*/
#include <linux/cgroup.h>
+#include <linux/cred.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
+#include <linux/init_task.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/poll.h>
#include <linux/flex_array.h> /* used in cgroup_attach_proc */
-#include <asm/atomic.h>
+#include <linux/atomic.h>
+/*
+ * cgroup_mutex is the master lock. Any modification to cgroup or its
+ * hierarchy must be performed while holding it.
+ *
+ * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify
+ * cgroupfs_root of any cgroup hierarchy - subsys list, flags,
+ * release_agent_path and so on. Modifying requires both cgroup_mutex and
+ * cgroup_root_mutex. Readers can acquire either of the two. This is to
+ * break the following locking order cycle.
+ *
+ * A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem
+ * B. namespace_sem -> cgroup_mutex
+ *
+ * B happens only through cgroup_show_options() and using cgroup_root_mutex
+ * breaks it.
+ */
static DEFINE_MUTEX(cgroup_mutex);
+static DEFINE_MUTEX(cgroup_root_mutex);
/*
* Generate an array of cgroup subsystem pointers. At boot time, this is
/* the list of cgroups eligible for automatic release. Protected by
* release_list_lock */
static LIST_HEAD(release_list);
-static DEFINE_SPINLOCK(release_list_lock);
+static DEFINE_RAW_SPINLOCK(release_list_lock);
static void cgroup_release_agent(struct work_struct *work);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);
struct cgroup *cgrp = link->cgrp;
list_del(&link->cg_link_list);
list_del(&link->cgrp_link_list);
+
+ /*
+ * We may not be holding cgroup_mutex, and if cgrp->count is
+ * dropped to 0 the cgroup can be destroyed at any time, hence
+ * rcu_read_lock is used to keep it alive.
+ */
+ rcu_read_lock();
if (atomic_dec_and_test(&cgrp->count) &&
notify_on_release(cgrp)) {
if (taskexit)
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
}
+ rcu_read_unlock();
kfree(link);
}
* -> cgroup_mkdir.
*/
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
+static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static int alloc_css_id(struct cgroup_subsys *ss,
struct cgroup *parent, struct cgroup *child);
-static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
+static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
{
struct inode *inode = new_inode(sb);
for_each_subsys(cgrp->root, ss)
if (ss->pre_destroy) {
- ret = ss->pre_destroy(ss, cgrp);
+ ret = ss->pre_destroy(cgrp);
if (ret)
break;
}
* Release the subsystem state objects.
*/
for_each_subsys(cgrp->root, ss)
- ss->destroy(ss, cgrp);
+ ss->destroy(cgrp);
cgrp->root->number_of_cgroups--;
mutex_unlock(&cgroup_mutex);
*
* CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
*/
-DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
+static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
{
int i;
BUG_ON(!mutex_is_locked(&cgroup_mutex));
+ BUG_ON(!mutex_is_locked(&cgroup_root_mutex));
removed_bits = root->actual_subsys_bits & ~final_bits;
added_bits = final_bits & ~root->actual_subsys_bits;
list_move(&ss->sibling, &root->subsys_list);
ss->root = root;
if (ss->bind)
- ss->bind(ss, cgrp);
+ ss->bind(cgrp);
mutex_unlock(&ss->hierarchy_mutex);
/* refcount was already taken, and we're keeping it */
} else if (bit & removed_bits) {
BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
mutex_lock(&ss->hierarchy_mutex);
if (ss->bind)
- ss->bind(ss, dummytop);
+ ss->bind(dummytop);
dummytop->subsys[i]->cgroup = dummytop;
cgrp->subsys[i] = NULL;
subsys[i]->root = &rootnode;
return 0;
}
-static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
+static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
{
- struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info;
+ struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
struct cgroup_subsys *ss;
- mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
for_each_subsys(root, ss)
seq_printf(seq, ",%s", ss->name);
if (test_bit(ROOT_NOPREFIX, &root->flags))
seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
- mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_root_mutex);
return 0;
}
/*
* If the 'all' option was specified select all the subsystems,
- * otherwise 'all, 'none' and a subsystem name options were not
- * specified, let's default to 'all'
+ * otherwise if 'none', 'name=' and a subsystem name options
+ * were not specified, let's default to 'all'
*/
- if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+ if (all_ss || (!one_ss && !opts->none && !opts->name)) {
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
if (ss == NULL)
mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
/* See what subsystems are wanted */
ret = parse_cgroupfs_options(data, &opts);
out_unlock:
kfree(opts.release_agent);
kfree(opts.name);
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
return ret;
struct inode *inode =
cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
- struct dentry *dentry;
if (!inode)
return -ENOMEM;
inode->i_op = &cgroup_dir_inode_operations;
