1 files changed, 210 insertions, 61 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f9d0515db130..8590113e4a60 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -5,6 +5,7 @@
 #ifndef _KERNEL_SCHED_SCHED_H
 #define _KERNEL_SCHED_SCHED_H
 
+#include <linux/prandom.h>
 #include <linux/sched/affinity.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/cpufreq.h>
@@ -20,7 +21,6 @@
 #include <linux/sched/task_flags.h>
 #include <linux/sched/task.h>
 #include <linux/sched/topology.h>
-
 #include <linux/atomic.h>
 #include <linux/bitmap.h>
 #include <linux/bug.h>
@@ -405,6 +405,7 @@ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s6
  * naturally thottled to once per period, avoiding high context switch
  * workloads from spamming the hrtimer program/cancel paths.
  */
+extern void dl_server_update_idle(struct sched_dl_entity *dl_se, s64 delta_exec);
 extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
 extern void dl_server_start(struct sched_dl_entity *dl_se);
 extern void dl_server_stop(struct sched_dl_entity *dl_se);
@@ -412,8 +413,6 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_pick_f pick_task);
 extern void sched_init_dl_servers(void);
 
-extern void dl_server_update_idle_time(struct rq *rq,
-		    struct task_struct *p);
 extern void fair_server_init(struct rq *rq);
 extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
 extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
@@ -682,10 +681,10 @@ struct cfs_rq {
 	s64			avg_vruntime;
 	u64			avg_load;
 
-	u64			min_vruntime;
+	u64			zero_vruntime;
 #ifdef CONFIG_SCHED_CORE
 	unsigned int		forceidle_seq;
-	u64			min_vruntime_fi;
+	u64			zero_vruntime_fi;
 #endif
 
 	struct rb_root_cached	tasks_timeline;
@@ -780,7 +779,6 @@ enum scx_rq_flags {
 	 */
 	SCX_RQ_ONLINE		= 1 << 0,
 	SCX_RQ_CAN_STOP_TICK	= 1 << 1,
-	SCX_RQ_BAL_PENDING	= 1 << 2, /* balance hasn't run yet */
 	SCX_RQ_BAL_KEEP		= 1 << 3, /* balance decided to keep current */
 	SCX_RQ_BYPASSING	= 1 << 4,
 	SCX_RQ_CLK_VALID	= 1 << 5, /* RQ clock is fresh and valid */
@@ -1120,6 +1118,8 @@ struct rq {
 	/* runqueue lock: */
 	raw_spinlock_t		__lock;
 
+	/* Per class runqueue modification mask; bits in class order. */
+	unsigned int		queue_mask;
 	unsigned int		nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;
@@ -1349,6 +1349,12 @@ static inline bool is_migration_disabled(struct task_struct *p)
 }
 
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DECLARE_PER_CPU(struct rnd_state, sched_rnd_state);
+
+static inline u32 sched_rng(void)
+{
+	return prandom_u32_state(this_cpu_ptr(&sched_rnd_state));
+}
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
 #define this_rq()		this_cpu_ptr(&runqueues)
@@ -1432,6 +1438,9 @@ static inline bool sched_core_cookie_match(struct rq *rq, struct task_struct *p)
 	if (!sched_core_enabled(rq))
 		return true;
 
+	if (rq->core->core_cookie == p->core_cookie)
+		return true;
+
 	for_each_cpu(cpu, cpu_smt_mask(cpu_of(rq))) {
 		if (!available_idle_cpu(cpu)) {
 			idle_core = false;
@@ -1443,7 +1452,7 @@ static inline bool sched_core_cookie_match(struct rq *rq, struct task_struct *p)
 	 * A CPU in an idle core is always the best choice for tasks with
 	 * cookies.
 	 */
-	return idle_core || rq->core->core_cookie == p->core_cookie;
+	return idle_core;
 }
 
 static inline bool sched_group_cookie_match(struct rq *rq,
@@ -1827,7 +1836,8 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(p->pi_lock)
 	__acquires(rq->lock);
 
-static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
+static inline void
+__task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	__releases(rq->lock)
 {
 	rq_unpin_lock(rq, rf);
@@ -1839,8 +1849,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	__releases(rq->lock)
 	__releases(p->pi_lock)
 {
-	rq_unpin_lock(rq, rf);
-	raw_spin_rq_unlock(rq);
+	__task_rq_unlock(rq, p, rf);
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
@@ -1849,6 +1858,11 @@ DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct,
 		    task_rq_unlock(_T->rq, _T->lock, &_T->rf),
 		    struct rq *rq; struct rq_flags rf)
 
