Scheduler changes in this cycle were:

- Updates to scheduler metrics:
 
     - PELT fixes & enhancements
     - PSI fixes & enhancements
     - Refactor cpu_util_without()
 
  - Updates to instrumentation/debugging:
 
     - Remove sched_trace_*() helper functions - can be done via debug info
     - Fix double update_rq_clock() warnings
 
  - Introduce & use "preemption model accessors" to simplify some of
    the Kconfig complexity.
 
  - Make softirq handling RT-safe.
 
  - Misc smaller fixes & cleanups.
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmKLvXYRHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1hcXg//fJ1jAB9pQOg/Su9wwwbcOeaXNUpQA38e
 970nXdK6i7w+YeAT2x1ikIQZq5S/px7k9S4Fzks8U9LMhnKPxhjdnG6J69h5XLuB
 z1BtRJBB6W8BAYWzAeq1M+R8whQylciOMZOBSjeTIEdpYBK7c9QA/R1DkDqPRlBA
 7nW0mFbpYcK8Q1n1ItjP0wkpiHG4q8orp+BXiPG8rjiHdCa3GFt7g38hiqNls64H
 fOQ/Ka25tBSYrmeqQY3QsWKnKNHKQRLNareHAwI/x4V8F8d4tn/OmJzmWGDdtprn
 6/gi/E99ej1j5Do8sgx/oTp/aVg4j8AsurrpGFd4/er+euoG4UyHr42UhX6zmFM6
 /KIinp0Z/V2n9okgI9LUZ2x7mD682iXDilNDgiSAwu1bNDUvxBXPD30gThh+KasA
 HxeKxTzb4/dZV4ih4xUMsCOjUT4NFZT2rmiMorUystgyNRk28DtFCdBMtrs/zVtG
 qAktb7v5g76pKAmV4nQu4imZeSD+f+RJP2fuSUYQCJbCxQfthTZkn8GfCMYEdY7Y
 sDyBx4Te8Vu/dcnal9qMpY/m5EPruPQAkvC9zK4YvkvLUmGC742PG/xHfCdC9J2m
 Adbl/Cmn7tD9dOGYbHPsrViqwIiZUcjbnBlMN5DjJXQF6kWNOIXUEguZpBocminP
 1CSy0+gyI6o=
 =GY8N
 -----END PGP SIGNATURE-----

Merge tag 'sched-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Updates to scheduler metrics:
     - PELT fixes & enhancements
     - PSI fixes & enhancements
     - Refactor cpu_util_without()

 - Updates to instrumentation/debugging:
     - Remove sched_trace_*() helper functions - can be done via debug
       info
     - Fix double update_rq_clock() warnings

 - Introduce & use "preemption model accessors" to simplify some of the
   Kconfig complexity.

 - Make softirq handling RT-safe.

 - Misc smaller fixes & cleanups.

* tag 'sched-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  topology: Remove unused cpu_cluster_mask()
  sched: Reverse sched_class layout
  sched/deadline: Remove superfluous rq clock update in push_dl_task()
  sched/core: Avoid obvious double update_rq_clock warning
  smp: Make softirq handling RT safe in flush_smp_call_function_queue()
  smp: Rename flush_smp_call_function_from_idle()
  sched: Fix missing prototype warnings
  sched/fair: Remove cfs_rq_tg_path()
  sched/fair: Remove sched_trace_*() helper functions
  sched/fair: Refactor cpu_util_without()
  sched/fair: Revise comment about lb decision matrix
  sched/psi: report zeroes for CPU full at the system level
  sched/fair: Delete useless condition in tg_unthrottle_up()
  sched/fair: Fix cfs_rq_clock_pelt() for throttled cfs_rq
  sched/fair: Move calculate of avg_load to a better location
  mailmap: Update my email address to @redhat.com
  MAINTAINERS: Add myself as scheduler topology reviewer
  psi: Fix trigger being fired unexpectedly at initial
  ftrace: Use preemption model accessors for trace header printout
  kcsan: Use preemption model accessors

.mailmap

@@ -398,6 +398,7 @@ Vasily Averin <vasily.averin@linux.dev> <vvs@virtuozzo.com>
 Vasily Averin <vasily.averin@linux.dev> <vvs@openvz.org>
 Vasily Averin <vasily.averin@linux.dev> <vvs@parallels.com>
 Vasily Averin <vasily.averin@linux.dev> <vvs@sw.ru>
+Valentin Schneider <vschneid@redhat.com> <valentin.schneider@arm.com>
 Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com>
 Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com>
 Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org>

Documentation/accounting/psi.rst

@@ -37,11 +37,7 @@ Pressure interface
 Pressure information for each resource is exported through the
 respective file in /proc/pressure/ -- cpu, memory, and io.
 
