#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/eventfd.h>
#include <linux/poll.h>
-#include <linux/flex_array.h> /* used in cgroup_attach_proc */
+#include <linux/flex_array.h> /* used in cgroup_attach_task */
#include <linux/kthread.h>
#include <linux/atomic.h>
* B happens only through cgroup_show_options() and using cgroup_root_mutex
* breaks it.
*/
+#ifdef CONFIG_PROVE_RCU
+DEFINE_MUTEX(cgroup_mutex);
+EXPORT_SYMBOL_GPL(cgroup_mutex); /* only for task_subsys_state_check() */
+#else
static DEFINE_MUTEX(cgroup_mutex);
+#endif
+
static DEFINE_MUTEX(cgroup_root_mutex);
/*
static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
struct cftype cfts[], bool is_add);
-#ifdef CONFIG_PROVE_LOCKING
-int cgroup_lock_is_held(void)
-{
- return lockdep_is_held(&cgroup_mutex);
-}
-#else /* #ifdef CONFIG_PROVE_LOCKING */
-int cgroup_lock_is_held(void)
-{
- return mutex_is_locked(&cgroup_mutex);
-}
-#endif /* #else #ifdef CONFIG_PROVE_LOCKING */
-
-EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
-
static int css_unbias_refcnt(int refcnt)
{
return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
return test_bit(CGRP_REMOVED, &cgrp->flags);
}
-/* bits in struct cgroupfs_root flags field */
+/**
+ * cgroup_is_descendant - test ancestry
+ * @cgrp: the cgroup to be tested
+ * @ancestor: possible ancestor of @cgrp
+ *
+ * Test whether @cgrp is a descendant of @ancestor. It also returns %true
+ * if @cgrp == @ancestor. This function is safe to call as long as @cgrp
+ * and @ancestor are accessible.
+ */
+bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
+{
+ while (cgrp) {
+ if (cgrp == ancestor)
+ return true;
+ cgrp = cgrp->parent;
+ }
+ return false;
+}
+EXPORT_SYMBOL_GPL(cgroup_is_descendant);
+
+/* cgroupfs_root->flags */
enum {
- ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
- ROOT_XATTR, /* supports extended attributes */
+ CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */
+ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */
};
static int cgroup_is_releasable(const struct cgroup *cgrp)
return __d_cfe(dentry)->type;
}
+/**
+ * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
+ * @cgrp: the cgroup to be checked for liveness
+ *
+ * On success, returns true; the mutex should be later unlocked. On
+ * failure returns false with no lock held.
+ */
+static bool cgroup_lock_live_group(struct cgroup *cgrp)
+{
+ mutex_lock(&cgroup_mutex);
+ if (cgroup_is_removed(cgrp)) {
+ mutex_unlock(&cgroup_mutex);
+ return false;
+ }
+ return true;
+}
+
/* the list of cgroups eligible for automatic release. Protected by
* release_list_lock */
static LIST_HEAD(release_list);
* update of a tasks cgroup pointer by cgroup_attach_task()
*/
-/**
- * cgroup_lock - lock out any changes to cgroup structures
- *
- */
-void cgroup_lock(void)
-{
- mutex_lock(&cgroup_mutex);
-}
-EXPORT_SYMBOL_GPL(cgroup_lock);
-
-/**
- * cgroup_unlock - release lock on cgroup changes
- *
- * Undo the lock taken in a previous cgroup_lock() call.
- */
-void cgroup_unlock(void)
-{
- mutex_unlock(&cgroup_mutex);
-}
-EXPORT_SYMBOL_GPL(cgroup_unlock);
-
/*
* A couple of forward declarations required, due to cyclic reference loop:
* cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
cgrp->root->number_of_cgroups--;
mutex_unlock(&cgroup_mutex);
+ /*
+ * We get a ref to the parent's dentry, and put the ref when
+ * this cgroup is being freed, so it's guaranteed that the
+ * parent won't be destroyed before its children.
