * Change the parent's subparts_cpus. + * Newly added CPUs will be removed from effective_cpus and + * newly deleted ones will be added back to effective_cpus. + */ + spin_lock_irq(&callback_lock); + if (adding) { + cpumask_or(parent->subparts_cpus, + parent->subparts_cpus, tmp->addmask); + cpumask_andnot(parent->effective_cpus, + parent->effective_cpus, tmp->addmask); + } + if (deleting) { + cpumask_andnot(parent->subparts_cpus, + parent->subparts_cpus, tmp->delmask); + /* + * Some of the CPUs in subparts_cpus might have been offlined. + */ + cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask); + cpumask_or(parent->effective_cpus, + parent->effective_cpus, tmp->delmask); + } + + parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); + + if (old_prs != new_prs) + cs->partition_root_state = new_prs; + + spin_unlock_irq(&callback_lock); + + if (adding || deleting) + update_tasks_cpumask(parent, tmp->addmask); + + /* + * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary. + * rebuild_sched_domains_locked() may be called. + */ + if (old_prs != new_prs) { + if (old_prs == PRS_ISOLATED) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 1); + else if (new_prs == PRS_ISOLATED) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + } + notify_partition_change(cs, old_prs); + return 0; +} + +/* + * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree + * @cs: the cpuset to consider + * @tmp: temp variables for calculating effective_cpus & partition setup + * @force: don't skip any descendant cpusets if set + * + * When configured cpumask is changed, the effective cpumasks of this cpuset + * and all its descendants need to be updated. + * + * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. + * + * Called with cpuset_mutex held + */ +static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, + bool force) +{ + struct cpuset *cp; + struct cgroup_subsys_state *pos_css; + bool need_rebuild_sched_domains = false; + int old_prs, new_prs; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_css, cs) { + struct cpuset *parent = parent_cs(cp); + bool update_parent = false; + + compute_effective_cpumask(tmp->new_cpus, cp, parent); + + /* + * If it becomes empty, inherit the effective mask of the + * parent, which is guaranteed to have some CPUs unless + * it is a partition root that has explicitly distributed + * out all its CPUs. + */ + if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { + if (is_partition_valid(cp) && + cpumask_equal(cp->cpus_allowed, cp->subparts_cpus)) + goto update_parent_subparts; + + cpumask_copy(tmp->new_cpus, parent->effective_cpus); + if (!cp->use_parent_ecpus) { + cp->use_parent_ecpus = true; + parent->child_ecpus_count++; + } + } else if (cp->use_parent_ecpus) { + cp->use_parent_ecpus = false; + WARN_ON_ONCE(!parent->child_ecpus_count); + parent->child_ecpus_count--; + } + + /* + * Skip the whole subtree if + * 1) the cpumask remains the same, + * 2) has no partition root state, + * 3) force flag not set, and + * 4) for v2 load balance state same as its parent. + */ + if (!cp->partition_root_state && !force && + cpumask_equal(tmp->new_cpus, cp->effective_cpus) && + (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || + (is_sched_load_balance(parent) == is_sched_load_balance(cp)))) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + +update_parent_subparts: + /* + * update_parent_subparts_cpumask() should have been called + * for cs already in update_cpumask(). We should also call + * update_tasks_cpumask() again for tasks in the parent + * cpuset if the parent's subparts_cpus changes. + */ + old_prs = new_prs = cp->partition_root_state; + if ((cp != cs) && old_prs) { + switch (parent->partition_root_state) { + case PRS_ROOT: + case PRS_ISOLATED: + update_parent = true; + break; + + default: + /* + * When parent is not a partition root or is + * invalid, child partition roots become + * invalid too. + */ + if (is_partition_valid(cp)) + new_prs = -cp->partition_root_state; + WRITE_ONCE(cp->prs_err, + is_partition_invalid(parent) + ? PERR_INVPARENT : PERR_NOTPART); + break; + } + } + + if (!css_tryget_online(&cp->css)) + continue; + rcu_read_unlock(); + + if (update_parent) { + update_parent_subparts_cpumask(cp, partcmd_update, NULL, + tmp); + /* + * The cpuset partition_root_state may become + * invalid. Capture it. + */ + new_prs = cp->partition_root_state; + } + + spin_lock_irq(&callback_lock); + + if (cp->nr_subparts_cpus && !is_partition_valid(cp)) { + /* + * Put all active subparts_cpus back to effective_cpus. + */ + cpumask_or(tmp->new_cpus, tmp->new_cpus, + cp->subparts_cpus); + cpumask_and(tmp->new_cpus, tmp->new_cpus, + cpu_active_mask); + cp->nr_subparts_cpus = 0; + cpumask_clear(cp->subparts_cpus); + } + + cpumask_copy(cp->effective_cpus, tmp->new_cpus); + if (cp->nr_subparts_cpus) { + /* + * Make sure that effective_cpus & subparts_cpus + * are mutually exclusive. + */ + cpumask_andnot(cp->effective_cpus, cp->effective_cpus, + cp->subparts_cpus); + } + + cp->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock); + + notify_partition_change(cp, old_prs); + + WARN_ON(!is_in_v2_mode() && + !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); + + update_tasks_cpumask(cp, tmp->new_cpus); + + /* + * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE + * from parent if current cpuset isn't a valid partition root + * and their load balance states differ. + */ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + !is_partition_valid(cp) && + (is_sched_load_balance(parent) != is_sched_load_balance(cp))) { + if (is_sched_load_balance(parent)) + set_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); + else + clear_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); + } + + /* + * On legacy hierarchy, if the effective cpumask of any non- + * empty cpuset is changed, we need to rebuild sched domains. + * On default hierarchy, the cpuset needs to be a partition + * root as well. + */ + if (!cpumask_empty(cp->cpus_allowed) && + is_sched_load_balance(cp) && + (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || + is_partition_valid(cp))) + need_rebuild_sched_domains = true; + + rcu_read_lock(); + css_put(&cp->css); + } + rcu_read_unlock(); + + if (need_rebuild_sched_domains) + rebuild_sched_domains_locked(); +} + +/** + * update_sibling_cpumasks - Update siblings cpumasks + * @parent: Parent cpuset + * @cs: Current cpuset + * @tmp: Temp variables + */ +static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, + struct tmpmasks *tmp) +{ + struct cpuset *sibling; + struct cgroup_subsys_state *pos_css; + + lockdep_assert_held(&cpuset_mutex); + + /* + * Check all its siblings and call update_cpumasks_hier() + * if their use_parent_ecpus flag is set in order for them + * to use the right effective_cpus value. + * + * The update_cpumasks_hier() function may sleep. So we have to + * release the RCU read lock before calling it. + */ + rcu_read_lock(); + cpuset_for_each_child(sibling, pos_css, parent) { + if (sibling == cs) + continue; + if (!sibling->use_parent_ecpus) + continue; + if (!css_tryget_online(&sibling->css)) + continue; + + rcu_read_unlock(); + update_cpumasks_hier(sibling, tmp, false); + rcu_read_lock(); + css_put(&sibling->css); + } + rcu_read_unlock(); +} + +/** + * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it + * @cs: the cpuset to consider + * @trialcs: trial cpuset + * @buf: buffer of cpu numbers written to this cpuset + */ +static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) +{ + int retval; + struct tmpmasks tmp; + bool invalidate = false; + + /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ + if (cs == &top_cpuset) + return -EACCES; + + /* + * An empty cpus_allowed is ok only if the cpuset has no tasks. + * Since cpulist_parse() fails on an empty mask, we special case + * that parsing. The validate_change() call ensures that cpusets + * with tasks have cpus. + */ + if (!*buf) { + cpumask_clear(trialcs->cpus_allowed); + } else { + retval = cpulist_parse(buf, trialcs->cpus_allowed); + if (retval < 0) + return retval; + + if (!cpumask_subset(trialcs->cpus_allowed, + top_cpuset.cpus_allowed)) + return -EINVAL; + } + + /* Nothing to do if the cpus didn't change */ + if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) + return 0; + +#ifdef CONFIG_CPUMASK_OFFSTACK + /* + * Use the cpumasks in trialcs for tmpmasks when they are pointers + * to allocated cpumasks. + * + * Note that update_parent_subparts_cpumask() uses only addmask & + * delmask, but not new_cpus. + */ + tmp.addmask = trialcs->subparts_cpus; + tmp.delmask = trialcs->effective_cpus; + tmp.new_cpus = NULL; +#endif + + retval = validate_change(cs, trialcs); + + if ((retval == -EINVAL) && cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) { + struct cpuset *cp, *parent; + struct cgroup_subsys_state *css; + + /* + * The -EINVAL error code indicates that partition sibling + * CPU exclusivity rule has been violated. We still allow + * the cpumask change to proceed while invalidating the + * partition. However, any conflicting sibling partitions + * have to be marked as invalid too. + */ + invalidate = true; + rcu_read_lock(); + parent = parent_cs(cs); + cpuset_for_each_child(cp, css, parent) + if (is_partition_valid(cp) && + cpumask_intersects(trialcs->cpus_allowed, cp->cpus_allowed)) { + rcu_read_unlock(); + update_parent_subparts_cpumask(cp, partcmd_invalidate, NULL, &tmp); + rcu_read_lock(); + } + rcu_read_unlock(); + retval = 0; + } + if (retval < 0) + return retval; + + if (cs->partition_root_state) { + if (invalidate) + update_parent_subparts_cpumask(cs, partcmd_invalidate, + NULL, &tmp); + else + update_parent_subparts_cpumask(cs, partcmd_update, + trialcs->cpus_allowed, &tmp); + } + + compute_effective_cpumask(trialcs->effective_cpus, trialcs, + parent_cs(cs)); + spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); + + /* + * Make sure that subparts_cpus, if not empty, is a subset of + * cpus_allowed. Clear subparts_cpus if partition not valid or + * empty effective cpus with tasks. + */ + if (cs->nr_subparts_cpus) { + if (!is_partition_valid(cs) || + (cpumask_subset(trialcs->effective_cpus, cs->subparts_cpus) && + partition_is_populated(cs, NULL))) { + cs->nr_subparts_cpus = 0; + cpumask_clear(cs->subparts_cpus); + } else { + cpumask_and(cs->subparts_cpus, cs->subparts_cpus, + cs->cpus_allowed); + cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); + } + } + spin_unlock_irq(&callback_lock); + +#ifdef CONFIG_CPUMASK_OFFSTACK + /* Now trialcs->cpus_allowed is available */ + tmp.new_cpus = trialcs->cpus_allowed; +#endif + + /* effective_cpus will be updated here */ + update_cpumasks_hier(cs, &tmp, false); + + if (cs->partition_root_state) { + struct cpuset *parent = parent_cs(cs); + + /* + * For partition root, update the cpumasks of sibling + * cpusets if they use parent's effective_cpus. + */ + if (parent->child_ecpus_count) + update_sibling_cpumasks(parent, cs, &tmp); + } + return 0; +} + +/* + * Migrate memory region from one set of nodes to another. This is + * performed asynchronously as it can be called from process migration path + * holding locks involved in process management. All mm migrations are + * performed in the queued order and can be waited for by flushing + * cpuset_migrate_mm_wq. + */ + +struct cpuset_migrate_mm_work { + struct work_struct work; + struct mm_struct *mm; + nodemask_t from; + nodemask_t to; +}; + +static void cpuset_migrate_mm_workfn(struct work_struct *work) +{ + struct cpuset_migrate_mm_work *mwork = + container_of(work, struct cpuset_migrate_mm_work, work); + + /* on a wq worker, no need to worry about %current's mems_allowed */ + do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); + mmput(mwork->mm); + kfree(mwork); +} + +static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to) +{ + struct cpuset_migrate_mm_work *mwork; + + if (nodes_equal(*from, *to)) { + mmput(mm); + return; + } + + mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); + if (mwork) { + mwork->mm = mm; + mwork->from = *from; + mwork->to = *to; + INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); + queue_work(cpuset_migrate_mm_wq, &mwork->work); + } else { + mmput(mm); + } +} + +static void cpuset_post_attach(void) +{ + flush_workqueue(cpuset_migrate_mm_wq); +} + +/* + * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy + * @tsk: the task to change + * @newmems: new nodes that the task will be set + * + * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed + * and rebind an eventual tasks' mempolicy. If the task is allocating in + * parallel, it might temporarily see an empty intersection, which results in + * a seqlock check and retry before OOM or allocation failure. + */ +static void cpuset_change_task_nodemask(struct task_struct *tsk, + nodemask_t *newmems) +{ + task_lock(tsk); + + local_irq_disable(); + write_seqcount_begin(&tsk->mems_allowed_seq); + + nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); + mpol_rebind_task(tsk, newmems); + tsk->mems_allowed = *newmems; + + write_seqcount_end(&tsk->mems_allowed_seq); + local_irq_enable(); + + task_unlock(tsk); +} + +static void *cpuset_being_rebound; + +/** + * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. + * @cs: the cpuset in which each task's mems_allowed mask needs to be changed + * + * Iterate through each task of @cs updating its mems_allowed to the + * effective cpuset's. As this function is called with cpuset_mutex held, + * cpuset membership stays stable. + */ +static void update_tasks_nodemask(struct cpuset *cs) +{ + static nodemask_t newmems; /* protected by cpuset_mutex */ + struct css_task_iter it; + struct task_struct *task; + + cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ + + guarantee_online_mems(cs, &newmems); + + /* + * The mpol_rebind_mm() call takes mmap_lock, which we couldn't + * take while holding tasklist_lock. Forks can happen - the + * mpol_dup() cpuset_being_rebound check will catch such forks, + * and rebind their vma mempolicies too. Because we still hold + * the global cpuset_mutex, we know that no other rebind effort + * will be contending for the global variable cpuset_being_rebound. + * It's ok if we rebind the same mm twice; mpol_rebind_mm() + * is idempotent. Also migrate pages in each mm to new nodes. + */ + css_task_iter_start(&cs->css, 0, &it); + while ((task = css_task_iter_next(&it))) { + struct mm_struct *mm; + bool migrate; + + cpuset_change_task_nodemask(task, &newmems); + + mm = get_task_mm(task); + if (!mm) + continue; + + migrate = is_memory_migrate(cs); + + mpol_rebind_mm(mm, &cs->mems_allowed); + if (migrate) + cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); + else + mmput(mm); + } + css_task_iter_end(&it); + + /* + * All the tasks' nodemasks have been updated, update + * cs->old_mems_allowed. + */ + cs->old_mems_allowed = newmems; + + /* We're done rebinding vmas to this cpuset's new mems_allowed. */ + cpuset_being_rebound = NULL; +} + +/* + * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree + * @cs: the cpuset to consider + * @new_mems: a temp variable for calculating new effective_mems + * + * When configured nodemask is changed, the effective nodemasks of this cpuset + * and all its descendants need to be updated. + * + * On legacy hierarchy, effective_mems will be the same with mems_allowed. + * + * Called with cpuset_mutex held + */ +static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) +{ + struct cpuset *cp; + struct cgroup_subsys_state *pos_css; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_css, cs) { + struct cpuset *parent = parent_cs(cp); + + nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); + + /* + * If it becomes empty, inherit the effective mask of the + * parent, which is guaranteed to have some MEMs. + */ + if (is_in_v2_mode() && nodes_empty(*new_mems)) + *new_mems = parent->effective_mems; + + /* Skip the whole subtree if the nodemask remains the same. */ + if (nodes_equal(*new_mems, cp->effective_mems)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } + + if (!css_tryget_online(&cp->css)) + continue; + rcu_read_unlock(); + + spin_lock_irq(&callback_lock); + cp->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + WARN_ON(!is_in_v2_mode() && + !nodes_equal(cp->mems_allowed, cp->effective_mems)); + + update_tasks_nodemask(cp); + + rcu_read_lock(); + css_put(&cp->css); + } + rcu_read_unlock(); +} + +/* + * Handle user request to change the 'mems' memory placement + * of a cpuset. Needs to validate the request, update the + * cpusets mems_allowed, and for each task in the cpuset, + * update mems_allowed and rebind task's mempolicy and any vma + * mempolicies and if the cpuset is marked 'memory_migrate', + * migrate the tasks pages to the new memory. + * + * Call with cpuset_mutex held. May take callback_lock during call. + * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, + * lock each such tasks mm->mmap_lock, scan its vma's and rebind + * their mempolicies to the cpusets new mems_allowed. + */ +static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) +{ + int retval; + + /* + * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; + * it's read-only + */ + if (cs == &top_cpuset) { + retval = -EACCES; + goto done; + } + + /* + * An empty mems_allowed is ok iff there are no tasks in the cpuset. + * Since nodelist_parse() fails on an empty mask, we special case + * that parsing. The validate_change() call ensures that cpusets + * with tasks have memory. + */ + if (!