[PATCH v3 2/7] sched: accumulate per-cfs_rq cpu usage

[Bharata B Rao <bharata@linux.vnet.ibm.com>]

sched: accumulate per-cfs_rq cpu usage

From: Paul Turner <pjt@google.com>

Introduce account_cfs_rq_quota() to account bandwidth usage on the cfs_rq
level versus task_groups for which bandwidth has been assigned.  This is
tracked by whether the local cfs_rq->quota_assigned is finite or infinite
(RUNTIME_INF).

For cfs_rq's that belong to a bandwidth constrained task_group we introduce
tg_request_cfs_quota() which attempts to allocate quota from the global pool
for use locally.  Updates involving the global pool are currently protected
under cfs_bandwidth->lock, local pools are protected by rq->lock.

This patch only attempts to assign and track quota, no action is taken in the
case that cfs_rq->quota_used exceeds cfs_rq->quota_assigned.

Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
---
 include/linux/sched.h |    4 ++++
 kernel/sched.c        |   13 +++++++++++++
 kernel/sched_fair.c   |   50 ++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sysctl.c       |   10 ++++++++++
 4 files changed, 77 insertions(+)

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1898,6 +1898,10 @@ int sched_rt_handler(struct ctl_table *t
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
+#ifdef CONFIG_CFS_BANDWIDTH
+extern unsigned int sysctl_sched_cfs_bandwidth_slice;
+#endif
+
 extern unsigned int sysctl_sched_compat_yield;
 
 #ifdef CONFIG_RT_MUTEXES
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1929,6 +1929,19 @@ static const struct sched_class rt_sched
  * default: 0.5s
  */
 static u64 sched_cfs_bandwidth_period = 500000000ULL;
+
+/*
+ * default slice of quota to allocate from global tg to local cfs_rq pool on
+ * each refresh
+ * default: 10ms
+ */
+unsigned int sysctl_sched_cfs_bandwidth_slice = 10000UL;
+
+static inline u64 sched_cfs_bandwidth_slice(void)
+{
+	return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
+}
+
 #endif
 
 #define sched_class_highest (&rt_sched_class)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -267,6 +267,16 @@ find_matching_se(struct sched_entity **s
 
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
+#ifdef CONFIG_CFS_BANDWIDTH
+static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
+{
+	return &tg->cfs_bandwidth;
+}
+
+static void account_cfs_rq_quota(struct cfs_rq *cfs_rq,
+		unsigned long delta_exec);
+#endif
+
 
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
@@ -547,6 +557,9 @@ static void update_curr(struct cfs_rq *c
 		cpuacct_charge(curtask, delta_exec);
 		account_group_exec_runtime(curtask, delta_exec);
 	}
+#ifdef CONFIG_CFS_BANDWIDTH
+	account_cfs_rq_quota(cfs_rq, delta_exec);
+#endif
 }
 
 static inline void
@@ -1130,6 +1143,43 @@ static void yield_task_fair(struct rq *r
 }
 
 #ifdef CONFIG_CFS_BANDWIDTH
+static u64 tg_request_cfs_quota(struct task_group *tg)
+{
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
+	u64 delta = 0;
+
+	if (cfs_b->runtime > 0 || cfs_b->quota == RUNTIME_INF) {
+		raw_spin_lock(&cfs_b->lock);
+		/*
+		 * it's possible a bandwidth update has changed the global
+		 * pool.
+		 */
+		if (cfs_b->quota == RUNTIME_INF)
+			delta = sched_cfs_bandwidth_slice();
+		else {
+			delta = min(cfs_b->runtime,
+					sched_cfs_bandwidth_slice());
+			cfs_b->runtime -= delta;
+		}
+		raw_spin_unlock(&cfs_b->lock);
+	}
+	return delta;
+}
+
+static void account_cfs_rq_quota(struct cfs_rq *cfs_rq,
+		unsigned long delta_exec)
+{
+	if (cfs_rq->quota_assigned == RUNTIME_INF)
+		return;
+
+	cfs_rq->quota_used += delta_exec;
+
+	if (cfs_rq->quota_used < cfs_rq->quota_assigned)
+		return;
+
+	cfs_rq->quota_assigned += tg_request_cfs_quota(cfs_rq->tg);
+}
+
 static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 {
 	return 1;
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -384,6 +384,16 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_CFS_BANDWIDTH
+	{
+		.procname	= "sched_cfs_bandwidth_slice_us",
+		.data		= &sysctl_sched_cfs_bandwidth_slice,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+	},
+#endif
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname	= "prove_locking",