Merge branch 'tip/sched/urgent'

Avoid merge conflicts

Signed-off-by: Peter Zijlstra <peterz@infradead.org>

7 files changed, 30 insertions, 27 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 89b3ed637465..e9c8bda84d80 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3333,10 +3333,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
-	__schedstat_inc(p->stats.numa_task_swapped);
-	count_vm_numa_event(NUMA_TASK_SWAP);
-	count_memcg_event_mm(p->mm, NUMA_TASK_SWAP);
-
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
 		struct rq_flags srf, drf;
@@ -3898,6 +3894,11 @@ static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 	if (!scx_allow_ttwu_queue(p))
 		return false;
 
+#ifdef CONFIG_SMP
+	if (p->sched_class == &stop_sched_class)
+		return false;
+#endif
+
 	/*
 	 * Do not complicate things with the async wake_list while the CPU is
 	 * in hotplug state.
@@ -7574,7 +7575,7 @@ const char *preempt_model_str(void)
 
 		if (IS_ENABLED(CONFIG_PREEMPT_DYNAMIC)) {
 			seq_buf_printf(&s, "(%s)%s",
-				       preempt_dynamic_mode > 0 ?
+				       preempt_dynamic_mode >= 0 ?
 				       preempt_modes[preempt_dynamic_mode] : "undef",
 				       brace ? "}" : "");
 			return seq_buf_str(&s);
@@ -7835,9 +7836,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
-	__schedstat_inc(p->stats.numa_task_migrated);
-	count_vm_numa_event(NUMA_TASK_MIGRATE);
-	count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE);
+	/* TODO: This is not properly updating schedstats */
+
 	trace_sched_move_numa(p, curr_cpu, target_cpu);
 	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
@@ -8439,7 +8439,7 @@ void __init sched_init(void)
 		init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_EXT_GROUP_SCHED
-		root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+		scx_tg_init(&root_task_group);
 #endif /* CONFIG_EXT_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -8874,7 +8874,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
-	scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
+	scx_tg_init(tg);
 	alloc_uclamp_sched_group(tg, parent);
 
 	return tg;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9c7d9528d5fa..1af06e48227d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1442,7 +1442,9 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 	if (dl_entity_is_special(dl_se))
 		return;
 
-	scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
+	scaled_delta_exec = delta_exec;
+	if (!dl_server(dl_se))
+		scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
 
 	dl_se->runtime -= scaled_delta_exec;
 
@@ -1549,7 +1551,7 @@ throttle:
  */
 void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 {
-	s64 delta_exec, scaled_delta_exec;
+	s64 delta_exec;
 
 	if (!rq->fair_server.dl_defer)
 		return;
@@ -1562,9 +1564,7 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 	if (delta_exec < 0)
 		return;
 
-	scaled_delta_exec = dl_scaled_delta_exec(rq, &rq->fair_server, delta_exec);
-
-	rq->fair_server.runtime -= scaled_delta_exec;
+	rq->fair_server.runtime -= delta_exec;
 
 	if (rq->fair_server.runtime < 0) {
 		rq->fair_server.dl_defer_running = 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index f16d53928bb9..3f06ab84d53f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1189,10 +1189,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P_SCHEDSTAT(nr_failed_migrations_running);
 		P_SCHEDSTAT(nr_failed_migrations_hot);
 		P_SCHEDSTAT(nr_forced_migrations);
-#ifdef CONFIG_NUMA_BALANCING
-		P_SCHEDSTAT(numa_task_migrated);
-		P_SCHEDSTAT(numa_task_swapped);
-#endif
 		P_SCHEDSTAT(nr_wakeups);
 		P_SCHEDSTAT(nr_wakeups_sync);
 		P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2c41c78be61e..b498d867ba21 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4092,6 +4092,11 @@ bool scx_can_stop_tick(struct rq *rq)
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
 
+void scx_tg_init(struct task_group *tg)
+{
+	tg->scx_weight = CGROUP_WEIGHT_DFL;
+}
+
 int scx_tg_online(struct task_group *tg)
 {
 	struct scx_sched *sch = scx_root;
@@ -4241,12 +4246,12 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	if (scx_cgroup_enabled && tg->scx_weight != weight) {
-		if (SCX_HAS_OP(sch, cgroup_set_weight))
-			SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
-				    tg_cgrp(tg), weight);
-		tg->scx_weight = weight;
-	}
+	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) &&
+	    tg->scx_weight != weight)
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
+			    tg_cgrp(tg), weight);
+
+	tg->scx_weight = weight;
 
 	percpu_up_read(&scx_cgroup_rwsem);
 }
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 6e5072f57771..a75835c23f15 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -79,6 +79,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
 
 #ifdef CONFIG_CGROUP_SCHED
 #ifdef CONFIG_EXT_GROUP_SCHED
+void scx_tg_init(struct task_group *tg);
 int scx_tg_online(struct task_group *tg);
 void scx_tg_offline(struct task_group *tg);
 int scx_cgroup_can_attach(struct cgroup_taskset *tset);
@@ -88,6 +89,7 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
 void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
 void scx_group_set_idle(struct task_group *tg, bool idle);
 #else	/* CONFIG_EXT_GROUP_SCHED */
+static inline void scx_tg_init(struct task_group *tg) {}
 static inline int scx_tg_online(struct task_group *tg) { return 0; }
 static inline void scx_tg_offline(struct task_group *tg) {}
 static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index e3a1ce923f9f..b601e0243d0e 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -82,7 +82,7 @@ long calc_load_fold_active(struct rq *this_rq, long adjust)
 	long nr_active, delta = 0;
 
 	nr_active = this_rq->nr_running - adjust;
-	nr_active += (int)this_rq->nr_uninterruptible;
+	nr_active += (long)this_rq->nr_uninterruptible;
 
 	if (nr_active != this_rq->calc_load_active) {
 		delta = nr_active - this_rq->calc_load_active;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3058fb6246da..ac953fad8c21 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1140,7 +1140,7 @@ struct rq {
 	 * one CPU and if it got migrated afterwards it may decrease
 	 * it on another CPU. Always updated under the runqueue lock:
 	 */
-	unsigned int		nr_uninterruptible;
+	unsigned long 		nr_uninterruptible;
 
 	union {
 		struct task_struct __rcu *donor; /* Scheduler context */