cgroups: add css_tryget()

Add css_tryget(), that obtains a counted reference on a CSS.  It is used
in situations where the caller has a "weak" reference to the CSS, i.e.
one that does not protect the cgroup from removal via a reference count,
but would instead be cleaned up by a destroy() callback.

css_tryget() will return true on success, or false if the cgroup is being
removed.

This is similar to Kamezawa Hiroyuki's patch from a week or two ago, but
with the difference that in the event of css_tryget() racing with a
cgroup_rmdir(), css_tryget() will only return false if the cgroup really
does get removed.

This implementation is done by biasing css->refcnt, so that a refcnt of 1
means "releasable" and 0 means "released or releasing".  In the event of a
race, css_tryget() distinguishes between "released" and "releasing" by
checking for the CSS_REMOVED flag in css->flags.

Signed-off-by: Paul Menage <menage@google.com>
Tested-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ce1c1f34c30c81c310393959c793cfa6ad729538..e267e62827bbc4e564c930576fcee8b70a8c4a79 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -52,9 +52,9 @@ struct cgroup_subsys_state {
         * hierarchy structure */
        struct cgroup *cgroup;
 
-       /* State maintained by the cgroup system to allow
-        * subsystems to be "busy". Should be accessed via css_get()
-        * and css_put() */
+       /* State maintained by the cgroup system to allow subsystems
+        * to be "busy". Should be accessed via css_get(),
+        * css_tryget() and and css_put(). */
 
        atomic_t refcnt;
 
@@ -64,11 +64,14 @@ struct cgroup_subsys_state {
 /* bits in struct cgroup_subsys_state flags field */
 enum {
        CSS_ROOT, /* This CSS is the root of the subsystem */
+       CSS_REMOVED, /* This CSS is dead */
 };
 
 /*
- * Call css_get() to hold a reference on the cgroup;
- *
+ * Call css_get() to hold a reference on the css; it can be used
+ * for a reference obtained via:
+ * - an existing ref-counted reference to the css
+ * - task->cgroups for a locked task
  */
 
 static inline void css_get(struct cgroup_subsys_state *css)
@@ -77,9 +80,32 @@ static inline void css_get(struct cgroup_subsys_state *css)
        if (!test_bit(CSS_ROOT, &css->flags))
                atomic_inc(&css->refcnt);
 }
+
+static inline bool css_is_removed(struct cgroup_subsys_state *css)
+{
+       return test_bit(CSS_REMOVED, &css->flags);
+}
+
+/*
+ * Call css_tryget() to take a reference on a css if your existing
+ * (known-valid) reference isn't already ref-counted. Returns false if
+ * the css has been destroyed.
+ */
+
+static inline bool css_tryget(struct cgroup_subsys_state *css)
+{
+       if (test_bit(CSS_ROOT, &css->flags))
+               return true;
+       while (!atomic_inc_not_zero(&css->refcnt)) {
+               if (test_bit(CSS_REMOVED, &css->flags))
+                       return false;
+       }
+       return true;
+}
+
 /*
  * css_put() should be called to release a reference taken by
- * css_get()
+ * css_get() or css_tryget()
  */
 
 extern void __css_put(struct cgroup_subsys_state *css);

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8b6379cdf637fe5e6d5e55ac7915808c87dd55ea..c29831076e7a2e156e584725453c51568682eb93 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2333,7 +2333,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
                               struct cgroup *cgrp)
 {
        css->cgroup = cgrp;
-       atomic_set(&css->refcnt, 0);
+       atomic_set(&css->refcnt, 1);
        css->flags = 0;
        if (cgrp == dummytop)
                set_bit(CSS_ROOT, &css->flags);
@@ -2465,7 +2465,7 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 {
        /* Check the reference count on each subsystem. Since we
         * already established that there are no tasks in the
-        * cgroup, if the css refcount is also 0, then there should
+        * cgroup, if the css refcount is also 1, then there should
         * be no outstanding references, so the subsystem is safe to
         * destroy. We scan across all subsystems rather than using
         * the per-hierarchy linked list of mounted subsystems since
@@ -2486,12 +2486,62 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
                 * matter, since it can only happen if the cgroup
                 * has been deleted and hence no longer needs the
                 * release agent to be called anyway. */
-               if (css && atomic_read(&css->refcnt))
+               if (css && (atomic_read(&css->refcnt) > 1))
                        return 1;
        }
        return 0;
 }
 
+/*
+ * Atomically mark all (or else none) of the cgroup's CSS objects as
+ * CSS_REMOVED. Return true on success, or false if the cgroup has
+ * busy subsystems. Call with cgroup_mutex held
+ */
+
+static int cgroup_clear_css_refs(struct cgroup *cgrp)
+{
+       struct cgroup_subsys *ss;
+       unsigned long flags;
+       bool failed = false;
+       local_irq_save(flags);
+       for_each_subsys(cgrp->root, ss) {
+               struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+               int refcnt;
+               do {
+                       /* We can only remove a CSS with a refcnt==1 */
+                       refcnt = atomic_read(&css->refcnt);
+                       if (refcnt > 1) {
+                               failed = true;
+                               goto done;
+                       }
+                       BUG_ON(!refcnt);
+                       /*
+                        * Drop the refcnt to 0 while we check other
+                        * subsystems. This will cause any racing
+                        * css_tryget() to spin until we set the
+                        * CSS_REMOVED bits or abort
+                        */
+               } while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt);
+       }
+ done:
+       for_each_subsys(cgrp->root, ss) {
+               struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+               if (failed) {
+                       /*
+                        * Restore old refcnt if we previously managed
+                        * to clear it from 1 to 0
+                        */
+                       if (!atomic_read(&css->refcnt))
+                               atomic_set(&css->refcnt, 1);
+               } else {
+                       /* Commit the fact that the CSS is removed */
+                       set_bit(CSS_REMOVED, &css->flags);
+               }
+       }
+       local_irq_restore(flags);
+       return !failed;
+}
+
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 {
        struct cgroup *cgrp = dentry->d_fsdata;
@@ -2522,7 +2572,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 
        if (atomic_read(&cgrp->count)
            || !list_empty(&cgrp->children)
-           || cgroup_has_css_refs(cgrp)) {
+           || !cgroup_clear_css_refs(cgrp)) {
                mutex_unlock(&cgroup_mutex);
                return -EBUSY;
        }
@@ -3078,7 +3128,8 @@ void __css_put(struct cgroup_subsys_state *css)
 {
        struct cgroup *cgrp = css->cgroup;
        rcu_read_lock();
-       if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) {
+       if ((atomic_dec_return(&css->refcnt) == 1) &&
+           notify_on_release(cgrp)) {
                set_bit(CGRP_RELEASABLE, &cgrp->flags);
                check_for_release(cgrp);
        }