cgroup: fix idr_preload usage

[linux-2.6-block.git] / kernel / cgroup.c

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9ef9fc8a774b08820a0dea814ecc4456dd83376c..97e2da0d3b2788961cb4d56194ce260d4ac60367 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -186,6 +186,9 @@ static u64 css_serial_nr_next = 1;
 static unsigned long have_fork_callback __read_mostly;
 static unsigned long have_exit_callback __read_mostly;
 
+/* Ditto for the can_fork callback. */
+static unsigned long have_canfork_callback __read_mostly;
+
 static struct cftype cgroup_dfl_base_files[];
 static struct cftype cgroup_legacy_base_files[];
 
@@ -207,7 +210,7 @@ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
 
        idr_preload(gfp_mask);
        spin_lock_bh(&cgroup_idr_lock);
-       ret = idr_alloc(idr, ptr, start, end, gfp_mask);
+       ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_WAIT);
        spin_unlock_bh(&cgroup_idr_lock);
        idr_preload_end();
        return ret;
@@ -1666,7 +1669,7 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 
        lockdep_assert_held(&cgroup_mutex);
 
-       ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_NOWAIT);
+       ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL);
        if (ret < 0)
                goto out;
        root_cgrp->id = ret;
@@ -1939,8 +1942,6 @@ static struct file_system_type cgroup_fs_type = {
        .kill_sb = cgroup_kill_sb,
 };
 
-static struct kobject *cgroup_kobj;
-
 /**
  * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
  * @task: target task
@@ -4581,7 +4582,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
        if (err)
                goto err_free_css;
 
-       err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_NOWAIT);
+       err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL);
        if (err < 0)
                goto err_free_percpu_ref;
        css->id = err;
@@ -4658,7 +4659,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
         * Temporarily set the pointer to NULL, so idr_find() won't return
         * a half-baked cgroup.
         */
-       cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_NOWAIT);
+       cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
        if (cgrp->id < 0) {
                ret = -ENOMEM;
                goto out_cancel_ref;
@@ -4957,6 +4958,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 
        have_fork_callback |= (bool)ss->fork << ss->id;
        have_exit_callback |= (bool)ss->exit << ss->id;
+       have_canfork_callback |= (bool)ss->can_fork << ss->id;
 
        /* At system boot, before all subsystems have been
         * registered, no tasks have been forked, so we don't
@@ -5070,13 +5072,13 @@ int __init cgroup_init(void)
                        ss->bind(init_css_set.subsys[ssid]);
        }
 
-       cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
-       if (!cgroup_kobj)
-               return -ENOMEM;
+       err = sysfs_create_mount_point(fs_kobj, "cgroup");
+       if (err)
+               return err;
 
        err = register_filesystem(&cgroup_fs_type);
        if (err < 0) {
-               kobject_put(cgroup_kobj);
+               sysfs_remove_mount_point(fs_kobj, "cgroup");
                return err;
        }
 
@@ -5199,6 +5201,19 @@ static const struct file_operations proc_cgroupstats_operations = {
        .release = single_release,
 };
 
+static void **subsys_canfork_priv_p(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
+{
+       if (CGROUP_CANFORK_START <= i && i < CGROUP_CANFORK_END)
+               return &ss_priv[i - CGROUP_CANFORK_START];
+       return NULL;
+}
+
+static void *subsys_canfork_priv(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
+{
+       void **private = subsys_canfork_priv_p(ss_priv, i);
+       return private ? *private : NULL;
+}
+
 /**
  * cgroup_fork - initialize cgroup related fields during copy_process()
  * @child: pointer to task_struct of forking parent process.
@@ -5213,6 +5228,57 @@ void cgroup_fork(struct task_struct *child)
        INIT_LIST_HEAD(&child->cg_list);
 }
 
+/**
+ * cgroup_can_fork - called on a new task before the process is exposed
+ * @child: the task in question.
+ *
+ * This calls the subsystem can_fork() callbacks. If the can_fork() callback
+ * returns an error, the fork aborts with that error code. This allows for
+ * a cgroup subsystem to conditionally allow or deny new forks.
+ */
+int cgroup_can_fork(struct task_struct *child,
+                   void *ss_priv[CGROUP_CANFORK_COUNT])
+{
+       struct cgroup_subsys *ss;
+       int i, j, ret;
+
+       for_each_subsys_which(ss, i, &have_canfork_callback) {
+               ret = ss->can_fork(child, subsys_canfork_priv_p(ss_priv, i));
+               if (ret)
+                       goto out_revert;
+       }
+
+       return 0;
+
+out_revert:
+       for_each_subsys(ss, j) {
+               if (j >= i)
+                       break;
+               if (ss->cancel_fork)
+                       ss->cancel_fork(child, subsys_canfork_priv(ss_priv, j));
+       }
+
+       return ret;
+}
+
+/**
+ * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
+ * @child: the task in question
+ *
+ * This calls the cancel_fork() callbacks if a fork failed *after*
+ * cgroup_can_fork() succeded.
+ */
+void cgroup_cancel_fork(struct task_struct *child,
+                       void *ss_priv[CGROUP_CANFORK_COUNT])
+{
+       struct cgroup_subsys *ss;
+       int i;
+
+       for_each_subsys(ss, i)
+               if (ss->cancel_fork)
+                       ss->cancel_fork(child, subsys_canfork_priv(ss_priv, i));
+}
+
 /**
  * cgroup_post_fork - called on a new task after adding it to the task list
  * @child: the task in question
@@ -5223,7 +5289,8 @@ void cgroup_fork(struct task_struct *child)
  * cgroup_task_iter_start() - to guarantee that the new task ends up on its
  * list.
  */
-void cgroup_post_fork(struct task_struct *child)
+void cgroup_post_fork(struct task_struct *child,
+                     void *old_ss_priv[CGROUP_CANFORK_COUNT])
 {
        struct cgroup_subsys *ss;
        int i;
@@ -5268,7 +5335,7 @@ void cgroup_post_fork(struct task_struct *child)
         * and addition to css_set.
         */
        for_each_subsys_which(ss, i, &have_fork_callback)
-               ss->fork(child);
+               ss->fork(child, subsys_canfork_priv(old_ss_priv, i));
 }
 
 /**