*buf) { + nodes_clear(trialcs->mems_allowed); + } else { + retval = nodelist_parse(buf, trialcs->mems_allowed); + if (retval < 0) + goto done; + + if (!nodes_subset(trialcs->mems_allowed, + top_cpuset.mems_allowed)) { + retval = -EINVAL; + goto done; + } + } + + if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { + retval = 0; /* Too easy - nothing to do */ + goto done; + } + retval = validate_change(cs, trialcs); + if (retval < 0) + goto done; + + check_insane_mems_config(&trialcs->mems_allowed); + + spin_lock_irq(&callback_lock); + cs->mems_allowed = trialcs->mems_allowed; + spin_unlock_irq(&callback_lock); + + /* use trialcs->mems_allowed as a temp variable */ + update_nodemasks_hier(cs, &trialcs->mems_allowed); +done: + return retval; +} + +bool current_cpuset_is_being_rebound(void) +{ + bool ret; + + rcu_read_lock(); + ret = task_cs(current) == cpuset_being_rebound; + rcu_read_unlock(); + + return ret; +} + +static int update_relax_domain_level(struct cpuset *cs, s64 val) +{ +#ifdef CONFIG_SMP + if (val < -1 || val >= sched_domain_level_max) + return -EINVAL; +#endif + + if (val != cs->relax_domain_level) { + cs->relax_domain_level = val; + if (!cpumask_empty(cs->cpus_allowed) && + is_sched_load_balance(cs)) + rebuild_sched_domains_locked(); + } + + return 0; +} + +/** + * update_tasks_flags - update the spread flags of tasks in the cpuset. + * @cs: the cpuset in which each task's spread flags needs to be changed + * + * Iterate through each task of @cs updating its spread flags. As this + * function is called with cpuset_mutex held, cpuset membership stays + * stable. + */ +static void update_tasks_flags(struct cpuset *cs) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&cs->css, 0, &it); + while ((task = css_task_iter_next(&it))) + cpuset_update_task_spread_flags(cs, task); + css_task_iter_end(&it); +} + +/* + * update_flag - read a 0 or a 1 in a file and update associated flag + * bit: the bit to update (see cpuset_flagbits_t) + * cs: the cpuset to update + * turning_on: whether the flag is being set or cleared + * + * Call with cpuset_mutex held. + */ + +static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, + int turning_on) +{ + struct cpuset *trialcs; + int balance_flag_changed; + int spread_flag_changed; + int err; + + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) + return -ENOMEM; + + if (turning_on) + set_bit(bit, &trialcs->flags); + else + clear_bit(bit, &trialcs->flags); + + err = validate_change(cs, trialcs); + if (err < 0) + goto out; + + balance_flag_changed = (is_sched_load_balance(cs) != + is_sched_load_balance(trialcs)); + + spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) + || (is_spread_page(cs) != is_spread_page(trialcs))); + + spin_lock_irq(&callback_lock); + cs->flags = trialcs->flags; + spin_unlock_irq(&callback_lock); + + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) + rebuild_sched_domains_locked(); + + if (spread_flag_changed) + update_tasks_flags(cs); +out: + free_cpuset(trialcs); + return err; +} + +/** + * update_prstate - update partition_root_state + * @cs: the cpuset to update + * @new_prs: new partition root state + * Return: 0 if successful, != 0 if error + * + * Call with cpuset_mutex held. + */ +static int update_prstate(struct cpuset *cs, int new_prs) +{ + int err = PERR_NONE, old_prs = cs->partition_root_state; + bool sched_domain_rebuilt = false; + struct cpuset *parent = parent_cs(cs); + struct tmpmasks tmpmask; + + if (old_prs == new_prs) + return 0; + + /* + * For a previously invalid partition root, leave it at being + * invalid if new_prs is not "member". + */ + if (new_prs && is_prs_invalid(old_prs)) { + cs->partition_root_state = -new_prs; + return 0; + } + + if (alloc_cpumasks(NULL, &tmpmask)) + return -ENOMEM; + + if (!old_prs) { + /* + * Turning on partition root requires setting the + * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed + * cannot be empty. + */ + if (cpumask_empty(cs->cpus_allowed)) { + err = PERR_CPUSEMPTY; + goto out; + } + + err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); + if (err) { + err = PERR_NOTEXCL; + goto out; + } + + err = update_parent_subparts_cpumask(cs, partcmd_enable, + NULL, &tmpmask); + if (err) { + update_flag(CS_CPU_EXCLUSIVE, cs, 0); + goto out; + } + + if (new_prs == PRS_ISOLATED) { + /* + * Disable the load balance flag should not return an + * error unless the system is running out of memory. + */ + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + sched_domain_rebuilt = true; + } + } else if (old_prs && new_prs) { + /* + * A change in load balance state only, no change in cpumasks. + */ + update_flag(CS_SCHED_LOAD_BALANCE, cs, (new_prs != PRS_ISOLATED)); + sched_domain_rebuilt = true; + goto out; /* Sched domain is rebuilt in update_flag() */ + } else { + /* + * Switching back to member is always allowed even if it + * disables child partitions. + */ + update_parent_subparts_cpumask(cs, partcmd_disable, NULL, + &tmpmask); + + /* + * If there are child partitions, they will all become invalid. + */ + if (unlikely(cs->nr_subparts_cpus)) { + spin_lock_irq(&callback_lock); + cs->nr_subparts_cpus = 0; + cpumask_clear(cs->subparts_cpus); + compute_effective_cpumask(cs->effective_cpus, cs, parent); + spin_unlock_irq(&callback_lock); + } + + /* Turning off CS_CPU_EXCLUSIVE will not return error */ + update_flag(CS_CPU_EXCLUSIVE, cs, 0); + + if (!is_sched_load_balance(cs)) { + /* Make sure load balance is on */ + update_flag(CS_SCHED_LOAD_BALANCE, cs, 1); + sched_domain_rebuilt = true; + } + } + + update_tasks_cpumask(parent, tmpmask.new_cpus); + + if (parent->child_ecpus_count) + update_sibling_cpumasks(parent, cs, &tmpmask); + + if (!sched_domain_rebuilt) + rebuild_sched_domains_locked(); +out: + /* + * Make partition invalid if an error happen + */ + if (err) + new_prs = -new_prs; + spin_lock_irq(&callback_lock); + cs->partition_root_state = new_prs; + WRITE_ONCE(cs->prs_err, err); + spin_unlock_irq(&callback_lock); + /* + * Update child cpusets, if present. + * Force update if switching back to member. + */ + if (!list_empty(&cs->css.children)) + update_cpumasks_hier(cs, &tmpmask, !new_prs); + + notify_partition_change(cs, old_prs); + free_cpumasks(NULL, &tmpmask); + return 0; +} + +/* + * Frequency meter - How fast is some event occurring? + * + * These routines manage a digitally filtered, constant time based, + * event frequency meter. There are four routines: + * fmeter_init() - initialize a frequency meter. + * fmeter_markevent() - called each time the event happens. + * fmeter_getrate() - returns the recent rate of such events. + * fmeter_update() - internal routine used to update fmeter. + * + * A common data structure is passed to each of these routines, + * which is used to keep track of the state required to manage the + * frequency meter and its digital filter. + * + * The filter works on the number of events marked per unit time. + * The filter is single-pole low-pass recursive (IIR). The time unit + * is 1 second. Arithmetic is done using 32-bit integers scaled to + * simulate 3 decimal digits of precision (multiplied by 1000). + * + * With an FM_COEF of 933, and a time base of 1 second, the filter + * has a half-life of 10 seconds, meaning that if the events quit + * happening, then the rate returned from the fmeter_getrate() + * will be cut in half each 10 seconds, until it converges to zero. + * + * It is not worth doing a real infinitely recursive filter. If more + * than FM_MAXTICKS ticks have elapsed since the last filter event, + * just compute FM_MAXTICKS ticks worth, by which point the level + * will be stable. + * + * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid + * arithmetic overflow in the fmeter_update() routine. + * + * Given the simple 32 bit integer arithmetic used, this meter works + * best for reporting rates between one per millisecond (msec) and + * one per 32 (approx) seconds. At constant rates faster than one + * per msec it maxes out at values just under 1,000,000. At constant + * rates between one per msec, and one per second it will stabilize + * to a value N*1000, where N is the rate of events per second. + * At constant rates between one per second and one per 32 seconds, + * it will be choppy, moving up on the seconds that have an event, + * and then decaying until the next event. At rates slower than + * about one in 32 seconds, it decays all the way back to zero between + * each event. + */ + +#define FM_COEF 933 /* coefficient for half-life of 10 secs */ +#define FM_MAXTICKS ((u32)99) /* useless computing more ticks than this */ +#define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ +#define FM_SCALE 1000 /* faux fixed point scale */ + +/* Initialize a frequency meter */ +static void fmeter_init(struct fmeter *fmp) +{ + fmp->cnt = 0; + fmp->val = 0; + fmp->time = 0; + spin_lock_init(&fmp->lock); +} + +/* Internal meter update - process cnt events and update value */ +static void fmeter_update(struct fmeter *fmp) +{ + time64_t now; + u32 ticks; + + now = ktime_get_seconds(); + ticks = now - fmp->time; + + if (ticks == 0) + return; + + ticks = min(FM_MAXTICKS, ticks); + while (ticks-- > 0) + fmp->val = (FM_COEF * fmp->val) / FM_SCALE; + fmp->time = now; + + fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; + fmp->cnt = 0; +} + +/* Process any previous ticks, then bump cnt by one (times scale). */ +static void fmeter_markevent(struct fmeter *fmp) +{ + spin_lock(&fmp->lock); + fmeter_update(fmp); + fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); + spin_unlock(&fmp->lock); +} + +/* Process any previous ticks, then return current value. */ +static int fmeter_getrate(struct fmeter *fmp) +{ + int val; + + spin_lock(&fmp->lock); + fmeter_update(fmp); + val = fmp->val; + spin_unlock(&fmp->lock); + return val; +} + +static struct cpuset *cpuset_attach_old_cs; + +/* + * Check to see if a cpuset can accept a new task + * For v1, cpus_allowed and mems_allowed can't be empty. + * For v2, effective_cpus can't be empty. + * Note that in v1, effective_cpus = cpus_allowed. + */ +static int cpuset_can_attach_check(struct cpuset *cs) +{ + if (cpumask_empty(cs->effective_cpus) || + (!is_in_v2_mode() && nodes_empty(cs->mems_allowed))) + return -ENOSPC; + return 0; +} + +static void reset_migrate_dl_data(struct cpuset *cs) +{ + cs->nr_migrate_dl_tasks = 0; + cs->sum_migrate_dl_bw = 0; +} + +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ +static int cpuset_can_attach(struct cgroup_taskset *tset) +{ + struct cgroup_subsys_state *css; + struct cpuset *cs, *oldcs; + struct task_struct *task; + int ret; + + /* used later by cpuset_attach() */ + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + oldcs = cpuset_attach_old_cs; + cs = css_cs(css); + + mutex_lock(&cpuset_mutex); + + /* Check to see if task is allowed in the cpuset */ + ret = cpuset_can_attach_check(cs); + if (ret) + goto out_unlock; + + cgroup_taskset_for_each(task, css, tset) { + ret = task_can_attach(task); + if (ret) + goto out_unlock; + ret = security_task_setscheduler(task); + if (ret) + goto out_unlock; + + if (dl_task(task)) { + cs->nr_migrate_dl_tasks++; + cs->sum_migrate_dl_bw += task->dl.dl_bw; + } + } + + if (!cs->nr_migrate_dl_tasks) + goto out_success; + + if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { + int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + + if (unlikely(cpu >= nr_cpu_ids)) { + reset_migrate_dl_data(cs); + ret = -EINVAL; + goto out_unlock; + } + + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) { + reset_migrate_dl_data(cs); + goto out_unlock; + } + } + +out_success: + /* + * Mark attach is in progress. This makes validate_change() fail + * changes which zero cpus/mems_allowed. + */ + cs->attach_in_progress++; +out_unlock: + mutex_unlock(&cpuset_mutex); + return ret; +} + +static void cpuset_cancel_attach(struct cgroup_taskset *tset) +{ + struct cgroup_subsys_state *css; + struct cpuset *cs; + + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + + mutex_lock(&cpuset_mutex); + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + + if (cs->nr_migrate_dl_tasks) { + int cpu = cpumask_any(cs->effective_cpus); + + dl_bw_free(cpu, cs->sum_migrate_dl_bw); + reset_migrate_dl_data(cs); + } + + mutex_unlock(&cpuset_mutex); +} + +/* + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task() + * but we can't allocate it dynamically there. Define it global and + * allocate from cpuset_init(). + */ +static cpumask_var_t cpus_attach; +static nodemask_t cpuset_attach_nodemask_to; + +static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) +{ + lockdep_assert_held(&cpuset_mutex); + + if (cs != &top_cpuset) + guarantee_online_cpus(task, cpus_attach); + else + cpumask_copy(cpus_attach, task_cpu_possible_mask(task)); + /* + * can_attach beforehand should guarantee that this doesn't + * fail. TODO: have a better way to handle failure here + */ + WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); + + cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); + cpuset_update_task_spread_flags(cs, task); +} + +static void cpuset_attach(struct cgroup_taskset *tset) +{ + struct task_struct *task; + struct task_struct *leader; + struct cgroup_subsys_state *css; + struct cpuset *cs; + struct cpuset *oldcs = cpuset_attach_old_cs; + + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + + lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ + mutex_lock(&cpuset_mutex); + + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + + cgroup_taskset_for_each(task, css, tset) + cpuset_attach_task(cs, task); + + /* + * Change mm for all threadgroup leaders. This is expensive and may + * sleep and should be moved outside migration path proper. + */ + cpuset_attach_nodemask_to = cs->effective_mems; + cgroup_taskset_for_each_leader(leader, css, tset) { + struct mm_struct *mm = get_task_mm(leader); + + if (mm) { + mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); + + /* + * old_mems_allowed is the same with mems_allowed + * here, except if this task is being moved + * automatically due to hotplug. In that case + * @mems_allowed has been updated and is empty, so + * @old_mems_allowed is the right nodesets that we + * migrate mm from. + */ + if (is_memory_migrate(cs)) + cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, + &cpuset_attach_nodemask_to); + else + mmput(mm); + } + } + + cs->old_mems_allowed = cpuset_attach_nodemask_to; + + if (cs->nr_migrate_dl_tasks) { + cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; + oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; + reset_migrate_dl_data(cs); + } + + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + + mutex_unlock(&cpuset_mutex); +} + +/* The various types of files and directories in a cpuset file system */ + +typedef enum { + FILE_MEMORY_MIGRATE, + FILE_CPULIST, + FILE_MEMLIST, + FILE_EFFECTIVE_CPULIST, + FILE_EFFECTIVE_MEMLIST, + FILE_SUBPARTS_CPULIST, + FILE_CPU_EXCLUSIVE, + FILE_MEM_EXCLUSIVE, + FILE_MEM_HARDWALL, + FILE_SCHED_LOAD_BALANCE, + FILE_PARTITION_ROOT, + FILE_SCHED_RELAX_DOMAIN_LEVEL, + FILE_MEMORY_PRESSURE_ENABLED, + FILE_MEMORY_PRESSURE, + FILE_SPREAD_PAGE, + FILE_SPREAD_SLAB, +} cpuset_filetype_t; + +static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + int retval = 0; + + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) { + retval = -ENODEV; + goto out_unlock; + } + + switch (type) { + case FILE_CPU_EXCLUSIVE: + retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); + break; + case FILE_MEM_EXCLUSIVE: + retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); + break; + case FILE_MEM_HARDWALL: + retval = update_flag(CS_MEM_HARDWALL, cs, val); + break; + case FILE_SCHED_LOAD_BALANCE: + retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); + break; + case FILE_MEMORY_MIGRATE: + retval = update_flag(CS_MEMORY_MIGRATE, cs, val); + break; + case FILE_MEMORY_PRESSURE_ENABLED: + cpuset_memory_pressure_enabled = !!val; + break; + case FILE_SPREAD_PAGE: + retval = update_flag(CS_SPREAD_PAGE, cs, val); + break; + case FILE_SPREAD_SLAB: + retval = update_flag(CS_SPREAD_SLAB, cs, val); + break; + default: + retval = -EINVAL; + break; + } +out_unlock: + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + return retval; +} + +static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + int retval = -ENODEV; + + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; + + switch (type) { + case FILE_SCHED_RELAX_DOMAIN_LEVEL: + retval = update_relax_domain_level(cs, val); + break; + default: + retval = -EINVAL; + break; + } +out_unlock: + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + return retval; +} + +/* + * Common handling for a write to a "cpus" or "mems" file. + */ +static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cpuset *cs = css_cs(of_css(of)); + struct cpuset *trialcs; + int retval = -ENODEV; + + buf = strstrip(buf); + + /* + * CPU or memory hotunplug may leave @cs w/o any execution + * resources, in which case the hotplug code asynchronously updates + * configuration and transfers all tasks to the nearest ancestor + * which can execute. + * + * As writes to "cpus" or "mems" may restore @cs's execution + * resources, wait for the previously scheduled operations before + * proceeding, so that we don't end up keep removing tasks added + * after execution capability is restored. + * + * cpuset_hotplug_work calls back into cgroup core via + * cgroup_transfer_tasks() and waiting for it from a cgroupfs + * operation like this one can lead to a deadlock through kernfs + * active_ref protection. Let's break the protection. Losing the + * protection is okay as we check whether @cs is online after + * grabbing cpuset_mutex anyway. This only happens on the legacy + * hierarchies. + */ + css_get(&cs->css); + kernfs_break_active_protection(of->kn); + flush_work(&cpuset_hotplug_work); + + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; + + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) { + retval = -ENOMEM; + goto out_unlock; + } + + switch (of_cft(of)->private) { + case FILE_CPULIST: + retval = update_cpumask(cs, trialcs, buf); + break; + case FILE_MEMLIST: + retval = update_nodemask(cs, trialcs, buf); + break; + default: + retval = -EINVAL; + break; + } + + free_cpuset(trialcs); +out_unlock: + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + kernfs_unbreak_active_protection(of->kn); + css_put(&cs->css); + flush_workqueue(cpuset_migrate_mm_wq); + return retval ?: nbytes; +} + +/* + * These ascii lists should be read in a single call, by using a user + * buffer large enough to hold the entire map. If read in smaller + * chunks, there is no guarantee of atomicity. Since the display format + * used, list of ranges of sequential numbers, is variable length, + * and since these maps can change value dynamically, one could read + * gibberish by doing partial reads while a list was changing. + */ +static int cpuset_common_seq_show(struct seq_file *sf, void *v) +{ + struct cpuset *cs = css_cs(seq_css(sf)); + cpuset_filetype_t type = seq_cft(sf)->private; + int ret = 0; + + spin_lock_irq(&callback_lock); + + switch (type) { + case FILE_CPULIST: + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); + break; + case FILE_MEMLIST: + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); + break; + case FILE_EFFECTIVE_CPULIST: + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); + break; + case FILE_EFFECTIVE_MEMLIST: + seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); + break; + case FILE_SUBPARTS_CPULIST: + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus)); + break; + default: + ret = -EINVAL; + } + + spin_unlock_irq(&callback_lock); + return ret; +} + +static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + switch (type) { + case FILE_CPU_EXCLUSIVE: + return is_cpu_exclusive(cs); + case FILE_MEM_EXCLUSIVE: + return is_mem_exclusive(cs); + case FILE_MEM_HARDWALL: + return is_mem_hardwall(cs); + case FILE_SCHED_LOAD_BALANCE: + return is_sched_load_balance(cs); + case FILE_MEMORY_MIGRATE: + return is_memory_migrate(cs); + case FILE_MEMORY_PRESSURE_ENABLED: + return cpuset_memory_pressure_enabled; + case FILE_MEMORY_PRESSURE: + return fmeter_getrate(&cs->fmeter); + case FILE_SPREAD_PAGE: + return is_spread_page(cs); + case FILE_SPREAD_SLAB: + return is_spread_slab(cs); + default: + BUG(); + } + + /* Unreachable but makes gcc happy */ + return 0; +} + +static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct cpuset *cs = css_cs(css); + cpuset_filetype_t type = cft->private; + switch (type) { + case FILE_SCHED_RELAX_DOMAIN_LEVEL: + return cs->relax_domain_level; + default: + BUG(); + } + + /* Unreachable but makes gcc happy */ + return 0; +} + +static int sched_partition_show(struct seq_file *seq, void *v) +{ + struct cpuset *cs = css_cs(seq_css(seq)); + const char *err, *type = NULL; + + switch (cs->partition_root_state) { + case PRS_ROOT: + seq_puts(seq, "root\n"); + break; + case PRS_ISOLATED: + seq_puts(seq, "isolated\n"); + break; + case PRS_MEMBER: + seq_puts(seq, "member\n"); + break; + case PRS_INVALID_ROOT: + type = "root"; + fallthrough; + case PRS_INVALID_ISOLATED: + if (!type) + type = "isolated"; + err = perr_strings[READ_ONCE(cs->prs_err)]; + if (err) + seq_printf(seq, "%s invalid (%s)\n", type, err); + else + seq_printf(seq, "%s invalid\n", type); + break; + } + return 0; +} + +static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct cpuset *cs = css_cs(of_css(of)); + int val; + int retval = -ENODEV; + + buf = strstrip(buf); + + /* + * Convert "root" to ENABLED, and convert "member" to DISABLED. + */ + if (!strcmp(buf, "root")) + val = PRS_ROOT; + else if (!strcmp(buf, "member")) + val = PRS_MEMBER; + else if (!strcmp(buf, "isolated")) + val = PRS_ISOLATED; + else + return -EINVAL; + + css_get(&cs->css); + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; + + retval = update_prstate(cs, val); +out_unlock: + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + css_put(&cs->css); + return retval ?: nbytes; +} + +/* + * for the common functions, 'private' gives the type of file + */ + +static struct cftype legacy_files[] = { + { + .name = "cpus", + .seq_show = cpuset_common_seq_show, + .write = cpuset_write_resmask, + .max_write_len = (100U + 6 * NR_CPUS), + .private = FILE_CPULIST, + }, + + { + .name = "mems", + .seq_show = cpuset_common_seq_show, + .write = cpuset_write_resmask, + .max_write_len = (100U + 6 * MAX_NUMNODES), + .private = FILE_MEMLIST, + }, + + { + .name = "effective_cpus", + .seq_show = cpuset_common_seq_show, + .private = FILE_EFFECTIVE_CPULIST, + }, + + { + .name = "effective_mems", + .seq_show = cpuset_common_seq_show, + .private = FILE_EFFECTIVE_MEMLIST, + }, + + { + .name = "cpu_exclusive", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_CPU_EXCLUSIVE, + }, + + { + .name = "mem_exclusive", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEM_EXCLUSIVE, + }, + + { + .name = "mem_hardwall", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEM_HARDWALL, + }, + + { + .name = "sched_load_balance", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_SCHED_LOAD_BALANCE, + }, + + { + .name = "sched_relax_domain_level", + .read_s64 = cpuset_read_s64, + .write_s64 = cpuset_write_s64, + .