/* directories start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
- dentry = d_alloc_root(inode);
- if (!dentry) {
- iput(inode);
+ sb->s_root = d_make_root(inode);
+ if (!sb->s_root)
return -ENOMEM;
- }
- sb->s_root = dentry;
/* for everything else we want ->d_op set */
sb->s_d_op = &cgroup_dops;
return 0;
int ret = 0;
struct super_block *sb;
struct cgroupfs_root *new_root;
+ struct inode *inode;
/* First find the desired set of subsystems */
mutex_lock(&cgroup_mutex);
/* We used the new root structure, so this is a new hierarchy */
struct list_head tmp_cg_links;
struct cgroup *root_cgrp = &root->top_cgroup;
- struct inode *inode;
struct cgroupfs_root *existing_root;
+ const struct cred *cred;
int i;
BUG_ON(sb->s_root != NULL);
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
- if (strlen(root->name)) {
- /* Check for name clashes with existing mounts */
- for_each_active_root(existing_root) {
- if (!strcmp(existing_root->name, root->name)) {
- ret = -EBUSY;
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- goto drop_new_super;
- }
- }
- }
+ /* Check for name clashes with existing mounts */
+ ret = -EBUSY;
+ if (strlen(root->name))
+ for_each_active_root(existing_root)
+ if (!strcmp(existing_root->name, root->name))
+ goto unlock_drop;
/*
* We're accessing css_set_count without locking
* have some link structures left over
*/
ret = allocate_cg_links(css_set_count, &tmp_cg_links);
- if (ret) {
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- goto drop_new_super;
- }
+ if (ret)
+ goto unlock_drop;
ret = rebind_subsystems(root, root->subsys_bits);
if (ret == -EBUSY) {
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
free_cg_links(&tmp_cg_links);
- goto drop_new_super;
+ goto unlock_drop;
}
/*
* There must be no failure case after here, since rebinding
BUG_ON(!list_empty(&root_cgrp->children));
BUG_ON(root->number_of_cgroups != 1);
+ cred = override_creds(&init_cred);
cgroup_populate_dir(root_cgrp);
+ revert_creds(cred);
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
} else {
kfree(opts.name);
return dget(sb->s_root);
+ unlock_drop:
+ mutex_unlock(&cgroup_root_mutex);
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&inode->i_mutex);
drop_new_super:
deactivate_locked_super(sb);
drop_modules:
BUG_ON(!list_empty(&cgrp->sibling));
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
/* Rebind all subsystems back to the default hierarchy */
ret = rebind_subsystems(root, 0);
root_count--;
}
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
kill_litter_super(sb);
{
char *start;
struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
- rcu_read_lock_held() ||
cgroup_lock_is_held());
if (!dentry || cgrp == dummytop) {
break;
dentry = rcu_dereference_check(cgrp->dentry,
- rcu_read_lock_held() ||
cgroup_lock_is_held());
if (!cgrp->parent)
continue;
}
EXPORT_SYMBOL_GPL(cgroup_path);
+/*
+ * Control Group taskset
+ */
+struct task_and_cgroup {
+ struct task_struct *task;
+ struct cgroup *cgrp;
+ struct css_set *cg;
+};
+
+struct cgroup_taskset {
+ struct task_and_cgroup single;
+ struct flex_array *tc_array;
+ int tc_array_len;
+ int idx;
+ struct cgroup *cur_cgrp;
+};
+
+/**
+ * cgroup_taskset_first - reset taskset and return the first task
+ * @tset: taskset of interest
+ *
+ * @tset iteration is initialized and the first task is returned.
+ */
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+{
+ if (tset->tc_array) {
+ tset->idx = 0;
+ return cgroup_taskset_next(tset);
+ } else {
+ tset->cur_cgrp = tset->single.cgrp;
+ return tset->single.task;
+ }
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_first);
+
+/**
+ * cgroup_taskset_next - iterate to the next task in taskset
+ * @tset: taskset of interest
+ *
+ * Return the next task in @tset. Iteration must have been initialized
+ * with cgroup_taskset_first().
+ */
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+{
+ struct task_and_cgroup *tc;
+
+ if (!tset->tc_array || tset->idx >= tset->tc_array_len)
+ return NULL;
+
+ tc = flex_array_get(tset->tc_array, tset->idx++);
+ tset->cur_cgrp = tc->cgrp;
+ return tc->task;
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_next);
+
+/**
+ * cgroup_taskset_cur_cgroup - return the matching cgroup for the current task
+ * @tset: taskset of interest
+ *
+ * Return the cgroup for the current (last returned) task of @tset. This
+ * function must be preceded by either cgroup_taskset_first() or
+ * cgroup_taskset_next().
+ */
+struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset)
+{
+ return tset->cur_cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_cur_cgroup);
+
+/**
+ * cgroup_taskset_size - return the number of tasks in taskset
+ * @tset: taskset of interest
+ */
+int cgroup_taskset_size(struct cgroup_taskset *tset)
+{
+ return tset->tc_array ? tset->tc_array_len : 1;
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_size);
+
+
/*
* cgroup_task_migrate - move a task from one cgroup to another.
