Merge tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - Revert the printk format based wchan() symbol resolution as it can
   leak the raw value in case that the symbol is not resolvable.

 - Make wchan() more robust and work with all kind of unwinders by
   enforcing that the task stays blocked while unwinding is in progress.

 - Prevent sched_fork() from accessing an invalid sched_task_group

 - Improve asymmetric packing logic

 - Extend scheduler statistics to RT and DL scheduling classes and add
   statistics for bandwith burst to the SCHED_FAIR class.

 - Properly account SCHED_IDLE entities

 - Prevent a potential deadlock when initial priority is assigned to a
   newly created kthread. A recent change to plug a race between cpuset
   and __sched_setscheduler() introduced a new lock dependency which is
   now triggered. Break the lock dependency chain by moving the priority
   assignment to the thread function.

 - Fix the idle time reporting in /proc/uptime for NOHZ enabled systems.

 - Improve idle balancing in general and especially for NOHZ enabled
   systems.

 - Provide proper interfaces for live patching so it does not have to
   fiddle with scheduler internals.

 - Add cluster aware scheduling support.

 - A small set of tweaks for RT (irqwork, wait_task_inactive(), various
   scheduler options and delaying mmdrop)

 - The usual small tweaks and improvements all over the place

* tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits)
  sched/fair: Cleanup newidle_balance
  sched/fair: Remove sysctl_sched_migration_cost condition
  sched/fair: Wait before decaying max_newidle_lb_cost
  sched/fair: Skip update_blocked_averages if we are defering load balance
  sched/fair: Account update_blocked_averages in newidle_balance cost
  x86: Fix __get_wchan() for !STACKTRACE
  sched,x86: Fix L2 cache mask
  sched/core: Remove rq_relock()
  sched: Improve wake_up_all_idle_cpus() take #2
  irq_work: Also rcuwait for !IRQ_WORK_HARD_IRQ on PREEMPT_RT
  irq_work: Handle some irq_work in a per-CPU thread on PREEMPT_RT
  irq_work: Allow irq_work_sync() to sleep if irq_work() no IRQ support.
  sched/rt: Annotate the RT balancing logic irqwork as IRQ_WORK_HARD_IRQ
  sched: Add cluster scheduler level for x86
  sched: Add cluster scheduler level in core and related Kconfig for ARM64
  topology: Represent clusters of CPUs within a die
  sched: Disable -Wunused-but-set-variable
  sched: Add wrapper for get_wchan() to keep task blocked
  x86: Fix get_wchan() to support the ORC unwinder
  proc: Use task_is_running() for wchan in /proc/$pid/stat
  ...

1 files changed, 13 insertions, 19 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 66128dfc05fb..56ff343d4119 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -368,6 +368,7 @@ struct cfs_bandwidth {
 	u64			quota;
 	u64			runtime;
 	u64			burst;
+	u64			runtime_snap;
 	s64			hierarchical_quota;
 
 	u8			idle;
@@ -380,7 +381,9 @@ struct cfs_bandwidth {
 	/* Statistics: */
 	int			nr_periods;
 	int			nr_throttled;
+	int			nr_burst;
 	u64			throttled_time;
+	u64			burst_time;
 #endif
 };
 
@@ -529,6 +532,7 @@ struct cfs_rq {
 	struct load_weight	load;
 	unsigned int		nr_running;
 	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
+	unsigned int		idle_nr_running;   /* SCHED_IDLE */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
 	u64			exec_clock;
@@ -1253,11 +1257,6 @@ extern void sched_core_dequeue(struct rq *rq, struct task_struct *p);
 extern void sched_core_get(void);
 extern void sched_core_put(void);
 
-extern unsigned long sched_core_alloc_cookie(void);
-extern void sched_core_put_cookie(unsigned long cookie);
-extern unsigned long sched_core_get_cookie(unsigned long cookie);
-extern unsigned long sched_core_update_cookie(struct task_struct *p, unsigned long cookie);
-
 #else /* !CONFIG_SCHED_CORE */
 
 static inline bool sched_core_enabled(struct rq *rq)
@@ -1421,11 +1420,6 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
 
 extern void update_rq_clock(struct rq *rq);
 
-static inline u64 __rq_clock_broken(struct rq *rq)
-{
-	return READ_ONCE(rq->clock);
-}
-
 /*
  * rq::clock_update_flags bits
  *
@@ -1621,14 +1615,6 @@ rq_lock(struct rq *rq, struct rq_flags *rf)
 }
 
 static inline void
-rq_relock(struct rq *rq, struct rq_flags *rf)
-	__acquires(rq->lock)
-{
-	raw_spin_rq_lock(rq);
-	rq_repin_lock(rq, rf);
-}
-
-static inline void
 rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
@@ -1808,6 +1794,7 @@ struct sched_group {
 	unsigned int		group_weight;
 	struct sched_group_capacity *sgc;
 	int			asym_prefer_cpu;	/* CPU of highest priority in group */
+	int			flags;
 
 	/*
 	 * The CPUs this group covers.
@@ -2401,6 +2388,7 @@ extern const_debug unsigned int sysctl_sched_migration_cost;
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_latency;
 extern unsigned int sysctl_sched_min_granularity;
+extern unsigned int sysctl_sched_idle_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern int sysctl_resched_latency_warn_ms;
 extern int sysctl_resched_latency_warn_once;
@@ -2708,12 +2696,18 @@ extern void cfs_bandwidth_usage_dec(void);
 #define NOHZ_BALANCE_KICK_BIT	0
 #define NOHZ_STATS_KICK_BIT	1
 #define NOHZ_NEWILB_KICK_BIT	2
+#define NOHZ_NEXT_KICK_BIT	3
 
+/* Run rebalance_domains() */
 #define NOHZ_BALANCE_KICK	BIT(NOHZ_BALANCE_KICK_BIT)
+/* Update blocked load */
 #define NOHZ_STATS_KICK		BIT(NOHZ_STATS_KICK_BIT)
+/* Update blocked load when entering idle */
 #define NOHZ_NEWILB_KICK	BIT(NOHZ_NEWILB_KICK_BIT)
+/* Update nohz.next_balance */
+#define NOHZ_NEXT_KICK		BIT(NOHZ_NEXT_KICK_BIT)
 
-#define NOHZ_KICK_MASK	(NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
+#define NOHZ_KICK_MASK	(NOHZ_BALANCE_KICK | NOHZ_STATS_KICK | NOHZ_NEXT_KICK)
 
 #define nohz_flags(cpu)	(&cpu_rq(cpu)->nohz_flags)