1 files changed, 42 insertions, 24 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0cd1d0f7c1bd..0f8736991427 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -178,6 +178,11 @@ int __weak arch_asym_cpu_priority(int cpu)
 static unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
 #endif
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Restrict the NUMA promotion throughput (MB/s) for each target node. */
+static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
+#endif
+
 #ifdef CONFIG_SYSCTL
 static struct ctl_table sched_fair_sysctls[] = {
 	{
@@ -197,6 +202,16 @@ static struct ctl_table sched_fair_sysctls[] = {
 		.extra1         = SYSCTL_ONE,
 	},
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	{
+		.procname	= "numa_balancing_promote_rate_limit_MBps",
+		.data		= &sysctl_numa_balancing_promote_rate_limit,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+#endif /* CONFIG_NUMA_BALANCING */
 	{}
 };
 
@@ -1094,9 +1109,6 @@ unsigned int sysctl_numa_balancing_scan_delay = 1000;
 /* The page with hint page fault latency < threshold in ms is considered hot */
 unsigned int sysctl_numa_balancing_hot_threshold = MSEC_PER_SEC;
 
-/* Restrict the NUMA promotion throughput (MB/s) for each target node. */
-unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
-
 struct numa_group {
 	refcount_t refcount;
 
@@ -7217,10 +7229,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	eenv_task_busy_time(&eenv, p, prev_cpu);
 
 	for (; pd; pd = pd->next) {
+		unsigned long util_min = p_util_min, util_max = p_util_max;
 		unsigned long cpu_cap, cpu_thermal_cap, util;
 		unsigned long cur_delta, max_spare_cap = 0;
 		unsigned long rq_util_min, rq_util_max;
-		unsigned long util_min, util_max;
 		unsigned long prev_spare_cap = 0;
 		int max_spare_cap_cpu = -1;
 		unsigned long base_energy;
@@ -7239,6 +7251,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 		eenv.pd_cap = 0;
 
 		for_each_cpu(cpu, cpus) {
+			struct rq *rq = cpu_rq(cpu);
+
 			eenv.pd_cap += cpu_thermal_cap;
 
 			if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
@@ -7257,24 +7271,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			 * much capacity we can get out of the CPU; this is
 			 * aligned with sched_cpu_util().
 			 */
-			if (uclamp_is_used()) {
-				if (uclamp_rq_is_idle(cpu_rq(cpu))) {
-					util_min = p_util_min;
-					util_max = p_util_max;
-				} else {
-					/*
-					 * Open code uclamp_rq_util_with() except for
-					 * the clamp() part. Ie: apply max aggregation
-					 * only. util_fits_cpu() logic requires to
-					 * operate on non clamped util but must use the
-					 * max-aggregated uclamp_{min, max}.
-					 */
-					rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
-					rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
-
-					util_min = max(rq_util_min, p_util_min);
-					util_max = max(rq_util_max, p_util_max);
-				}
+			if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) {
+				/*
+				 * Open code uclamp_rq_util_with() except for
+				 * the clamp() part. Ie: apply max aggregation
+				 * only. util_fits_cpu() logic requires to
+				 * operate on non clamped util but must use the
+				 * max-aggregated uclamp_{min, max}.
+				 */
+				rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN);
+				rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX);
+
+				util_min = max(rq_util_min, p_util_min);
+				util_max = max(rq_util_max, p_util_max);
 			}
 			if (!util_fits_cpu(util, util_min, util_max, cpu))
 				continue;
@@ -8859,16 +8868,23 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 	 *   * Thermal pressure will impact all cpus in this perf domain
 	 *     equally.
 	 */
-	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+	if (sched_energy_enabled()) {
 		unsigned long inv_cap = capacity_orig - thermal_load_avg(rq);
-		struct perf_domain *pd = rcu_dereference(rq->rd->pd);
+		struct perf_domain *pd;
 
+		rcu_read_lock();
+
+		pd = rcu_dereference(rq->rd->pd);
 		rq->cpu_capacity_inverted = 0;
 
 		for (; pd; pd = pd->next) {
 			struct cpumask *pd_span = perf_domain_span(pd);
 			unsigned long pd_cap_orig, pd_cap;
 
+			/* We can't be inverted against our own pd */
+			if (cpumask_test_cpu(cpu_of(rq), pd_span))
+				continue;
+
 			cpu = cpumask_any(pd_span);
 			pd_cap_orig = arch_scale_cpu_capacity(cpu);
 
@@ -8893,6 +8909,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 				break;
 			}
 		}
+
+		rcu_read_unlock();
 	}
 
 	trace_sched_cpu_capacity_tp(rq);