*
* 'guarantee' is set if the caller promises that a new css_set for the task
* will already exist. If not set, this function might sleep, and can fail with
- * -ENOMEM. Otherwise, it can only fail with -ESRCH.
+ * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked.
*/
-static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
- struct task_struct *tsk, bool guarantee)
+static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
+ struct task_struct *tsk, struct css_set *newcg)
{
struct css_set *oldcg;
- struct css_set *newcg;
/*
- * get old css_set. we need to take task_lock and refcount it, because
- * an exiting task can change its css_set to init_css_set and drop its
- * old one without taking cgroup_mutex.
+ * We are synchronized through threadgroup_lock() against PF_EXITING
+ * setting such that we can't race against cgroup_exit() changing the
+ * css_set to init_css_set and dropping the old one.
*/
- task_lock(tsk);
+ WARN_ON_ONCE(tsk->flags & PF_EXITING);
oldcg = tsk->cgroups;
- get_css_set(oldcg);
- task_unlock(tsk);
-
- /* locate or allocate a new css_set for this task. */
- if (guarantee) {
- /* we know the css_set we want already exists. */
- struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
- read_lock(&css_set_lock);
- newcg = find_existing_css_set(oldcg, cgrp, template);
- BUG_ON(!newcg);
- get_css_set(newcg);
- read_unlock(&css_set_lock);
- } else {
- might_sleep();
- /* find_css_set will give us newcg already referenced. */
- newcg = find_css_set(oldcg, cgrp);
- if (!newcg) {
- put_css_set(oldcg);
- return -ENOMEM;
- }
- }
- put_css_set(oldcg);
- /* if PF_EXITING is set, the tsk->cgroups pointer is no longer safe. */
task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- task_unlock(tsk);
- put_css_set(newcg);
- return -ESRCH;
- }
rcu_assign_pointer(tsk->cgroups, newcg);
task_unlock(tsk);
* trading it for newcg is protected by cgroup_mutex, we're safe to drop
* it here; it will be freed under RCU.
*/
- put_css_set(oldcg);
-
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
- return 0;
+ put_css_set(oldcg);
}
/**
* @cgrp: the cgroup the task is attaching to
* @tsk: the task to be attached
*
- * Call holding cgroup_mutex. May take task_lock of
- * the task 'tsk' during call.
+ * 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;
+ 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(ss, cgrp, tsk);
+ retval = ss->can_attach(cgrp, &tset);
if (retval) {
/*
* Remember on which subsystem the can_attach()
goto out;
}
}
- if (ss->can_attach_task) {
- retval = ss->can_attach_task(cgrp, tsk);
- if (retval) {
- failed_ss = ss;
- goto out;
- }
- }
}
- retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false);
- if (retval)
+ 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->pre_attach)
- ss->pre_attach(cgrp);
- if (ss->attach_task)
- ss->attach_task(cgrp, tsk);
if (ss->attach)
- ss->attach(ss, cgrp, oldcgrp, tsk);
+ ss->attach(cgrp, &tset);
}
synchronize_rcu();
*/
break;
if (ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, tsk);
+ ss->cancel_attach(cgrp, &tset);
}
}
return retval;
}
EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
-/*
- * cgroup_attach_proc works in two stages, the first of which prefetches all
- * new css_sets needed (to make sure we have enough memory before committing
- * to the move) and stores them in a list of entries of the following type.
- * TODO: possible optimization: use css_set->rcu_head for chaining instead
- */
-struct cg_list_entry {
- struct css_set *cg;
- struct list_head links;
-};
-
-static bool css_set_check_fetched(struct cgroup *cgrp,
- struct task_struct *tsk, struct css_set *cg,
- struct list_head *newcg_list)
-{
- struct css_set *newcg;
- struct cg_list_entry *cg_entry;
- struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
-
- read_lock(&css_set_lock);
- newcg = find_existing_css_set(cg, cgrp, template);
- if (newcg)
- get_css_set(newcg);
- read_unlock(&css_set_lock);
-
- /* doesn't exist at all? */
- if (!newcg)
- return false;
- /* see if it's already in the list */
- list_for_each_entry(cg_entry, newcg_list, links) {
- if (cg_entry->cg == newcg) {
- put_css_set(newcg);
- return true;
- }
- }
-
- /* not found */
- put_css_set(newcg);
- return false;
-}
-
-/*
- * Find the new css_set and store it in the list in preparation for moving the
- * given task to the given cgroup. Returns 0 or -ENOMEM.