+ */
+ dput(cgrp->parent->dentry);
+
/*
* Drop the active superblock reference that we took when we
* created the cgroup
mutex_lock(&cgroup_root_mutex);
for_each_subsys(root, ss)
seq_printf(seq, ",%s", ss->name);
- if (test_bit(ROOT_NOPREFIX, &root->flags))
+ if (root->flags & CGRP_ROOT_NOPREFIX)
seq_puts(seq, ",noprefix");
- if (test_bit(ROOT_XATTR, &root->flags))
+ if (root->flags & CGRP_ROOT_XATTR)
seq_puts(seq, ",xattr");
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
continue;
}
if (!strcmp(token, "noprefix")) {
- set_bit(ROOT_NOPREFIX, &opts->flags);
+ opts->flags |= CGRP_ROOT_NOPREFIX;
continue;
}
if (!strcmp(token, "clone_children")) {
continue;
}
if (!strcmp(token, "xattr")) {
- set_bit(ROOT_XATTR, &opts->flags);
+ opts->flags |= CGRP_ROOT_XATTR;
continue;
}
if (!strncmp(token, "release_agent=", 14)) {
* with the old cpuset, so we allow noprefix only if mounting just
* the cpuset subsystem.
*/
- if (test_bit(ROOT_NOPREFIX, &opts->flags) &&
- (opts->subsys_mask & mask))
+ if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
return -EINVAL;
int ret = -ENAMETOOLONG;
char *start;
+ if (!cgrp->parent) {
+ if (strlcpy(buf, "/", buflen) >= buflen)
+ return -ENAMETOOLONG;
+ return 0;
+ }
+
start = buf + buflen - 1;
*start = '\0';
rcu_read_lock();
- while (cgrp) {
+ do {
const char *name = cgroup_name(cgrp);
int len;
goto out;
memcpy(start, name, len);
- if (!cgrp->parent)
- break;
-
if (--start < buf)
goto out;
*start = '/';
cgrp = cgrp->parent;
- }
+ } while (cgrp->parent);
ret = 0;
memmove(buf, start, buf + buflen - start);
out:
*
* Must be called with cgroup_mutex and threadgroup locked.
*/
-static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
+static void cgroup_task_migrate(struct cgroup *oldcgrp,
struct task_struct *tsk, struct css_set *newcg)
{
struct css_set *oldcg;
}
/**
- * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
- * @cgrp: the cgroup the task is attaching to
- * @tsk: the task to be attached
- *
- * Call with cgroup_mutex and threadgroup locked. May take task_lock of
- * @tsk during call.
- */
-int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
-{
- int retval = 0;
- struct cgroup_subsys *ss, *failed_ss = NULL;
- struct cgroup *oldcgrp;
- struct cgroupfs_root *root = cgrp->root;
- struct cgroup_taskset tset = { };
- struct css_set *newcg;
-
- /* @tsk either already exited or can't exit until the end */
- if (tsk->flags & PF_EXITING)
- return -ESRCH;
-
- /* Nothing to do if the task is already in that cgroup */
- oldcgrp = task_cgroup_from_root(tsk, root);
- if (cgrp == oldcgrp)
- return 0;
-
- tset.single.task = tsk;
- tset.single.cgrp = oldcgrp;
-
- for_each_subsys(root, ss) {
- if (ss->can_attach) {
- retval = ss->can_attach(cgrp, &tset);
- if (retval) {
- /*
- * Remember on which subsystem the can_attach()
- * failed, so that we only call cancel_attach()
- * against the subsystems whose can_attach()
- * succeeded. (See below)
- */
- failed_ss = ss;
- goto out;
- }
- }
- }
-
- newcg = find_css_set(tsk->cgroups, cgrp);
- if (!newcg) {
- retval = -ENOMEM;
- goto out;
- }
-
- cgroup_task_migrate(cgrp, oldcgrp, tsk, newcg);
-
- for_each_subsys(root, ss) {
- if (ss->attach)
- ss->attach(cgrp, &tset);
- }
-
-out:
- if (retval) {
- for_each_subsys(root, ss) {
- if (ss == failed_ss)
- /*
- * This subsystem was the one that failed the
- * can_attach() check earlier, so we don't need
- * to call cancel_attach() against it or any
- * remaining subsystems.
