cregit-Linux how code gets into the kernel

Release 4.15 kernel/cgroup/cgroup-v1.c

Directory: kernel/cgroup
#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 <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;

/*
 * 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.  Modifying it also requires
 * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
 */
static DEFINE_SPINLOCK(release_agent_path_lock);


bool cgroup1_ssid_disabled(int ssid) { return cgroup_no_v1_mask & (1 << ssid); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo17100.00%2100.00%
Total17100.00%2100.00%

/** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached */
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroup_root *root; int retval = 0; mutex_lock(&cgroup_mutex); percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; if (root == &cgrp_dfl_root) continue; 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; } percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return retval; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo108100.00%1100.00%
Total108100.00%1100.00%

EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /** * cgroup_trasnsfer_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. */
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; mutex_lock(&cgroup_mutex); percpu_down_write(&cgroup_threadgroup_rwsem); /* 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_transfer_tasks(to, task, false); put_task_struct(task); } } while (task && !ret); out_err: cgroup_migrate_finish(&mgctx); percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo23093.50%480.00%
Prateek Sood166.50%120.00%
Total246100.00%5100.00%

/* * 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; }; /* * The following two functions "fix" the issue where there are more pids * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. * TODO: replace with a kernel-wide solution to this problem */ #define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
static void *pidlist_allocate(int count) { if (PIDLIST_TOO_LARGE(count)) return vmalloc(count * sizeof(pid_t)); else return kmalloc(count * sizeof(pid_t), GFP_KERNEL); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo42100.00%1100.00%
Total42100.00%1100.00%


static void pidlist_free(void *p) { kvfree(p); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo15100.00%1100.00%
Total15100.00%1100.00%

/* * 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)); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo73100.00%2100.00%
Total73100.00%2100.00%


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); pidlist_free(l->list); put_pid_ns(l->key.ns); tofree = l; } mutex_unlock(&l->owner->pidlist_mutex); kfree(tofree); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo107100.00%1100.00%
Total107100.00%1100.00%

/* * 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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo98100.00%1100.00%
Total98100.00%1100.00%

/* * 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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo31100.00%1100.00%
Total31100.00%1100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo73100.00%1100.00%
Total73100.00%1100.00%

/* * 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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo123100.00%1100.00%
Total123100.00%1100.00%

/** * 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 = 0; struct cgrp_cset_link *link; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += link->cset->nr_tasks; spin_unlock_irq(&css_set_lock); return count; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo5198.08%150.00%
Waiman Long11.92%150.00%
Total52100.00%2100.00%

/* * 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 = pidlist_allocate(length); 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 & (if procs) strip out duplicates */ sort(array, length, sizeof(pid_t), cmppid, NULL); if (type == CGROUP_FILE_PROCS) length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { pidlist_free(array); return -ENOMEM; } /* store array, freeing old if necessary */ pidlist_free(l->list); l->list = array; l->length = length; *lp = l; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo252100.00%2100.00%
Total252100.00%2100.00%

/* * 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 *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 @of->priv 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 @of->priv can't be used directly. It * could already have been destroyed. */ if (of->priv) of->priv = 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 (!of->priv) { ret = pidlist_array_load(cgrp, type, (struct cgroup_pidlist **)&of->priv); if (ret) return ERR_PTR(ret); } l = of->priv; 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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo245100.00%1100.00%
Total245100.00%1100.00%


static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; struct cgroup_pidlist *l = of->priv; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, CGROUP_PIDLIST_DESTROY_DELAY); mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo62100.00%1100.00%
Total62100.00%1100.00%


static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_pidlist *l = of->priv; 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) { return NULL; } else { *pos = *p; return p; } }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo83100.00%1100.00%
Total83100.00%1100.00%


static int cgroup_pidlist_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *(int *)v); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo32100.00%1100.00%
Total32100.00%1100.00%


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; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup); 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. */ cred = current_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); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo188100.00%2100.00%
Total188100.00%2100.00%


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); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo35100.00%1100.00%
Total35100.00%1100.00%


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); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo35100.00%2100.00%
Total35100.00%2100.00%


static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); 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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo105100.00%1100.00%
Total105100.00%1100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo60100.00%1100.00%
Total60100.00%1100.00%


static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) { seq_puts(seq, "0\n"); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo25100.00%1100.00%
Total25100.00%1100.00%


static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft) { return notify_on_release(css->cgroup); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo24100.00%1100.00%
Total24100.00%1100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo51100.00%1100.00%
Total51100.00%1100.00%


static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo29100.00%1100.00%
Total29100.00%1100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo51100.00%1100.00%
Total51100.00%1100.00%

/* 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 */
static 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"); /* * ideally we don't want subsystems moving around while we do this. * cgroup_mutex is also necessary to guarantee an atomic snapshot of * subsys/hierarchy state. */ mutex_lock(&cgroup_mutex); 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)); mutex_unlock(&cgroup_mutex); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo84100.00%1100.00%
Total84100.00%1100.00%


static int cgroupstats_open(struct inode *inode, struct file *file) { return single_open(file, proc_cgroupstats_show, NULL); }

Contributors

PersonTokensPropCommitsCommitProp
Tejun Heo26100.00%1100.00%
Total26100.00%1100.00%

const struct file_operations proc_cgroupstats_operations = {