[Deepin-Kernel-SIG] [linux 6.6.y] [Upstream] sched update for sched_ext

include/linux/cgroup.h

@@ -29,8 +29,6 @@
 
 struct kernel_clone_args;
 
-#ifdef CONFIG_CGROUPS
-
 /*
  * All weight knobs on the default hierarchy should use the following min,
  * default and max values.  The default value is the logarithmic center of
@@ -40,13 +38,13 @@ struct kernel_clone_args;
 #define CGROUP_WEIGHT_DFL		100
 #define CGROUP_WEIGHT_MAX		10000
 
-/* walk only threadgroup leaders */
-#define CSS_TASK_ITER_PROCS		(1U << 0)
-/* walk all threaded css_sets in the domain */
-#define CSS_TASK_ITER_THREADED		(1U << 1)
+#ifdef CONFIG_CGROUPS
 
-/* internal flags */
-#define CSS_TASK_ITER_SKIPPED		(1U << 16)
+enum {
+	CSS_TASK_ITER_PROCS    = (1U << 0),  /* walk only threadgroup leaders */
+	CSS_TASK_ITER_THREADED = (1U << 1),  /* walk all threaded css_sets in the domain */
+	CSS_TASK_ITER_SKIPPED  = (1U << 16), /* internal flags */
+};
 
 /* a css_task_iter should be treated as an opaque object */
 struct css_task_iter {

include/linux/sched/task.h

@@ -64,7 +64,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
-extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
+extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
+extern void sched_cancel_fork(struct task_struct *p);
 extern void sched_post_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 

kernel/cgroup/cgroup.c

@@ -4950,9 +4950,11 @@ static void css_task_iter_advance(struct css_task_iter *it)
 void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 			 struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	memset(it, 0, sizeof(*it));
 
-	spin_lock_irq(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, irqflags);
 
 	it->ss = css->ss;
 	it->flags = flags;
@@ -4966,7 +4968,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 
 	css_task_iter_advance(it);
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, irqflags);
 }
 
 /**
@@ -4979,12 +4981,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
  */
 struct task_struct *css_task_iter_next(struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	if (it->cur_task) {
 		put_task_struct(it->cur_task);
 		it->cur_task = NULL;
 	}
 
-	spin_lock_irq(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, irqflags);
 
 	/* @it may be half-advanced by skips, finish advancing */
 	if (it->flags & CSS_TASK_ITER_SKIPPED)
@@ -4997,7 +5001,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 		css_task_iter_advance(it);
 	}
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, irqflags);
 
 	return it->cur_task;
 }
@@ -5010,11 +5014,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
  */
 void css_task_iter_end(struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	if (it->cur_cset) {
-		spin_lock_irq(&css_set_lock);
+		spin_lock_irqsave(&css_set_lock, irqflags);
 		list_del(&it->iters_node);
 		put_css_set_locked(it->cur_cset);
-		spin_unlock_irq(&css_set_lock);
+		spin_unlock_irqrestore(&css_set_lock, irqflags);
 	}
 
 	if (it->cur_dcset)

kernel/fork.c

@@ -2557,7 +2557,7 @@ __latent_entropy struct task_struct *copy_process(
 
 	retval = perf_event_init_task(p, clone_flags);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_sched_cancel_fork;
 	retval = audit_alloc(p);
 	if (retval)
 		goto bad_fork_cleanup_perf;
@@ -2689,7 +2689,9 @@ __latent_entropy struct task_struct *copy_process(
 	 * cgroup specific, it unconditionally needs to place the task on a
 	 * runqueue.
 	 */
-	sched_cgroup_fork(p, args);
+	retval = sched_cgroup_fork(p, args);
+	if (retval)
+		goto bad_fork_cancel_cgroup;
 
 	/*
 	 * From this point on we must avoid any synchronous user-space
@@ -2735,13 +2737,13 @@ __latent_entropy struct task_struct *copy_process(
 	/* Don't start children in a dying pid namespace */
 	if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
 		retval = -ENOMEM;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* Let kill terminate clone/fork in the middle */
 	if (fatal_signal_pending(current)) {
 		retval = -EINTR;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* No more failure paths after this point. */
@@ -2815,10 +2817,11 @@ __latent_entropy struct task_struct *copy_process(
 
 	return p;
 
