* -> 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)
{
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_root_mutex);
/*
* 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)
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;
struct task_and_cgroup {
struct task_struct *task;
struct cgroup *cgrp;
+ struct css_set *cg;
};
struct cgroup_taskset {
* will already exist. If not set, this function might sleep, and can fail with
* -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;
/*
* We are synchronized through threadgroup_lock() against PF_EXITING
WARN_ON_ONCE(tsk->flags & PF_EXITING);
oldcg = tsk->cgroups;
- /* 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)
- return -ENOMEM;
- }
-
task_lock(tsk);
rcu_assign_pointer(tsk->cgroups, newcg);
task_unlock(tsk);
put_css_set(oldcg);
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
- return 0;
}
/**
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)
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, &tset);
+ retval = ss->can_attach(cgrp, &tset);
if (retval) {
/*
* Remember on which subsystem the can_attach()
}
}
- 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->attach)
- ss->attach(ss, cgrp, &tset);
+ ss->attach(cgrp, &tset);
}
synchronize_rcu();
*/
break;
if (ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, &tset);
+ 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);
- 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)
- return true;
-
- /* not found */
- 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
* 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, nr_migrating_tasks;
+ int retval, i, group_size;
struct cgroup_subsys *ss, *failed_ss = NULL;
/* guaranteed to be initialized later, but the compiler needs this */
- 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;
struct cgroup_taskset tset = { };
- /*
- * 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;
/*
* step 0: in order to do expensive, possibly blocking operations for
if (retval)
goto out_free_group_list;
- /* prevent changes to the threadgroup list while we take a snapshot. */
- read_lock(&tasklist_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".
- */
- read_unlock(&tasklist_lock);
- retval = -EAGAIN;
- goto out_free_group_list;
- }
-
tsk = leader;
- i = nr_migrating_tasks = 0;
+ 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;
/* as per above, nr_threads may decrease, but not increase. */
BUG_ON(i >= group_size);
+ 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.
*/
- ent.task = tsk;
- ent.cgrp = task_cgroup_from_root(tsk, root);
retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
BUG_ON(retval != 0);
i++;
- if (ent.cgrp != cgrp)
- nr_migrating_tasks++;
} while_each_thread(leader, tsk);
+ rcu_read_unlock();
/* remember the number of threads in the array for later. */
group_size = i;
tset.tc_array = group;
tset.tc_array_len = group_size;
- read_unlock(&tasklist_lock);
/* methods shouldn't be called if no task is actually migrating */
retval = 0;
- if (!nr_migrating_tasks)
+ if (!group_size)
goto out_free_group_list;
/*
*/
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, &tset);
+ retval = ss->can_attach(cgrp, &tset);
if (retval) {
failed_ss = ss;
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++) {
tc = flex_array_get(group, i);
- /* nothing to do if this task is already in the cgroup */
- if (tc->cgrp == cgrp)
- continue;
- /*
- * get old css_set pointer. threadgroup is locked so this is
- * safe against concurrent cgroup_exit() changing this to
- * init_css_set.
- */
- oldcg = tc->task->cgroups;
-
- /* if we don't already have it in the list get a new one */
- if (!css_set_check_fetched(cgrp, tc->task, oldcg, &newcg_list))
- if (retval = css_set_prefetch(cgrp, oldcg, &newcg_list))
- goto out_list_teardown;
+ tc->cg = find_css_set(tc->task->cgroups, cgrp);
+ if (!tc->cg) {
+ retval = -ENOMEM;
+ goto out_put_css_set_refs;
+ }
}
/*
*/
for (i = 0; i < group_size; i++) {
tc = flex_array_get(group, i);
- /* leave current thread as it is if it's already there */
- if (tc->cgrp == cgrp)
- continue;
- retval = cgroup_task_migrate(cgrp, tc->cgrp, tc->task, true);
- BUG_ON(retval);
+ cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg);
}
/* nothing is sensitive to fork() after this point. */
*/
for_each_subsys(root, ss) {
if (ss->attach)
- ss->attach(ss, cgrp, &tset);
+ 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)
break;
if (ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, &tset);
+ ss->cancel_attach(cgrp, &tset);
}
}
out_free_group_list:
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;
+ ret= -ESRCH;
+ goto out_unlock_cgroup;
}
/*
* even if we're attaching all tasks in the thread group, we
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);
- }
-
- threadgroup_lock(tsk);
+ } else
+ tsk = current;
if (threadgroup)
+ tsk = tsk->group_leader;
+ get_task_struct(tsk);
+ rcu_read_unlock();
+
+ threadgroup_lock(tsk);
+ if (threadgroup) {
+ 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);
- 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 __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;
* 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.
* 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;
/* 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);
- if (list_empty(&child->cg_list))
+ if (list_empty(&child->cg_list)) {
+ /*
+ * It's safe to use child->cgroups without task_lock()
+ * here because we are protected through
+ * threadgroup_change_begin() against concurrent
+ * css_set change in cgroup_task_migrate(). Also
+ * the task can't exit at that point until
+ * wake_up_new_task() is called, so we are protected
+ * against cgroup_exit() setting child->cgroup to
+ * init_css_set.
+ */
list_add(&child->cg_list, &child->cgroups->tasks);
- task_unlock(child);
+ }
write_unlock(&css_set_lock);
}
}
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);
}
}
}
rcu_assign_pointer(id->css, NULL);
rcu_assign_pointer(css->id, NULL);
- write_lock(&ss->id_lock);
+ spin_lock(&ss->id_lock);
idr_remove(&ss->idr, id->id);
- write_unlock(&ss->id_lock);
+ spin_unlock(&ss->id_lock);
kfree_rcu(id, rcu_head);
}
EXPORT_SYMBOL_GPL(free_css_id);
error = -ENOMEM;
goto err_out;
}
- write_lock(&ss->id_lock);
+ spin_lock(&ss->id_lock);
/* Don't use 0. allocates an ID of 1-65535 */
error = idr_get_new_above(&ss->idr, newid, 1, &myid);
- write_unlock(&ss->id_lock);
+ spin_unlock(&ss->id_lock);
/* Returns error when there are no free spaces for new ID.*/
if (error) {
return newid;
remove_idr:
error = -ENOSPC;
- write_lock(&ss->id_lock);
+ spin_lock(&ss->id_lock);
idr_remove(&ss->idr, myid);
- write_unlock(&ss->id_lock);
+ spin_unlock(&ss->id_lock);
err_out:
kfree(newid);
return ERR_PTR(error);
{
struct css_id *newid;
- rwlock_init(&ss->id_lock);
+ spin_lock_init(&ss->id_lock);
idr_init(&ss->idr);
newid = get_new_cssid(ss, 0);
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().
*/
- read_lock(&ss->id_lock);
tmp = idr_get_next(&ss->idr, &tmpid);
- read_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]);
}
projects / linux-flexiantxendom0-3.2.10.git / blobdiff