+DEFINE_LOCK_GUARD_1(__task_rq_lock, struct task_struct,
+		    _T->rq = __task_rq_lock(_T->lock, &_T->rf),
+		    __task_rq_unlock(_T->rq, _T->lock, &_T->rf),
+		    struct rq *rq; struct rq_flags rf)
+
 static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
@@ -2343,8 +2357,7 @@ extern const u32		sched_prio_to_wmult[40];
 /*
  * {de,en}queue flags:
  *
- * DEQUEUE_SLEEP  - task is no longer runnable
- * ENQUEUE_WAKEUP - task just became runnable
+ * SLEEP/WAKEUP - task is no-longer/just-became runnable
  *
  * SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks
  *                are in a known state which allows modification. Such pairs
@@ -2357,34 +2370,46 @@ extern const u32		sched_prio_to_wmult[40];
  *
  * MIGRATION - p->on_rq == TASK_ON_RQ_MIGRATING (used for DEADLINE)
  *
+ * DELAYED - de/re-queue a sched_delayed task
+ *
+ * CLASS - going to update p->sched_class; makes sched_change call the
+ *         various switch methods.
+ *
  * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
  * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
  * ENQUEUE_MIGRATED  - the task was migrated during wakeup
  * ENQUEUE_RQ_SELECTED - ->select_task_rq() was called
  *
+ * XXX SAVE/RESTORE in combination with CLASS doesn't really make sense, but
+ * SCHED_DEADLINE seems to rely on this for now.
  */
 
-#define DEQUEUE_SLEEP		0x01 /* Matches ENQUEUE_WAKEUP */
-#define DEQUEUE_SAVE		0x02 /* Matches ENQUEUE_RESTORE */
-#define DEQUEUE_MOVE		0x04 /* Matches ENQUEUE_MOVE */
-#define DEQUEUE_NOCLOCK		0x08 /* Matches ENQUEUE_NOCLOCK */
-#define DEQUEUE_SPECIAL		0x10
-#define DEQUEUE_MIGRATING	0x100 /* Matches ENQUEUE_MIGRATING */
-#define DEQUEUE_DELAYED		0x200 /* Matches ENQUEUE_DELAYED */
-#define DEQUEUE_THROTTLE	0x800
-
-#define ENQUEUE_WAKEUP		0x01
-#define ENQUEUE_RESTORE		0x02
-#define ENQUEUE_MOVE		0x04
-#define ENQUEUE_NOCLOCK		0x08
-
-#define ENQUEUE_HEAD		0x10
-#define ENQUEUE_REPLENISH	0x20
-#define ENQUEUE_MIGRATED	0x40
-#define ENQUEUE_INITIAL		0x80
-#define ENQUEUE_MIGRATING	0x100
-#define ENQUEUE_DELAYED		0x200
-#define ENQUEUE_RQ_SELECTED	0x400
+#define DEQUEUE_SLEEP		0x0001 /* Matches ENQUEUE_WAKEUP */
+#define DEQUEUE_SAVE		0x0002 /* Matches ENQUEUE_RESTORE */
+#define DEQUEUE_MOVE		0x0004 /* Matches ENQUEUE_MOVE */
+#define DEQUEUE_NOCLOCK		0x0008 /* Matches ENQUEUE_NOCLOCK */
+
+#define DEQUEUE_MIGRATING	0x0010 /* Matches ENQUEUE_MIGRATING */
+#define DEQUEUE_DELAYED		0x0020 /* Matches ENQUEUE_DELAYED */
+#define DEQUEUE_CLASS		0x0040 /* Matches ENQUEUE_CLASS */
+
+#define DEQUEUE_SPECIAL		0x00010000
+#define DEQUEUE_THROTTLE	0x00020000
+
+#define ENQUEUE_WAKEUP		0x0001
+#define ENQUEUE_RESTORE		0x0002
+#define ENQUEUE_MOVE		0x0004
+#define ENQUEUE_NOCLOCK		0x0008
+
+#define ENQUEUE_MIGRATING	0x0010
+#define ENQUEUE_DELAYED		0x0020
+#define ENQUEUE_CLASS		0x0040
+
+#define ENQUEUE_HEAD		0x00010000
+#define ENQUEUE_REPLENISH	0x00020000
+#define ENQUEUE_MIGRATED	0x00040000
+#define ENQUEUE_INITIAL		0x00080000
+#define ENQUEUE_RQ_SELECTED	0x00100000
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -2401,16 +2426,61 @@ struct sched_class {
 #ifdef CONFIG_UCLAMP_TASK
 	int uclamp_enabled;
 #endif
+	/*
+	 * idle:  0
+	 * ext:   1
+	 * fair:  2
+	 * rt:    4
+	 * dl:    8
+	 * stop: 16
+	 */
+	unsigned int queue_mask;
 