-bad_fork_cancel_cgroup:
+bad_fork_core_free:
 	sched_core_free(p);
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
+bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p, args);
 bad_fork_put_pidfd:
 	if (clone_flags & CLONE_PIDFD) {
@@ -2857,6 +2860,8 @@ __latent_entropy struct task_struct *copy_process(
 	audit_free(p);
 bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_sched_cancel_fork:
+	sched_cancel_fork(p);
 bad_fork_cleanup_policy:
 	lockdep_free_task(p);
 #ifdef CONFIG_NUMA

kernel/sched/core.c

@@ -1341,8 +1341,8 @@ void set_load_weight(struct task_struct *p, bool update_load)
 	 * SCHED_OTHER tasks have to update their load when changing their
 	 * weight
 	 */
-	if (update_load && p->sched_class == &fair_sched_class)
-		reweight_task(p, &lw);
+	if (update_load && p->sched_class->reweight_task)
+		p->sched_class->reweight_task(task_rq(p), p, &lw);
 	else
 		p->se.load = lw;
 }
@@ -2064,6 +2064,17 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
+/*
+ * ->switching_to() is called with the pi_lock and rq_lock held and must not
+ * mess with locking.
+ */
+void check_class_changing(struct rq *rq, struct task_struct *p,
+			  const struct sched_class *prev_class)
+{
+	if (prev_class != p->sched_class && p->sched_class->switching_to)
+		p->sched_class->switching_to(rq, p);
+}
+
 /*
  * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
  * use the balance_callback list if you want balancing.
@@ -4648,7 +4659,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
-void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
+int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 {
 	unsigned long flags;
 
@@ -4675,6 +4686,12 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	return 0;
+}
+
+void sched_cancel_fork(struct task_struct *p)
+{
 }
 
 void sched_post_fork(struct task_struct *p)
@@ -7128,6 +7145,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 
 	p->sched_class = next_class;
 	p->prio = prio;
+	check_class_changing(rq, p, prev_class);
 
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
@@ -8301,12 +8319,12 @@ void __init sched_init(void)
 	int i;
 
 	/* Make sure the linker didn't screw up */
-	BUG_ON(&idle_sched_class != &fair_sched_class + 1 ||
-	       &fair_sched_class != &rt_sched_class + 1 ||
-	       &rt_sched_class   != &dl_sched_class + 1);
 #ifdef CONFIG_SMP
-	BUG_ON(&dl_sched_class != &stop_sched_class + 1);
+	BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
 #endif
+	BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
+	BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
+	BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
 
 	wait_bit_init();
 
@@ -9681,37 +9699,35 @@ static int cpu_local_stat_show(struct seq_file *sf,
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static unsigned long tg_weight(struct task_group *tg)
+{
+	return scale_load_down(tg->shares);
+}
+
 static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
-	struct task_group *tg = css_tg(css);
-	u64 weight = scale_load_down(tg->shares);
-
-	return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
+	return sched_weight_to_cgroup(tg_weight(css_tg(css)));
 }
 
 static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
-				struct cftype *cft, u64 weight)
+				struct cftype *cft, u64 cgrp_weight)
 {
-	/*
-	 * cgroup weight knobs should use the common MIN, DFL and MAX
-	 * values which are 1, 100 and 10000 respectively.  While it loses
-	 * a bit of range on both ends, it maps pretty well onto the shares
-	 * value used by scheduler and the round-trip conversions preserve
-	 * the original value over the entire range.
-	 */
-	if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
+	unsigned long weight;
+
+	if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX)
 		return -ERANGE;
 
-	weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);
+	weight = sched_weight_from_cgroup(cgrp_weight);
 
 	return sched_group_set_shares(css_tg(css), scale_load(weight));
 }
 
 static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
 				    struct cftype *cft)
 {
-	unsigned long weight = scale_load_down(css_tg(css)->shares);
+	unsigned long weight = tg_weight(css_tg(css));
 	int last_delta = INT_MAX;
 	int prio, delta;
 

kernel/sched/fair.c

@@ -3958,7 +3958,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	}
 }
 
-void reweight_task(struct task_struct *p, const struct load_weight *lw)
+static void reweight_task_fair(struct rq *this_rq, struct task_struct *p, const struct load_weight *lw)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -8692,7 +8692,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	/*
 	 * BATCH and IDLE tasks do not preempt others.
 	 */
-	if (unlikely(p->policy != SCHED_NORMAL))
+	if (unlikely(!normal_policy(p->policy)))
 		return;
 
 	cfs_rq = cfs_rq_of(se);
@@ -9649,28 +9649,18 @@ static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {
 
 static bool __update_blocked_others(struct rq *rq, bool *done)
 {
-	const struct sched_class *curr_class;
-	u64 now = rq_clock_pelt(rq);
-	unsigned long thermal_pressure;
-	bool decayed;
+	bool updated;
 
 	/*
 	 * update_load_avg() can call cpufreq_update_util(). Make sure that RT,
 	 * DL and IRQ signals have been updated before updating CFS.
 	 */
-	curr_class = rq->curr->sched_class;
-
-	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
-
-	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
-		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-		  update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) |
-		  update_irq_load_avg(rq, 0);
+	updated = update_other_load_avgs(rq);
 
 	if (others_have_blocked(rq))
 		*done = false;
 
-	return decayed;
+	return updated;
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -13551,6 +13541,7 @@ DEFINE_SCHED_CLASS(fair) = {
 	.task_tick		= task_tick_fair,
 	.task_fork		= task_fork_fair,
 
+	.reweight_task		= reweight_task_fair,
 	.prio_changed		= prio_changed_fair,
 	.switched_from		= switched_from_fair,
 	.switched_to		= switched_to_fair,