Merge tag 'sched_urgent_for_v6.2_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:

 - Make sure the scheduler doesn't use stale frequency scaling values
   when latter get disabled due to a value error

 - Fix a NULL pointer access on UP configs

 - Use the proper locking when updating CPU capacity

* tag 'sched_urgent_for_v6.2_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/aperfmperf: Erase stale arch_freq_scale values when disabling frequency invariance readings
  sched/core: Fix NULL pointer access fault in sched_setaffinity() with non-SMP configs
  sched/fair: Fixes for capacity inversion detection
  sched/uclamp: Fix a uninitialized variable warnings

arch/x86/kernel/cpu/aperfmperf.c

@@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void)
 
 static void disable_freq_invariance_workfn(struct work_struct *work)
 {
+	int cpu;
+
 	static_branch_disable(&arch_scale_freq_key);
+
+	/*
+	 * Set arch_freq_scale to a default value on all cpus
+	 * This negates the effect of scaling
+	 */
+	for_each_possible_cpu(cpu)
+		per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE;
 }
 
 static DECLARE_WORK(disable_freq_invariance_work,

kernel/sched/core.c

@@ -8290,12 +8290,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_put_task;
 
+	/*
+	 * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
+	 * alloc_user_cpus_ptr() returns NULL.
+	 */
 	user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
-	if (IS_ENABLED(CONFIG_SMP) && !user_mask) {
+	if (user_mask) {
+		cpumask_copy(user_mask, in_mask);
+	} else if (IS_ENABLED(CONFIG_SMP)) {
 		retval = -ENOMEM;
 		goto out_put_task;
 	}
-	cpumask_copy(user_mask, in_mask);
+
 	ac = (struct affinity_context){
 		.new_mask  = in_mask,
 		.user_mask = user_mask,

kernel/sched/fair.c

@@ -7229,10 +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;
@@ -7251,6 +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)))
@@ -7269,11 +7271,7 @@ 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 {
+			if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) {
 				/*
 				 * Open code uclamp_rq_util_with() except for
 				 * the clamp() part. Ie: apply max aggregation
@@ -7281,13 +7279,12 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 				 * 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);
+				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;
 
@@ -8871,16 +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);
 
@@ -8905,6 +8909,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 				break;
 			}
 		}
+
+		rcu_read_unlock();
 	}
 
 	trace_sched_cpu_capacity_tp(rq);