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, + }, + + { + .name = "memory_migrate", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEMORY_MIGRATE, + }, + + { + .name = "memory_pressure", + .read_u64 = cpuset_read_u64, + .private = FILE_MEMORY_PRESSURE, + }, + + { + .name = "memory_spread_page", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_SPREAD_PAGE, + }, + + { + .name = "memory_spread_slab", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_SPREAD_SLAB, + }, + + { + .name = "memory_pressure_enabled", + .flags = CFTYPE_ONLY_ON_ROOT, + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEMORY_PRESSURE_ENABLED, + }, + + { } /* terminate */ +}; + +/* + * This is currently a minimal set for the default hierarchy. It can be + * expanded later on by migrating more features and control files from v1. + */ +static struct cftype dfl_files[] = { + { + .name = "cpus", + .seq_show = cpuset_common_seq_show, + .write = cpuset_write_resmask, + .max_write_len = (100U + 6 * NR_CPUS), + .private = FILE_CPULIST, + .flags = CFTYPE_NOT_ON_ROOT, + }, + + { + .name = "mems", + .seq_show = cpuset_common_seq_show, + .write = cpuset_write_resmask, + .max_write_len = (100U + 6 * MAX_NUMNODES), + .private = FILE_MEMLIST, + .flags = CFTYPE_NOT_ON_ROOT, + }, + + { + .name = "cpus.effective", + .seq_show = cpuset_common_seq_show, + .private = FILE_EFFECTIVE_CPULIST, + }, + + { + .name = "mems.effective", + .seq_show = cpuset_common_seq_show, + .private = FILE_EFFECTIVE_MEMLIST, + }, + + { + .name = "cpus.partition", + .seq_show = sched_partition_show, + .write = sched_partition_write, + .private = FILE_PARTITION_ROOT, + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct cpuset, partition_file), + }, + + { + .name = "cpus.subpartitions", + .seq_show = cpuset_common_seq_show, + .private = FILE_SUBPARTS_CPULIST, + .flags = CFTYPE_DEBUG, + }, + + { } /* terminate */ +}; + + +/* + * cpuset_css_alloc - allocate a cpuset css + * cgrp: control group that the new cpuset will be part of + */ + +static struct cgroup_subsys_state * +cpuset_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cpuset *cs; + + if (!parent_css) + return &top_cpuset.css; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + if (alloc_cpumasks(cs, NULL)) { + kfree(cs); + return ERR_PTR(-ENOMEM); + } + + __set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); + nodes_clear(cs->mems_allowed); + nodes_clear(cs->effective_mems); + fmeter_init(&cs->fmeter); + cs->relax_domain_level = -1; + + /* Set CS_MEMORY_MIGRATE for default hierarchy */ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) + __set_bit(CS_MEMORY_MIGRATE, &cs->flags); + + return &cs->css; +} + +static int cpuset_css_online(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + struct cpuset *parent = parent_cs(cs); + struct cpuset *tmp_cs; + struct cgroup_subsys_state *pos_css; + + if (!parent) + return 0; + + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + + set_bit(CS_ONLINE, &cs->flags); + if (is_spread_page(parent)) + set_bit(CS_SPREAD_PAGE, &cs->flags); + if (is_spread_slab(parent)) + set_bit(CS_SPREAD_SLAB, &cs->flags); + + cpuset_inc(); + + spin_lock_irq(&callback_lock); + if (is_in_v2_mode()) { + cpumask_copy(cs->effective_cpus, parent->effective_cpus); + cs->effective_mems = parent->effective_mems; + cs->use_parent_ecpus = true; + parent->child_ecpus_count++; + } + + /* + * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated + */ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + !is_sched_load_balance(parent)) + clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); + + spin_unlock_irq(&callback_lock); + + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) + goto out_unlock; + + /* + * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is + * set. This flag handling is implemented in cgroup core for + * historical reasons - the flag may be specified during mount. + * + * Currently, if any sibling cpusets have exclusive cpus or mem, we + * refuse to clone the configuration - thereby refusing the task to + * be entered, and as a result refusing the sys_unshare() or + * clone() which initiated it. If this becomes a problem for some + * users who wish to allow that scenario, then this could be + * changed to grant parent->cpus_allowed-sibling_cpus_exclusive + * (and likewise for mems) to the new cgroup. + */ + rcu_read_lock(); + cpuset_for_each_child(tmp_cs, pos_css, parent) { + if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { + rcu_read_unlock(); + goto out_unlock; + } + } + rcu_read_unlock(); + + spin_lock_irq(&callback_lock); + cs->mems_allowed = parent->mems_allowed; + cs->effective_mems = parent->mems_allowed; + cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); + cpumask_copy(cs->effective_cpus, parent->cpus_allowed); + spin_unlock_irq(&callback_lock); +out_unlock: + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + return 0; +} + +/* + * If the cpuset being removed has its flag 'sched_load_balance' + * enabled, then simulate turning sched_load_balance off, which + * will call rebuild_sched_domains_locked(). That is not needed + * in the default hierarchy where only changes in partition + * will cause repartitioning. + * + * If the cpuset has the 'sched.partition' flag enabled, simulate + * turning 'sched.partition" off. + */ + +static void cpuset_css_offline(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + + if (is_partition_valid(cs)) + update_prstate(cs, 0); + + if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + is_sched_load_balance(cs)) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + + if (cs->use_parent_ecpus) { + struct cpuset *parent = parent_cs(cs); + + cs->use_parent_ecpus = false; + parent->child_ecpus_count--; + } + + cpuset_dec(); + clear_bit(CS_ONLINE, &cs->flags); + + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); +} + +static void cpuset_css_free(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + + free_cpuset(cs); +} + +static void cpuset_bind(struct cgroup_subsys_state *root_css) +{ + mutex_lock(&cpuset_mutex); + spin_lock_irq(&callback_lock); + + if (is_in_v2_mode()) { + cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); + top_cpuset.mems_allowed = node_possible_map; + } else { + cpumask_copy(top_cpuset.cpus_allowed, + top_cpuset.effective_cpus); + top_cpuset.mems_allowed = top_cpuset.effective_mems; + } + + spin_unlock_irq(&callback_lock); + mutex_unlock(&cpuset_mutex); +} + +/* + * In case the child is cloned into a cpuset different from its parent, + * additional checks are done to see if the move is allowed. + */ +static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) +{ + struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); + bool same_cs; + int ret; + + rcu_read_lock(); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) + return 0; + + lockdep_assert_held(&cgroup_mutex); + mutex_lock(&cpuset_mutex); + + /* Check to see if task is allowed in the cpuset */ + ret = cpuset_can_attach_check(cs); + if (ret) + goto out_unlock; + + ret = task_can_attach(task); + if (ret) + goto out_unlock; + + ret = security_task_setscheduler(task); + if (ret) + goto out_unlock; + + /* + * Mark attach is in progress. This makes validate_change() fail + * changes which zero cpus/mems_allowed. + */ + cs->attach_in_progress++; +out_unlock: + mutex_unlock(&cpuset_mutex); + return ret; +} + +static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) +{ + struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); + bool same_cs; + + rcu_read_lock(); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) + return; + + mutex_lock(&cpuset_mutex); + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + mutex_unlock(&cpuset_mutex); +} + +/* + * Make sure the new task conform to the current state of its parent, + * which could have been changed by cpuset just after it inherits the + * state from the parent and before it sits on the cgroup's task list. + */ +static void cpuset_fork(struct task_struct *task) +{ + struct cpuset *cs; + bool same_cs; + + rcu_read_lock(); + cs = task_cs(task); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) { + if (cs == &top_cpuset) + return; + + set_cpus_allowed_ptr(task, current->cpus_ptr); + task->mems_allowed = current->mems_allowed; + return; + } + + /* CLONE_INTO_CGROUP */ + mutex_lock(&cpuset_mutex); + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + cpuset_attach_task(cs, task); + + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + + mutex_unlock(&cpuset_mutex); +} + +struct cgroup_subsys cpuset_cgrp_subsys = { + .css_alloc = cpuset_css_alloc, + .css_online = cpuset_css_online, + .css_offline = cpuset_css_offline, + .css_free = cpuset_css_free, + .can_attach = cpuset_can_attach, + .cancel_attach = cpuset_cancel_attach, + .attach = cpuset_attach, + .post_attach = cpuset_post_attach, + .bind = cpuset_bind, + .can_fork = cpuset_can_fork, + .cancel_fork = cpuset_cancel_fork, + .fork = cpuset_fork, + .legacy_cftypes = legacy_files, + .dfl_cftypes = dfl_files, + .early_init = true, + .threaded = true, +}; + +/** + * cpuset_init - initialize cpusets at system boot + * + * Description: Initialize top_cpuset + **/ + +int __init cpuset_init(void) +{ + BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); + + cpumask_setall(top_cpuset.cpus_allowed); + nodes_setall(top_cpuset.mems_allowed); + cpumask_setall(top_cpuset.effective_cpus); + nodes_setall(top_cpuset.effective_mems); + + fmeter_init(&top_cpuset.fmeter); + set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); + top_cpuset.relax_domain_level = -1; + + BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); + + return 0; +} + +/* + * If CPU and/or memory hotplug handlers, below, unplug any CPUs + * or memory nodes, we need to walk over the cpuset hierarchy, + * removing that CPU or node from all cpusets. If this removes the + * last CPU or node from a cpuset, then move the tasks in the empty + * cpuset to its next-highest non-empty parent. + */ +static void remove_tasks_in_empty_cpuset(struct cpuset *cs) +{ + struct cpuset *parent; + + /* + * Find its next-highest non-empty parent, (top cpuset + * has online cpus, so can't be empty). + */ + parent = parent_cs(cs); + while (cpumask_empty(parent->cpus_allowed) || + nodes_empty(parent->mems_allowed)) + parent = parent_cs(parent); + + if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { + pr_err("cpuset: failed to transfer tasks out of empty cpuset "); + pr_cont_cgroup_name(cs->css.cgroup); + pr_cont("\n"); + } +} + +static void +hotplug_update_tasks_legacy(struct cpuset *cs, + struct cpumask *new_cpus, nodemask_t *new_mems, + bool cpus_updated, bool mems_updated) +{ + bool is_empty; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, new_cpus); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->mems_allowed = *new_mems; + cs->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + /* + * Don't call update_tasks_cpumask() if the cpuset becomes empty, + * as the tasks will be migrated to an ancestor. + */ + if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) + update_tasks_cpumask(cs, new_cpus); + if (mems_updated && !nodes_empty(cs->mems_allowed)) + update_tasks_nodemask(cs); + + is_empty = cpumask_empty(cs->cpus_allowed) || + nodes_empty(cs->mems_allowed); + + mutex_unlock(&cpuset_mutex); + + /* + * Move tasks to the nearest ancestor with execution resources, + * This is full cgroup operation which will also call back into + * cpuset. Should be done outside any lock. + */ + if (is_empty) + remove_tasks_in_empty_cpuset(cs); + + mutex_lock(&cpuset_mutex); +} + +static void +hotplug_update_tasks(struct cpuset *cs, + struct cpumask *new_cpus, nodemask_t *new_mems, + bool cpus_updated, bool mems_updated) +{ + /* A partition root is allowed to have empty effective cpus */ + if (cpumask_empty(new_cpus) && !is_partition_valid(cs)) + cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); + if (nodes_empty(*new_mems)) + *new_mems = parent_cs(cs)->effective_mems; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + if (cpus_updated) + update_tasks_cpumask(cs, new_cpus); + if (mems_updated) + update_tasks_nodemask(cs); +} + +static bool force_rebuild; + +void cpuset_force_rebuild(void) +{ + force_rebuild = true; +} + +/** + * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug + * @cs: cpuset in interest + * @tmp: the tmpmasks structure pointer + * + * Compare @cs's cpu and mem masks against top_cpuset and if some have gone + * offline, update @cs accordingly. If @cs ends up with no CPU or memory, + * all its tasks are moved to the nearest ancestor with both resources. + */ +static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) +{ + static cpumask_t new_cpus; + static nodemask_t new_mems; + bool cpus_updated; + bool mems_updated; + struct cpuset *parent; +retry: + wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); + + mutex_lock(&cpuset_mutex); + + /* + * We have raced with task attaching. We wait until attaching + * is finished, so we won't attach a task to an empty cpuset. + */ + if (cs->attach_in_progress) { + mutex_unlock(&cpuset_mutex); + goto retry; + } + + parent = parent_cs(cs); + compute_effective_cpumask(&new_cpus, cs, parent); + nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); + + if (cs->nr_subparts_cpus) + /* + * Make sure that CPUs allocated to child partitions + * do not show up in effective_cpus. + */ + cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus); + + if (!tmp || !cs->partition_root_state) + goto update_tasks; + + /* + * In the unlikely event that a partition root has empty + * effective_cpus with tasks, we will have to invalidate child + * partitions, if present, by setting nr_subparts_cpus to 0 to + * reclaim their cpus. + */ + if (cs->nr_subparts_cpus && is_partition_valid(cs) && + cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) { + spin_lock_irq(&callback_lock); + cs->nr_subparts_cpus = 0; + cpumask_clear(cs->subparts_cpus); + spin_unlock_irq(&callback_lock); + compute_effective_cpumask(&new_cpus, cs, parent); + } + + /* + * Force the partition to become invalid if either one of + * the following conditions hold: + * 1) empty effective cpus but not valid empty partition. + * 2) parent is invalid or doesn't grant any cpus to child + * partitions. + */ + if (is_partition_valid(cs) && (!parent->nr_subparts_cpus || + (cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)))) { + int old_prs, parent_prs; + + update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); + if (cs->nr_subparts_cpus) { + spin_lock_irq(&callback_lock); + cs->nr_subparts_cpus = 0; + cpumask_clear(cs->subparts_cpus); + spin_unlock_irq(&callback_lock); + compute_effective_cpumask(&new_cpus, cs, parent); + } + + old_prs = cs->partition_root_state; + parent_prs = parent->partition_root_state; + if (is_partition_valid(cs)) { + spin_lock_irq(&callback_lock); + make_partition_invalid(cs); + spin_unlock_irq(&callback_lock); + if (is_prs_invalid(parent_prs)) + WRITE_ONCE(cs->prs_err, PERR_INVPARENT); + else if (!parent_prs) + WRITE_ONCE(cs->prs_err, PERR_NOTPART); + else + WRITE_ONCE(cs->prs_err, PERR_HOTPLUG); + notify_partition_change(cs, old_prs); + } + cpuset_force_rebuild(); + } + + /* + * On the other hand, an invalid partition root may be transitioned + * back to a regular one. + */ + else if (is_partition_valid(parent) && is_partition_invalid(cs)) { + update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp); + if (is_partition_valid(cs)) + cpuset_force_rebuild(); + } + +update_tasks: + cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); + mems_updated = !nodes_equal(new_mems, cs->effective_mems); + + if (mems_updated) + check_insane_mems_config(&new_mems); + + if (is_in_v2_mode()) + hotplug_update_tasks(cs, &new_cpus, &new_mems, + cpus_updated, mems_updated); + else + hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, + cpus_updated, mems_updated); + + mutex_unlock(&cpuset_mutex); +} + +/** + * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset + * + * This function is called after either CPU or memory configuration has + * changed and updates cpuset accordingly. The top_cpuset is always + * synchronized to cpu_active_mask and N_MEMORY, which is necessary in + * order to make cpusets transparent (of no affect) on systems that are + * actively using CPU hotplug but making no active use of cpusets. + * + * Non-root cpusets are only affected by offlining. If any CPUs or memory + * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on + * all descendants. + * + * Note that CPU offlining during suspend is ignored. We don't modify + * cpusets across suspend/resume cycles at all. + */ +static void cpuset_hotplug_workfn(struct work_struct *work) +{ + static cpumask_t new_cpus; + static nodemask_t new_mems; + bool cpus_updated, mems_updated; + bool on_dfl = is_in_v2_mode(); + struct tmpmasks tmp, *ptmp = NULL; + + if (on_dfl && !alloc_cpumasks(NULL, &tmp)) + ptmp = &tmp; + + mutex_lock(&cpuset_mutex); + + /* fetch the available cpus/mems and find out which changed how */ + cpumask_copy(&new_cpus, cpu_active_mask); + new_mems = node_states[N_MEMORY]; + + /* + * If subparts_cpus is populated, it is likely that the check below + * will produce a false positive on cpus_updated when the cpu list + * isn't changed. It is extra work, but it is better to be safe. + */ + cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); + mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); + + /* + * In the rare case that hotplug removes all the cpus in subparts_cpus, + * we assumed that cpus are updated. + */ + if (!cpus_updated && top_cpuset.nr_subparts_cpus) + cpus_updated = true; + + /* synchronize cpus_allowed to cpu_active_mask */ + if (cpus_updated) { + spin_lock_irq(&callback_lock); + if (!on_dfl) + cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); + /* + * Make sure that CPUs allocated to child partitions + * do not show up in effective_cpus. If no CPU is left, + * we clear the subparts_cpus & let the child partitions + * fight for the CPUs again. + */ + if (top_cpuset.nr_subparts_cpus) { + if (cpumask_subset(&new_cpus, + top_cpuset.subparts_cpus)) { + top_cpuset.nr_subparts_cpus = 0; + cpumask_clear(top_cpuset.subparts_cpus); + } else { + cpumask_andnot(&new_cpus, &new_cpus, + top_cpuset.subparts_cpus); + } + } + cpumask_copy(top_cpuset.effective_cpus, &new_cpus); + spin_unlock_irq(&callback_lock); + /* we