rcu: slim down rcutiny by removing rcu_scheduler_active and friends

[safe/jmp/linux-2.6] / kernel / cgroup.c

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ea94984..3a53c77 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -27,7 +27,6 @@
  */
 
 #include <linux/cgroup.h>
-#include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -795,28 +794,15 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 {
        struct cgroup_subsys *ss;
-       struct cgroup_event *event, *tmp;
        int ret = 0;
 
        for_each_subsys(cgrp->root, ss)
                if (ss->pre_destroy) {
                        ret = ss->pre_destroy(ss, cgrp);
                        if (ret)
-                               goto out;
+                               break;
                }
 
-       /*
-        * Unregister events and notify userspace.
-        */
-       spin_lock(&cgrp->event_list_lock);
-       list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
-               list_del(&event->list);
-               eventfd_signal(event->eventfd, 1);
-               schedule_work(&event->remove);
-       }
-       spin_unlock(&cgrp->event_list_lock);
-
-out:
        return ret;
 }
 
@@ -1660,7 +1646,9 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
        char *start;
-       struct dentry *dentry = rcu_dereference(cgrp->dentry);
+       struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
+                                                     rcu_read_lock_held() ||
+                                                     cgroup_lock_is_held());
 
        if (!dentry || cgrp == dummytop) {
                /*
@@ -1676,13 +1664,17 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
        *--start = '\0';
        for (;;) {
                int len = dentry->d_name.len;
+
                if ((start -= len) < buf)
                        return -ENAMETOOLONG;
-               memcpy(start, cgrp->dentry->d_name.name, len);
+               memcpy(start, dentry->d_name.name, len);
                cgrp = cgrp->parent;
                if (!cgrp)
                        break;
-               dentry = rcu_dereference(cgrp->dentry);
+
+               dentry = rcu_dereference_check(cgrp->dentry,
+                                              rcu_read_lock_held() ||
+                                              cgroup_lock_is_held());
                if (!cgrp->parent)
                        continue;
                if (--start < buf)
@@ -3006,8 +2998,8 @@ static void cgroup_event_remove(struct work_struct *work)
        event->cft->unregister_event(cgrp, event->cft, event->eventfd);
 
        eventfd_ctx_put(event->eventfd);
-       remove_wait_queue(event->wqh, &event->wait);
        kfree(event);
+       dput(cgrp->dentry);
 }
 
 /*
@@ -3024,6 +3016,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
        unsigned long flags = (unsigned long)key;
 
        if (flags & POLLHUP) {
+               remove_wait_queue_locked(event->wqh, &event->wait);
                spin_lock(&cgrp->event_list_lock);
                list_del(&event->list);
                spin_unlock(&cgrp->event_list_lock);
@@ -3127,6 +3120,13 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
                goto fail;
        }
 
+       /*
+        * Events should be removed after rmdir of cgroup directory, but before
+        * destroying subsystem state objects. Let's take reference to cgroup
+        * directory dentry to do that.
+        */
+       dget(cgrp->dentry);
+
        spin_lock(&cgrp->event_list_lock);
        list_add(&event->list, &cgrp->event_list);
        spin_unlock(&cgrp->event_list_lock);
@@ -3472,6 +3472,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
        struct dentry *d;
        struct cgroup *parent;
        DEFINE_WAIT(wait);
+       struct cgroup_event *event, *tmp;
        int ret;
 
        /* the vfs holds both inode->i_mutex already */
@@ -3555,6 +3556,20 @@ again:
        set_bit(CGRP_RELEASABLE, &parent->flags);
        check_for_release(parent);
 
+       /*
+        * Unregister events and notify userspace.
+        * Notify userspace about cgroup removing only after rmdir of cgroup
+        * directory to avoid race between userspace and kernelspace
+        */
+       spin_lock(&cgrp->event_list_lock);
+       list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
+               list_del(&event->list);
+               remove_wait_queue(event->wqh, &event->wait);
+               eventfd_signal(event->eventfd, 1);
+               schedule_work(&event->remove);
+       }
+       spin_unlock(&cgrp->event_list_lock);
+
        mutex_unlock(&cgroup_mutex);
        return 0;
 }
@@ -4546,13 +4561,13 @@ static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
 {
        int subsys_id, i, depth = 0;
        struct cgroup_subsys_state *parent_css, *child_css;
-       struct css_id *child_id, *parent_id = NULL;
+       struct css_id *child_id, *parent_id;
 
        subsys_id = ss->subsys_id;
        parent_css = parent->subsys[subsys_id];
        child_css = child->subsys[subsys_id];
-       depth = css_depth(parent_css) + 1;
        parent_id = parent_css->id;
+       depth = parent_id->depth;
 
        child_id = get_new_cssid(ss, depth);
        if (IS_ERR(child_id))