+	/*
+	 * move_queued_task/activate_task/enqueue_task: rq->lock
+	 * ttwu_do_activate/activate_task/enqueue_task: rq->lock
+	 * wake_up_new_task/activate_task/enqueue_task: task_rq_lock
+	 * ttwu_runnable/enqueue_task: task_rq_lock
+	 * proxy_task_current: rq->lock
+	 * sched_change_end
+	 */
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
+	/*
+	 * move_queued_task/deactivate_task/dequeue_task: rq->lock
+	 * __schedule/block_task/dequeue_task: rq->lock
+	 * proxy_task_current: rq->lock
+	 * wait_task_inactive: task_rq_lock
+	 * sched_change_begin
+	 */
 	bool (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
+
+	/*
+	 * do_sched_yield: rq->lock
+	 */
 	void (*yield_task)   (struct rq *rq);
+	/*
+	 * yield_to: rq->lock (double)
+	 */
 	bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
 
+	/*
+	 * move_queued_task: rq->lock
+	 * __migrate_swap_task: rq->lock
+	 * ttwu_do_activate: rq->lock
+	 * ttwu_runnable: task_rq_lock
+	 * wake_up_new_task: task_rq_lock
+	 */
 	void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
 
+	/*
+	 * schedule/pick_next_task/prev_balance: rq->lock
+	 */
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-	struct task_struct *(*pick_task)(struct rq *rq);
+
+	/*
+	 * schedule/pick_next_task: rq->lock
+	 */
+	struct task_struct *(*pick_task)(struct rq *rq, struct rq_flags *rf);
 	/*
 	 * Optional! When implemented pick_next_task() should be equivalent to:
 	 *
@@ -2420,55 +2490,123 @@ struct sched_class {
 	 *       set_next_task_first(next);
 	 *   }
 	 */
-	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev);
+	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev,
+					      struct rq_flags *rf);
 
+	/*
+	 * sched_change:
+	 * __schedule: rq->lock
+	 */
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
+	/*
+	 * select_task_rq: p->pi_lock
+	 * sched_exec: p->pi_lock
+	 */
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
 
+	/*
+	 * set_task_cpu: p->pi_lock || rq->lock (ttwu like)
+	 */
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
+	/*
+	 * ttwu_do_activate: rq->lock
+	 * wake_up_new_task: task_rq_lock
+	 */
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);
 
+	/*
+	 * do_set_cpus_allowed: task_rq_lock + sched_change
+	 */
 	void (*set_cpus_allowed)(struct task_struct *p, struct affinity_context *ctx);
 
+	/*
+	 * sched_set_rq_{on,off}line: rq->lock
+	 */
 	void (*rq_online)(struct rq *rq);
 	void (*rq_offline)(struct rq *rq);
 
+	/*
+	 * push_cpu_stop: p->pi_lock && rq->lock
+	 */
 	struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
 
+	/*
+	 * hrtick: rq->lock
+	 * sched_tick: rq->lock
+	 * sched_tick_remote: rq->lock
+	 */
 	void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
+	/*
+	 * sched_cgroup_fork: p->pi_lock
+	 */
 	void (*task_fork)(struct task_struct *p);
+	/*
+	 * finish_task_switch: no locks
+	 */
 	void (*task_dead)(struct task_struct *p);
 
 	/*
-	 * The switched_from() call is allowed to drop rq->lock, therefore we
-	 * cannot assume the switched_from/switched_to pair is serialized by
-	 * rq->lock. They are however serialized by p->pi_lock.
+	 * sched_change
+	 */
+	void (*switching_from)(struct rq *this_rq, struct task_struct *task);
+	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
+	void (*switching_to)  (struct rq *this_rq, struct task_struct *task);
+	void (*switched_to)   (struct rq *this_rq, struct task_struct *task);
+	u64  (*get_prio)     (struct rq *this_rq, struct task_struct *task);
+	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
+			      u64 oldprio);
+
+	/*
+	 * set_load_weight: task_rq_lock + sched_change
+	 * __setscheduler_parms: task_rq_lock + sched_change
 	 */
-	void (*switching_to) (struct rq *this_rq, struct task_struct *task);
-	void (*switched_from)(struct rq *this_rq, struct task_struct *task);
-	void (*switched_to)  (struct rq *this_rq, struct task_struct *task);
 	void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
 			      const struct load_weight *lw);
-	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
-			      int oldprio);
 