don't mess with cpumasks of tasks in top_cpuset */ + } + + /* synchronize mems_allowed to N_MEMORY */ + if (mems_updated) { + spin_lock_irq(&callback_lock); + if (!on_dfl) + top_cpuset.mems_allowed = new_mems; + top_cpuset.effective_mems = new_mems; + spin_unlock_irq(&callback_lock); + update_tasks_nodemask(&top_cpuset); + } + + mutex_unlock(&cpuset_mutex); + + /* if cpus or mems changed, we need to propagate to descendants */ + if (cpus_updated || mems_updated) { + struct cpuset *cs; + struct cgroup_subsys_state *pos_css; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { + if (cs == &top_cpuset || !css_tryget_online(&cs->css)) + continue; + rcu_read_unlock(); + + cpuset_hotplug_update_tasks(cs, ptmp); + + rcu_read_lock(); + css_put(&cs->css); + } + rcu_read_unlock(); + } + + /* rebuild sched domains if cpus_allowed has changed */ + if (cpus_updated || force_rebuild) { + force_rebuild = false; + rebuild_sched_domains(); + } + + free_cpumasks(NULL, ptmp); +} + +void cpuset_update_active_cpus(void) +{ + /* + * We're inside cpu hotplug critical region which usually nests + * inside cgroup synchronization. Bounce actual hotplug processing + * to a work item to avoid reverse locking order. + */ + schedule_work(&cpuset_hotplug_work); +} + +void cpuset_wait_for_hotplug(void) +{ + flush_work(&cpuset_hotplug_work); +} + +/* + * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. + * Call this routine anytime after node_states[N_MEMORY] changes. + * See cpuset_update_active_cpus() for CPU hotplug handling. + */ +static int cpuset_track_online_nodes(struct notifier_block *self, + unsigned long action, void *arg) +{ + schedule_work(&cpuset_hotplug_work); + return NOTIFY_OK; +} + +static struct notifier_block cpuset_track_online_nodes_nb = { + .notifier_call = cpuset_track_online_nodes, + .priority = 10, /* ??! */ +}; + +/** + * cpuset_init_smp - initialize cpus_allowed + * + * Description: Finish top cpuset after cpu, node maps are initialized + */ +void __init cpuset_init_smp(void) +{ + /* + * cpus_allowd/mems_allowed set to v2 values in the initial + * cpuset_bind() call will be reset to v1 values in another + * cpuset_bind() call when v1 cpuset is mounted. + */ + top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; + + cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); + top_cpuset.effective_mems = node_states[N_MEMORY]; + + register_hotmemory_notifier(&cpuset_track_online_nodes_nb); + + cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); + BUG_ON(!cpuset_migrate_mm_wq); +} + +/** + * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. + * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. + * + * Description: Returns the cpumask_var_t cpus_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of cpu_online_mask, even if this means going outside the + * tasks cpuset. + **/ + +void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) +{ + unsigned long flags; + + spin_lock_irqsave(&callback_lock, flags); + guarantee_online_cpus(tsk, pmask); + spin_unlock_irqrestore(&callback_lock, flags); +} + +/** + * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. + * @tsk: pointer to task_struct with which the scheduler is struggling + * + * Description: In the case that the scheduler cannot find an allowed cpu in + * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy + * mode however, this value is the same as task_cs(tsk)->effective_cpus, + * which will not contain a sane cpumask during cases such as cpu hotplugging. + * This is the absolute last resort for the scheduler and it is only used if + * _every_ other avenue has been traveled. + * + * Returns true if the affinity of @tsk was changed, false otherwise. + **/ + +bool cpuset_cpus_allowed_fallback(struct task_struct *tsk) +{ + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + const struct cpumask *cs_mask; + bool changed = false; + + rcu_read_lock(); + cs_mask = task_cs(tsk)->cpus_allowed; + if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) { + do_set_cpus_allowed(tsk, cs_mask); + changed = true; + } + rcu_read_unlock(); + + /* + * We own tsk->cpus_allowed, nobody can change it under us. + * + * But we used cs && cs->cpus_allowed lockless and thus can + * race with cgroup_attach_task() or update_cpumask() and get + * the wrong tsk->cpus_allowed. However, both cases imply the + * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() + * which takes task_rq_lock(). + * + * If we are called after it dropped the lock we must see all + * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary + * set any mask even if it is not right from task_cs() pov, + * the pending set_cpus_allowed_ptr() will fix things. + * + * select_fallback_rq() will fix things ups and set cpu_possible_mask + * if required. + */ + return changed; +} + +void __init cpuset_init_current_mems_allowed(void) +{ + nodes_setall(current->mems_allowed); +} + +/** + * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. + * + * Description: Returns the nodemask_t mems_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of node_states[N_MEMORY], even if this means going outside the + * tasks cpuset. + **/ + +nodemask_t cpuset_mems_allowed(struct task_struct *tsk) +{ + nodemask_t mask; + unsigned long flags; + + spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &mask); + rcu_read_unlock(); + spin_unlock_irqrestore(&callback_lock, flags); + + return mask; +} + +/** + * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed + * @nodemask: the nodemask to be checked + * + * Are any of the nodes in the nodemask allowed in current->mems_allowed? + */ +int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) +{ + return nodes_intersects(*nodemask, current->mems_allowed); +} + +/* + * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or + * mem_hardwall ancestor to the specified cpuset. Call holding + * callback_lock. If no ancestor is mem_exclusive or mem_hardwall + * (an unusual configuration), then returns the root cpuset. + */ +static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) +{ + while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) + cs = parent_cs(cs); + return cs; +} + +/* + * __cpuset_node_allowed - Can we allocate on a memory node? + * @node: is this an allowed node? + * @gfp_mask: memory allocation flags + * + * If we're in interrupt, yes, we can always allocate. If @node is set in + * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this + * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, + * yes. If current has access to memory reserves as an oom victim, yes. + * Otherwise, no. + * + * GFP_USER allocations are marked with the __GFP_HARDWALL bit, + * and do not allow allocations outside the current tasks cpuset + * unless the task has been OOM killed. + * GFP_KERNEL allocations are not so marked, so can escape to the + * nearest enclosing hardwalled ancestor cpuset. + * + * Scanning up parent cpusets requires callback_lock. The + * __alloc_pages() routine only calls here with __GFP_HARDWALL bit + * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the + * current tasks mems_allowed came up empty on the first pass over + * the zonelist. So only GFP_KERNEL allocations, if all nodes in the + * cpuset are short of memory, might require taking the callback_lock. + * + * The first call here from mm/page_alloc:get_page_from_freelist() + * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, + * so no allocation on a node outside the cpuset is allowed (unless + * in interrupt, of course). + * + * The second pass through get_page_from_freelist() doesn't even call + * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() + * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set + * in alloc_flags. That logic and the checks below have the combined + * affect that: + * in_interrupt - any node ok (current task context irrelevant) + * GFP_ATOMIC - any node ok + * tsk_is_oom_victim - any node ok + * GFP_KERNEL - any node in enclosing hardwalled cpuset ok + * GFP_USER - only nodes in current tasks mems allowed ok. + */ +bool __cpuset_node_allowed(int node, gfp_t gfp_mask) +{ + struct cpuset *cs; /* current cpuset ancestors */ + bool allowed; /* is allocation in zone z allowed? */ + unsigned long flags; + + if (in_interrupt()) + return true; + if (node_isset(node, current->mems_allowed)) + return true; + /* + * Allow tasks that have access to memory reserves because they have + * been OOM killed to get memory anywhere. + */ + if (unlikely(tsk_is_oom_victim(current))) + return true; + if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ + return false; + + if (current->flags & PF_EXITING) /* Let dying task have memory */ + return true; + + /* Not hardwall and node outside mems_allowed: scan up cpusets */ + spin_lock_irqsave(&callback_lock, flags); + + rcu_read_lock(); + cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); + rcu_read_unlock(); + + spin_unlock_irqrestore(&callback_lock, flags); + return allowed; +} + +/** + * cpuset_mem_spread_node() - On which node to begin search for a file page + * cpuset_slab_spread_node() - On which node to begin search for a slab page + * + * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for + * tasks in a cpuset with is_spread_page or is_spread_slab set), + * and if the memory allocation used cpuset_mem_spread_node() + * to determine on which node to start looking, as it will for + * certain page cache or slab cache pages such as used for file + * system buffers and inode caches, then instead of starting on the + * local node to look for a free page, rather spread the starting + * node around the tasks mems_allowed nodes. + * + * We don't have to worry about the returned node being offline + * because "it can't happen", and even if it did, it would be ok. + * + * The routines calling guarantee_online_mems() are careful to + * only set nodes in task->mems_allowed that are online. So it + * should not be possible for the following code to return an + * offline node. But if it did, that would be ok, as this routine + * is not returning the node where the allocation must be, only + * the node where the search should start. The zonelist passed to + * __alloc_pages() will include all nodes. If the slab allocator + * is passed an offline node, it will fall back to the local node. + * See kmem_cache_alloc_node(). + */ + +static int cpuset_spread_node(int *rotor) +{ + return *rotor = next_node_in(*rotor, current->mems_allowed); +} + +int cpuset_mem_spread_node(void) +{ + if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) + current->cpuset_mem_spread_rotor = + node_random(¤t->mems_allowed); + + return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); +} + +int cpuset_slab_spread_node(void) +{ + if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) + current->cpuset_slab_spread_rotor = + node_random(¤t->mems_allowed); + + return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); +} + +EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); + +/** + * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? + * @tsk1: pointer to task_struct of some task. + * @tsk2: pointer to task_struct of some other task. + * + * Description: Return true if @tsk1's mems_allowed intersects the + * mems_allowed of @tsk2. Used by the OOM killer to determine if + * one of the task's memory usage might impact the memory available + * to the other. + **/ + +int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, + const struct task_struct *tsk2) +{ + return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); +} + +/** + * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed + * + * Description: Prints current's name, cpuset name, and cached copy of its + * mems_allowed to the kernel log. + */ +void cpuset_print_current_mems_allowed(void) +{ + struct cgroup *cgrp; + + rcu_read_lock(); + + cgrp = task_cs(current)->css.cgroup; + pr_cont(",cpuset="); + pr_cont_cgroup_name(cgrp); + pr_cont(",mems_allowed=%*pbl", + nodemask_pr_args(¤t->mems_allowed)); + + rcu_read_unlock(); +} + +/* + * Collection of memory_pressure is suppressed unless + * this flag is enabled by writing "1" to the special + * cpuset file 'memory_pressure_enabled' in the root cpuset. + */ + +int cpuset_memory_pressure_enabled __read_mostly; + +/* + * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. + * + * Keep a running average of the rate of synchronous (direct) + * page reclaim efforts initiated by tasks in each cpuset. + * + * This represents the rate at which some task in the cpuset + * ran low on memory on all nodes it was allowed to use, and + * had to enter the kernels page reclaim code in an effort to + * create more free memory by tossing clean pages or swapping + * or writing dirty pages. + * + * Display to user space in the per-cpuset read-only file + * "memory_pressure". Value displayed is an integer + * representing the recent rate of entry into the synchronous + * (direct) page reclaim by any task attached to the cpuset. + */ + +void __cpuset_memory_pressure_bump(void) +{ + rcu_read_lock(); + fmeter_markevent(&task_cs(current)->fmeter); + rcu_read_unlock(); +} + +#ifdef CONFIG_PROC_PID_CPUSET +/* + * proc_cpuset_show() + * - Print tasks cpuset path into seq_file. + * - Used for /proc/<pid>/cpuset. + * - No need to task_lock(tsk) on this tsk->cpuset reference, as it + * doesn't really matter if tsk->cpuset changes after we read it, + * and we take cpuset_mutex, keeping cpuset_attach() from changing it + * anyway. + */ +int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + char *buf; + struct cgroup_subsys_state *css; + int retval; + + retval = -ENOMEM; + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) + goto out; + + css = task_get_css(tsk, cpuset_cgrp_id); + retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX, + current->nsproxy->cgroup_ns); + css_put(css); + if (retval >= PATH_MAX) + retval = -ENAMETOOLONG; + if (retval < 0) + goto out_free; + seq_puts(m, buf); + seq_putc(m, '\n'); + retval = 0; +out_free: + kfree(buf); +out: + return retval; +} +#endif /* CONFIG_PROC_PID_CPUSET */ + +/* Display task mems_allowed in /proc/<pid>/status file. */ +void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) +{ + seq_printf(m, "Mems_allowed:\t%*pb\n", + nodemask_pr_args(&task->mems_allowed)); + seq_printf(m, "Mems_allowed_list:\t%*pbl\n", + nodemask_pr_args(&task->mems_allowed)); +} diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c new file mode 100644 index 000000000..80aa3f027 --- /dev/null +++ b/kernel/cgroup/debug.c @@ -0,0 +1,381 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Debug controller + * + * WARNING: This controller is for cgroup core debugging only. + * Its interfaces are unstable and subject to changes at any time. + */ +#include <linux/ctype.h> +#include <linux/mm.h> +#include <linux/slab.h> + +#include "cgroup-internal.h" + +static struct cgroup_subsys_state * +debug_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); + + if (!css) + return ERR_PTR(-ENOMEM); + + return css; +} + +static void debug_css_free(struct cgroup_subsys_state *css) +{ + kfree(css); +} + +/* + * debug_taskcount_read - return the number of tasks in a cgroup. + * @cgrp: the cgroup in question + */ +static u64 debug_taskcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return cgroup_task_count(css->cgroup); +} + +static int current_css_set_read(struct seq_file *seq, void *v) +{ + struct kernfs_open_file *of = seq->private; + struct css_set *cset; + struct cgroup_subsys *ss; + struct cgroup_subsys_state *css; + int i, refcnt; + + if (!cgroup_kn_lock_live(of->kn, false)) + return -ENODEV; + + spin_lock_irq(&css_set_lock); + rcu_read_lock(); + cset = task_css_set(current); + refcnt = refcount_read(&cset->refcount); + seq_printf(seq, "css_set %pK %d", cset, refcnt); + if (refcnt > cset->nr_tasks) + seq_printf(seq, " +%d", refcnt - cset->nr_tasks); + seq_puts(seq, "\n"); + + /* + * Print the css'es stored in the current css_set. + */ + for_each_subsys(ss, i) { + css = cset->subsys[ss->id]; + if (!css) + continue; + seq_printf(seq, "%2d: %-4s\t- %p[%d]\n", ss->id, ss->name, + css, css->id); + } + rcu_read_unlock(); + spin_unlock_irq(&css_set_lock); + cgroup_kn_unlock(of->kn); + return 0; +} + +static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + u64 count; + + rcu_read_lock(); + count = refcount_read(&task_css_set(current)->refcount); + rcu_read_unlock(); + return count; +} + +static int current_css_set_cg_links_read(struct seq_file *seq, void *v) +{ + struct cgrp_cset_link *link; + struct css_set *cset; + char *name_buf; + + name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!name_buf) + return -ENOMEM; + + spin_lock_irq(&css_set_lock); + rcu_read_lock(); + cset = task_css_set(current); + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + cgroup_name(c, name_buf, NAME_MAX + 1); + seq_printf(seq, "Root %d group %s\n", + c->root->hierarchy_id, name_buf); + } + rcu_read_unlock(); + spin_unlock_irq(&css_set_lock); + kfree(name_buf); + return 0; +} + +#define MAX_TASKS_SHOWN_PER_CSS 25 +static int cgroup_css_links_read(struct seq_file *seq, void *v) +{ + struct cgroup_subsys_state *css = seq_css(seq); + struct cgrp_cset_link *link; + int dead_cnt = 0, extra_refs = 0, threaded_csets = 0; + + spin_lock_irq(&css_set_lock); + + list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { + struct css_set *cset = link->cset; + struct task_struct *task; + int count = 0; + int refcnt = refcount_read(&cset->refcount); + + /* + * Print out the proc_cset and threaded_cset relationship + * and highlight difference between refcount and task_count. + */ + seq_printf(seq, "css_set %pK", cset); + if (rcu_dereference_protected(cset->dom_cset, 1) != cset) { + threaded_csets++; + seq_printf(seq, "=>%pK", cset->dom_cset); + } + if (!list_empty(&cset->threaded_csets)) { + struct css_set *tcset; + int idx = 0; + + list_for_each_entry(tcset, &cset->threaded_csets, + threaded_csets_node) { + seq_puts(seq, idx ? "," : "<="); + seq_printf(seq, "%pK", tcset); + idx++; + } + } else { + seq_printf(seq, " %d", refcnt); + if (refcnt - cset->nr_tasks > 0) { + int extra = refcnt - cset->nr_tasks; + + seq_printf(seq, " +%d", extra); + /* + * Take out the one additional reference in + * init_css_set. + */ + if (cset == &init_css_set) + extra--; + extra_refs += extra; + } + } + seq_puts(seq, "\n"); + + list_for_each_entry(task, &cset->tasks, cg_list) { + if (count++ <= MAX_TASKS_SHOWN_PER_CSS) + seq_printf(seq, " task %d\n", + task_pid_vnr(task)); + } + + list_for_each_entry(task, &cset->mg_tasks, cg_list) { + if (count++ <= MAX_TASKS_SHOWN_PER_CSS) + seq_printf(seq, " task %d\n", + task_pid_vnr(task)); + } + /* show # of overflowed tasks */ + if (count > MAX_TASKS_SHOWN_PER_CSS) + seq_printf(seq, " ... (%d)\n", + count - MAX_TASKS_SHOWN_PER_CSS); + + if (cset->dead) { + seq_puts(seq, " [dead]\n"); + dead_cnt++; + } + + WARN_ON(count != cset->nr_tasks); + } + spin_unlock_irq(&css_set_lock); + + if (!dead_cnt && !extra_refs && !threaded_csets) + return 0; + + seq_puts(seq, "\n"); + if (threaded_csets) + seq_printf(seq, "threaded css_sets = %d\n", threaded_csets); + if (extra_refs) + seq_printf(seq, "extra references = %d\n", extra_refs); + if (dead_cnt) + seq_printf(seq, "dead css_sets = %d\n", dead_cnt); + + return 0; +} + +static int cgroup_subsys_states_read(struct seq_file *seq, void *v) +{ + struct kernfs_open_file *of = seq->private; + struct cgroup *cgrp; + struct cgroup_subsys *ss; + struct cgroup_subsys_state *css; + char pbuf[16]; + int i; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + for_each_subsys(ss, i) { + css = rcu_dereference_check(cgrp->subsys[ss->id], true); + if (!css) + continue; + + pbuf[0] = '\0'; + + /* Show the parent CSS if applicable*/ + if (css->parent) + snprintf(pbuf, sizeof(pbuf) - 1, " P=%d", + css->parent->id); + seq_printf(seq, "%2d: %-4s\t- %p[%d] %d%s\n", ss->id, ss->name, + css, css->id, + atomic_read(&css->online_cnt), pbuf); + } + + cgroup_kn_unlock(of->kn); + return 0; +} + +static void cgroup_masks_read_one(struct seq_file *seq, const char *name, + u16 mask) +{ + struct cgroup_subsys *ss; + int ssid; + bool first = true; + + seq_printf(seq, "%-17s: ", name); + for_each_subsys(ss, ssid) { + if (!