- */
-static int css_set_prefetch(struct cgroup *cgrp, struct css_set *cg,
- struct list_head *newcg_list)
-{
- struct css_set *newcg;
- struct cg_list_entry *cg_entry;
-
- /* ensure a new css_set will exist for this thread */
- newcg = find_css_set(cg, cgrp);
- if (!newcg)
- return -ENOMEM;
- /* add it to the list */
- cg_entry = kmalloc(sizeof(struct cg_list_entry), GFP_KERNEL);
- if (!cg_entry) {
- put_css_set(newcg);
- return -ENOMEM;
- }
- cg_entry->cg = newcg;
- list_add(&cg_entry->links, newcg_list);
- return 0;
-}
-
/**
* cgroup_attach_proc - attach all threads in a threadgroup to a cgroup
* @cgrp: the cgroup to attach to
* @leader: the threadgroup leader task_struct of the group to be attached
*
- * Call holding cgroup_mutex and the threadgroup_fork_lock of the leader. Will
- * take task_lock of each thread in leader's threadgroup individually in turn.
+ * 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.
*/
-int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
+static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
{
int retval, i, group_size;
struct cgroup_subsys *ss, *failed_ss = NULL;
- bool cancel_failed_ss = false;
/* guaranteed to be initialized later, but the compiler needs this */
- struct cgroup *oldcgrp = NULL;
- struct css_set *oldcg;
struct cgroupfs_root *root = cgrp->root;
/* threadgroup list cursor and array */
struct task_struct *tsk;
+ struct task_and_cgroup *tc;
struct flex_array *group;
- /*
- * we need to make sure we have css_sets for all the tasks we're
- * going to move -before- we actually start moving them, so that in
- * case we get an ENOMEM we can bail out before making any changes.
- */
- struct list_head newcg_list;
- struct cg_list_entry *cg_entry, *temp_nobe;
+ struct cgroup_taskset tset = { };
/*
* step 0: in order to do expensive, possibly blocking operations for
* every thread, we cannot iterate the thread group list, since it needs
* rcu or tasklist locked. instead, build an array of all threads in the
- * group - threadgroup_fork_lock prevents new threads from appearing,
- * and if threads exit, this will just be an over-estimate.
+ * 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);
/* flex_array supports very large thread-groups better than kmalloc. */
- group = flex_array_alloc(sizeof(struct task_struct *), group_size,
- GFP_KERNEL);
+ 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;
- /* prevent changes to the threadgroup list while we take a snapshot. */
- rcu_read_lock();
- if (!thread_group_leader(leader)) {
- /*
- * a race with de_thread from another thread's exec() may strip
- * us of our leadership, making while_each_thread unsafe to use
- * on this task. if this happens, there is no choice but to
- * throw this task away and try again (from cgroup_procs_write);
- * this is "double-double-toil-and-trouble-check locking".
- */
- rcu_read_unlock();
- retval = -EAGAIN;
- goto out_free_group_list;
- }
- /* take a reference on each task in the group to go in the array. */
tsk = leader;
i = 0;
+ /*
+ * Prevent freeing of tasks while we take a snapshot. Tasks that are
+ * already PF_EXITING could be freed from underneath us unless we
+ * take an rcu_read_lock.
+ */
+ rcu_read_lock();
do {
+ struct task_and_cgroup ent;
+
+ /* @tsk either already exited or can't exit until the end */
+ if (tsk->flags & PF_EXITING)
+ continue;
+
/* as per above, nr_threads may decrease, but not increase. */
BUG_ON(i >= group_size);
- get_task_struct(tsk);
+ ent.task = tsk;
+ ent.cgrp = task_cgroup_from_root(tsk, root);
+ /* nothing to do if this task is already in the cgroup */
+ if (ent.cgrp == cgrp)
+ continue;
/*
* saying GFP_ATOMIC has no effect here because we did prealloc
* earlier, but it's good form to communicate our expectations.
*/
- retval = flex_array_put_ptr(group, i, tsk, GFP_ATOMIC);
+ retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
BUG_ON(retval != 0);
i++;
} while_each_thread(leader, tsk);
+ rcu_read_unlock();
/* remember the number of threads in the array for later. */
group_size = i;
- rcu_read_unlock();
+ tset.tc_array = group;
+ tset.tc_array_len = group_size;
+
+ /* methods shouldn't be called if no task is actually migrating */
+ retval = 0;
+ if (!group_size)
+ goto out_free_group_list;
/*
* step 1: check that we can legitimately attach to the cgroup.
*/
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, leader);
+ retval = ss->can_attach(cgrp, &tset);
if (retval) {
failed_ss = ss;
goto out_cancel_attach;
}
}
- /* a callback to be run on every thread in the threadgroup. */
- if (ss->can_attach_task) {
- /* run on each task in the threadgroup. */
- for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- retval = ss->can_attach_task(cgrp, tsk);
- if (retval) {
- failed_ss = ss;
- cancel_failed_ss = true;
- goto out_cancel_attach;
- }
- }
- }
}
/*
* step 2: make sure css_sets exist for all threads to be migrated.
* we use find_css_set, which allocates a new one if necessary.