-The format for CPU is as such::
+The format is as such::
-
-	some avg10=0.00 avg60=0.00 avg300=0.00 total=0
-
-and for memory and IO::
 
 	some avg10=0.00 avg60=0.00 avg300=0.00 total=0
 	full avg10=0.00 avg60=0.00 avg300=0.00 total=0
@@ -58,6 +54,9 @@ situation from a state where some tasks are stalled but the CPU is
 still doing productive work. As such, time spent in this subset of the
 stall state is tracked separately and exported in the "full" averages.
 
+CPU full is undefined at the system level, but has been reported
+since 5.13, so it is set to zero for backward compatibility.
+
 The ratios (in %) are tracked as recent trends over ten, sixty, and
 three hundred second windows, which gives insight into short term events
 as well as medium and long term trends. The total absolute stall time

MAINTAINERS

@@ -17524,6 +17524,7 @@ R:	Steven Rostedt <rostedt@goodmis.org> (SCHED_FIFO/SCHED_RR)
 R:	Ben Segall <bsegall@google.com> (CONFIG_CFS_BANDWIDTH)
 R:	Mel Gorman <mgorman@suse.de> (CONFIG_NUMA_BALANCING)
 R:	Daniel Bristot de Oliveira <bristot@redhat.com> (SCHED_DEADLINE)
+R:	Valentin Schneider <vschneid@redhat.com> (TOPOLOGY)
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core

include/asm-generic/vmlinux.lds.h

@@ -126,13 +126,13 @@
  */
 #define SCHED_DATA				\
 	STRUCT_ALIGN();				\
-	__begin_sched_classes = .;		\
+	__sched_class_highest = .;		\
-	*(__idle_sched_class)			\
-	*(__fair_sched_class)			\
-	*(__rt_sched_class)			\
-	*(__dl_sched_class)			\
 	*(__stop_sched_class)			\
-	__end_sched_classes = .;
+	*(__dl_sched_class)			\
+	*(__rt_sched_class)			\
+	*(__fair_sched_class)			\
+	*(__idle_sched_class)			\
+	__sched_class_lowest = .;
 
 /* The actual configuration determine if the init/exit sections
  * are handled as text/data or they can be discarded (which

include/linux/interrupt.h

@@ -589,6 +589,15 @@ struct softirq_action
 asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 
+#ifdef CONFIG_PREEMPT_RT
+extern void do_softirq_post_smp_call_flush(unsigned int was_pending);
+#else
+static inline void do_softirq_post_smp_call_flush(unsigned int unused)
+{
+	do_softirq();
+}
+#endif
+
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
 extern void __raise_softirq_irqoff(unsigned int nr);

include/linux/sched.h

@@ -2382,20 +2382,6 @@ static inline void rseq_syscall(struct pt_regs *regs)
 
 #endif
 
-const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq);
-char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len);
-int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq);
-
-const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq);
-const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
-const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
-
-int sched_trace_rq_cpu(struct rq *rq);
-int sched_trace_rq_cpu_capacity(struct rq *rq);
-int sched_trace_rq_nr_running(struct rq *rq);
-
-const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
-
 #ifdef CONFIG_SCHED_CORE
 extern void sched_core_free(struct task_struct *tsk);
 extern void sched_core_fork(struct task_struct *p);
@@ -2406,4 +2392,6 @@ static inline void sched_core_free(struct task_struct *tsk) { }
 static inline void sched_core_fork(struct task_struct *p) { }
 #endif
 
+extern void sched_set_stop_task(int cpu, struct task_struct *stop);
+
 #endif

include/linux/topology.h

@@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu)
 }
 #endif
 
-#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask)
-static inline const struct cpumask *cpu_cluster_mask(int cpu)
-{
-	return topology_cluster_cpumask(cpu);
-}
-#endif
-
 static inline const struct cpumask *cpu_cpu_mask(int cpu)
 {
 	return cpumask_of_node(cpu_to_node(cpu));

kernel/kcsan/kcsan_test.c

@@ -1380,13 +1380,14 @@ static const void *nthreads_gen_params(const void *prev, char *desc)
 	else
 		nthreads *= 2;
 
-	if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) {
+	if (!preempt_model_preemptible() ||
+	    !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) {
 		/*
 		 * Without any preemption, keep 2 CPUs free for other tasks, one
 		 * of which is the main test case function checking for
 		 * completion or failure.
 		 */
-		const long min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0;
+		const long min_unused_cpus = preempt_model_none() ? 2 : 0;
 		const long min_required_cpus = 2 + min_unused_cpus;
 
 		if (num_online_cpus() < min_required_cpus) {

kernel/sched/build_policy.c

@@ -15,6 +15,7 @@
 /* Headers: */
 #include <linux/sched/clock.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/hotplug.h>
 #include <linux/sched/posix-timers.h>
 #include <linux/sched/rt.h>
 
