summaryrefslogtreecommitdiff
path: root/kernel/cgroup.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/cgroup.c')
-rw-r--r--kernel/cgroup.c587
1 files changed, 422 insertions, 165 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 909a35510af5..2731d115d725 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,6 +57,7 @@
#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 <asm/atomic.h>
@@ -1735,6 +1736,76 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
}
EXPORT_SYMBOL_GPL(cgroup_path);
+/*
+ * 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.
+ */
+static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
+ struct task_struct *tsk, bool guarantee)
+{
+ 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.
+ */
+ task_lock(tsk);
+ 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);
+
+ /* Update the css_set linked lists if we're using them */
+ write_lock(&css_set_lock);
+ if (!list_empty(&tsk->cg_list))
+ list_move(&tsk->cg_list, &newcg->tasks);
+ write_unlock(&css_set_lock);
+
+ /*
+ * We just gained a reference on oldcg by taking it from the task. As
+ * 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;
+}
+
/**
* cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
* @cgrp: the cgroup the task is attaching to
@@ -1745,11 +1816,9 @@ EXPORT_SYMBOL_GPL(cgroup_path);
*/
int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
- int retval = 0;
+ int retval;
struct cgroup_subsys *ss, *failed_ss = NULL;
struct cgroup *oldcgrp;
- struct css_set *cg;
- struct css_set *newcg;
struct cgroupfs_root *root = cgrp->root;
/* Nothing to do if the task is already in that cgroup */
@@ -1759,7 +1828,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, tsk, false);
+ retval = ss->can_attach(ss, cgrp, tsk);
if (retval) {
/*
* Remember on which subsystem the can_attach()
@@ -1771,46 +1840,29 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
goto out;
}
}
+ if (ss->can_attach_task) {
+ retval = ss->can_attach_task(cgrp, tsk);
+ if (retval) {
+ failed_ss = ss;
+ goto out;
+ }
+ }
}
- task_lock(tsk);
- cg = tsk->cgroups;
- get_css_set(cg);
- task_unlock(tsk);
- /*
- * Locate or allocate a new css_set for this task,
- * based on its final set of cgroups
- */
- newcg = find_css_set(cg, cgrp);
- put_css_set(cg);
- if (!newcg) {
- retval = -ENOMEM;
- goto out;
- }
-
- task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- task_unlock(tsk);
- put_css_set(newcg);
- retval = -ESRCH;
+ retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false);
+ if (retval)
goto out;
- }
- rcu_assign_pointer(tsk->cgroups, newcg);
- task_unlock(tsk);
-
- /* Update the css_set linked lists if we're using them */
- write_lock(&css_set_lock);
- if (!list_empty(&tsk->cg_list))
- list_move(&tsk->cg_list, &newcg->tasks);
- write_unlock(&css_set_lock);
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, false);
+ ss->attach(ss, cgrp, oldcgrp, tsk);
}
- set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+
synchronize_rcu();
- put_css_set(cg);
/*
* wake up rmdir() waiter. the rmdir should fail since the cgroup
@@ -1829,7 +1881,7 @@ out:
*/
break;
if (ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, tsk, false);
+ ss->cancel_attach(ss, cgrp, tsk);
}
}
return retval;
@@ -1860,49 +1912,370 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
/*
- * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
- * held. May take task_lock of task
+ * 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.
+ */
+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 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;
+
+ /*
+ * 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_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);
+ 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);
+ 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;
+ do {
+ /* as per above, nr_threads may decrease, but not increase. */
+ BUG_ON(i >= group_size);
+ get_task_struct(tsk);
+ /*
+ * 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);
+ BUG_ON(retval != 0);
+ i++;
+ } while_each_thread(leader, tsk);
+ /* remember the number of threads in the array for later. */
+ group_size = i;
+ rcu_read_unlock();
+
+ /*
+ * 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);
+ 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;
+ }
+ }
+
+ /*
+ * 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.
+ */
+ 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);
+ }
+ /* 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.
+ */
+ for_each_subsys(root, ss) {
+ if (ss->attach)
+ ss->attach(ss, cgrp, oldcgrp, leader);
+ }
+
+ /*
+ * step 5: success! and cleanup
+ */
+ 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_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);
+ break;
+ }
+ if (ss->cancel_attach)
+ ss->cancel_attach(ss, cgrp, leader);
+ }
+ }
+ /* 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.
*/
-static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
+static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
struct task_struct *tsk;
const struct cred *cred = current_cred(), *tcred;
int ret;
+ if (!cgroup_lock_live_group(cgrp))
+ return -ENODEV;
+
if (pid) {
rcu_read_lock();
tsk = find_task_by_vpid(pid);
- if (!tsk || tsk->flags & PF_EXITING) {
+ 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;
}
+ /*
+ * even if we're attaching all tasks in the thread group, we
+ * only need to check permissions on one of them.
+ */
tcred = __task_cred(tsk);
if (cred->euid &&
cred->euid != tcred->uid &&
cred->euid != tcred->suid) {
rcu_read_unlock();
+ cgroup_unlock();
return -EACCES;
}
get_task_struct(tsk);
rcu_read_unlock();
} else {
- tsk = current;
+ if (threadgroup)
+ tsk = current->group_leader;
+ else
+ tsk = current;
get_task_struct(tsk);
}
- ret = cgroup_attach_task(cgrp, tsk);
+ if (threadgroup) {
+ threadgroup_fork_write_lock(tsk);
+ ret = cgroup_attach_proc(cgrp, tsk);
+ threadgroup_fork_write_unlock(tsk);
+ } else {
+ ret = cgroup_attach_task(cgrp, tsk);
+ }
put_task_struct(tsk);
+ cgroup_unlock();
return ret;
}
static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
{
+ return attach_task_by_pid(cgrp, pid, false);
+}
+
+static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid)
+{
int ret;
- if (!cgroup_lock_live_group(cgrp))
- return -ENODEV;
- ret = attach_task_by_pid(cgrp, pid);
- cgroup_unlock();
+ 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;
}
@@ -3259,9 +3632,9 @@ static struct cftype files[] = {
{
.name = CGROUP_FILE_GENERIC_PREFIX "procs",
.open = cgroup_procs_open,
- /* .write_u64 = cgroup_procs_write, TODO */
+ .write_u64 = cgroup_procs_write,
.release = cgroup_pidlist_release,
- .mode = S_IRUGO,
+ .mode = S_IRUGO | S_IWUSR,
},
{
.name = "notify_on_release",
@@ -4257,122 +4630,6 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
}
/**
- * 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
* @task: the task in question