Merge tag 'sched-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - The biggest change is introduction of a new iteration of the
   SCHED_FAIR interactivity code: the EEVDF ("Earliest Eligible Virtual
   Deadline First") scheduler

   EEVDF too is a virtual-time scheduler, with two parameters (weight
   and relative deadline), compared to CFS that had weight only. It
   completely reworks the base scheduler: placement, preemption, picking
   -- everything

   LWN.net, as usual, has a terrific writeup about EEVDF:

      https://lwn.net/Articles/925371/

   Preemption (both tick and wakeup) is driven by testing against a
   fresh pick. Because the tree is now effectively an interval tree, and
   the selection is no longer the 'leftmost' task, over-scheduling is
   less of a problem. A lot of the CFS heuristics are removed or
   replaced by more natural latency-space parameters & constructs

   In terms of expected performance regressions: we will and can fix
   everything where a 'good' workload misbehaves with the new scheduler,
   but EEVDF inevitably changes workload scheduling in a binary fashion,
   hopefully for the better in the overwhelming majority of cases, but
   in some cases it won't, especially in adversarial loads that got
   lucky with the previous code, such as some variants of hackbench. We
   are trying hard to err on the side of fixing all performance
   regressions, but we expect some inevitable post-release iterations of
   that process

 - Improve load-balancing on hybrid x86 systems: enable cluster
   scheduling (again)

 - Improve & fix bandwidth-scheduling on nohz systems

 - Improve bandwidth-throttling

 - Use lock guards to simplify and de-goto-ify control flow

 - Misc improvements, cleanups and fixes

* tag 'sched-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  sched/eevdf/doc: Modify the documented knob to base_slice_ns as well
  sched/eevdf: Curb wakeup-preemption
  sched: Simplify sched_core_cpu_{starting,deactivate}()
  sched: Simplify try_steal_cookie()
  sched: Simplify sched_tick_remote()
  sched: Simplify sched_exec()
  sched: Simplify ttwu()
  sched: Simplify wake_up_if_idle()
  sched: Simplify: migrate_swap_stop()
  sched: Simplify sysctl_sched_uclamp_handler()
  sched: Simplify get_nohz_timer_target()
  sched/rt: sysctl_sched_rr_timeslice show default timeslice after reset
  sched/rt: Fix sysctl_sched_rr_timeslice intial value
  sched/fair: Block nohz tick_stop when cfs bandwidth in use
  sched, cgroup: Restore meaning to hierarchical_quota
  MAINTAINERS: Add Peter explicitly to the psi section
  sched/psi: Select KERNFS as needed
  sched/topology: Align group flags when removing degenerate domain
  sched/fair: remove util_est boosting
  sched/fair: Propagate enqueue flags into place_entity()
  ...

1 files changed, 50 insertions, 7 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 48d0be005f08..11a88469b55e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -454,11 +454,12 @@ extern void unregister_fair_sched_group(struct task_group *tg);
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
 			struct sched_entity *parent);
-extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
 
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
 extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
+extern bool cfs_task_bw_constrained(struct task_struct *p);
 
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
@@ -494,6 +495,7 @@ static inline void set_task_rq_fair(struct sched_entity *se,
 #else /* CONFIG_CGROUP_SCHED */
 
 struct cfs_bandwidth { };
+static inline bool cfs_task_bw_constrained(struct task_struct *p) { return false; }
 
 #endif	/* CONFIG_CGROUP_SCHED */
 
@@ -548,6 +550,9 @@ struct cfs_rq {
 	unsigned int		idle_nr_running;   /* SCHED_IDLE */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
+	s64			avg_vruntime;
+	u64			avg_load;
+
 	u64			exec_clock;
 	u64			min_vruntime;
 #ifdef CONFIG_SCHED_CORE
@@ -567,8 +572,6 @@ struct cfs_rq {
 	 */
 	struct sched_entity	*curr;
 	struct sched_entity	*next;
-	struct sched_entity	*last;
-	struct sched_entity	*skip;
 
 #ifdef	CONFIG_SCHED_DEBUG
 	unsigned int		nr_spread_over;
@@ -636,6 +639,8 @@ struct cfs_rq {
 	u64			throttled_clock;
 	u64			throttled_clock_pelt;
 	u64			throttled_clock_pelt_time;
+	u64			throttled_clock_self;
+	u64			throttled_clock_self_time;
 	int			throttled;
 	int			throttle_count;
 	struct list_head	throttled_list;
@@ -1700,6 +1705,21 @@ rq_unlock(struct rq *rq, struct rq_flags *rf)
 	raw_spin_rq_unlock(rq);
 }
 
+DEFINE_LOCK_GUARD_1(rq_lock, struct rq,
+		    rq_lock(_T->lock, &_T->rf),
+		    rq_unlock(_T->lock, &_T->rf),
+		    struct rq_flags rf)
+
+DEFINE_LOCK_GUARD_1(rq_lock_irq, struct rq,
+		    rq_lock_irq(_T->lock, &_T->rf),
+		    rq_unlock_irq(_T->lock, &_T->rf),
+		    struct rq_flags rf)
+
+DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
+		    rq_lock_irqsave(_T->lock, &_T->rf),
+		    rq_unlock_irqrestore(_T->lock, &_T->rf),
+		    struct rq_flags rf)
+
 static inline struct rq *
 this_rq_lock_irq(struct rq_flags *rf)
 	__acquires(rq->lock)
@@ -1882,6 +1902,7 @@ struct sched_group {
 	atomic_t		ref;
 
 	unsigned int		group_weight;
+	unsigned int		cores;
 	struct sched_group_capacity *sgc;
 	int			asym_prefer_cpu;	/* CPU of highest priority in group */
 	int			flags;
@@ -2196,6 +2217,7 @@ extern const u32		sched_prio_to_wmult[40];
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif
+#define ENQUEUE_INITIAL		0x80
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -2500,11 +2522,9 @@ extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
+extern unsigned int sysctl_sched_base_slice;
+
 #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;
 
@@ -2610,6 +2630,12 @@ static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
 static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
 #endif
 
+#define DEFINE_LOCK_GUARD_2(name, type, _lock, _unlock, ...)		\
+__DEFINE_UNLOCK_GUARD(name, type, _unlock, type *lock2; __VA_ARGS__) \
+static inline class_##name##_t class_##name##_constructor(type *lock, type *lock2) \
+{ class_##name##_t _t = { .lock = lock, .lock2 = lock2 }, *_T = &_t;	\
+  _lock; return _t; }
+
 #ifdef CONFIG_SMP
 
 static inline bool rq_order_less(struct rq *rq1, struct rq *rq2)
@@ -2739,6 +2765,16 @@ static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
 	raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
 }
 
+static inline void double_raw_unlock(raw_spinlock_t *l1, raw_spinlock_t *l2)
+{
+	raw_spin_unlock(l1);
+	raw_spin_unlock(l2);
+}
+
+DEFINE_LOCK_GUARD_2(double_raw_spinlock, raw_spinlock_t,
+		    double_raw_lock(_T->lock, _T->lock2),
+		    double_raw_unlock(_T->lock, _T->lock2))
+
 /*
  * double_rq_unlock - safely unlock two runqueues
  *
@@ -2796,6 +2832,10 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 
 #endif
 
+DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
+		    double_rq_lock(_T->lock, _T->lock2),
+		    double_rq_unlock(_T->lock, _T->lock2))
+
 extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 
@@ -3483,4 +3523,7 @@ static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
 static inline void init_sched_mm_cid(struct task_struct *t) { }
 #endif
 
+extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
+extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
 #endif /* _KERNEL_SCHED_SCHED_H */