*/
- INIT_LIST_HEAD(&newcg_list);
for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- /* nothing to do if this task is already in the cgroup */
- oldcgrp = task_cgroup_from_root(tsk, root);
- if (cgrp == oldcgrp)
- continue;
- /* get old css_set pointer */
- task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- /* ignore this task if it's going away */
- task_unlock(tsk);
- continue;
- }
- oldcg = tsk->cgroups;
- get_css_set(oldcg);
- task_unlock(tsk);
- /* see if the new one for us is already in the list? */
- if (css_set_check_fetched(cgrp, tsk, oldcg, &newcg_list)) {
- /* was already there, nothing to do. */
- put_css_set(oldcg);
- } else {
- /* we don't already have it. get new one. */
- retval = css_set_prefetch(cgrp, oldcg, &newcg_list);
- put_css_set(oldcg);
- if (retval)
- goto out_list_teardown;
+ tc = flex_array_get(group, i);
+ tc->cg = find_css_set(tc->task->cgroups, cgrp);
+ if (!tc->cg) {
+ retval = -ENOMEM;
+ goto out_put_css_set_refs;
}
}
/*
- * step 3: now that we're guaranteed success wrt the css_sets, proceed
- * to move all tasks to the new cgroup, calling ss->attach_task for each
- * one along the way. there are no failure cases after here, so this is
- * the commit point.
+ * step 3: now that we're guaranteed success wrt the css_sets,
+ * proceed to move all tasks to the new cgroup. There are no
+ * failure cases after here, so this is the commit point.
*/
- for_each_subsys(root, ss) {
- if (ss->pre_attach)
- ss->pre_attach(cgrp);
- }
for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- /* leave current thread as it is if it's already there */
- oldcgrp = task_cgroup_from_root(tsk, root);
- if (cgrp == oldcgrp)
- continue;
- /* attach each task to each subsystem */
- for_each_subsys(root, ss) {
- if (ss->attach_task)
- ss->attach_task(cgrp, tsk);
- }
- /* if the thread is PF_EXITING, it can just get skipped. */
- retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true);
- BUG_ON(retval != 0 && retval != -ESRCH);
+ tc = flex_array_get(group, i);
+ cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg);
}
/* nothing is sensitive to fork() after this point. */
/*
- * step 4: do expensive, non-thread-specific subsystem callbacks.
- * TODO: if ever a subsystem needs to know the oldcgrp for each task
- * being moved, this call will need to be reworked to communicate that.
+ * step 4: do subsystem attach callbacks.
*/
for_each_subsys(root, ss) {
if (ss->attach)
- ss->attach(ss, cgrp, oldcgrp, leader);
+ ss->attach(cgrp, &tset);
}
/*
synchronize_rcu();
cgroup_wakeup_rmdir_waiter(cgrp);
retval = 0;
-out_list_teardown:
- /* clean up the list of prefetched css_sets. */
- list_for_each_entry_safe(cg_entry, temp_nobe, &newcg_list, links) {
- list_del(&cg_entry->links);
- put_css_set(cg_entry->cg);
- kfree(cg_entry);
+out_put_css_set_refs:
+ if (retval) {
+ for (i = 0; i < group_size; i++) {
+ tc = flex_array_get(group, i);
+ if (!tc->cg)
+ break;
+ put_css_set(tc->cg);
+ }
}
out_cancel_attach:
- /* same deal as in cgroup_attach_task */
if (retval) {
for_each_subsys(root, ss) {
- if (ss == failed_ss) {
- if (cancel_failed_ss && ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, leader);
+ if (ss == failed_ss)
break;
- }
if (ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, leader);
+ ss->cancel_attach(cgrp, &tset);
}
}
- /* clean up the array of referenced threads in the group. */
- for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- put_task_struct(tsk);
- }
out_free_group_list:
flex_array_free(group);
return retval;
/*
* Find the task_struct of the task to attach by vpid and pass it along to the
- * function to attach either it or all tasks in its threadgroup. Will take
- * cgroup_mutex; may take task_lock of task.
+ * function to attach either it or all tasks in its threadgroup. Will lock
+ * cgroup_mutex and threadgroup; may take task_lock of task.
*/
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
+retry_find_task:
+ rcu_read_lock();
if (pid) {
- rcu_read_lock();
tsk = find_task_by_vpid(pid);
if (!tsk) {
rcu_read_unlock();
- cgroup_unlock();
- return -ESRCH;
- }
- if (threadgroup) {
- /*
- * RCU protects this access, since tsk was found in the
- * tid map. a race with de_thread may cause group_leader
- * to stop being the leader, but cgroup_attach_proc will
- * detect it later.