@@ -31,6 +32,7 @@
 #include <uapi/linux/sched/types.h>
 
 #include "sched.h"
+#include "smp.h"
 
 #include "autogroup.h"
 #include "stats.h"

kernel/sched/build_utility.c

@@ -14,6 +14,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/nohz.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/rseq_api.h>
 #include <linux/sched/task_stack.h>

kernel/sched/core.c

@@ -26,7 +26,10 @@
 #include <linux/topology.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/cond_resched.h>
+#include <linux/sched/cputime.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/hotplug.h>
+#include <linux/sched/init.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/mm.h>
@@ -610,10 +613,10 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2)
 		swap(rq1, rq2);
 
 	raw_spin_rq_lock(rq1);
-	if (__rq_lockp(rq1) == __rq_lockp(rq2))
+	if (__rq_lockp(rq1) != __rq_lockp(rq2))
-		return;
+		raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
 
-	raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
+	double_rq_clock_clear_update(rq1, rq2);
 }
 #endif
 
@@ -2190,7 +2193,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->sched_class == rq->curr->sched_class)
 		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
-	else if (p->sched_class > rq->curr->sched_class)
+	else if (sched_class_above(p->sched_class, rq->curr->sched_class))
 		resched_curr(rq);
 
 	/*
@@ -2408,7 +2411,7 @@ static int migration_cpu_stop(void *data)
 	 * __migrate_task() such that we will not miss enforcing cpus_ptr
 	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
 	 */
-	flush_smp_call_function_from_idle();
+	flush_smp_call_function_queue();
 
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
@@ -5689,7 +5692,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * higher scheduling class, because otherwise those lose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely(prev->sched_class <= &fair_sched_class &&
+	if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 
 		p = pick_next_task_fair(rq, prev, rf);
@@ -9469,11 +9472,11 @@ void __init sched_init(void)
 	int i;
 
 	/* Make sure the linker didn't screw up */
-	BUG_ON(&idle_sched_class + 1 != &fair_sched_class ||
+	BUG_ON(&idle_sched_class != &fair_sched_class + 1 ||
-	       &fair_sched_class + 1 != &rt_sched_class ||
+	       &fair_sched_class != &rt_sched_class + 1 ||
-	       &rt_sched_class + 1   != &dl_sched_class);
+	       &rt_sched_class   != &dl_sched_class + 1);
 #ifdef CONFIG_SMP
-	BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
+	BUG_ON(&dl_sched_class != &stop_sched_class + 1);
 #endif
 
 	wait_bit_init();

kernel/sched/deadline.c

@@ -1220,8 +1220,6 @@ int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 	return (dl_se->runtime <= 0);
 }
 
-extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
-
 /*
  * This function implements the GRUB accounting rule:
  * according to the GRUB reclaiming algorithm, the runtime is
@@ -1832,6 +1830,7 @@ out:
 
 static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused)
 {
+	struct rq_flags rf;
 	struct rq *rq;
 
 	if (READ_ONCE(p->__state) != TASK_WAKING)
@@ -1843,7 +1842,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 	 * from try_to_wake_up(). Hence, p->pi_lock is locked, but
 	 * rq->lock is not... So, lock it
 	 */
-	raw_spin_rq_lock(rq);
+	rq_lock(rq, &rf);
 	if (p->dl.dl_non_contending) {
 		update_rq_clock(rq);
 		sub_running_bw(&p->dl, &rq->dl);
@@ -1859,7 +1858,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 			put_task_struct(p);
 	}
 	sub_rq_bw(&p->dl, &rq->dl);
-	raw_spin_rq_unlock(rq);
+	rq_unlock(rq, &rf);
 }
 
 static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
@@ -2319,13 +2318,7 @@ retry:
 
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, later_rq->cpu);
-
+	activate_task(later_rq, next_task, 0);
-	/*
-	 * Update the later_rq clock here, because the clock is used
-	 * by the cpufreq_update_util() inside __add_running_bw().
-	 */
-	update_rq_clock(later_rq);
-	activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
 	ret = 1;
 
 	resched_curr(later_rq);

kernel/sched/fair.c

@@ -36,6 +36,7 @@
 #include <linux/sched/cond_resched.h>
 #include <linux/sched/cputime.h>
 #include <linux/sched/isolation.h>
+#include <linux/sched/nohz.h>
 
 #include <linux/cpuidle.h>
 #include <linux/interrupt.h>
@@ -313,19 +314,6 @@ const struct sched_class fair_sched_class;
 #define for_each_sched_entity(se) \
 		for (; se; se = se->parent)
 