(mask & (1 << ssid))) + continue; + if (!first) + seq_puts(seq, ", "); + seq_puts(seq, ss->name); + first = false; + } + seq_putc(seq, '\n'); +} + +static int cgroup_masks_read(struct seq_file *seq, void *v) +{ + struct kernfs_open_file *of = seq->private; + struct cgroup *cgrp; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + cgroup_masks_read_one(seq, "subtree_control", cgrp->subtree_control); + cgroup_masks_read_one(seq, "subtree_ss_mask", cgrp->subtree_ss_mask); + + cgroup_kn_unlock(of->kn); + return 0; +} + +static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return (!cgroup_is_populated(css->cgroup) && + !css_has_online_children(&css->cgroup->self)); +} + +static struct cftype debug_legacy_files[] = { + { + .name = "taskcount", + .read_u64 = debug_taskcount_read, + }, + + { + .name = "current_css_set", + .seq_show = current_css_set_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_refcount", + .read_u64 = current_css_set_refcount_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_cg_links", + .seq_show = current_css_set_cg_links_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "cgroup_css_links", + .seq_show = cgroup_css_links_read, + }, + + { + .name = "cgroup_subsys_states", + .seq_show = cgroup_subsys_states_read, + }, + + { + .name = "cgroup_masks", + .seq_show = cgroup_masks_read, + }, + + { + .name = "releasable", + .read_u64 = releasable_read, + }, + + { } /* terminate */ +}; + +static struct cftype debug_files[] = { + { + .name = "taskcount", + .read_u64 = debug_taskcount_read, + }, + + { + .name = "current_css_set", + .seq_show = current_css_set_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_refcount", + .read_u64 = current_css_set_refcount_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_cg_links", + .seq_show = current_css_set_cg_links_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "css_links", + .seq_show = cgroup_css_links_read, + }, + + { + .name = "csses", + .seq_show = cgroup_subsys_states_read, + }, + + { + .name = "masks", + .seq_show = cgroup_masks_read, + }, + + { } /* terminate */ +}; + +struct cgroup_subsys debug_cgrp_subsys = { + .css_alloc = debug_css_alloc, + .css_free = debug_css_free, + .legacy_cftypes = debug_legacy_files, +}; + +/* + * On v2, debug is an implicit controller enabled by "cgroup_debug" boot + * parameter. + */ +void __init enable_debug_cgroup(void) +{ + debug_cgrp_subsys.dfl_cftypes = debug_files; + debug_cgrp_subsys.implicit_on_dfl = true; + debug_cgrp_subsys.threaded = true; +} diff --git a/kernel/cgroup/freezer.c b/kernel/cgroup/freezer.c new file mode 100644 index 000000000..617861a54 --- /dev/null +++ b/kernel/cgroup/freezer.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cgroup.h> +#include <linux/sched.h> +#include <linux/sched/task.h> +#include <linux/sched/signal.h> + +#include "cgroup-internal.h" + +#include <trace/events/cgroup.h> + +/* + * Propagate the cgroup frozen state upwards by the cgroup tree. + */ +static void cgroup_propagate_frozen(struct cgroup *cgrp, bool frozen) +{ + int desc = 1; + + /* + * If the new state is frozen, some freezing ancestor cgroups may change + * their state too, depending on if all their descendants are frozen. + * + * Otherwise, all ancestor cgroups are forced into the non-frozen state. + */ + while ((cgrp = cgroup_parent(cgrp))) { + if (frozen) { + cgrp->freezer.nr_frozen_descendants += desc; + if (!test_bit(CGRP_FROZEN, &cgrp->flags) && + test_bit(CGRP_FREEZE, &cgrp->flags) && + cgrp->freezer.nr_frozen_descendants == + cgrp->nr_descendants) { + set_bit(CGRP_FROZEN, &cgrp->flags); + cgroup_file_notify(&cgrp->events_file); + TRACE_CGROUP_PATH(notify_frozen, cgrp, 1); + desc++; + } + } else { + cgrp->freezer.nr_frozen_descendants -= desc; + if (test_bit(CGRP_FROZEN, &cgrp->flags)) { + clear_bit(CGRP_FROZEN, &cgrp->flags); + cgroup_file_notify(&cgrp->events_file); + TRACE_CGROUP_PATH(notify_frozen, cgrp, 0); + desc++; + } + } + } +} + +/* + * Revisit the cgroup frozen state. + * Checks if the cgroup is really frozen and perform all state transitions. + */ +void cgroup_update_frozen(struct cgroup *cgrp) +{ + bool frozen; + + lockdep_assert_held(&css_set_lock); + + /* + * If the cgroup has to be frozen (CGRP_FREEZE bit set), + * and all tasks are frozen and/or stopped, let's consider + * the cgroup frozen. Otherwise it's not frozen. + */ + frozen = test_bit(CGRP_FREEZE, &cgrp->flags) && + cgrp->freezer.nr_frozen_tasks == __cgroup_task_count(cgrp); + + if (frozen) { + /* Already there? */ + if (test_bit(CGRP_FROZEN, &cgrp->flags)) + return; + + set_bit(CGRP_FROZEN, &cgrp->flags); + } else { + /* Already there? */ + if (!test_bit(CGRP_FROZEN, &cgrp->flags)) + return; + + clear_bit(CGRP_FROZEN, &cgrp->flags); + } + cgroup_file_notify(&cgrp->events_file); + TRACE_CGROUP_PATH(notify_frozen, cgrp, frozen); + + /* Update the state of ancestor cgroups. */ + cgroup_propagate_frozen(cgrp, frozen); +} + +/* + * Increment cgroup's nr_frozen_tasks. + */ +static void cgroup_inc_frozen_cnt(struct cgroup *cgrp) +{ + cgrp->freezer.nr_frozen_tasks++; +} + +/* + * Decrement cgroup's nr_frozen_tasks. + */ +static void cgroup_dec_frozen_cnt(struct cgroup *cgrp) +{ + cgrp->freezer.nr_frozen_tasks--; + WARN_ON_ONCE(cgrp->freezer.nr_frozen_tasks < 0); +} + +/* + * Enter frozen/stopped state, if not yet there. Update cgroup's counters, + * and revisit the state of the cgroup, if necessary. + */ +void cgroup_enter_frozen(void) +{ + struct cgroup *cgrp; + + if (current->frozen) + return; + + spin_lock_irq(&css_set_lock); + current->frozen = true; + cgrp = task_dfl_cgroup(current); + cgroup_inc_frozen_cnt(cgrp); + cgroup_update_frozen(cgrp); + spin_unlock_irq(&css_set_lock); +} + +/* + * Conditionally leave frozen/stopped state. Update cgroup's counters, + * and revisit the state of the cgroup, if necessary. + * + * If always_leave is not set, and the cgroup is freezing, + * we're racing with the cgroup freezing. In this case, we don't + * drop the frozen counter to avoid a transient switch to + * the unfrozen state. + */ +void cgroup_leave_frozen(bool always_leave) +{ + struct cgroup *cgrp; + + spin_lock_irq(&css_set_lock); + cgrp = task_dfl_cgroup(current); + if (always_leave || !test_bit(CGRP_FREEZE, &cgrp->flags)) { + cgroup_dec_frozen_cnt(cgrp); + cgroup_update_frozen(cgrp); + WARN_ON_ONCE(!current->frozen); + current->frozen = false; + } else if (!(current->jobctl & JOBCTL_TRAP_FREEZE)) { + spin_lock(¤t->sighand->siglock); + current->jobctl |= JOBCTL_TRAP_FREEZE; + set_thread_flag(TIF_SIGPENDING); + spin_unlock(¤t->sighand->siglock); + } + spin_unlock_irq(&css_set_lock); +} + +/* + * Freeze or unfreeze the task by setting or clearing the JOBCTL_TRAP_FREEZE + * jobctl bit. + */ +static void cgroup_freeze_task(struct task_struct *task, bool freeze) +{ + unsigned long flags; + + /* If the task is about to die, don't bother with freezing it. */ + if (!lock_task_sighand(task, &flags)) + return; + + if (freeze) { + task->jobctl |= JOBCTL_TRAP_FREEZE; + signal_wake_up(task, false); + } else { + task->jobctl &= ~JOBCTL_TRAP_FREEZE; + wake_up_process(task); + } + + unlock_task_sighand(task, &flags); +} + +/* + * Freeze or unfreeze all tasks in the given cgroup. + */ +static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze) +{ + struct css_task_iter it; + struct task_struct *task; + + lockdep_assert_held(&cgroup_mutex); + + spin_lock_irq(&css_set_lock); + if (freeze) + set_bit(CGRP_FREEZE, &cgrp->flags); + else + clear_bit(CGRP_FREEZE, &cgrp->flags); + spin_unlock_irq(&css_set_lock); + + if (freeze) + TRACE_CGROUP_PATH(freeze, cgrp); + else + TRACE_CGROUP_PATH(unfreeze, cgrp); + + css_task_iter_start(&cgrp->self, 0, &it); + while ((task = css_task_iter_next(&it))) { + /* + * Ignore kernel threads here. Freezing cgroups containing + * kthreads isn't supported. + */ + if (task->flags & PF_KTHREAD) + continue; + cgroup_freeze_task(task, freeze); + } + css_task_iter_end(&it); + + /* + * Cgroup state should be revisited here to cover empty leaf cgroups + * and cgroups which descendants are already in the desired state. + */ + spin_lock_irq(&css_set_lock); + if (cgrp->nr_descendants == cgrp->freezer.nr_frozen_descendants) + cgroup_update_frozen(cgrp); + spin_unlock_irq(&css_set_lock); +} + +/* + * Adjust the task state (freeze or unfreeze) and revisit the state of + * source and destination cgroups. + */ +void cgroup_freezer_migrate_task(struct task_struct *task, + struct cgroup *src, struct cgroup *dst) +{ + lockdep_assert_held(&css_set_lock); + + /* + * Kernel threads are not supposed to be frozen at all. + */ + if (task->flags & PF_KTHREAD) + return; + + /* + * It's not necessary to do changes if both of the src and dst cgroups + * are not freezing and task is not frozen. + */ + if (!test_bit(CGRP_FREEZE, &src->flags) && + !test_bit(CGRP_FREEZE, &dst->flags) && + !task->frozen) + return; + + /* + * Adjust counters of freezing and frozen tasks. + * Note, that if the task is frozen, but the destination cgroup is not + * frozen, we bump both counters to keep them balanced. + */ + if (task->frozen) { + cgroup_inc_frozen_cnt(dst); + cgroup_dec_frozen_cnt(src); + } + cgroup_update_frozen(dst); + cgroup_update_frozen(src); + + /* + * Force the task to the desired state. + */ + cgroup_freeze_task(task, test_bit(CGRP_FREEZE, &dst->flags)); +} + +void cgroup_freeze(struct cgroup *cgrp, bool freeze) +{ + struct cgroup_subsys_state *css; + struct cgroup *dsct; + bool applied = false; + + lockdep_assert_held(&cgroup_mutex); + + /* + * Nothing changed? Just exit. + */ + if (cgrp->freezer.freeze == freeze) + return; + + cgrp->freezer.freeze = freeze; + + /* + * Propagate changes downwards the cgroup tree. + */ + css_for_each_descendant_pre(css, &cgrp->self) { + dsct = css->cgroup; + + if (cgroup_is_dead(dsct)) + continue; + + if (freeze) { + dsct->freezer.e_freeze++; + /* + * Already frozen because of ancestor's settings? + */ + if (dsct->freezer.e_freeze > 1) + continue; + } else { + dsct->freezer.e_freeze--; + /* + * Still frozen because of ancestor's settings? + */ + if (dsct->freezer.e_freeze > 0) + continue; + + WARN_ON_ONCE(dsct->freezer.e_freeze < 0); + } + + /* + * Do change actual state: freeze or unfreeze. + */ + cgroup_do_freeze(dsct, freeze); + applied = true; + } + + /* + * Even if the actual state hasn't changed, let's notify a user. + * The state can be enforced by an ancestor cgroup: the cgroup + * can already be in the desired state or it can be locked in the + * opposite state, so that the transition will never happen. + * In both cases it's better to notify a user, that there is + * nothing to wait for. + */ + if (!applied) { + TRACE_CGROUP_PATH(notify_frozen, cgrp, + test_bit(CGRP_FROZEN, &cgrp->flags)); + cgroup_file_notify(&cgrp->events_file); + } +} diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c new file mode 100644 index 000000000..66d170804 --- /dev/null +++ b/kernel/cgroup/legacy_freezer.c @@ -0,0 +1,487 @@ +/* + * cgroup_freezer.c - control group freezer subsystem + * + * Copyright IBM Corporation, 2007 + * + * Author : Cedric Le Goater <clg@fr.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + */ + +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/cgroup.h> +#include <linux/fs.h> +#include <linux/uaccess.h> +#include <linux/freezer.h> +#include <linux/seq_file.h> +#include <linux/mutex.h> +#include <linux/cpu.h> + +/* + * A cgroup is freezing if any FREEZING flags are set. FREEZING_SELF is + * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared + * for "THAWED". FREEZING_PARENT is set if the parent freezer is FREEZING + * for whatever reason. IOW, a cgroup has FREEZING_PARENT set if one of + * its ancestors has FREEZING_SELF set. + */ +enum freezer_state_flags { + CGROUP_FREEZER_ONLINE = (1 << 0), /* freezer is fully online */ + CGROUP_FREEZING_SELF = (1 << 1), /* this freezer is freezing */ + CGROUP_FREEZING_PARENT = (1 << 2), /* the parent freezer is freezing */ + CGROUP_FROZEN = (1 << 3), /* this and its descendants frozen */ + + /* mask for all FREEZING flags */ + CGROUP_FREEZING = CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT, +}; + +struct freezer { + struct cgroup_subsys_state css; + unsigned int state; +}; + +static DEFINE_MUTEX(freezer_mutex); + +static inline struct freezer *css_freezer(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct freezer, css) : NULL; +} + +static inline struct freezer *task_freezer(struct task_struct *task) +{ + return css_freezer(task_css(task, freezer_cgrp_id)); +} + +static struct freezer *parent_freezer(struct freezer *freezer) +{ + return css_freezer(freezer->css.parent); +} + +bool cgroup_freezing(struct task_struct *task) +{ + bool ret; + unsigned int state; + + rcu_read_lock(); + /* Check if the cgroup is still FREEZING, but not FROZEN. The extra + * !FROZEN check is required, because the FREEZING bit is not cleared + * when the state FROZEN is reached. + */ + state = task_freezer(task)->state; + ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN); + rcu_read_unlock(); + + return ret; +} + +static const char *freezer_state_strs(unsigned int state) +{ + if (state & CGROUP_FROZEN) + return "FROZEN"; + if (state & CGROUP_FREEZING) + return "FREEZING"; + return "THAWED"; +}; + +static struct cgroup_subsys_state * +freezer_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct freezer *freezer; + + freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL); + if (!freezer) + return ERR_PTR(-ENOMEM); + + return &freezer->css; +} + +/** + * freezer_css_online - commit creation of a freezer css + * @css: css being created + * + * We're committing to creation of @css. Mark it online and inherit + * parent's freezing state while holding both parent's and our + * freezer->lock. + */ +static int freezer_css_online(struct cgroup_subsys_state *css) +{ + struct freezer *freezer = css_freezer(css); + struct freezer *parent = parent_freezer(freezer); + + cpus_read_lock(); + mutex_lock(&freezer_mutex); + + freezer->state |= CGROUP_FREEZER_ONLINE; + + if (parent && (parent->state & CGROUP_FREEZING)) { + freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN; + static_branch_inc_cpuslocked(&freezer_active); + } + + mutex_unlock(&freezer_mutex); + cpus_read_unlock(); + return 0; +} + +/** + * freezer_css_offline - initiate destruction of a freezer css + * @css: css being destroyed + * + * @css is going away. Mark it dead and decrement system_freezing_count if + * it was holding one. + */ +static void freezer_css_offline(struct cgroup_subsys_state *css) +{ + struct freezer *freezer = css_freezer(css); + + cpus_read_lock(); + mutex_lock(&freezer_mutex); + + if (freezer->state & CGROUP_FREEZING) + static_branch_dec_cpuslocked(&freezer_active); + + freezer->state = 0; + + mutex_unlock(&freezer_mutex); + cpus_read_unlock(); +} + +static void freezer_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_freezer(css)); +} + +/* + * Tasks can be migrated into a different freezer anytime regardless of its + * current state. freezer_attach() is responsible for making new tasks + * conform to the current state. + * + * Freezer state changes and task migration are synchronized via + * @freezer->lock. freezer_attach() makes the new tasks conform to the + * current state and all following state changes can see the new tasks. + */ +static void freezer_attach(struct cgroup_taskset *tset) +{ + struct task_struct *task; + struct cgroup_subsys_state *new_css; + + mutex_lock(&freezer_mutex); + + /* + * Make the new tasks conform to the current state of @new_css. + * For simplicity, when migrating any task to a FROZEN cgroup, we + * revert it to FREEZING and let update_if_frozen() determine the + * correct state later. + * + * Tasks in @tset are on @new_css but may not conform to its + * current state before executing the following - !frozen tasks may + * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. + */ + cgroup_taskset_for_each(task, new_css, tset) { + struct freezer *freezer = css_freezer(new_css); + + if (!(freezer->state & CGROUP_FREEZING)) { + __thaw_task(task); + } else { + freeze_task(task); + + /* clear FROZEN and propagate upwards */ + while (freezer && (freezer->state & CGROUP_FROZEN)) { + freezer->state &= ~CGROUP_FROZEN; + freezer = parent_freezer(freezer); + } + } + } + + mutex_unlock(&freezer_mutex); +} + +/** + * freezer_fork - cgroup post fork callback + * @task: a task which has just been forked + * + * @task has just been created and should conform to the current state of + * the cgroup_freezer it belongs to. This function may race against + * freezer_attach(). Losing to freezer_attach() means that we don't have + * to do anything as freezer_attach() will put @task into the appropriate + * state. + */ +static void freezer_fork(struct task_struct *task) +{ + struct freezer *freezer; + + /* + * The root cgroup is non-freezable, so we can skip locking the + * freezer. This is safe regardless of race with task migration. + * If we didn't race or won, skipping is obviously the right thing + * to do. If we lost and root is the new cgroup, noop is still the + * right thing to do. + */ + if (task_css_is_root(task, freezer_cgrp_id)) + return; + + mutex_lock(&freezer_mutex); + rcu_read_lock(); + + freezer = task_freezer(task); + if (freezer->state & CGROUP_FREEZING) + freeze_task(task); + + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); +} + +/** + * update_if_frozen - update whether a cgroup finished freezing + * @css: css of interest + * + * Once FREEZING is initiated, transition to FROZEN is lazily updated by + * calling this function. If the current state is FREEZING but not FROZEN, + * this function checks whether all tasks of this cgroup and the descendant + * cgroups finished freezing and, if so, sets FROZEN. + * + * The caller is responsible for grabbing RCU read lock and calling + * update_if_frozen() on all descendants prior to invoking this function. + * + * Task states and freezer state might disagree while tasks are being + * migrated into or out of @css, so we can't verify task states against + * @freezer state here. See freezer_attach() for details. + */ +static void update_if_frozen(struct cgroup_subsys_state *css) +{ + struct freezer *freezer = css_freezer(css); + struct cgroup_subsys_state *pos; + struct css_task_iter it; + struct task_struct *task; + + lockdep_assert_held(&freezer_mutex); + + if (!(freezer->state & CGROUP_FREEZING) || + (freezer->state & CGROUP_FROZEN)) + return; + + /* are all (live) children frozen? */ + rcu_read_lock(); + css_for_each_child(pos, css) { + struct freezer *child = css_freezer(pos); + + if ((child->state & CGROUP_FREEZER_ONLINE) && + !