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/kernel/cgroup.c b/kernel/cgroup.c
index 8b6379c..c298310 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2333,7 +2333,7 @@
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 @@
{
/* 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 @@
* 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 @@
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 @@
{
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);
}