- */
- tsk = tsk->group_leader;
- } else if (tsk->flags & PF_EXITING) {
- /* optimization for the single-task-only case */
- rcu_read_unlock();
- cgroup_unlock();
- return -ESRCH;
+ ret= -ESRCH;
+ goto out_unlock_cgroup;
}
-
/*
* even if we're attaching all tasks in the thread group, we
* only need to check permissions on one of them.
cred->euid != tcred->uid &&
cred->euid != tcred->suid) {
rcu_read_unlock();
- cgroup_unlock();
- return -EACCES;
+ ret = -EACCES;
+ goto out_unlock_cgroup;
}
- get_task_struct(tsk);
- rcu_read_unlock();
- } else {
- if (threadgroup)
- tsk = current->group_leader;
- else
- tsk = current;
- get_task_struct(tsk);
- }
+ } else
+ tsk = current;
+
+ if (threadgroup)
+ tsk = tsk->group_leader;
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ threadgroup_lock(tsk);
if (threadgroup) {
- threadgroup_fork_write_lock(tsk);
+ if (!thread_group_leader(tsk)) {
+ /*
+ * a race with de_thread from another thread's exec()
+ * may strip us of our leadership, if this happens,
+ * there is no choice but to throw this task away and
+ * try again; this is
+ * "double-double-toil-and-trouble-check locking".
+ */
+ threadgroup_unlock(tsk);
+ put_task_struct(tsk);
+ goto retry_find_task;
+ }
ret = cgroup_attach_proc(cgrp, tsk);
- threadgroup_fork_write_unlock(tsk);
- } else {
+ } else
ret = cgroup_attach_task(cgrp, tsk);
- }
+ threadgroup_unlock(tsk);
+
put_task_struct(tsk);
+out_unlock_cgroup:
cgroup_unlock();
return ret;
}
static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid)
{
- int ret;
- do {
- /*
- * attach_proc fails with -EAGAIN if threadgroup leadership
- * changes in the middle of the operation, in which case we need
- * to find the task_struct for the new leader and start over.
- */
- ret = attach_task_by_pid(cgrp, tgid, true);
- } while (ret == -EAGAIN);
- return ret;
+ return attach_task_by_pid(cgrp, tgid, true);
}
/**
return -EINVAL;
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
+ mutex_lock(&cgroup_root_mutex);
strcpy(cgrp->root->release_agent_path, buffer);
+ mutex_unlock(&cgroup_root_mutex);
cgroup_unlock();
return 0;
}
return __d_cft(file->f_dentry);
}
-static int cgroup_create_file(struct dentry *dentry, mode_t mode,
+static int cgroup_create_file(struct dentry *dentry, umode_t mode,
struct super_block *sb)
{
struct inode *inode;
* @mode: mode to set on new directory.
*/
static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
- mode_t mode)
+ umode_t mode)
{
struct dentry *parent;
int error = 0;
dentry->d_fsdata = cgrp;
inc_nlink(parent->d_inode);
rcu_assign_pointer(cgrp->dentry, dentry);
- dget(dentry);
}
- dput(dentry);
return error;
}
* returns S_IRUGO if it has only a read handler
* returns S_IWUSR if it has only a write hander
*/
-static mode_t cgroup_file_mode(const struct cftype *cft)
+static umode_t cgroup_file_mode(const struct cftype *cft)
{
- mode_t mode = 0;
+ umode_t mode = 0;
if (cft->mode)
return cft->mode;
struct dentry *dir = cgrp->dentry;
struct dentry *dentry;
int error;
- mode_t mode;
+ umode_t mode;
char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
* using their cgroups capability, we don't maintain the lists running
* through each css_set to its tasks until we see the list actually
* used - in other words after the first call to cgroup_iter_start().
- *
- * The tasklist_lock is not held here, as do_each_thread() and
- * while_each_thread() are protected by RCU.
*/
static void cgroup_enable_task_cg_lists(void)
{
struct task_struct *p, *g;
write_lock(&css_set_lock);
use_task_css_set_links = 1;
+ /*
+ * We need tasklist_lock because RCU is not safe against
+ * while_each_thread(). Besides, a forking task that has passed
+ * cgroup_post_fork() without seeing use_task_css_set_links = 1
+ * is not guaranteed to have its child immediately visible in the
+ * tasklist if we walk through it with RCU.
+ */
+ read_lock(&tasklist_lock);
do_each_thread(g, p) {
task_lock(p);
/*
list_add(&p->cg_list, &p->cgroups->tasks);
task_unlock(p);
} while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
write_unlock(&css_set_lock);
}
void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
+ __acquires(css_set_lock)
{
/*
* The first time anyone tries to iterate across a cgroup,
}
void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
+ __releases(css_set_lock)
{
read_unlock(&css_set_lock);
}
*
*/
+/* 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;
+ /* how many files are using the current array */
+ int use_count;
+ /* 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;
+ /* protects the other fields */
+ struct rw_semaphore mutex;
+};
+
/*
* 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.
