cgroup: cgroup.stat.local time accounting

There isn't yet a clear way to identify a set of "lost" time that
everyone (or at least a wider group of users) cares about. However,
users can perform some delay accounting by iterating over components of
interest. This patch allows cgroup v2 freezing time to be one of those
components.

Track the cumulative time that each v2 cgroup spends freezing and expose
it to userland via a new local stat file in cgroupfs. Thank you to
Michal, who provided the ASCII art in the updated documentation.

To access this value:
  $ mkdir /sys/fs/cgroup/test
  $ cat /sys/fs/cgroup/test/cgroup.stat.local
  freeze_time_total 0

Ensure consistent freeze time reads with freeze_seq, a per-cgroup
sequence counter. Writes are serialized using the css_set_lock.

Signed-off-by: Tiffany Yang <ynaffit@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

2 files changed, 40 insertions, 4 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 312c6a8b55bb..ab096b884bbc 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3763,6 +3763,27 @@ static int cgroup_stat_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
+static int cgroup_core_local_stat_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	unsigned int sequence;
+	u64 freeze_time;
+
+	do {
+		sequence = read_seqcount_begin(&cgrp->freezer.freeze_seq);
+		freeze_time = cgrp->freezer.frozen_nsec;
+		/* Add in current freezer interval if the cgroup is freezing. */
+		if (test_bit(CGRP_FREEZE, &cgrp->flags))
+			freeze_time += (ktime_get_ns() -
+					cgrp->freezer.freeze_start_nsec);
+	} while (read_seqcount_retry(&cgrp->freezer.freeze_seq, sequence));
+
+	seq_printf(seq, "frozen_usec %llu\n",
+		   (unsigned long long) freeze_time / NSEC_PER_USEC);
+
+	return 0;
+}
+
 #ifdef CONFIG_CGROUP_SCHED
 /**
  * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem
@@ -5355,6 +5376,11 @@ static struct cftype cgroup_base_files[] = {
 		.seq_show = cgroup_stat_show,
 	},
 	{
+		.name = "cgroup.stat.local",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_core_local_stat_show,
+	},
+	{
 		.name = "cgroup.freeze",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cgroup_freeze_show,
@@ -5763,6 +5789,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	 * if the parent has to be frozen, the child has too.
 	 */
 	cgrp->freezer.e_freeze = parent->freezer.e_freeze;
+	seqcount_init(&cgrp->freezer.freeze_seq);
 	if (cgrp->freezer.e_freeze) {
 		/*
 		 * Set the CGRP_FREEZE flag, so when a process will be
@@ -5771,6 +5798,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 		 * consider it frozen immediately.
 		 */
 		set_bit(CGRP_FREEZE, &cgrp->flags);
+		cgrp->freezer.freeze_start_nsec = ktime_get_ns();
 		set_bit(CGRP_FROZEN, &cgrp->flags);
 	}
 
diff --git a/kernel/cgroup/freezer.c b/kernel/cgroup/freezer.c
index bf1690a167dd..6c18854bff34 100644
--- a/kernel/cgroup/freezer.c
+++ b/kernel/cgroup/freezer.c
@@ -171,7 +171,7 @@ static void cgroup_freeze_task(struct task_struct *task, bool freeze)
 /*
  * Freeze or unfreeze all tasks in the given cgroup.
  */
-static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze)
+static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze, u64 ts_nsec)
 {
 	struct css_task_iter it;
 	struct task_struct *task;
@@ -179,10 +179,16 @@ static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze)
 	lockdep_assert_held(&cgroup_mutex);
 
 	spin_lock_irq(&css_set_lock);
-	if (freeze)
+	write_seqcount_begin(&cgrp->freezer.freeze_seq);
+	if (freeze) {
 		set_bit(CGRP_FREEZE, &cgrp->flags);
-	else
+		cgrp->freezer.freeze_start_nsec = ts_nsec;
+	} else {
 		clear_bit(CGRP_FREEZE, &cgrp->flags);
+		cgrp->freezer.frozen_nsec += (ts_nsec -
+			cgrp->freezer.freeze_start_nsec);
+	}
+	write_seqcount_end(&cgrp->freezer.freeze_seq);
 	spin_unlock_irq(&css_set_lock);
 
 	if (freeze)
@@ -260,6 +266,7 @@ void cgroup_freeze(struct cgroup *cgrp, bool freeze)
 	struct cgroup *parent;
 	struct cgroup *dsct;
 	bool applied = false;
+	u64 ts_nsec;
 	bool old_e;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -271,6 +278,7 @@ void cgroup_freeze(struct cgroup *cgrp, bool freeze)
 		return;
 
 	cgrp->freezer.freeze = freeze;
+	ts_nsec = ktime_get_ns();
 
 	/*
 	 * Propagate changes downwards the cgroup tree.
@@ -298,7 +306,7 @@ void cgroup_freeze(struct cgroup *cgrp, bool freeze)
 		/*
 		 * Do change actual state: freeze or unfreeze.
 		 */
-		cgroup_do_freeze(dsct, freeze);
+		cgroup_do_freeze(dsct, freeze, ts_nsec);
 		applied = true;
 	}