-static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
-{
-	if (!path)
-		return;
-
-	if (cfs_rq && task_group_is_autogroup(cfs_rq->tg))
-		autogroup_path(cfs_rq->tg, path, len);
-	else if (cfs_rq && cfs_rq->tg->css.cgroup)
-		cgroup_path(cfs_rq->tg->css.cgroup, path, len);
-	else
-		strlcpy(path, "(null)", len);
-}
-
 static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
@@ -493,12 +481,6 @@ static int se_is_idle(struct sched_entity *se)
 #define for_each_sched_entity(se) \
 		for (; se; se = NULL)
 
-static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len)
-{
-	if (path)
-		strlcpy(path, "(null)", len);
-}
-
 static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	return true;
@@ -4846,11 +4828,11 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 
 	cfs_rq->throttle_count--;
 	if (!cfs_rq->throttle_count) {
-		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
+		cfs_rq->throttled_clock_pelt_time += rq_clock_pelt(rq) -
-					     cfs_rq->throttled_clock_task;
+					     cfs_rq->throttled_clock_pelt;
 
 		/* Add cfs_rq with load or one or more already running entities to the list */
-		if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running)
+		if (!cfs_rq_is_decayed(cfs_rq))
 			list_add_leaf_cfs_rq(cfs_rq);
 	}
 
@@ -4864,7 +4846,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 
 	/* group is entering throttled state, stop time */
 	if (!cfs_rq->throttle_count) {
-		cfs_rq->throttled_clock_task = rq_clock_task(rq);
+		cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq);
 		list_del_leaf_cfs_rq(cfs_rq);
 	}
 	cfs_rq->throttle_count++;
@@ -5308,7 +5290,7 @@ static void sync_throttle(struct task_group *tg, int cpu)
 	pcfs_rq = tg->parent->cfs_rq[cpu];
 
 	cfs_rq->throttle_count = pcfs_rq->throttle_count;
-	cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+	cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu));
 }
 
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
@@ -6543,6 +6525,68 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	return target;
 }
 
+/*
+ * Predicts what cpu_util(@cpu) would return if @p was removed from @cpu
+ * (@dst_cpu = -1) or migrated to @dst_cpu.
+ */
+static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
+{
+	struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs;
+	unsigned long util = READ_ONCE(cfs_rq->avg.util_avg);
+
+	/*
+	 * If @dst_cpu is -1 or @p migrates from @cpu to @dst_cpu remove its
+	 * contribution. If @p migrates from another CPU to @cpu add its
+	 * contribution. In all the other cases @cpu is not impacted by the
+	 * migration so its util_avg is already correct.
+	 */
+	if (task_cpu(p) == cpu && dst_cpu != cpu)
+		lsub_positive(&util, task_util(p));
+	else if (task_cpu(p) != cpu && dst_cpu == cpu)
+		util += task_util(p);
+
+	if (sched_feat(UTIL_EST)) {
+		unsigned long util_est;
+
+		util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+		/*
+		 * During wake-up @p isn't enqueued yet and doesn't contribute
+		 * to any cpu_rq(cpu)->cfs.avg.util_est.enqueued.
+		 * If @dst_cpu == @cpu add it to "simulate" cpu_util after @p
+		 * has been enqueued.
+		 *
+		 * During exec (@dst_cpu = -1) @p is enqueued and does
+		 * contribute to cpu_rq(cpu)->cfs.util_est.enqueued.
+		 * Remove it to "simulate" cpu_util without @p's contribution.
+		 *
+		 * Despite the task_on_rq_queued(@p) check there is still a
+		 * small window for a possible race when an exec
+		 * select_task_rq_fair() races with LB's detach_task().
+		 *
+		 *   detach_task()
+		 *     deactivate_task()
+		 *       p->on_rq = TASK_ON_RQ_MIGRATING;
+		 *       -------------------------------- A
+		 *       dequeue_task()                    \
+		 *         dequeue_task_fair()              + Race Time
+		 *           util_est_dequeue()            /
+		 *       -------------------------------- B
+		 *
+		 * The additional check "current == p" is required to further
+		 * reduce the race window.
+		 */
+		if (dst_cpu == cpu)
+			util_est += _task_util_est(p);
+		else if (unlikely(task_on_rq_queued(p) || current == p))
+			lsub_positive(&util_est, _task_util_est(p));
+
+		util = max(util, util_est);
+	}
+
+	return min(util, capacity_orig_of(cpu));
+}
+
 /*
  * cpu_util_without: compute cpu utilization without any contributions from *p
  * @cpu: the CPU which utilization is requested
@@ -6558,116 +6602,11 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
  */
 static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 {
-	struct cfs_rq *cfs_rq;
-	unsigned int util;
-
 	/* Task has no contribution or is new */
 	if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
 		return cpu_util_cfs(cpu);
 
