cgroup/rstat: Record the cumulative per-cpu time of cgroup and its descendants

The member variable bstat of the structure cgroup_rstat_cpu
records the per-cpu time of the cgroup itself, but does not
include the per-cpu time of its descendants. The per-cpu time
including descendants is very useful for calculating the
per-cpu usage of cgroups.

Although we can indirectly obtain the total per-cpu time
of the cgroup and its descendants by accumulating the per-cpu
bstat of each descendant of the cgroup. But after a child cgroup
is removed, we will lose its bstat information. This will cause
the cumulative value to be non-monotonic, thus affecting
the accuracy of cgroup per-cpu usage.

So we add the subtree_bstat variable to record the total
per-cpu time of this cgroup and its descendants, which is
similar to "cpuacct.usage*" in cgroup v1. And this is
also helpful for the migration from cgroup v1 to cgroup v2.
After adding this variable, we can obtain the per-cpu time of
cgroup and its descendants in user mode through eBPF/drgn, etc.
And we are still trying to determine how to expose it in the
cgroupfs interface.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

2 files changed, 24 insertions, 2 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8a0d5466c7be..7a2862172f51 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -342,6 +342,20 @@ struct cgroup_rstat_cpu {
 	struct cgroup_base_stat last_bstat;
 
 	/*
+	 * This field is used to record the cumulative per-cpu time of
+	 * the cgroup and its descendants. Currently it can be read via
+	 * eBPF/drgn etc, and we are still trying to determine how to
+	 * expose it in the cgroupfs interface.
+	 */
+	struct cgroup_base_stat subtree_bstat;
+
+	/*
+	 * Snapshots at the last reading. These are used to calculate the
+	 * deltas to propagate to the per-cpu subtree_bstat.
+	 */
+	struct cgroup_base_stat last_subtree_bstat;
+
+	/*
 	 * Child cgroups with stat updates on this cpu since the last read
 	 * are linked on the parent's ->updated_children through
 	 * ->updated_next.
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 2542c21b6b6d..d80d7a608141 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -344,6 +344,7 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 {
 	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
 	struct cgroup *parent = cgroup_parent(cgrp);
+	struct cgroup_rstat_cpu *prstatc;
 	struct cgroup_base_stat delta;
 	unsigned seq;
 
@@ -357,17 +358,24 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 		delta = rstatc->bstat;
 	} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
 
-	/* propagate percpu delta to global */
+	/* propagate per-cpu delta to cgroup and per-cpu global statistics */
 	cgroup_base_stat_sub(&delta, &rstatc->last_bstat);
 	cgroup_base_stat_add(&cgrp->bstat, &delta);
 	cgroup_base_stat_add(&rstatc->last_bstat, &delta);
+	cgroup_base_stat_add(&rstatc->subtree_bstat, &delta);
 
-	/* propagate global delta to parent (unless that's root) */
+	/* propagate cgroup and per-cpu global delta to parent (unless that's root) */
 	if (cgroup_parent(parent)) {
 		delta = cgrp->bstat;
 		cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
 		cgroup_base_stat_add(&parent->bstat, &delta);
 		cgroup_base_stat_add(&cgrp->last_bstat, &delta);
+
+		delta = rstatc->subtree_bstat;
+		prstatc = cgroup_rstat_cpu(parent, cpu);
+		cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat);
+		cgroup_base_stat_add(&prstatc->subtree_bstat, &delta);
+		cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta);
 	}
 }