- */
- break;
- if (ss->cancel_attach)
- ss->cancel_attach(cgrp, &tset);
- }
- }
- return retval;
-}
-
-/**
- * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
- * @from: attach to all cgroups of a given task
- * @tsk: the task to be attached
- */
-int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
-{
- struct cgroupfs_root *root;
- int retval = 0;
-
- cgroup_lock();
- for_each_active_root(root) {
- struct cgroup *from_cg = task_cgroup_from_root(from, root);
-
- retval = cgroup_attach_task(from_cg, tsk);
- if (retval)
- break;
- }
- cgroup_unlock();
-
- return retval;
-}
-EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
-
-/**
- * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup
+ * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
* @cgrp: the cgroup to attach to
- * @leader: the threadgroup leader task_struct of the group to be attached
+ * @tsk: the task or the leader of the threadgroup to be attached
+ * @threadgroup: attach the whole threadgroup?
*
* Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of each thread in leader's threadgroup individually in turn.
+ * task_lock of @tsk or each thread in the threadgroup individually in turn.
*/
-static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
+static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
+ bool threadgroup)
{
int retval, i, group_size;
struct cgroup_subsys *ss, *failed_ss = NULL;
- /* guaranteed to be initialized later, but the compiler needs this */
struct cgroupfs_root *root = cgrp->root;
/* threadgroup list cursor and array */
- struct task_struct *tsk;
+ struct task_struct *leader = tsk;
struct task_and_cgroup *tc;
struct flex_array *group;
struct cgroup_taskset tset = { };
* group - group_rwsem prevents new threads from appearing, and if
* threads exit, this will just be an over-estimate.
*/
- group_size = get_nr_threads(leader);
+ if (threadgroup)
+ group_size = get_nr_threads(tsk);
+ else
+ group_size = 1;
/* flex_array supports very large thread-groups better than kmalloc. */
group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
if (!group)
return -ENOMEM;
/* pre-allocate to guarantee space while iterating in rcu read-side. */
- retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
+ retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
if (retval)
goto out_free_group_list;
- tsk = leader;
i = 0;
/*
* Prevent freeing of tasks while we take a snapshot. Tasks that are
retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
BUG_ON(retval != 0);
i++;
+
+ if (!threadgroup)
+ break;
} while_each_thread(leader, tsk);
rcu_read_unlock();
/* remember the number of threads in the array for later. */
*/
for (i = 0; i < group_size; i++) {
tc = flex_array_get(group, i);
- cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg);
+ cgroup_task_migrate(tc->cgrp, tc->task, tc->cg);
}
/* nothing is sensitive to fork() after this point. */
put_task_struct(tsk);
goto retry_find_task;
}
- ret = cgroup_attach_proc(cgrp, tsk);
- } else
- ret = cgroup_attach_task(cgrp, tsk);
+ }
+
+ ret = cgroup_attach_task(cgrp, tsk, threadgroup);
+
threadgroup_unlock(tsk);
put_task_struct(tsk);
out_unlock_cgroup:
- cgroup_unlock();
+ mutex_unlock(&cgroup_mutex);
return ret;
}
+/**
+ * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
+ * @from: attach to all cgroups of a given task
+ * @tsk: the task to be attached
+ */
+int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
+{
+ struct cgroupfs_root *root;
+ int retval = 0;
+
+ mutex_lock(&cgroup_mutex);
+ for_each_active_root(root) {
+ struct cgroup *from_cg = task_cgroup_from_root(from, root);
+
+ retval = cgroup_attach_task(from_cg, tsk, false);
+ if (retval)
+ break;
+ }
+ mutex_unlock(&cgroup_mutex);
+
+ return retval;
+}
+EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
+
static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
{
return attach_task_by_pid(cgrp, pid, false);
return attach_task_by_pid(cgrp, tgid, true);
}
-/**
- * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
- * @cgrp: the cgroup to be checked for liveness
- *
- * On success, returns true; the lock should be later released with
- * cgroup_unlock(). On failure returns false with no lock held.