(child->state & CGROUP_FROZEN)) { + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + + /* are all tasks frozen? */ + css_task_iter_start(css, 0, &it); + + while ((task = css_task_iter_next(&it))) { + if (freezing(task) && !frozen(task)) + goto out_iter_end; + } + + freezer->state |= CGROUP_FROZEN; +out_iter_end: + css_task_iter_end(&it); +} + +static int freezer_read(struct seq_file *m, void *v) +{ + struct cgroup_subsys_state *css = seq_css(m), *pos; + + mutex_lock(&freezer_mutex); + rcu_read_lock(); + + /* update states bottom-up */ + css_for_each_descendant_post(pos, css) { + if (!css_tryget_online(pos)) + continue; + rcu_read_unlock(); + + update_if_frozen(pos); + + rcu_read_lock(); + css_put(pos); + } + + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); + + seq_puts(m, freezer_state_strs(css_freezer(css)->state)); + seq_putc(m, '\n'); + return 0; +} + +static void freeze_cgroup(struct freezer *freezer) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&freezer->css, 0, &it); + while ((task = css_task_iter_next(&it))) + freeze_task(task); + css_task_iter_end(&it); +} + +static void unfreeze_cgroup(struct freezer *freezer) +{ + struct css_task_iter it; + struct task_struct *task; + + css_task_iter_start(&freezer->css, 0, &it); + while ((task = css_task_iter_next(&it))) + __thaw_task(task); + css_task_iter_end(&it); +} + +/** + * freezer_apply_state - apply state change to a single cgroup_freezer + * @freezer: freezer to apply state change to + * @freeze: whether to freeze or unfreeze + * @state: CGROUP_FREEZING_* flag to set or clear + * + * Set or clear @state on @cgroup according to @freeze, and perform + * freezing or thawing as necessary. + */ +static void freezer_apply_state(struct freezer *freezer, bool freeze, + unsigned int state) +{ + /* also synchronizes against task migration, see freezer_attach() */ + lockdep_assert_held(&freezer_mutex); + + if (!(freezer->state & CGROUP_FREEZER_ONLINE)) + return; + + if (freeze) { + if (!(freezer->state & CGROUP_FREEZING)) + static_branch_inc_cpuslocked(&freezer_active); + freezer->state |= state; + freeze_cgroup(freezer); + } else { + bool was_freezing = freezer->state & CGROUP_FREEZING; + + freezer->state &= ~state; + + if (!(freezer->state & CGROUP_FREEZING)) { + freezer->state &= ~CGROUP_FROZEN; + if (was_freezing) + static_branch_dec_cpuslocked(&freezer_active); + unfreeze_cgroup(freezer); + } + } +} + +/** + * freezer_change_state - change the freezing state of a cgroup_freezer + * @freezer: freezer of interest + * @freeze: whether to freeze or thaw + * + * Freeze or thaw @freezer according to @freeze. The operations are + * recursive - all descendants of @freezer will be affected. + */ +static void freezer_change_state(struct freezer *freezer, bool freeze) +{ + struct cgroup_subsys_state *pos; + + cpus_read_lock(); + /* + * Update all its descendants in pre-order traversal. Each + * descendant will try to inherit its parent's FREEZING state as + * CGROUP_FREEZING_PARENT. + */ + mutex_lock(&freezer_mutex); + rcu_read_lock(); + css_for_each_descendant_pre(pos, &freezer->css) { + struct freezer *pos_f = css_freezer(pos); + struct freezer *parent = parent_freezer(pos_f); + + if (!css_tryget_online(pos)) + continue; + rcu_read_unlock(); + + if (pos_f == freezer) + freezer_apply_state(pos_f, freeze, + CGROUP_FREEZING_SELF); + else + freezer_apply_state(pos_f, + parent->state & CGROUP_FREEZING, + CGROUP_FREEZING_PARENT); + + rcu_read_lock(); + css_put(pos); + } + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); + cpus_read_unlock(); +} + +static ssize_t freezer_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + bool freeze; + + buf = strstrip(buf); + + if (strcmp(buf, freezer_state_strs(0)) == 0) + freeze = false; + else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0) + freeze = true; + else + return -EINVAL; + + freezer_change_state(css_freezer(of_css(of)), freeze); + return nbytes; +} + +static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct freezer *freezer = css_freezer(css); + + return (bool)(freezer->state & CGROUP_FREEZING_SELF); +} + +static u64 freezer_parent_freezing_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct freezer *freezer = css_freezer(css); + + return (bool)(freezer->state & CGROUP_FREEZING_PARENT); +} + +static struct cftype files[] = { + { + .name = "state", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = freezer_read, + .write = freezer_write, + }, + { + .name = "self_freezing", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = freezer_self_freezing_read, + }, + { + .name = "parent_freezing", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = freezer_parent_freezing_read, + }, + { } /* terminate */ +}; + +struct cgroup_subsys freezer_cgrp_subsys = { + .css_alloc = freezer_css_alloc, + .css_online = freezer_css_online, + .css_offline = freezer_css_offline, + .css_free = freezer_css_free, + .attach = freezer_attach, + .fork = freezer_fork, + .legacy_cftypes = files, +}; diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c new file mode 100644 index 000000000..fe3e8a0eb --- /dev/null +++ b/kernel/cgroup/misc.c @@ -0,0 +1,424 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Miscellaneous cgroup controller + * + * Copyright 2020 Google LLC + * Author: Vipin Sharma <vipinsh@google.com> + */ + +#include <linux/limits.h> +#include <linux/cgroup.h> +#include <linux/errno.h> +#include <linux/atomic.h> +#include <linux/slab.h> +#include <linux/misc_cgroup.h> + +#define MAX_STR "max" +#define MAX_NUM ULONG_MAX + +/* Miscellaneous res name, keep it in sync with enum misc_res_type */ +static const char *const misc_res_name[] = { +#ifdef CONFIG_KVM_AMD_SEV + /* AMD SEV ASIDs resource */ + "sev", + /* AMD SEV-ES ASIDs resource */ + "sev_es", +#endif +}; + +/* Root misc cgroup */ +static struct misc_cg root_cg; + +/* + * Miscellaneous resources capacity for the entire machine. 0 capacity means + * resource is not initialized or not present in the host. + * + * root_cg.max and capacity are independent of each other. root_cg.max can be + * more than the actual capacity. We are using Limits resource distribution + * model of cgroup for miscellaneous controller. + */ +static unsigned long misc_res_capacity[MISC_CG_RES_TYPES]; + +/** + * parent_misc() - Get the parent of the passed misc cgroup. + * @cgroup: cgroup whose parent needs to be fetched. + * + * Context: Any context. + * Return: + * * struct misc_cg* - Parent of the @cgroup. + * * %NULL - If @cgroup is null or the passed cgroup does not have a parent. + */ +static struct misc_cg *parent_misc(struct misc_cg *cgroup) +{ + return cgroup ? css_misc(cgroup->css.parent) : NULL; +} + +/** + * valid_type() - Check if @type is valid or not. + * @type: misc res type. + * + * Context: Any context. + * Return: + * * true - If valid type. + * * false - If not valid type. + */ +static inline bool valid_type(enum misc_res_type type) +{ + return type >= 0 && type < MISC_CG_RES_TYPES; +} + +/** + * misc_cg_res_total_usage() - Get the current total usage of the resource. + * @type: misc res type. + * + * Context: Any context. + * Return: Current total usage of the resource. + */ +unsigned long misc_cg_res_total_usage(enum misc_res_type type) +{ + if (valid_type(type)) + return atomic_long_read(&root_cg.res[type].usage); + + return 0; +} +EXPORT_SYMBOL_GPL(misc_cg_res_total_usage); + +/** + * misc_cg_set_capacity() - Set the capacity of the misc cgroup res. + * @type: Type of the misc res. + * @capacity: Supported capacity of the misc res on the host. + * + * If capacity is 0 then the charging a misc cgroup fails for that type. + * + * Context: Any context. + * Return: + * * %0 - Successfully registered the capacity. + * * %-EINVAL - If @type is invalid. + */ +int misc_cg_set_capacity(enum misc_res_type type, unsigned long capacity) +{ + if (!valid_type(type)) + return -EINVAL; + + WRITE_ONCE(misc_res_capacity[type], capacity); + return 0; +} +EXPORT_SYMBOL_GPL(misc_cg_set_capacity); + +/** + * misc_cg_cancel_charge() - Cancel the charge from the misc cgroup. + * @type: Misc res type in misc cg to cancel the charge from. + * @cg: Misc cgroup to cancel charge from. + * @amount: Amount to cancel. + * + * Context: Any context. + */ +static void misc_cg_cancel_charge(enum misc_res_type type, struct misc_cg *cg, + unsigned long amount) +{ + WARN_ONCE(atomic_long_add_negative(-amount, &cg->res[type].usage), + "misc cgroup resource %s became less than 0", + misc_res_name[type]); +} + +/** + * misc_cg_try_charge() - Try charging the misc cgroup. + * @type: Misc res type to charge. + * @cg: Misc cgroup which will be charged. + * @amount: Amount to charge. + * + * Charge @amount to the misc cgroup. Caller must use the same cgroup during + * the uncharge call. + * + * Context: Any context. + * Return: + * * %0 - If successfully charged. + * * -EINVAL - If @type is invalid or misc res has 0 capacity. + * * -EBUSY - If max limit will be crossed or total usage will be more than the + * capacity. + */ +int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, + unsigned long amount) +{ + struct misc_cg *i, *j; + int ret; + struct misc_res *res; + int new_usage; + + if (!(valid_type(type) && cg && READ_ONCE(misc_res_capacity[type]))) + return -EINVAL; + + if (!amount) + return 0; + + for (i = cg; i; i = parent_misc(i)) { + res = &i->res[type]; + + new_usage = atomic_long_add_return(amount, &res->usage); + if (new_usage > READ_ONCE(res->max) || + new_usage > READ_ONCE(misc_res_capacity[type])) { + ret = -EBUSY; + goto err_charge; + } + } + return 0; + +err_charge: + for (j = i; j; j = parent_misc(j)) { + atomic_long_inc(&j->res[type].events); + cgroup_file_notify(&j->events_file); + } + + for (j = cg; j != i; j = parent_misc(j)) + misc_cg_cancel_charge(type, j, amount); + misc_cg_cancel_charge(type, i, amount); + return ret; +} +EXPORT_SYMBOL_GPL(misc_cg_try_charge); + +/** + * misc_cg_uncharge() - Uncharge the misc cgroup. + * @type: Misc res type which was charged. + * @cg: Misc cgroup which will be uncharged. + * @amount: Charged amount. + * + * Context: Any context. + */ +void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg, + unsigned long amount) +{ + struct misc_cg *i; + + if (!(amount && valid_type(type) && cg)) + return; + + for (i = cg; i; i = parent_misc(i)) + misc_cg_cancel_charge(type, i, amount); +} +EXPORT_SYMBOL_GPL(misc_cg_uncharge); + +/** + * misc_cg_max_show() - Show the misc cgroup max limit. + * @sf: Interface file + * @v: Arguments passed + * + * Context: Any context. + * Return: 0 to denote successful print. + */ +static int misc_cg_max_show(struct seq_file *sf, void *v) +{ + int i; + struct misc_cg *cg = css_misc(seq_css(sf)); + unsigned long max; + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + if (READ_ONCE(misc_res_capacity[i])) { + max = READ_ONCE(cg->res[i].max); + if (max == MAX_NUM) + seq_printf(sf, "%s max\n", misc_res_name[i]); + else + seq_printf(sf, "%s %lu\n", misc_res_name[i], + max); + } + } + + return 0; +} + +/** + * misc_cg_max_write() - Update the maximum limit of the cgroup. + * @of: Handler for the file. + * @buf: Data from the user. It should be either "max", 0, or a positive + * integer. + * @nbytes: Number of bytes of the data. + * @off: Offset in the file. + * + * User can pass data like: + * echo sev 23 > misc.max, OR + * echo sev max > misc.max + * + * Context: Any context. + * Return: + * * >= 0 - Number of bytes processed in the input. + * * -EINVAL - If buf is not valid. + * * -ERANGE - If number is bigger than the unsigned long capacity. + */ +static ssize_t misc_cg_max_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct misc_cg *cg; + unsigned long max; + int ret = 0, i; + enum misc_res_type type = MISC_CG_RES_TYPES; + char *token; + + buf = strstrip(buf); + token = strsep(&buf, " "); + + if (!token || !buf) + return -EINVAL; + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + if (!strcmp(misc_res_name[i], token)) { + type = i; + break; + } + } + + if (type == MISC_CG_RES_TYPES) + return -EINVAL; + + if (!strcmp(MAX_STR, buf)) { + max = MAX_NUM; + } else { + ret = kstrtoul(buf, 0, &max); + if (ret) + return ret; + } + + cg = css_misc(of_css(of)); + + if (READ_ONCE(misc_res_capacity[type])) + WRITE_ONCE(cg->res[type].max, max); + else + ret = -EINVAL; + + return ret ? ret : nbytes; +} + +/** + * misc_cg_current_show() - Show the current usage of the misc cgroup. + * @sf: Interface file + * @v: Arguments passed + * + * Context: Any context. + * Return: 0 to denote successful print. + */ +static int misc_cg_current_show(struct seq_file *sf, void *v) +{ + int i; + unsigned long usage; + struct misc_cg *cg = css_misc(seq_css(sf)); + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + usage = atomic_long_read(&cg->res[i].usage); + if (READ_ONCE(misc_res_capacity[i]) || usage) + seq_printf(sf, "%s %lu\n", misc_res_name[i], usage); + } + + return 0; +} + +/** + * misc_cg_capacity_show() - Show the total capacity of misc res on the host. + * @sf: Interface file + * @v: Arguments passed + * + * Only present in the root cgroup directory. + * + * Context: Any context. + * Return: 0 to denote successful print. + */ +static int misc_cg_capacity_show(struct seq_file *sf, void *v) +{ + int i; + unsigned long cap; + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + cap = READ_ONCE(misc_res_capacity[i]); + if (cap) + seq_printf(sf, "%s %lu\n", misc_res_name[i], cap); + } + + return 0; +} + +static int misc_events_show(struct seq_file *sf, void *v) +{ + struct misc_cg *cg = css_misc(seq_css(sf)); + unsigned long events, i; + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + events = atomic_long_read(&cg->res[i].events); + if (READ_ONCE(misc_res_capacity[i]) || events) + seq_printf(sf, "%s.max %lu\n", misc_res_name[i], events); + } + return 0; +} + +/* Misc cgroup interface files */ +static struct cftype misc_cg_files[] = { + { + .name = "max", + .write = misc_cg_max_write, + .seq_show = misc_cg_max_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "current", + .seq_show = misc_cg_current_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "capacity", + .seq_show = misc_cg_capacity_show, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + { + .name = "events", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct misc_cg, events_file), + .seq_show = misc_events_show, + }, + {} +}; + +/** + * misc_cg_alloc() - Allocate misc cgroup. + * @parent_css: Parent cgroup. + * + * Context: Process context. + * Return: + * * struct cgroup_subsys_state* - css of the allocated cgroup. + * * ERR_PTR(-ENOMEM) - No memory available to allocate. + */ +static struct cgroup_subsys_state * +misc_cg_alloc(struct cgroup_subsys_state *parent_css) +{ + enum misc_res_type i; + struct misc_cg *cg; + + if (!parent_css) { + cg = &root_cg; + } else { + cg = kzalloc(sizeof(*cg), GFP_KERNEL); + if (!cg) + return ERR_PTR(-ENOMEM); + } + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + WRITE_ONCE(cg->res[i].max, MAX_NUM); + atomic_long_set(&cg->res[i].usage, 0); + } + + return &cg->css; +} + +/** + * misc_cg_free() - Free the misc cgroup. + * @css: cgroup subsys object. + * + * Context: Any context. + */ +static void misc_cg_free(struct cgroup_subsys_state *css) +{ + kfree(css_misc(css)); +} + +/* Cgroup controller callbacks */ +struct cgroup_subsys misc_cgrp_subsys = { + .css_alloc = misc_cg_alloc, + .css_free = misc_cg_free, + .legacy_cftypes = misc_cg_files, + .dfl_cftypes = misc_cg_files, +}; diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c new file mode 100644 index 000000000..144a464e4 --- /dev/null +++ b/kernel/cgroup/namespace.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "cgroup-internal.h" + +#include <linux/sched/task.h> +#include <linux/slab.h> +#include <linux/nsproxy.h> +#include <linux/proc_ns.h> + + +/* cgroup namespaces */ + +static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns) +{ + return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES); +} + +static void dec_cgroup_namespaces(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES); +} + +static struct cgroup_namespace *alloc_cgroup_ns(void) +{ + struct cgroup_namespace *new_ns; + int ret; + + new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL_ACCOUNT); + if (!new_ns) + return ERR_PTR(-ENOMEM); + ret = ns_alloc_inum(&new_ns->ns); + if (ret) { + kfree(new_ns); + return ERR_PTR(ret); + } + refcount_set(&new_ns->ns.count, 1); + new_ns->ns.ops = &cgroupns_operations; + return new_ns; +} + +void free_cgroup_ns(struct cgroup_namespace *ns) +{ + put_css_set(ns->root_cset); + dec_cgroup_namespaces(ns->ucounts); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + kfree(ns); +} +EXPORT_SYMBOL(free_cgroup_ns); + +struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + struct cgroup_namespace *new_ns; + struct ucounts *ucounts; + struct css_set *cset; + + BUG_ON(!old_ns); + + if (!(flags & CLONE_NEWCGROUP)) { + get_cgroup_ns(old_ns); + return old_ns; + } + + /* Allow only sysadmin to create cgroup namespace. */ + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + ucounts = inc_cgroup_namespaces(user_ns); + if (!ucounts) + return ERR_PTR(-ENOSPC); + + /* It is not safe to take cgroup_mutex here */ + spin_lock_irq(&css_set_lock); + cset = task_css_set(current); + get_css_set(cset); + spin_unlock_irq(&css_set_lock); + + new_ns = alloc_cgroup_ns(); + if (IS_ERR(new_ns)) { + put_css_set(cset); + dec_cgroup_namespaces(ucounts); + return new_ns; + } + + new_ns->user_ns = get_user_ns(user_ns); + new_ns->ucounts = ucounts; + new_ns->root_cset = cset; + + return new_ns; +} + +static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) +{ + return container_of(ns, struct cgroup_namespace, ns); +} + +static int cgroupns_install(struct nsset *nsset, struct ns_common *ns) +{ + struct nsproxy *nsproxy = nsset->nsproxy; + struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); + + if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) || + !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* Don't need to do anything if we are attaching to our own cgroupns. */ + if (cgroup_ns == nsproxy->cgroup_ns) + return 0; + + get_cgroup_ns(cgroup_ns); + put_cgroup_ns(nsproxy->cgroup_ns); + nsproxy->cgroup_ns = cgroup_ns; + + return 0; +} + +static struct ns_common *cgroupns_get(struct task_struct *task) +{ + struct cgroup_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->cgroup_ns; + get_cgroup_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void cgroupns_put(struct ns_common *ns) +{ + put_cgroup_ns(to_cg_ns(ns)); +} + +static struct user_namespace *cgroupns_owner(struct ns_common *ns) +{ + return to_cg_ns(ns)->user_ns; +} + +const struct proc_ns_operations cgroupns_operations = { + .name = "cgroup", + .type = CLONE_NEWCGROUP, + .get = cgroupns_get, + .put = cgroupns_put, + .install = cgroupns_install, + .owner = cgroupns_owner, +}; diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c new file mode 100644 index 000000000..7695e60bc --- /dev/null +++ b/kernel/cgroup/pids.