}
/* the process need read permission on control file */
- ret = file_permission(cfile, MAY_READ);
+ /* AV: shouldn't we check that it's been opened for read instead? */
+ ret = inode_permission(cfile->f_path.dentry->d_inode, MAY_READ);
if (ret < 0)
goto fail;
* Must be called with the mutex on the parent inode held
*/
static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
- mode_t mode)
+ umode_t mode)
{
struct cgroup *cgrp;
struct cgroupfs_root *root = parent->root;
set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
for_each_subsys(root, ss) {
- struct cgroup_subsys_state *css = ss->create(ss, cgrp);
+ struct cgroup_subsys_state *css = ss->create(cgrp);
if (IS_ERR(css)) {
err = PTR_ERR(css);
}
/* At error, ->destroy() callback has to free assigned ID. */
if (clone_children(parent) && ss->post_clone)
- ss->post_clone(ss, cgrp);
+ ss->post_clone(cgrp);
}
cgroup_lock_hierarchy(root);
for_each_subsys(root, ss) {
if (cgrp->subsys[ss->subsys_id])
- ss->destroy(ss, cgrp);
+ ss->destroy(cgrp);
}
mutex_unlock(&cgroup_mutex);
return err;
}
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct cgroup *c_parent = dentry->d_parent->d_fsdata;
finish_wait(&cgroup_rmdir_waitq, &wait);
clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
set_bit(CGRP_REMOVED, &cgrp->flags);
if (!list_empty(&cgrp->release_list))
list_del_init(&cgrp->release_list);
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
cgroup_lock_hierarchy(cgrp->root);
/* delete this cgroup from parent->children */
/* Create the top cgroup state for this subsystem */
list_add(&ss->sibling, &rootnode.subsys_list);
ss->root = &rootnode;
- css = ss->create(ss, dummytop);
+ css = ss->create(dummytop);
/* We don't handle early failures gracefully */
BUG_ON(IS_ERR(css));
init_cgroup_css(css, ss, dummytop);
* no ss->create seems to need anything important in the ss struct, so
* this can happen first (i.e. before the rootnode attachment).
*/
- css = ss->create(ss, dummytop);
+ css = ss->create(dummytop);
if (IS_ERR(css)) {
/* failure case - need to deassign the subsys[] slot. */
subsys[i] = NULL;
int ret = cgroup_init_idr(ss, css);
if (ret) {
dummytop->subsys[ss->subsys_id] = NULL;
- ss->destroy(ss, dummytop);
+ ss->destroy(dummytop);
subsys[i] = NULL;
mutex_unlock(&cgroup_mutex);
return ret;
* pointer to find their state. note that this also takes care of
* freeing the css_id.
*/
- ss->destroy(ss, dummytop);
+ ss->destroy(dummytop);
dummytop->subsys[ss->subsys_id] = NULL;
mutex_unlock(&cgroup_mutex);
for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
if (ss->fork)
- ss->fork(ss, child);
+ ss->fork(child);
}
}
}
*/
void cgroup_post_fork(struct task_struct *child)
{
+ /*
+ * use_task_css_set_links is set to 1 before we walk the tasklist
+ * under the tasklist_lock and we read it here after we added the child
+ * to the tasklist under the tasklist_lock as well. If the child wasn't
+ * yet in the tasklist when we walked through it from
+ * cgroup_enable_task_cg_lists(), then use_task_css_set_links value
+ * should be visible now due to the paired locking and barriers implied
+ * by LOCK/UNLOCK: it is written before the tasklist_lock unlock
+ * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
+ * lock on fork.
+ */
if (use_task_css_set_links) {
write_lock(&css_set_lock);
task_lock(child);
struct cgroup *old_cgrp =
rcu_dereference_raw(cg->subsys[i])->cgroup;
struct cgroup *cgrp = task_cgroup(tsk, i);
- ss->exit(ss, cgrp, old_cgrp, tsk);
+ ss->exit(cgrp, old_cgrp, tsk);
}
}
}
put_css_set_taskexit(cg);
}
-/**
- * cgroup_clone - clone the cgroup the given subsystem is attached to
- * @tsk: the task to be moved
- * @subsys: the given subsystem
- * @nodename: the name for the new cgroup
- *
- * Duplicate the current cgroup in the hierarchy that the given
- * subsystem is attached to, and move this task into the new
- * child.