- */
-bool cgroup_lock_live_group(struct cgroup *cgrp)
-{
- mutex_lock(&cgroup_mutex);
- if (cgroup_is_removed(cgrp)) {
- mutex_unlock(&cgroup_mutex);
- return false;
- }
- return true;
-}
-EXPORT_SYMBOL_GPL(cgroup_lock_live_group);
-
static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
const char *buffer)
{
mutex_lock(&cgroup_root_mutex);
strcpy(cgrp->root->release_agent_path, buffer);
mutex_unlock(&cgroup_root_mutex);
- cgroup_unlock();
+ mutex_unlock(&cgroup_mutex);
return 0;
}
return -ENODEV;
seq_puts(seq, cgrp->root->release_agent_path);
seq_putc(seq, '\n');
- cgroup_unlock();
+ mutex_unlock(&cgroup_mutex);
return 0;
}
static inline int xattr_enabled(struct dentry *dentry)
{
struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
- return test_bit(ROOT_XATTR, &root->flags);
+ return root->flags & CGRP_ROOT_XATTR;
}
static bool is_valid_xattr(const char *name)
simple_xattrs_init(&cft->xattrs);
- if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
+ if (subsys && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
strcpy(name, subsys->name);
strcat(name, ".");
}
return 0;
}
+static void cgroup_transfer_one_task(struct task_struct *task,
+ struct cgroup_scanner *scan)
+{
+ struct cgroup *new_cgroup = scan->data;
+
+ mutex_lock(&cgroup_mutex);
+ cgroup_attach_task(new_cgroup, task, false);
+ mutex_unlock(&cgroup_mutex);
+}
+
+/**
+ * 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
+ */
+int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
+{
+ struct cgroup_scanner scan;
+
+ scan.cg = from;
+ scan.test_task = NULL; /* select all tasks in cgroup */
+ scan.process_task = cgroup_transfer_one_task;
+ scan.heap = NULL;
+ scan.data = to;
+
+ return cgroup_scan_tasks(&scan);
+}
+
/*
* Stuff for reading the 'tasks'/'procs' files.
*
else
kfree(p);
}
-static void *pidlist_resize(void *p, int newcount)
-{
- void *newlist;
- /* note: if new alloc fails, old p will still be valid either way */
- if (is_vmalloc_addr(p)) {
- newlist = vmalloc(newcount * sizeof(pid_t));
- if (!newlist)
- return NULL;
- memcpy(newlist, p, newcount * sizeof(pid_t));
- vfree(p);
- } else {
- newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
- }
- return newlist;
-}
/*
* pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
- * If the new stripped list is sufficiently smaller and there's enough memory
- * to allocate a new buffer, will let go of the unneeded memory. Returns the
- * number of unique elements.
+ * Returns the number of unique elements.
*/
-/* is the size difference enough that we should re-allocate the array? */
-#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
-static int pidlist_uniq(pid_t **p, int length)
+static int pidlist_uniq(pid_t *list, int length)
{
int src, dest = 1;
- pid_t *list = *p;
- pid_t *newlist;
/*
* we presume the 0th element is unique, so i starts at 1. trivial
dest++;
}
after:
- /*
- * if the length difference is large enough, we want to allocate a
- * smaller buffer to save memory. if this fails due to out of memory,
- * we'll just stay with what we've got.
- */
- if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
- newlist = pidlist_resize(list, dest);
- if (newlist)
- *p = newlist;
- }
return dest;
}
/* 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);
+ length = pidlist_uniq(array, length);
l = cgroup_pidlist_find(cgrp, type);
if (!l) {
pidlist_free(array);
if (ret)
goto fail;
- if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
- event->cft->unregister_event(cgrp, event->cft, event->eventfd);
- ret = 0;
- goto fail;
- }
-
/*
* Events should be removed after rmdir of cgroup directory, but before
* destroying subsystem state objects. Let's take reference to cgroup
if (!(css->flags & CSS_ONLINE))
return;
- /*
- * css_offline() should be called with cgroup_mutex unlocked. See
- * 3fa59dfbc3 ("cgroup: fix potential deadlock in pre_destroy") for
- * details. This temporary unlocking should go away once
- * cgroup_mutex is unexported from controllers.
- */
- if (ss->css_offline) {
- mutex_unlock(&cgroup_mutex);
+ if (ss->css_offline)
ss->css_offline(cgrp);
- mutex_lock(&cgroup_mutex);
- }
cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
}
for_each_subsys(root, ss)
dget(dentry);
+ /* hold a ref to the parent's dentry */
+ dget(parent->dentry);
+
/* creation succeeded, notify subsystems */
for_each_subsys(root, ss) {
err = online_css(ss, cgrp);