-	cfs_rq = &cpu_rq(cpu)->cfs;
+	return cpu_util_next(cpu, p, -1);
-	util = READ_ONCE(cfs_rq->avg.util_avg);
-
-	/* Discount task's util from CPU's util */
-	lsub_positive(&util, task_util(p));
-
-	/*
-	 * Covered cases:
-	 *
-	 * a) if *p is the only task sleeping on this CPU, then:
-	 *      cpu_util (== task_util) > util_est (== 0)
-	 *    and thus we return:
-	 *      cpu_util_without = (cpu_util - task_util) = 0
-	 *
-	 * b) if other tasks are SLEEPING on this CPU, which is now exiting
-	 *    IDLE, then:
-	 *      cpu_util >= task_util
-	 *      cpu_util > util_est (== 0)
-	 *    and thus we discount *p's blocked utilization to return:
-	 *      cpu_util_without = (cpu_util - task_util) >= 0
-	 *
-	 * c) if other tasks are RUNNABLE on that CPU and
-	 *      util_est > cpu_util
-	 *    then we use util_est since it returns a more restrictive
-	 *    estimation of the spare capacity on that CPU, by just
-	 *    considering the expected utilization of tasks already
-	 *    runnable on that CPU.
-	 *
-	 * Cases a) and b) are covered by the above code, while case c) is
-	 * covered by the following code when estimated utilization is
-	 * enabled.
-	 */
-	if (sched_feat(UTIL_EST)) {
-		unsigned int estimated =
-			READ_ONCE(cfs_rq->avg.util_est.enqueued);
-
-		/*
-		 * Despite the following checks we still have a small window
-		 * for a possible race, when an execl's select_task_rq_fair()
-		 * races with LB's detach_task():
-		 *
-		 *   detach_task()
-		 *     p->on_rq = TASK_ON_RQ_MIGRATING;
-		 *     ---------------------------------- A
-		 *     deactivate_task()                   \
-		 *       dequeue_task()                     + RaceTime
-		 *         util_est_dequeue()              /
-		 *     ---------------------------------- B
-		 *
-		 * The additional check on "current == p" it's required to
-		 * properly fix the execl regression and it helps in further
-		 * reducing the chances for the above race.
-		 */
-		if (unlikely(task_on_rq_queued(p) || current == p))
-			lsub_positive(&estimated, _task_util_est(p));
-
-		util = max(util, estimated);
-	}
-
-	/*
-	 * Utilization (estimated) can exceed the CPU capacity, thus let's
-	 * clamp to the maximum CPU capacity to ensure consistency with
-	 * cpu_util.
-	 */
-	return min_t(unsigned long, util, capacity_orig_of(cpu));
-}
-
-/*
- * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued)
- * to @dst_cpu.
- */
-static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
-{
-	struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs;
-	unsigned long util_est, util = READ_ONCE(cfs_rq->avg.util_avg);
-
-	/*
-	 * If @p migrates from @cpu to another, remove its contribution. Or,
-	 * if @p migrates from another CPU to @cpu, add its contribution. In
-	 * the other cases, @cpu is not impacted by the migration, so the
-	 * util_avg should already be correct.
-	 */
-	if (task_cpu(p) == cpu && dst_cpu != cpu)
-		lsub_positive(&util, task_util(p));
-	else if (task_cpu(p) != cpu && dst_cpu == cpu)
-		util += task_util(p);
-
-	if (sched_feat(UTIL_EST)) {
-		util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
-
-		/*
-		 * During wake-up, the task isn't enqueued yet and doesn't
-		 * appear in the cfs_rq->avg.util_est.enqueued of any rq,
-		 * so just add it (if needed) to "simulate" what will be
-		 * cpu_util after the task has been enqueued.
-		 */
-		if (dst_cpu == cpu)
-			util_est += _task_util_est(p);
-
-		util = max(util, util_est);
-	}
-
-	return min(util, capacity_orig_of(cpu));
 }
 
 /*
@@ -9460,8 +9399,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		local->avg_load = (local->group_load * SCHED_CAPACITY_SCALE) /
 				  local->group_capacity;
 
-		sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) /
-				sds->total_capacity;
 		/*
 		 * If the local group is more loaded than the selected
 		 * busiest group don't try to pull any tasks.
@@ -9470,6 +9407,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 			env->imbalance = 0;
 			return;
 		}
+
+		sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) /
+				sds->total_capacity;
 	}
 
