Merge branch 'for-linus-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/mason...

[cascardo/linux.git] / kernel / cgroup.c

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 75c0ff0..5e8dab5 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -61,7 +61,7 @@
 #include <linux/cpuset.h>
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
-#include <linux/proc_ns.h>
+#include <linux/file.h>
 #include <net/sock.h>
 
 /*
@@ -1160,18 +1160,12 @@ static void cgroup_exit_root_id(struct cgroup_root *root)
 {
        lockdep_assert_held(&cgroup_mutex);
 
-       if (root->hierarchy_id) {
-               idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
-               root->hierarchy_id = 0;
-       }
+       idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
 }
 
 static void cgroup_free_root(struct cgroup_root *root)
 {
        if (root) {
-               /* hierarchy ID should already have been released */
-               WARN_ON_ONCE(root->hierarchy_id);
-
                idr_destroy(&root->cgroup_idr);
                kfree(root);
        }
@@ -2215,12 +2209,8 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                goto out_unlock;
        }
 
-       /*
-        * We know this subsystem has not yet been bound.  Users in a non-init
-        * user namespace may only mount hierarchies with no bound subsystems,
-        * i.e. 'none,name=user1'
-        */
-       if (!opts.none && !capable(CAP_SYS_ADMIN)) {
+       /* Hierarchies may only be created in the initial cgroup namespace. */
+       if (ns != &init_cgroup_ns) {
                ret = -EPERM;
                goto out_unlock;
        }
@@ -2962,6 +2952,7 @@ 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;
 
@@ -2976,6 +2967,7 @@ 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;
@@ -4343,6 +4335,8 @@ 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)
@@ -4371,6 +4365,7 @@ 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;
 }
@@ -5146,6 +5141,8 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
        lockdep_assert_held(&cgroup_mutex);
 
        css = ss->css_alloc(parent_css);
+       if (!css)
+               css = ERR_PTR(-ENOMEM);
        if (IS_ERR(css))
                return css;
 
@@ -6172,7 +6169,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
 {
        WARN_ON_ONCE(!rcu_read_lock_held());
-       return id > 0 ? idr_find(&ss->css_idr, id) : NULL;
+       return idr_find(&ss->css_idr, id);
 }
 
 /**
@@ -6209,6 +6206,40 @@ struct cgroup *cgroup_get_from_path(const char *path)
 }
 EXPORT_SYMBOL_GPL(cgroup_get_from_path);
 
+/**
+ * cgroup_get_from_fd - get a cgroup pointer from a fd
+ * @fd: fd obtained by open(cgroup2_dir)
+ *
+ * Find the cgroup from a fd which should be obtained
+ * by opening a cgroup directory.  Returns a pointer to the
+ * cgroup on success. ERR_PTR is returned if the cgroup
+ * cannot be found.
+ */
+struct cgroup *cgroup_get_from_fd(int fd)
+{
+       struct cgroup_subsys_state *css;
+       struct cgroup *cgrp;
+       struct file *f;
+
+       f = fget_raw(fd);
+       if (!f)
+               return ERR_PTR(-EBADF);
+
+       css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+       fput(f);
+       if (IS_ERR(css))
+               return ERR_CAST(css);
+
+       cgrp = css->cgroup;
+       if (!cgroup_on_dfl(cgrp)) {
+               cgroup_put(cgrp);
+               return ERR_PTR(-EBADF);
+       }
+
+       return cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
+
 /*
  * sock->sk_cgrp_data handling.  For more info, see sock_cgroup_data
  * definition in cgroup-defs.h.
@@ -6239,6 +6270,12 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
        if (cgroup_sk_alloc_disabled)
                return;
 
+       /* Socket clone path */
+       if (skcd->val) {
+               cgroup_get(sock_cgroup_ptr(skcd));
+               return;
+       }
+
        rcu_read_lock();
 
        while (true) {
@@ -6309,14 +6346,11 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
        if (!ns_capable(user_ns, CAP_SYS_ADMIN))
                return ERR_PTR(-EPERM);
 
-       mutex_lock(&cgroup_mutex);
+       /* It is not safe to take cgroup_mutex here */
        spin_lock_irq(&css_set_lock);
-
        cset = task_css_set(current);
        get_css_set(cset);
-
        spin_unlock_irq(&css_set_lock);
-       mutex_unlock(&cgroup_mutex);
 
        new_ns = alloc_cgroup_ns();
        if (IS_ERR(new_ns)) {