summaryrefslogtreecommitdiff
path: root/kernel/cgroup.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/cgroup.c')
-rw-r--r--kernel/cgroup.c77
1 files changed, 43 insertions, 34 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 96f0fe9441af..cd3d81961cc2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -211,6 +211,7 @@ static unsigned long have_free_callback __read_mostly;
/* Ditto for the can_fork callback. */
static unsigned long have_canfork_callback __read_mostly;
+static struct file_system_type cgroup2_fs_type;
static struct cftype cgroup_dfl_base_files[];
static struct cftype cgroup_legacy_base_files[];
@@ -716,10 +717,10 @@ static void css_set_move_task(struct task_struct *task,
if (to_cset) {
/*
- * We are synchronized through cgroup_threadgroup_rwsem
- * 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.
+ * We are synchronized through css_set_lock against
+ * PF_EXITING setting such that we can't race against
+ * cgroup_exit() disassociating the task from the
+ * css_set.
*/
WARN_ON_ONCE(task->flags & PF_EXITING);
@@ -1652,10 +1653,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
all_ss = true;
continue;
}
- if (!strcmp(token, "__DEVEL__sane_behavior")) {
- opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
- continue;
- }
if (!strcmp(token, "noprefix")) {
opts->flags |= CGRP_ROOT_NOPREFIX;
continue;
@@ -1722,15 +1719,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
return -ENOENT;
}
- if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
- pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
- if (nr_opts != 1) {
- pr_err("sane_behavior: no other mount options allowed\n");
- return -EINVAL;
- }
- return 0;
- }
-
/*
* If the 'all' option was specified select all the subsystems,
* otherwise if 'none', 'name=' and a subsystem name options were
@@ -2013,9 +2001,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data)
{
+ bool is_v2 = fs_type == &cgroup2_fs_type;
struct super_block *pinned_sb = NULL;
struct cgroup_subsys *ss;
- struct cgroup_root *root;
+ struct cgroup_root *root = NULL;
struct cgroup_sb_opts opts;
struct dentry *dentry;
int ret;
@@ -2029,6 +2018,17 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
if (!use_task_css_set_links)
cgroup_enable_task_cg_lists();
+ if (is_v2) {
+ if (data) {
+ pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
+ return ERR_PTR(-EINVAL);
+ }
+ cgrp_dfl_root_visible = true;
+ root = &cgrp_dfl_root;
+ cgroup_get(&root->cgrp);
+ goto out_mount;
+ }
+
mutex_lock(&cgroup_mutex);
/* First find the desired set of subsystems */
@@ -2036,15 +2036,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
if (ret)
goto out_unlock;
- /* look for a matching existing root */
- if (opts.flags & CGRP_ROOT_SANE_BEHAVIOR) {
- cgrp_dfl_root_visible = true;
- root = &cgrp_dfl_root;
- cgroup_get(&root->cgrp);
- ret = 0;
- goto out_unlock;
- }
-
/*
* Destruction of cgroup root is asynchronous, so subsystems may
* still be dying after the previous unmount. Let's drain the
@@ -2155,9 +2146,10 @@ out_free:
if (ret)
return ERR_PTR(ret);
-
+out_mount:
dentry = kernfs_mount(fs_type, flags, root->kf_root,
- CGROUP_SUPER_MAGIC, &new_sb);
+ is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
+ &new_sb);
if (IS_ERR(dentry) || !new_sb)
cgroup_put(&root->cgrp);
@@ -2200,6 +2192,12 @@ static struct file_system_type cgroup_fs_type = {
.kill_sb = cgroup_kill_sb,
};
+static struct file_system_type cgroup2_fs_type = {
+ .name = "cgroup2",
+ .mount = cgroup_mount,
+ .kill_sb = cgroup_kill_sb,
+};
+
/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
@@ -2801,6 +2799,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
int retval = 0;
mutex_lock(&cgroup_mutex);
+ percpu_down_write(&cgroup_threadgroup_rwsem);
for_each_root(root) {
struct cgroup *from_cgrp;
@@ -2815,6 +2814,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
if (retval)
break;
}
+ percpu_up_write(&cgroup_threadgroup_rwsem);
mutex_unlock(&cgroup_mutex);
return retval;
@@ -4074,6 +4074,8 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
mutex_lock(&cgroup_mutex);
+ percpu_down_write(&cgroup_threadgroup_rwsem);
+
/* all tasks in @from are being moved, all csets are source */
spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &from->cset_links, cset_link)
@@ -4106,6 +4108,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
} while (task && !ret);
out_err:
cgroup_migrate_finish(&preloaded_csets);
+ percpu_up_write(&cgroup_threadgroup_rwsem);
mutex_unlock(&cgroup_mutex);
return ret;
}
@@ -5401,6 +5404,7 @@ int __init cgroup_init(void)
WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
WARN_ON(register_filesystem(&cgroup_fs_type));
+ WARN_ON(register_filesystem(&cgroup2_fs_type));
WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations));
return 0;
@@ -5706,19 +5710,22 @@ void cgroup_exit(struct task_struct *tsk)
int i;
/*
- * Unlink from @tsk from its css_set. As migration path can't race
- * with us, we can check css_set and cg_list without synchronization.
+ * Avoid potential race with the migrate path.
+ */
+ spin_lock_irq(&css_set_lock);
+ /*
+ * Unlink from @tsk from its css_set.
*/
cset = task_css_set(tsk);
if (!list_empty(&tsk->cg_list)) {
- spin_lock_irq(&css_set_lock);
css_set_move_task(tsk, cset, NULL, false);
- spin_unlock_irq(&css_set_lock);
} else {
get_css_set(cset);
}
+ spin_unlock_irq(&css_set_lock);
+
/* see cgroup_post_fork() for details */
for_each_subsys_which(ss, i, &have_exit_callback)
ss->exit(tsk);
@@ -5780,7 +5787,9 @@ static void cgroup_release_agent(struct work_struct *work)
if (!pathbuf || !agentbuf)
goto out;
+ spin_lock_irq(&css_set_lock);
path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+ spin_unlock_irq(&css_set_lock);
if (!path)
goto out;
@@ -5955,7 +5964,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
struct task_struct *task;
int count = 0;
- seq_printf(seq, "css_set %p\n", cset);
+ seq_printf(seq, "css_set %pK\n", cset);
list_for_each_entry(task, &cset->tasks, cg_list) {
if (count++ > MAX_TASKS_SHOWN_PER_CSS)
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-18 06:19:39 +0000