 	/*
@@ -9495,7 +9435,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  * busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
  * has_spare        nr_idle   balanced   N/A    N/A  balanced   balanced
  * fully_busy       nr_idle   nr_idle    N/A    N/A  balanced   balanced
- * misfit_task      force     N/A        N/A    N/A  force      force
+ * misfit_task      force     N/A        N/A    N/A  N/A        N/A
  * asym_packing     force     force      N/A    N/A  force      force
  * imbalanced       force     force      N/A    N/A  force      force
  * overloaded       force     force      N/A    N/A  force      avg_load
@@ -11881,101 +11821,3 @@ __init void init_sched_fair_class(void)
 #endif /* SMP */
 
 }
-
-/*
- * Helper functions to facilitate extracting info from tracepoints.
- */
-
-const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq)
-{
-#ifdef CONFIG_SMP
-	return cfs_rq ? &cfs_rq->avg : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_avg);
-
-char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len)
-{
-	if (!cfs_rq) {
-		if (str)
-			strlcpy(str, "(null)", len);
-		else
-			return NULL;
-	}
-
-	cfs_rq_tg_path(cfs_rq, str, len);
-	return str;
-}
-EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_path);
-
-int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq)
-{
-	return cfs_rq ? cpu_of(rq_of(cfs_rq)) : -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_cpu);
-
-const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq)
-{
-#ifdef CONFIG_SMP
-	return rq ? &rq->avg_rt : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_avg_rt);
-
-const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq)
-{
-#ifdef CONFIG_SMP
-	return rq ? &rq->avg_dl : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_avg_dl);
-
-const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq)
-{
-#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_SCHED_AVG_IRQ)
-	return rq ? &rq->avg_irq : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_avg_irq);
-
-int sched_trace_rq_cpu(struct rq *rq)
-{
-	return rq ? cpu_of(rq) : -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_cpu);
-
-int sched_trace_rq_cpu_capacity(struct rq *rq)
-{
-	return rq ?
-#ifdef CONFIG_SMP
-		rq->cpu_capacity
-#else
-		SCHED_CAPACITY_SCALE
-#endif
-		: -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_cpu_capacity);
-
-const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
-{
-#ifdef CONFIG_SMP
-	return rd ? rd->span : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rd_span);
-
-int sched_trace_rq_nr_running(struct rq *rq)
-{
-        return rq ? rq->nr_running : -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);

kernel/sched/idle.c

@@ -327,7 +327,7 @@ static void do_idle(void)
 	 * RCU relies on this call to be done outside of an RCU read-side
 	 * critical section.
 	 */
-	flush_smp_call_function_from_idle();
+	flush_smp_call_function_queue();
 	schedule_idle();
 
 	if (unlikely(klp_patch_pending(current)))

kernel/sched/pelt.h

@@ -145,9 +145,9 @@ static inline u64 rq_clock_pelt(struct rq *rq)
 static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
 {
 	if (unlikely(cfs_rq->throttle_count))
-		return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time;
+		return cfs_rq->throttled_clock_pelt - cfs_rq->throttled_clock_pelt_time;
 
-	return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
+	return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_pelt_time;
 }
 #else
 static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)

kernel/sched/psi.c

@@ -1060,14 +1060,17 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 	mutex_unlock(&group->avgs_lock);
 
 	for (full = 0; full < 2; full++) {
-		unsigned long avg[3];
+		unsigned long avg[3] = { 0, };
-		u64 total;
+		u64 total = 0;
 		int w;
 
-		for (w = 0; w < 3; w++)
+		/* CPU FULL is undefined at the system level */
-			avg[w] = group->avg[res * 2 + full][w];
+		if (!(group == &psi_system && res == PSI_CPU && full)) {
-		total = div_u64(group->total[PSI_AVGS][res * 2 + full],
+			for (w = 0; w < 3; w++)
-				NSEC_PER_USEC);
+				avg[w] = group->avg[res * 2 + full][w];
+			total = div_u64(group->total[PSI_AVGS][res * 2 + full],
+					NSEC_PER_USEC);
+		}
 
 		seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
 			   full ? "full" : "some",
@@ -1117,7 +1120,8 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	t->state = state;
 	t->threshold = threshold_us * NSEC_PER_USEC;
 	t->win.size = window_us * NSEC_PER_USEC;
-	window_reset(&t->win, 0, 0, 0);
+	window_reset(&t->win, sched_clock(),
+			group->total[PSI_POLL][t->state], 0);
 
 	t->event = 0;
 	t->last_event_time = 0;

kernel/sched/rt.c

@@ -871,6 +871,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+		struct rq_flags rf;
 		int skip;
 
 		/*
@@ -885,7 +886,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		if (skip)
 			continue;
 