+	/*
+	 * sched_rr_get_interval: task_rq_lock
+	 */
 	unsigned int (*get_rr_interval)(struct rq *rq,
 					struct task_struct *task);
 
+	/*
+	 * task_sched_runtime: task_rq_lock
+	 */
 	void (*update_curr)(struct rq *rq);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	/*
+	 * sched_change_group: task_rq_lock + sched_change
+	 */
 	void (*task_change_group)(struct task_struct *p);
 #endif
 
 #ifdef CONFIG_SCHED_CORE
+	/*
+	 * pick_next_task: rq->lock
+	 * try_steal_cookie: rq->lock (double)
+	 */
 	int (*task_is_throttled)(struct task_struct *p, int cpu);
 #endif
 };
 
+/*
+ * Does not nest; only used around sched_class::pick_task() rq-lock-breaks.
+ */
+static inline void rq_modified_clear(struct rq *rq)
+{
+	rq->queue_mask = 0;
+}
+
+static inline bool rq_modified_above(struct rq *rq, const struct sched_class * class)
+{
+	unsigned int mask = class->queue_mask;
+	return rq->queue_mask & ~((mask << 1) - 1);
+}
+
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->donor != prev);
@@ -2580,8 +2718,9 @@ static inline bool sched_fair_runnable(struct rq *rq)
 	return rq->cfs.nr_queued > 0;
 }
 
-extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-extern struct task_struct *pick_task_idle(struct rq *rq);
+extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev,
+					       struct rq_flags *rf);
+extern struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf);
 
 #define SCA_CHECK		0x01
 #define SCA_MIGRATE_DISABLE	0x02
@@ -2611,7 +2750,7 @@ static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu)
 static inline cpumask_t *alloc_user_cpus_ptr(int node)
 {
 	/*
-	 * See do_set_cpus_allowed() above for the rcu_head usage.
+	 * See set_cpus_allowed_force() above for the rcu_head usage.
 	 */
 	int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
 
@@ -3805,32 +3944,42 @@ extern void set_load_weight(struct task_struct *p, bool update_load);
 extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
 extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags);
 
-extern void check_class_changing(struct rq *rq, struct task_struct *p,
-				 const struct sched_class *prev_class);
-extern void check_class_changed(struct rq *rq, struct task_struct *p,
-				const struct sched_class *prev_class,
-				int oldprio);
-
 extern struct balance_callback *splice_balance_callbacks(struct rq *rq);
 extern void balance_callbacks(struct rq *rq, struct balance_callback *head);
 
-#ifdef CONFIG_SCHED_CLASS_EXT
 /*
- * Used by SCX in the enable/disable paths to move tasks between sched_classes
- * and establish invariants.
+ * The 'sched_change' pattern is the safe, easy and slow way of changing a
+ * task's scheduling properties. It dequeues a task, such that the scheduler
+ * is fully unaware of it; at which point its properties can be modified;
+ * after which it is enqueued again.
+ *
+ * Typically this must be called while holding task_rq_lock, since most/all
+ * properties are serialized under those locks. There is currently one
+ * exception to this rule in sched/ext which only holds rq->lock.
+ */
+
+/*
+ * This structure is a temporary, used to preserve/convey the queueing state
+ * of the task between sched_change_begin() and sched_change_end(). Ensuring
+ * the task's queueing state is idempotent across the operation.
  */
-struct sched_enq_and_set_ctx {
+struct sched_change_ctx {
+	u64			prio;
 	struct task_struct	*p;
-	int			queue_flags;
+	int			flags;
 	bool			queued;
 	bool			running;
 };
 
-void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
-			    struct sched_enq_and_set_ctx *ctx);
-void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx);
+struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags);
+void sched_change_end(struct sched_change_ctx *ctx);
 
-#endif /* CONFIG_SCHED_CLASS_EXT */
+DEFINE_CLASS(sched_change, struct sched_change_ctx *,
+	     sched_change_end(_T),
+	     sched_change_begin(p, flags),
+	     struct task_struct *p, unsigned int flags)
+
+DEFINE_CLASS_IS_UNCONDITIONAL(sched_change)
 
 #include "ext.h"