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Process number limiting controller for cgroups. + * + * Used to allow a cgroup hierarchy to stop any new processes from fork()ing + * after a certain limit is reached. + * + * Since it is trivial to hit the task limit without hitting any kmemcg limits + * in place, PIDs are a fundamental resource. As such, PID exhaustion must be + * preventable in the scope of a cgroup hierarchy by allowing resource limiting + * of the number of tasks in a cgroup. + * + * In order to use the `pids` controller, set the maximum number of tasks in + * pids.max (this is not available in the root cgroup for obvious reasons). The + * number of processes currently in the cgroup is given by pids.current. + * Organisational operations are not blocked by cgroup policies, so it is + * possible to have pids.current > pids.max. However, it is not possible to + * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking + * would cause a cgroup policy to be violated. + * + * To set a cgroup to have no limit, set pids.max to "max". This is the default + * for all new cgroups (N.B. that PID limits are hierarchical, so the most + * stringent limit in the hierarchy is followed). + * + * pids.current tracks all child cgroup hierarchies, so parent/pids.current is + * a superset of parent/child/pids.current. + * + * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com> + */ + +#include <linux/kernel.h> +#include <linux/threads.h> +#include <linux/atomic.h> +#include <linux/cgroup.h> +#include <linux/slab.h> +#include <linux/sched/task.h> + +#define PIDS_MAX (PID_MAX_LIMIT + 1ULL) +#define PIDS_MAX_STR "max" + +struct pids_cgroup { + struct cgroup_subsys_state css; + + /* + * Use 64-bit types so that we can safely represent "max" as + * %PIDS_MAX = (%PID_MAX_LIMIT + 1). + */ + atomic64_t counter; + atomic64_t limit; + int64_t watermark; + + /* Handle for "pids.events" */ + struct cgroup_file events_file; + + /* Number of times fork failed because limit was hit. */ + atomic64_t events_limit; +}; + +static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css) +{ + return container_of(css, struct pids_cgroup, css); +} + +static struct pids_cgroup *parent_pids(struct pids_cgroup *pids) +{ + return css_pids(pids->css.parent); +} + +static struct cgroup_subsys_state * +pids_css_alloc(struct cgroup_subsys_state *parent) +{ + struct pids_cgroup *pids; + + pids = kzalloc(sizeof(struct pids_cgroup), GFP_KERNEL); + if (!pids) + return ERR_PTR(-ENOMEM); + + atomic64_set(&pids->counter, 0); + atomic64_set(&pids->limit, PIDS_MAX); + atomic64_set(&pids->events_limit, 0); + return &pids->css; +} + +static void pids_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_pids(css)); +} + +static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids) +{ + /* + * This is racy, but we don't need perfectly accurate tallying of + * the watermark, and this lets us avoid extra atomic overhead. + */ + if (nr_pids > READ_ONCE(p->watermark)) + WRITE_ONCE(p->watermark, nr_pids); +} + +/** + * pids_cancel - uncharge the local pid count + * @pids: the pid cgroup state + * @num: the number of pids to cancel + * + * This function will WARN if the pid count goes under 0, because such a case is + * a bug in the pids controller proper. + */ +static void pids_cancel(struct pids_cgroup *pids, int num) +{ + /* + * A negative count (or overflow for that matter) is invalid, + * and indicates a bug in the `pids` controller proper. + */ + WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter)); +} + +/** + * pids_uncharge - hierarchically uncharge the pid count + * @pids: the pid cgroup state + * @num: the number of pids to uncharge + */ +static void pids_uncharge(struct pids_cgroup *pids, int num) +{ + struct pids_cgroup *p; + + for (p = pids; parent_pids(p); p = parent_pids(p)) + pids_cancel(p, num); +} + +/** + * pids_charge - hierarchically charge the pid count + * @pids: the pid cgroup state + * @num: the number of pids to charge + * + * This function does *not* follow the pid limit set. It cannot fail and the new + * pid count may exceed the limit. This is only used for reverting failed + * attaches, where there is no other way out than violating the limit. + */ +static void pids_charge(struct pids_cgroup *pids, int num) +{ + struct pids_cgroup *p; + + for (p = pids; parent_pids(p); p = parent_pids(p)) { + int64_t new = atomic64_add_return(num, &p->counter); + + pids_update_watermark(p, new); + } +} + +/** + * pids_try_charge - hierarchically try to charge the pid count + * @pids: the pid cgroup state + * @num: the number of pids to charge + * + * This function follows the set limit. It will fail if the charge would cause + * the new value to exceed the hierarchical limit. Returns 0 if the charge + * succeeded, otherwise -EAGAIN. + */ +static int pids_try_charge(struct pids_cgroup *pids, int num) +{ + struct pids_cgroup *p, *q; + + for (p = pids; parent_pids(p); p = parent_pids(p)) { + int64_t new = atomic64_add_return(num, &p->counter); + int64_t limit = atomic64_read(&p->limit); + + /* + * Since new is capped to the maximum number of pid_t, if + * p->limit is %PIDS_MAX then we know that this test will never + * fail. + */ + if (new > limit) + goto revert; + + /* + * Not technically accurate if we go over limit somewhere up + * the hierarchy, but that's tolerable for the watermark. + */ + pids_update_watermark(p, new); + } + + return 0; + +revert: + for (q = pids; q != p; q = parent_pids(q)) + pids_cancel(q, num); + pids_cancel(p, num); + + return -EAGAIN; +} + +static int pids_can_attach(struct cgroup_taskset *tset) +{ + struct task_struct *task; + struct cgroup_subsys_state *dst_css; + + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); + struct cgroup_subsys_state *old_css; + struct pids_cgroup *old_pids; + + /* + * No need to pin @old_css between here and cancel_attach() + * because cgroup core protects it from being freed before + * the migration completes or fails. + */ + old_css = task_css(task, pids_cgrp_id); + old_pids = css_pids(old_css); + + pids_charge(pids, 1); + pids_uncharge(old_pids, 1); + } + + return 0; +} + +static void pids_cancel_attach(struct cgroup_taskset *tset) +{ + struct task_struct *task; + struct cgroup_subsys_state *dst_css; + + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); + struct cgroup_subsys_state *old_css; + struct pids_cgroup *old_pids; + + old_css = task_css(task, pids_cgrp_id); + old_pids = css_pids(old_css); + + pids_charge(old_pids, 1); + pids_uncharge(pids, 1); + } +} + +/* + * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies + * on cgroup_threadgroup_change_begin() held by the copy_process(). + */ +static int pids_can_fork(struct task_struct *task, struct css_set *cset) +{ + struct cgroup_subsys_state *css; + struct pids_cgroup *pids; + int err; + + if (cset) + css = cset->subsys[pids_cgrp_id]; + else + css = task_css_check(current, pids_cgrp_id, true); + pids = css_pids(css); + err = pids_try_charge(pids, 1); + if (err) { + /* Only log the first time events_limit is incremented. */ + if (atomic64_inc_return(&pids->events_limit) == 1) { + pr_info("cgroup: fork rejected by pids controller in "); + pr_cont_cgroup_path(css->cgroup); + pr_cont("\n"); + } + cgroup_file_notify(&pids->events_file); + } + return err; +} + +static void pids_cancel_fork(struct task_struct *task, struct css_set *cset) +{ + struct cgroup_subsys_state *css; + struct pids_cgroup *pids; + + if (cset) + css = cset->subsys[pids_cgrp_id]; + else + css = task_css_check(current, pids_cgrp_id, true); + pids = css_pids(css); + pids_uncharge(pids, 1); +} + +static void pids_release(struct task_struct *task) +{ + struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id)); + + pids_uncharge(pids, 1); +} + +static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct cgroup_subsys_state *css = of_css(of); + struct pids_cgroup *pids = css_pids(css); + int64_t limit; + int err; + + buf = strstrip(buf); + if (!strcmp(buf, PIDS_MAX_STR)) { + limit = PIDS_MAX; + goto set_limit; + } + + err = kstrtoll(buf, 0, &limit); + if (err) + return err; + + if (limit < 0 || limit >= PIDS_MAX) + return -EINVAL; + +set_limit: + /* + * Limit updates don't need to be mutex'd, since it isn't + * critical that any racing fork()s follow the new limit. + */ + atomic64_set(&pids->limit, limit); + return nbytes; +} + +static int pids_max_show(struct seq_file *sf, void *v) +{ + struct cgroup_subsys_state *css = seq_css(sf); + struct pids_cgroup *pids = css_pids(css); + int64_t limit = atomic64_read(&pids->limit); + + if (limit >= PIDS_MAX) + seq_printf(sf, "%s\n", PIDS_MAX_STR); + else + seq_printf(sf, "%lld\n", limit); + + return 0; +} + +static s64 pids_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct pids_cgroup *pids = css_pids(css); + + return atomic64_read(&pids->counter); +} + +static s64 pids_peak_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct pids_cgroup *pids = css_pids(css); + + return READ_ONCE(pids->watermark); +} + +static int pids_events_show(struct seq_file *sf, void *v) +{ + struct pids_cgroup *pids = css_pids(seq_css(sf)); + + seq_printf(sf, "max %lld\n", (s64)atomic64_read(&pids->events_limit)); + return 0; +} + +static struct cftype pids_files[] = { + { + .name = "max", + .write = pids_max_write, + .seq_show = pids_max_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "current", + .read_s64 = pids_current_read, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "peak", + .flags = CFTYPE_NOT_ON_ROOT, + .read_s64 = pids_peak_read, + }, + { + .name = "events", + .seq_show = pids_events_show, + .file_offset = offsetof(struct pids_cgroup, events_file), + .flags = CFTYPE_NOT_ON_ROOT, + }, + { } /* terminate */ +}; + +struct cgroup_subsys pids_cgrp_subsys = { + .css_alloc = pids_css_alloc, + .css_free = pids_css_free, + .can_attach = pids_can_attach, + .cancel_attach = pids_cancel_attach, + .can_fork = pids_can_fork, + .cancel_fork = pids_cancel_fork, + .release = pids_release, + .legacy_cftypes = pids_files, + .dfl_cftypes = pids_files, + .threaded = true, +}; diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c new file mode 100644 index 000000000..313540660 --- /dev/null +++ b/kernel/cgroup/rdma.c @@ -0,0 +1,610 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * RDMA resource limiting controller for cgroups. + * + * Used to allow a cgroup hierarchy to stop processes from consuming + * additional RDMA resources after a certain limit is reached. + * + * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com> + */ + +#include <linux/bitops.h> +#include <linux/slab.h> +#include <linux/seq_file.h> +#include <linux/cgroup.h> +#include <linux/parser.h> +#include <linux/cgroup_rdma.h> + +#define RDMACG_MAX_STR "max" + +/* + * Protects list of resource pools maintained on per cgroup basis + * and rdma device list. + */ +static DEFINE_MUTEX(rdmacg_mutex); +static LIST_HEAD(rdmacg_devices); + +enum rdmacg_file_type { + RDMACG_RESOURCE_TYPE_MAX, + RDMACG_RESOURCE_TYPE_STAT, +}; + +/* + * resource table definition as to be seen by the user. + * Need to add entries to it when more resources are + * added/defined at IB verb/core layer. + */ +static char const *rdmacg_resource_names[] = { + [RDMACG_RESOURCE_HCA_HANDLE] = "hca_handle", + [RDMACG_RESOURCE_HCA_OBJECT] = "hca_object", +}; + +/* resource tracker for each resource of rdma cgroup */ +struct rdmacg_resource { + int max; + int usage; +}; + +/* + * resource pool object which represents per cgroup, per device + * resources. There are multiple instances of this object per cgroup, + * therefore it cannot be embedded within rdma_cgroup structure. It + * is maintained as list. + */ +struct rdmacg_resource_pool { + struct rdmacg_device *device; + struct rdmacg_resource resources[RDMACG_RESOURCE_MAX]; + + struct list_head cg_node; + struct list_head dev_node; + + /* count active user tasks of this pool */ + u64 usage_sum; + /* total number counts which are set to max */ + int num_max_cnt; +}; + +static struct rdma_cgroup *css_rdmacg(struct cgroup_subsys_state *css) +{ + return container_of(css, struct rdma_cgroup, css); +} + +static struct rdma_cgroup *parent_rdmacg(struct rdma_cgroup *cg) +{ + return css_rdmacg(cg->css.parent); +} + +static inline struct rdma_cgroup *get_current_rdmacg(void) +{ + return css_rdmacg(task_get_css(current, rdma_cgrp_id)); +} + +static void set_resource_limit(struct rdmacg_resource_pool *rpool, + int index, int new_max) +{ + if (new_max == S32_MAX) { + if (rpool->resources[index].max != S32_MAX) + rpool->num_max_cnt++; + } else { + if (rpool->resources[index].max == S32_MAX) + rpool->num_max_cnt--; + } + rpool->resources[index].max = new_max; +} + +static void set_all_resource_max_limit(struct rdmacg_resource_pool *rpool) +{ + int i; + + for (i = 0; i < RDMACG_RESOURCE_MAX; i++) + set_resource_limit(rpool, i, S32_MAX); +} + +static void free_cg_rpool_locked(struct rdmacg_resource_pool *rpool) +{ + lockdep_assert_held(&rdmacg_mutex); + + list_del(&rpool->cg_node); + list_del(&rpool->dev_node); + kfree(rpool); +} + +static struct rdmacg_resource_pool * +find_cg_rpool_locked(struct rdma_cgroup *cg, + struct rdmacg_device *device) + +{ + struct rdmacg_resource_pool *pool; + + lockdep_assert_held(&rdmacg_mutex); + + list_for_each_entry(pool, &cg->rpools, cg_node) + if (pool->device == device) + return pool; + + return NULL; +} + +static struct rdmacg_resource_pool * +get_cg_rpool_locked(struct rdma_cgroup *cg, struct rdmacg_device *device) +{ + struct rdmacg_resource_pool *rpool; + + rpool = find_cg_rpool_locked(cg, device); + if (rpool) + return rpool; + + rpool = kzalloc(sizeof(*rpool), GFP_KERNEL); + if (!rpool) + return ERR_PTR(-ENOMEM); + + rpool->device = device; + set_all_resource_max_limit(rpool); + + INIT_LIST_HEAD(&rpool->cg_node); + INIT_LIST_HEAD(&rpool->dev_node); + list_add_tail(&rpool->cg_node, &cg->rpools); + list_add_tail(&rpool->dev_node, &device->rpools); + return rpool; +} + +/** + * uncharge_cg_locked - uncharge resource for rdma cgroup + * @cg: pointer to cg to uncharge and all parents in hierarchy + * @device: pointer to rdmacg device + * @index: index of the resource to uncharge in cg (resource pool) + * + * It also frees the resource pool which was created as part of + * charging operation when there are no resources attached to + * resource pool. + */ +static void +uncharge_cg_locked(struct rdma_cgroup *cg, + struct rdmacg_device *device, + enum rdmacg_resource_type index) +{ + struct rdmacg_resource_pool *rpool; + + rpool = find_cg_rpool_locked(cg, device); + + /* + * rpool cannot be null at this stage. Let kernel operate in case + * if there a bug in IB stack or rdma controller, instead of crashing + * the system. + */ + if (unlikely(!rpool)) { + pr_warn("Invalid device %p or rdma cgroup %p\n", cg, device); + return; + } + + rpool->resources[index].usage--; + + /* + * A negative count (or overflow) is invalid, + * it indicates a bug in the rdma controller. + */ + WARN_ON_ONCE(rpool->resources[index].usage < 0); + rpool->usage_sum--; + if (rpool->usage_sum == 0 && + rpool->num_max_cnt == RDMACG_RESOURCE_MAX) { + /* + * No user of the rpool and all entries are set to max, so + * safe to delete this rpool. + */ + free_cg_rpool_locked(rpool); + } +} + +/** + * rdmacg_uncharge_hierarchy - hierarchically uncharge rdma resource count + * @device: pointer to rdmacg device + * @stop_cg: while traversing hirerchy, when meet with stop_cg cgroup + * stop uncharging + * @index: index of the resource to uncharge in cg in given resource pool + */ +static void rdmacg_uncharge_hierarchy(struct rdma_cgroup *cg, + struct rdmacg_device *device, + struct rdma_cgroup *stop_cg, + enum rdmacg_resource_type index) +{ + struct rdma_cgroup *p; + + mutex_lock(&rdmacg_mutex); + + for (p = cg; p != stop_cg; p = parent_rdmacg(p)) + uncharge_cg_locked(p, device, index); + + mutex_unlock(&rdmacg_mutex); + + css_put(&cg->css); +} + +/** + * rdmacg_uncharge - hierarchically uncharge rdma resource count + * @device: pointer to rdmacg device + * @index: index of the resource to uncharge in cgroup in given resource pool + */ +void rdmacg_uncharge(struct rdma_cgroup *cg, + struct rdmacg_device *device, + enum rdmacg_resource_type index) +{ + if (index >= RDMACG_RESOURCE_MAX) + return; + + rdmacg_uncharge_hierarchy(cg, device, NULL, index); +} +EXPORT_SYMBOL(rdmacg_uncharge); + +/** + * rdmacg_try_charge - hierarchically try to charge the rdma resource + * @rdmacg: pointer to rdma cgroup which will own this resource + * @device: pointer to rdmacg device + * @index: index of the resource to charge in cgroup (resource pool) + * + * This function follows charging resource in hierarchical way. + * It will fail if the charge would cause the new value to exceed the + * hierarchical limit. + * Returns 0 if the charge succeeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. + * Returns pointer to rdmacg for this resource when charging is successful. + * + * Charger needs to account resources on two criteria. + * (a) per cgroup & (b) per device resource usage. + * Per cgroup resource usage ensures that tasks of cgroup doesn't cross + * the configured limits. Per device provides granular configuration + * in multi device usage. It allocates resource pool in the hierarchy + * for each parent it come across for first resource. Later on resource + * pool will be available. Therefore it will be much faster thereon + * to charge/uncharge. + */ +int rdmacg_try_charge(struct rdma_cgroup **rdmacg, + struct rdmacg_device *device, + enum rdmacg_resource_type index) +{ + struct rdma_cgroup *cg, *p; + struct rdmacg_resource_pool *rpool; + s64 new; + int ret = 0; + + if (index >= RDMACG_RESOURCE_MAX) + return -EINVAL; + + /* + * hold on to css, as cgroup can be removed but resource + * accounting happens on css. + */ + cg = get_current_rdmacg(); + + mutex_lock(&rdmacg_mutex); + for (p = cg; p; p = parent_rdmacg(p)) { + rpool = get_cg_rpool_locked(p, device); + if (IS_ERR(rpool)) { + ret = PTR_ERR(rpool); + goto err; + } else { + new = rpool->resources[index].usage + 1; + if (new > rpool->resources[index].max) { + ret = -EAGAIN; + goto err; + } else { + rpool->resources[index].usage = new; + rpool->usage_sum++; + } + } + } + mutex_unlock(&rdmacg_mutex); + + *rdmacg = cg; + return 0; + +err: + mutex_unlock(&rdmacg_mutex); + rdmacg_uncharge_hierarchy(cg, device, p, index); + return ret; +} +EXPORT_SYMBOL(rdmacg_try_charge); + +/** + * rdmacg_register_device - register rdmacg device to rdma controller. + * @device: pointer to rdmacg device whose resources need to be accounted. + * + * If IB stack wish a device to participate in rdma cgroup resource + * tracking, it must invoke this API to register with rdma cgroup before + * any user space application can start using the RDMA resources. + */ +void rdmacg_register_device(struct rdmacg_device *device) +{ + INIT_LIST_HEAD(&device->dev_node); + INIT_LIST_HEAD(&device->rpools); + + mutex_lock(&rdmacg_mutex); + list_add_tail(&device->dev_node, &rdmacg_devices); + mutex_unlock(&rdmacg_mutex); +} +EXPORT_SYMBOL(rdmacg_register_device); + +/** + * rdmacg_unregister_device - unregister rdmacg device from rdma controller. + * @device: pointer to rdmacg device which was previously registered with rdma + * controller using rdmacg_register_device(). + * + * IB stack must invoke this after all the resources of the IB device + * are destroyed and after ensuring that no more resources will be created + * when this API is invoked. + */ +void rdmacg_unregister_device(struct rdmacg_device *device) +{ + struct rdmacg_resource_pool *rpool, *tmp; + + /* + * Synchronize with any active resource settings, + * usage query happening via configfs. + */ + mutex_lock(&rdmacg_mutex); + list_del_init(&device->dev_node); + + /* + * Now that this device is off the cgroup list, its safe to free + * all the rpool resources. + */ + list_for_each_entry_safe(rpool, tmp, &device->rpools, dev_node) + free_cg_rpool_locked(rpool); + + mutex_unlock(&rdmacg_mutex); +} +EXPORT_SYMBOL(rdmacg_unregister_device); + +static int parse_resource(char *c, int *intval) +{ + substring_t argstr; + char *name, *value = c; + size_t len; + int ret, i; + + name = strsep(&value, "="); + if (!name || !value) + return -EINVAL; + + i = match_string(rdmacg_resource_names, RDMACG_RESOURCE_MAX, name); + if (i < 0) + return i; + + len = strlen(value); + + argstr.from = value; + argstr.to = value + len; + + ret = match_int(&argstr, intval); + if (ret >= 0) { + if (*intval < 0) + return -EINVAL; + return i; + } + if (strncmp(value, RDMACG_MAX_STR, len) == 0) { + *intval = S32_MAX; + return i; + } + return -EINVAL; +} + +static int rdmacg_parse_limits(char *options, + int *new_limits, unsigned long *enables) +{ + char *c; + int err = -EINVAL; + + /* parse resource options */ + while ((c = strsep(&options, " ")) != NULL) { + int