-		raw_spin_rq_lock(rq);
+		rq_lock(rq, &rf);
 		update_rq_clock(rq);
 
 		if (rt_rq->rt_time) {
@@ -923,7 +924,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
-		raw_spin_rq_unlock(rq);
+		rq_unlock(rq, &rf);
 	}
 
 	if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))

kernel/sched/sched.h

@@ -603,8 +603,8 @@ struct cfs_rq {
 	s64			runtime_remaining;
 
 	u64			throttled_clock;
-	u64			throttled_clock_task;
+	u64			throttled_clock_pelt;
-	u64			throttled_clock_task_time;
+	u64			throttled_clock_pelt_time;
 	int			throttled;
 	int			throttle_count;
 	struct list_head	throttled_list;
@@ -1827,12 +1827,7 @@ static inline void dirty_sched_domain_sysctl(int cpu)
 #endif
 
 extern int sched_update_scaling(void);
-
+#endif /* CONFIG_SMP */
-extern void flush_smp_call_function_from_idle(void);
-
-#else /* !CONFIG_SMP: */
-static inline void flush_smp_call_function_from_idle(void) { }
-#endif
 
 #include "stats.h"
 
@@ -2182,6 +2177,8 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
  *
  *   include/asm-generic/vmlinux.lds.h
  *
+ * *CAREFUL* they are laid out in *REVERSE* order!!!
+ *
  * Also enforce alignment on the instance, not the type, to guarantee layout.
  */
 #define DEFINE_SCHED_CLASS(name) \
@@ -2190,17 +2187,16 @@ const struct sched_class name##_sched_class \
 	__section("__" #name "_sched_class")
 
 /* Defined in include/asm-generic/vmlinux.lds.h */
-extern struct sched_class __begin_sched_classes[];
+extern struct sched_class __sched_class_highest[];
-extern struct sched_class __end_sched_classes[];
+extern struct sched_class __sched_class_lowest[];
-
-#define sched_class_highest (__end_sched_classes - 1)
-#define sched_class_lowest  (__begin_sched_classes - 1)
 
 #define for_class_range(class, _from, _to) \
-	for (class = (_from); class != (_to); class--)
+	for (class = (_from); class < (_to); class++)
 
 #define for_each_class(class) \
-	for_class_range(class, sched_class_highest, sched_class_lowest)
+	for_class_range(class, __sched_class_highest, __sched_class_lowest)
+
+#define sched_class_above(_a, _b)	((_a) < (_b))
 
 extern const struct sched_class stop_sched_class;
 extern const struct sched_class dl_sched_class;
@@ -2309,6 +2305,7 @@ extern void resched_cpu(int cpu);
 
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
 
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
@@ -2478,6 +2475,24 @@ unsigned long arch_scale_freq_capacity(int cpu)
 }
 #endif
 
+#ifdef CONFIG_SCHED_DEBUG
+/*
+ * In double_lock_balance()/double_rq_lock(), we use raw_spin_rq_lock() to
+ * acquire rq lock instead of rq_lock(). So at the end of these two functions
+ * we need to call double_rq_clock_clear_update() to clear RQCF_UPDATED of
+ * rq->clock_update_flags to avoid the WARN_DOUBLE_CLOCK warning.
+ */
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
+{
+	rq1->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+	/* rq1 == rq2 for !CONFIG_SMP, so just clear RQCF_UPDATED once. */
+#ifdef CONFIG_SMP
+	rq2->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+#endif
+}
+#else
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
+#endif
 
 #ifdef CONFIG_SMP
 
@@ -2543,14 +2558,15 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
-	if (__rq_lockp(this_rq) == __rq_lockp(busiest))
+	if (__rq_lockp(this_rq) == __rq_lockp(busiest) ||
-		return 0;
+	    likely(raw_spin_rq_trylock(busiest))) {
-
+		double_rq_clock_clear_update(this_rq, busiest);
-	if (likely(raw_spin_rq_trylock(busiest)))
 		return 0;
+	}
 
 	if (rq_order_less(this_rq, busiest)) {
 		raw_spin_rq_lock_nested(busiest, SINGLE_DEPTH_NESTING);
+		double_rq_clock_clear_update(this_rq, busiest);
 		return 0;
 	}
 
@@ -2644,6 +2660,7 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
 	BUG_ON(rq1 != rq2);
 	raw_spin_rq_lock(rq1);
 	__acquire(rq2->lock);	/* Fake it out ;) */
+	double_rq_clock_clear_update(rq1, rq2);
 }
 
 /*

kernel/sched/smp.h

@@ -7,3 +7,9 @@
 extern void sched_ttwu_pending(void *arg);
 
 extern void send_call_function_single_ipi(int cpu);
+
+#ifdef CONFIG_SMP
+extern void flush_smp_call_function_queue(void);
+#else
+static inline void flush_smp_call_function_queue(void) { }
+#endif

kernel/smp.c

@@ -96,7 +96,7 @@ static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data);
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
 