- */
-int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
- char *nodename)
-{
- struct dentry *dentry;
- int ret = 0;
- struct cgroup *parent, *child;
- struct inode *inode;
- struct css_set *cg;
- struct cgroupfs_root *root;
- struct cgroup_subsys *ss;
-
- /* We shouldn't be called by an unregistered subsystem */
- BUG_ON(!subsys->active);
-
- /* First figure out what hierarchy and cgroup we're dealing
- * with, and pin them so we can drop cgroup_mutex */
- mutex_lock(&cgroup_mutex);
- again:
- root = subsys->root;
- if (root == &rootnode) {
- mutex_unlock(&cgroup_mutex);
- return 0;
- }
-
- /* Pin the hierarchy */
- if (!atomic_inc_not_zero(&root->sb->s_active)) {
- /* We race with the final deactivate_super() */
- mutex_unlock(&cgroup_mutex);
- return 0;
- }
-
- /* Keep the cgroup alive */
- task_lock(tsk);
- parent = task_cgroup(tsk, subsys->subsys_id);
- cg = tsk->cgroups;
- get_css_set(cg);
- task_unlock(tsk);
-
- mutex_unlock(&cgroup_mutex);
-
- /* Now do the VFS work to create a cgroup */
- inode = parent->dentry->d_inode;
-
- /* Hold the parent directory mutex across this operation to
- * stop anyone else deleting the new cgroup */
- mutex_lock(&inode->i_mutex);
- dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename));
- if (IS_ERR(dentry)) {
- printk(KERN_INFO
- "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename,
- PTR_ERR(dentry));
- ret = PTR_ERR(dentry);
- goto out_release;
- }
-
- /* Create the cgroup directory, which also creates the cgroup */
- ret = vfs_mkdir(inode, dentry, 0755);
- child = __d_cgrp(dentry);
- dput(dentry);
- if (ret) {
- printk(KERN_INFO
- "Failed to create cgroup %s: %d\n", nodename,
- ret);
- goto out_release;
- }
-
- /* The cgroup now exists. Retake cgroup_mutex and check
- * that we're still in the same state that we thought we
- * were. */
- mutex_lock(&cgroup_mutex);
- if ((root != subsys->root) ||
- (parent != task_cgroup(tsk, subsys->subsys_id))) {
- /* Aargh, we raced ... */
- mutex_unlock(&inode->i_mutex);
- put_css_set(cg);
-
- deactivate_super(root->sb);
- /* The cgroup is still accessible in the VFS, but
- * we're not going to try to rmdir() it at this
- * point. */
- printk(KERN_INFO
- "Race in cgroup_clone() - leaking cgroup %s\n",
- nodename);
- goto again;
- }
-
- /* do any required auto-setup */
- for_each_subsys(root, ss) {
- if (ss->post_clone)
- ss->post_clone(ss, child);
- }
-
- /* All seems fine. Finish by moving the task into the new cgroup */
- ret = cgroup_attach_task(child, tsk);
- mutex_unlock(&cgroup_mutex);
-
- out_release:
- mutex_unlock(&inode->i_mutex);
-
- mutex_lock(&cgroup_mutex);
- put_css_set(cg);
- mutex_unlock(&cgroup_mutex);
- deactivate_super(root->sb);
- return ret;
-}
-
/**
* cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
* @cgrp: the cgroup in question
* already queued for a userspace notification, queue
* it now */
int need_schedule_work = 0;
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
if (!cgroup_is_removed(cgrp) &&
list_empty(&cgrp->release_list)) {
list_add(&cgrp->release_list, &release_list);
need_schedule_work = 1;
}
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
if (need_schedule_work)
schedule_work(&release_agent_work);
}
{
BUG_ON(work != &release_agent_work);
mutex_lock(&cgroup_mutex);
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
while (!list_empty(&release_list)) {
char *argv[3], *envp[3];
int i;
struct cgroup,
release_list);
list_del_init(&cgrp->release_list);
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!pathbuf)
goto continue_free;
continue_free:
kfree(pathbuf);
kfree(agentbuf);
- spin_lock(&release_list_lock);
+ raw_spin_lock(&release_list_lock);
}
- spin_unlock(&release_list_lock);
+ raw_spin_unlock(&release_list_lock);
mutex_unlock(&cgroup_mutex);
}
* on this or this is under rcu_read_lock(). Once css->id is allocated,
* it's unchanged until freed.
*/
- cssid = rcu_dereference_check(css->id,
- rcu_read_lock_held() || atomic_read(&css->refcnt));
+ cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt));
if (cssid)
return cssid->id;
{
struct css_id *cssid;
- cssid = rcu_dereference_check(css->id,
- rcu_read_lock_held() || atomic_read(&css->refcnt));
+ cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt));
if (cssid)
return cssid->depth;
return NULL;
BUG_ON(!ss->use_id);
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
/* fill start point for scan */
tmpid = id;
while (1) {
* scan next entry from bitmap(tree), tmpid is updated after
* idr_get_next().
*/
- spin_lock(&ss->id_lock);
tmp = idr_get_next(&ss->idr, &tmpid);
- spin_unlock(&ss->id_lock);
-
if (!tmp)
break;
if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
}
#ifdef CONFIG_CGROUP_DEBUG
-static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
- struct cgroup *cont)
+static struct cgroup_subsys_state *debug_create(struct cgroup *cont)
{
struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
return css;
}
-static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+static void debug_destroy(struct cgroup *cont)
{
kfree(cont->subsys[debug_subsys_id]);
}