index, intval; + + index = parse_resource(c, &intval); + if (index < 0) + goto err; + + new_limits[index] = intval; + *enables |= BIT(index); + } + return 0; + +err: + return err; +} + +static struct rdmacg_device *rdmacg_get_device_locked(const char *name) +{ + struct rdmacg_device *device; + + lockdep_assert_held(&rdmacg_mutex); + + list_for_each_entry(device, &rdmacg_devices, dev_node) + if (!strcmp(name, device->name)) + return device; + + return NULL; +} + +static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdma_cgroup *cg = css_rdmacg(of_css(of)); + const char *dev_name; + struct rdmacg_resource_pool *rpool; + struct rdmacg_device *device; + char *options = strstrip(buf); + int *new_limits; + unsigned long enables = 0; + int i = 0, ret = 0; + + /* extract the device name first */ + dev_name = strsep(&options, " "); + if (!dev_name) { + ret = -EINVAL; + goto err; + } + + new_limits = kcalloc(RDMACG_RESOURCE_MAX, sizeof(int), GFP_KERNEL); + if (!new_limits) { + ret = -ENOMEM; + goto err; + } + + ret = rdmacg_parse_limits(options, new_limits, &enables); + if (ret) + goto parse_err; + + /* acquire lock to synchronize with hot plug devices */ + mutex_lock(&rdmacg_mutex); + + device = rdmacg_get_device_locked(dev_name); + if (!device) { + ret = -ENODEV; + goto dev_err; + } + + rpool = get_cg_rpool_locked(cg, device); + if (IS_ERR(rpool)) { + ret = PTR_ERR(rpool); + goto dev_err; + } + + /* now set the new limits of the rpool */ + for_each_set_bit(i, &enables, RDMACG_RESOURCE_MAX) + set_resource_limit(rpool, i, new_limits[i]); + + if (rpool->usage_sum == 0 && + rpool->num_max_cnt == RDMACG_RESOURCE_MAX) { + /* + * No user of the rpool and all entries are set to max, so + * safe to delete this rpool. + */ + free_cg_rpool_locked(rpool); + } + +dev_err: + mutex_unlock(&rdmacg_mutex); + +parse_err: + kfree(new_limits); + +err: + return ret ?: nbytes; +} + +static void print_rpool_values(struct seq_file *sf, + struct rdmacg_resource_pool *rpool) +{ + enum rdmacg_file_type sf_type; + int i; + u32 value; + + sf_type = seq_cft(sf)->private; + + for (i = 0; i < RDMACG_RESOURCE_MAX; i++) { + seq_puts(sf, rdmacg_resource_names[i]); + seq_putc(sf, '='); + if (sf_type == RDMACG_RESOURCE_TYPE_MAX) { + if (rpool) + value = rpool->resources[i].max; + else + value = S32_MAX; + } else { + if (rpool) + value = rpool->resources[i].usage; + else + value = 0; + } + + if (value == S32_MAX) + seq_puts(sf, RDMACG_MAX_STR); + else + seq_printf(sf, "%d", value); + seq_putc(sf, ' '); + } +} + +static int rdmacg_resource_read(struct seq_file *sf, void *v) +{ + struct rdmacg_device *device; + struct rdmacg_resource_pool *rpool; + struct rdma_cgroup *cg = css_rdmacg(seq_css(sf)); + + mutex_lock(&rdmacg_mutex); + + list_for_each_entry(device, &rdmacg_devices, dev_node) { + seq_printf(sf, "%s ", device->name); + + rpool = find_cg_rpool_locked(cg, device); + print_rpool_values(sf, rpool); + + seq_putc(sf, '\n'); + } + + mutex_unlock(&rdmacg_mutex); + return 0; +} + +static struct cftype rdmacg_files[] = { + { + .name = "max", + .write = rdmacg_resource_set_max, + .seq_show = rdmacg_resource_read, + .private = RDMACG_RESOURCE_TYPE_MAX, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "current", + .seq_show = rdmacg_resource_read, + .private = RDMACG_RESOURCE_TYPE_STAT, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { } /* terminate */ +}; + +static struct cgroup_subsys_state * +rdmacg_css_alloc(struct cgroup_subsys_state *parent) +{ + struct rdma_cgroup *cg; + + cg = kzalloc(sizeof(*cg), GFP_KERNEL); + if (!cg) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&cg->rpools); + return &cg->css; +} + +static void rdmacg_css_free(struct cgroup_subsys_state *css) +{ + struct rdma_cgroup *cg = css_rdmacg(css); + + kfree(cg); +} + +/** + * rdmacg_css_offline - cgroup css_offline callback + * @css: css of interest + * + * This function is called when @css is about to go away and responsible + * for shooting down all rdmacg associated with @css. As part of that it + * marks all the resource pool entries to max value, so that when resources are + * uncharged, associated resource pool can be freed as well. + */ +static void rdmacg_css_offline(struct cgroup_subsys_state *css) +{ + struct rdma_cgroup *cg = css_rdmacg(css); + struct rdmacg_resource_pool *rpool; + + mutex_lock(&rdmacg_mutex); + + list_for_each_entry(rpool, &cg->rpools, cg_node) + set_all_resource_max_limit(rpool); + + mutex_unlock(&rdmacg_mutex); +} + +struct cgroup_subsys rdma_cgrp_subsys = { + .css_alloc = rdmacg_css_alloc, + .css_free = rdmacg_css_free, + .css_offline = rdmacg_css_offline, + .legacy_cftypes = rdmacg_files, + .dfl_cftypes = rdmacg_files, +}; diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c new file mode 100644 index 000000000..7006fc8dd --- /dev/null +++ b/kernel/cgroup/rstat.c @@ -0,0 +1,549 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "cgroup-internal.h" + +#include <linux/sched/cputime.h> + +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/btf_ids.h> + +static DEFINE_SPINLOCK(cgroup_rstat_lock); +static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); + +static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); + +static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) +{ + return per_cpu_ptr(cgrp->rstat_cpu, cpu); +} + +/** + * cgroup_rstat_updated - keep track of updated rstat_cpu + * @cgrp: target cgroup + * @cpu: cpu on which rstat_cpu was updated + * + * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching + * rstat_cpu->updated_children list. See the comment on top of + * cgroup_rstat_cpu definition for details. + */ +void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) +{ + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); + unsigned long flags; + + /* + * Speculative already-on-list test. This may race leading to + * temporary inaccuracies, which is fine. + * + * Because @parent's updated_children is terminated with @parent + * instead of NULL, we can tell whether @cgrp is on the list by + * testing the next pointer for NULL. + */ + if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) + return; + + raw_spin_lock_irqsave(cpu_lock, flags); + + /* put @cgrp and all ancestors on the corresponding updated lists */ + while (true) { + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup_rstat_cpu *prstatc; + + /* + * Both additions and removals are bottom-up. If a cgroup + * is already in the tree, all ancestors are. + */ + if (rstatc->updated_next) + break; + + /* Root has no parent to link it to, but mark it busy */ + if (!parent) { + rstatc->updated_next = cgrp; + break; + } + + prstatc = cgroup_rstat_cpu(parent, cpu); + rstatc->updated_next = prstatc->updated_children; + prstatc->updated_children = cgrp; + + cgrp = parent; + } + + raw_spin_unlock_irqrestore(cpu_lock, flags); +} + +/** + * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree + * @pos: current position + * @root: root of the tree to traversal + * @cpu: target cpu + * + * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts + * the traversal and %NULL return indicates the end. During traversal, + * each returned cgroup is unlinked from the tree. Must be called with the + * matching cgroup_rstat_cpu_lock held. + * + * The only ordering guarantee is that, for a parent and a child pair + * covered by a given traversal, if a child is visited, its parent is + * guaranteed to be visited afterwards. + */ +static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, + struct cgroup *root, int cpu) +{ + struct cgroup_rstat_cpu *rstatc; + struct cgroup *parent; + + if (pos == root) + return NULL; + + /* + * We're gonna walk down to the first leaf and visit/remove it. We + * can pick whatever unvisited node as the starting point. + */ + if (!pos) { + pos = root; + /* return NULL if this subtree is not on-list */ + if (!cgroup_rstat_cpu(pos, cpu)->updated_next) + return NULL; + } else { + pos = cgroup_parent(pos); + } + + /* walk down to the first leaf */ + while (true) { + rstatc = cgroup_rstat_cpu(pos, cpu); + if (rstatc->updated_children == pos) + break; + pos = rstatc->updated_children; + } + + /* + * Unlink @pos from the tree. As the updated_children list is + * singly linked, we have to walk it to find the removal point. + * However, due to the way we traverse, @pos will be the first + * child in most cases. The only exception is @root. + */ + parent = cgroup_parent(pos); + if (parent) { + struct cgroup_rstat_cpu *prstatc; + struct cgroup **nextp; + + prstatc = cgroup_rstat_cpu(parent, cpu); + nextp = &prstatc->updated_children; + while (*nextp != pos) { + struct cgroup_rstat_cpu *nrstatc; + + nrstatc = cgroup_rstat_cpu(*nextp, cpu); + WARN_ON_ONCE(*nextp == parent); + nextp = &nrstatc->updated_next; + } + *nextp = rstatc->updated_next; + } + + rstatc->updated_next = NULL; + return pos; +} + +/* + * A hook for bpf stat collectors to attach to and flush their stats. + * Together with providing bpf kfuncs for cgroup_rstat_updated() and + * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that + * collect cgroup stats can integrate with rstat for efficient flushing. + * + * A static noinline declaration here could cause the compiler to optimize away + * the function. A global noinline declaration will keep the definition, but may + * optimize away the callsite. Therefore, __weak is needed to ensure that the + * call is still emitted, by telling the compiler that we don't know what the + * function might eventually be. + * + * __diag_* below are needed to dismiss the missing prototype warning. + */ +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "kfuncs which will be used in BPF programs"); + +__weak noinline void bpf_rstat_flush(struct cgroup *cgrp, + struct cgroup *parent, int cpu) +{ +} + +__diag_pop(); + +/* see cgroup_rstat_flush() */ +static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) + __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) +{ + int cpu; + + lockdep_assert_held(&cgroup_rstat_lock); + + for_each_possible_cpu(cpu) { + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, + cpu); + struct cgroup *pos = NULL; + unsigned long flags; + + /* + * The _irqsave() is needed because cgroup_rstat_lock is + * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring + * this lock with the _irq() suffix only disables interrupts on + * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables + * interrupts on both configurations. The _irqsave() ensures + * that interrupts are always disabled and later restored. + */ + raw_spin_lock_irqsave(cpu_lock, flags); + while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { + struct cgroup_subsys_state *css; + + cgroup_base_stat_flush(pos, cpu); + bpf_rstat_flush(pos, cgroup_parent(pos), cpu); + + rcu_read_lock(); + list_for_each_entry_rcu(css, &pos->rstat_css_list, + rstat_css_node) + css->ss->css_rstat_flush(css, cpu); + rcu_read_unlock(); + } + raw_spin_unlock_irqrestore(cpu_lock, flags); + + /* if @may_sleep, play nice and yield if necessary */ + if (may_sleep && (need_resched() || + spin_needbreak(&cgroup_rstat_lock))) { + spin_unlock_irq(&cgroup_rstat_lock); + if (!cond_resched()) + cpu_relax(); + spin_lock_irq(&cgroup_rstat_lock); + } + } +} + +/** + * cgroup_rstat_flush - flush stats in @cgrp's subtree + * @cgrp: target cgroup + * + * Collect all per-cpu stats in @cgrp's subtree into the global counters + * and propagate them upwards. After this function returns, all cgroups in + * the subtree have up-to-date ->stat. + * + * This also gets all cgroups in the subtree including @cgrp off the + * ->updated_children lists. + * + * This function may block. + */ +void cgroup_rstat_flush(struct cgroup *cgrp) +{ + might_sleep(); + + spin_lock_irq(&cgroup_rstat_lock); + cgroup_rstat_flush_locked(cgrp, true); + spin_unlock_irq(&cgroup_rstat_lock); +} + +/** + * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() + * @cgrp: target cgroup + * + * This function can be called from any context. + */ +void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) +{ + unsigned long flags; + + spin_lock_irqsave(&cgroup_rstat_lock, flags); + cgroup_rstat_flush_locked(cgrp, false); + spin_unlock_irqrestore(&cgroup_rstat_lock, flags); +} + +/** + * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold + * @cgrp: target cgroup + * + * Flush stats in @cgrp's subtree and prevent further flushes. Must be + * paired with cgroup_rstat_flush_release(). + * + * This function may block. + */ +void cgroup_rstat_flush_hold(struct cgroup *cgrp) + __acquires(&cgroup_rstat_lock) +{ + might_sleep(); + spin_lock_irq(&cgroup_rstat_lock); + cgroup_rstat_flush_locked(cgrp, true); +} + +/** + * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() + */ +void cgroup_rstat_flush_release(void) + __releases(&cgroup_rstat_lock) +{ + spin_unlock_irq(&cgroup_rstat_lock); +} + +int cgroup_rstat_init(struct cgroup *cgrp) +{ + int cpu; + + /* the root cgrp has rstat_cpu preallocated */ + if (!cgrp->rstat_cpu) { + cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); + if (!cgrp->rstat_cpu) + return -ENOMEM; + } + + /* ->updated_children list is self terminated */ + for_each_possible_cpu(cpu) { + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + + rstatc->updated_children = cgrp; + u64_stats_init(&rstatc->bsync); + } + + return 0; +} + +void cgroup_rstat_exit(struct cgroup *cgrp) +{ + int cpu; + + cgroup_rstat_flush(cgrp); + + /* sanity check */ + for_each_possible_cpu(cpu) { + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + + if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || + WARN_ON_ONCE(rstatc->updated_next)) + return; + } + + free_percpu(cgrp->rstat_cpu); + cgrp->rstat_cpu = NULL; +} + +void __init cgroup_rstat_boot(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); +} + +/* + * Functions for cgroup basic resource statistics implemented on top of + * rstat. + */ +static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, + struct cgroup_base_stat *src_bstat) +{ + dst_bstat->cputime.utime += src_bstat->cputime.utime; + dst_bstat->cputime.stime += src_bstat->cputime.stime; + dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; +#ifdef CONFIG_SCHED_CORE + dst_bstat->forceidle_sum += src_bstat->forceidle_sum; +#endif +} + +static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, + struct cgroup_base_stat *src_bstat) +{ + dst_bstat->cputime.utime -= src_bstat->cputime.utime; + dst_bstat->cputime.stime -= src_bstat->cputime.stime; + dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; +#ifdef CONFIG_SCHED_CORE + dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; +#endif +} + +static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) +{ + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup_base_stat delta; + unsigned seq; + + /* Root-level stats are sourced from system-wide CPU stats */ + if (!parent) + return; + + /* fetch the current per-cpu values */ + do { + seq = __u64_stats_fetch_begin(&rstatc->bsync); + delta = rstatc->bstat; + } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); + + /* propagate percpu delta to global */ + cgroup_base_stat_sub(&delta, &rstatc->last_bstat); + cgroup_base_stat_add(&cgrp->bstat, &delta); + cgroup_base_stat_add(&rstatc->last_bstat, &delta); + + /* propagate global delta to parent (unless that's root) */ + if (cgroup_parent(parent)) { + delta = cgrp->bstat; + cgroup_base_stat_sub(&delta, &cgrp->last_bstat); + cgroup_base_stat_add(&parent->bstat, &delta); + cgroup_base_stat_add(&cgrp->last_bstat, &delta); + } +} + +static struct cgroup_rstat_cpu * +cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) +{ + struct cgroup_rstat_cpu *rstatc; + + rstatc = get_cpu_ptr(cgrp->rstat_cpu); + *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); + return rstatc; +} + +static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, + struct cgroup_rstat_cpu *rstatc, + unsigned long flags) +{ + u64_stats_update_end_irqrestore(&rstatc->bsync, flags); + cgroup_rstat_updated(cgrp, smp_processor_id()); + put_cpu_ptr(rstatc); +} + +void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) +{ + struct cgroup_rstat_cpu *rstatc; + unsigned long flags; + + rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); + rstatc->bstat.cputime.sum_exec_runtime += delta_exec; + cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); +} + +void __cgroup_account_cputime_field(struct cgroup *cgrp, + enum cpu_usage_stat index, u64 delta_exec) +{ + struct cgroup_rstat_cpu *rstatc; + unsigned long flags; + + rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); + + switch (index) { + case CPUTIME_USER: + case CPUTIME_NICE: + rstatc->bstat.cputime.utime += delta_exec; + break; + case CPUTIME_SYSTEM: + case CPUTIME_IRQ: + case CPUTIME_SOFTIRQ: + rstatc->bstat.cputime.stime += delta_exec; + break; +#ifdef CONFIG_SCHED_CORE + case CPUTIME_FORCEIDLE: + rstatc->bstat.forceidle_sum += delta_exec; + break; +#endif + default: + break; + } + + cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); +} + +/* + * compute the cputime for the root cgroup by getting the per cpu data + * at a global level, then categorizing the fields in a manner consistent + * with how it is done by __cgroup_account_cputime_field for each bit of + * cpu time attributed to a cgroup. + */ +static void root_cgroup_cputime(struct cgroup_base_stat *bstat) +{ + struct task_cputime *cputime = &bstat->cputime; + int i; + + memset(bstat, 0, sizeof(*bstat)); + for_each_possible_cpu(i) { + struct kernel_cpustat kcpustat; + u64 *cpustat = kcpustat.cpustat; + u64 user = 0; + u64 sys = 0; + + kcpustat_cpu_fetch(&kcpustat, i); + + user += cpustat[CPUTIME_USER]; + user += cpustat[CPUTIME_NICE]; + cputime->utime += user; + + sys += cpustat[CPUTIME_SYSTEM]; + sys += cpustat[CPUTIME_IRQ]; + sys += cpustat[CPUTIME_SOFTIRQ]; + cputime->stime += sys; + + cputime->sum_exec_runtime += user; + cputime->sum_exec_runtime += sys; + cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; + +#ifdef CONFIG_SCHED_CORE + bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; +#endif + } +} + +void cgroup_base_stat_cputime_show(struct seq_file *seq) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + u64 usage, utime, stime; + struct cgroup_base_stat bstat; +#ifdef CONFIG_SCHED_CORE + u64 forceidle_time; +#endif + + if (cgroup_parent(cgrp)) { + cgroup_rstat_flush_hold(cgrp); + usage = cgrp->bstat.cputime.sum_exec_runtime; + cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, + &utime, &stime); +#ifdef CONFIG_SCHED_CORE + forceidle_time = cgrp->bstat.forceidle_sum; +#endif + cgroup_rstat_flush_release(); + } else { + root_cgroup_cputime(&bstat); + usage = bstat.cputime.sum_exec_runtime; + utime = bstat.cputime.utime; + stime = bstat.cputime.stime; +#ifdef CONFIG_SCHED_CORE + forceidle_time = bstat.forceidle_sum; +#endif + } + + do_div(usage, NSEC_PER_USEC); + do_div(utime, NSEC_PER_USEC); + do_div(stime, NSEC_PER_USEC); +#ifdef CONFIG_SCHED_CORE + do_div(forceidle_time, NSEC_PER_USEC); +#endif + + seq_printf(seq, "usage_usec %llu\n" + "user_usec %llu\n" + "system_usec %llu\n", + usage, utime, stime); + +#ifdef CONFIG_SCHED_CORE + seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); +#endif +} + +/* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ +BTF_SET8_START(bpf_rstat_kfunc_ids) +BTF_ID_FLAGS(func, cgroup_rstat_updated) +BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) +BTF_SET8_END(bpf_rstat_kfunc_ids) + +static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { + .owner = THIS_MODULE, + .set = &bpf_rstat_kfunc_ids, +}; + +static int __init bpf_rstat_kfunc_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, + &bpf_rstat_kfunc_set); +} +late_initcall(bpf_rstat_kfunc_init); |