-static void flush_smp_call_function_queue(bool warn_cpu_offline);
+static void __flush_smp_call_function_queue(bool warn_cpu_offline);
 
 int smpcfd_prepare_cpu(unsigned int cpu)
 {
@@ -141,7 +141,7 @@ int smpcfd_dying_cpu(unsigned int cpu)
 	 * ensure that the outgoing CPU doesn't go offline with work
 	 * still pending.
 	 */
-	flush_smp_call_function_queue(false);
+	__flush_smp_call_function_queue(false);
 	irq_work_run();
 	return 0;
 }
@@ -544,11 +544,11 @@ void generic_smp_call_function_single_interrupt(void)
 {
 	cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->gotipi, CFD_SEQ_NOCPU,
 		      smp_processor_id(), CFD_SEQ_GOTIPI);
-	flush_smp_call_function_queue(true);
+	__flush_smp_call_function_queue(true);
 }
 
 /**
- * flush_smp_call_function_queue - Flush pending smp-call-function callbacks
+ * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks
  *
  * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an
  *		      offline CPU. Skip this check if set to 'false'.
@@ -561,7 +561,7 @@ void generic_smp_call_function_single_interrupt(void)
  * Loop through the call_single_queue and run all the queued callbacks.
  * Must be called with interrupts disabled.
  */
-static void flush_smp_call_function_queue(bool warn_cpu_offline)
+static void __flush_smp_call_function_queue(bool warn_cpu_offline)
 {
 	call_single_data_t *csd, *csd_next;
 	struct llist_node *entry, *prev;
@@ -684,8 +684,22 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 		      smp_processor_id(), CFD_SEQ_HDLEND);
 }
 
-void flush_smp_call_function_from_idle(void)
+
+/**
+ * flush_smp_call_function_queue - Flush pending smp-call-function callbacks
+ *				   from task context (idle, migration thread)
+ *
+ * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it
+ * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by
+ * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to
+ * handle queued SMP function calls before scheduling.
+ *
+ * The migration thread has to ensure that an eventually pending wakeup has
+ * been handled before it migrates a task.
+ */
+void flush_smp_call_function_queue(void)
 {
+	unsigned int was_pending;
 	unsigned long flags;
 
 	if (llist_empty(this_cpu_ptr(&call_single_queue)))
@@ -694,9 +708,11 @@ void flush_smp_call_function_from_idle(void)
 	cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->idle, CFD_SEQ_NOCPU,
 		      smp_processor_id(), CFD_SEQ_IDLE);
 	local_irq_save(flags);
-	flush_smp_call_function_queue(true);
+	/* Get the already pending soft interrupts for RT enabled kernels */
+	was_pending = local_softirq_pending();
+	__flush_smp_call_function_queue(true);
 	if (local_softirq_pending())
-		do_softirq();
+		do_softirq_post_smp_call_flush(was_pending);
 
 	local_irq_restore(flags);
 }

kernel/softirq.c

@@ -294,6 +294,19 @@ static inline void invoke_softirq(void)
 		wakeup_softirqd();
 }
 
+/*
+ * flush_smp_call_function_queue() can raise a soft interrupt in a function
+ * call. On RT kernels this is undesired and the only known functionality
+ * in the block layer which does this is disabled on RT. If soft interrupts
+ * get raised which haven't been raised before the flush, warn so it can be
+ * investigated.
+ */
+void do_softirq_post_smp_call_flush(unsigned int was_pending)
+{
+	if (WARN_ON_ONCE(was_pending != local_softirq_pending()))
+		invoke_softirq();
+}
+
 #else /* CONFIG_PREEMPT_RT */
 
 /*

kernel/stop_machine.c

@@ -535,8 +535,6 @@ void stop_machine_park(int cpu)
 	kthread_park(stopper->thread);
 }
 
-extern void sched_set_stop_task(int cpu, struct task_struct *stop);
-
 static void cpu_stop_create(unsigned int cpu)
 {
 	sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu));

kernel/trace/trace.c

@@ -4289,17 +4289,11 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		   entries,
 		   total,
 		   buf->cpu,
-#if defined(CONFIG_PREEMPT_NONE)
+		   preempt_model_none()      ? "server" :
-		   "server",
+		   preempt_model_voluntary() ? "desktop" :
-#elif defined(CONFIG_PREEMPT_VOLUNTARY)
+		   preempt_model_full()      ? "preempt" :
-		   "desktop",
+		   preempt_model_rt()        ? "preempt_rt" :
-#elif defined(CONFIG_PREEMPT)
-		   "preempt",
-#elif defined(CONFIG_PREEMPT_RT)
-		   "preempt_rt",
-#else
 		   "unknown",
-#endif
 		   /* These are reserved for later use */
 		   0, 0, 0, 0);
 #ifdef CONFIG_SMP