summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2014-07-08 18:02:57 -0400
committerTejun Heo <tj@kernel.org>2014-07-08 18:02:57 -0400
commitaf0ba6789c8e43518635606d0af1ff475ba7471a (patch)
treee191c511bc1102149d4e44b196ec96691179f67f /kernel/cgroup.c
parentb4536f0cab2b18414e26101a2b9d484c5cbea0c0 (diff)
downloadlinux-af0ba6789c8e43518635606d0af1ff475ba7471a.tar.bz2
cgroup: implement cgroup_subsys->depends_on
Currently, the blkio subsystem attributes all of writeback IOs to the root. One of the issues is that there's no way to tell who originated a writeback IO from block layer. Those IOs are usually issued asynchronously from a task which didn't have anything to do with actually generating the dirty pages. The memory subsystem, when enabled, already keeps track of the ownership of each dirty page and it's desirable for blkio to piggyback instead of adding its own per-page tag. blkio piggybacking on memory is an implementation detail which preferably should be handled automatically without requiring explicit userland action. To achieve that, this patch implements cgroup_subsys->depends_on which contains the mask of subsystems which should be enabled together when the subsystem is enabled. The previous patches already implemented the support for enabled but invisible subsystems and cgroup_subsys->depends_on can be easily implemented by updating cgroup_refresh_child_subsys_mask() so that it calculates cgroup->child_subsys_mask considering cgroup_subsys->depends_on of the explicitly enabled subsystems. Documentation/cgroups/unified-hierarchy.txt is updated to explain that subsystems may not become immediately available after being unused from userland and that dependency could be a factor in it. As subsystems may already keep residual references, this doesn't significantly change how subsystem rebinding can be used. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Diffstat (limited to 'kernel/cgroup.c')
-rw-r--r--kernel/cgroup.c49
1 files changed, 48 insertions, 1 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3a6b77d7ba4a..cd02e99d5d3b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1037,9 +1037,56 @@ static void cgroup_put(struct cgroup *cgrp)
css_put(&cgrp->self);
}
+/**
+ * cgroup_refresh_child_subsys_mask - update child_subsys_mask
+ * @cgrp: the target cgroup
+ *
+ * On the default hierarchy, a subsystem may request other subsystems to be
+ * enabled together through its ->depends_on mask. In such cases, more
+ * subsystems than specified in "cgroup.subtree_control" may be enabled.
+ *
+ * This function determines which subsystems need to be enabled given the
+ * current @cgrp->subtree_control and records it in
+ * @cgrp->child_subsys_mask. The resulting mask is always a superset of
+ * @cgrp->subtree_control and follows the usual hierarchy rules.
+ */
static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp)
{
- cgrp->child_subsys_mask = cgrp->subtree_control;
+ struct cgroup *parent = cgroup_parent(cgrp);
+ unsigned int cur_ss_mask = cgrp->subtree_control;
+ struct cgroup_subsys *ss;
+ int ssid;
+
+ lockdep_assert_held(&cgroup_mutex);
+
+ if (!cgroup_on_dfl(cgrp)) {
+ cgrp->child_subsys_mask = cur_ss_mask;
+ return;
+ }
+
+ while (true) {
+ unsigned int new_ss_mask = cur_ss_mask;
+
+ for_each_subsys(ss, ssid)
+ if (cur_ss_mask & (1 << ssid))
+ new_ss_mask |= ss->depends_on;
+
+ /*
+ * Mask out subsystems which aren't available. This can
+ * happen only if some depended-upon subsystems were bound
+ * to non-default hierarchies.
+ */
+ if (parent)
+ new_ss_mask &= parent->child_subsys_mask;
+ else
+ new_ss_mask &= cgrp->root->subsys_mask;
+
+ if (new_ss_mask == cur_ss_mask)
+ break;
+ cur_ss_mask = new_ss_mask;
+ }
+
+ cgrp->child_subsys_mask = cur_ss_mask;
}
/**