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()
  ...

Author: torvalds

Documentation/scheduler/sched-design-CFS.rst

@@ -94,7 +94,7 @@ other HZ detail.  Thus the CFS scheduler has no notion of "timeslices" in the
 way the previous scheduler had, and has no heuristics whatsoever.  There is
 only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
 
-   /sys/kernel/debug/sched/min_granularity_ns
+   /sys/kernel/debug/sched/base_slice_ns
 
 which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
 "server" (i.e., good batching) workloads.  It defaults to a setting suitable

MAINTAINERS

@@ -17057,6 +17057,7 @@ F:	drivers/net/ppp/pptp.c
 PRESSURE STALL INFORMATION (PSI)
 M:	Johannes Weiner <[email protected]>
 M:	Suren Baghdasaryan <[email protected]>
+R:	Peter Ziljstra <[email protected]>
 S:	Maintained
 F:	include/linux/psi*
 F:	kernel/sched/psi.c

arch/x86/kernel/smpboot.c

@@ -624,14 +624,9 @@ static void __init build_sched_topology(void)
 	};
 #endif
 #ifdef CONFIG_SCHED_CLUSTER
-	/*
-	 * For now, skip the cluster domain on Hybrid.
-	 */
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
-		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS)
-		};
-	}
+	x86_topology[i++] = (struct sched_domain_topology_level){
+		cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS)
+	};
 #endif
 #ifdef CONFIG_SCHED_MC
 	x86_topology[i++] = (struct sched_domain_topology_level){

include/linux/cgroup-defs.h

@@ -661,6 +661,8 @@ struct cgroup_subsys {
 	void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu);
 	int (*css_extra_stat_show)(struct seq_file *seq,
 				   struct cgroup_subsys_state *css);
+	int (*css_local_stat_show)(struct seq_file *seq,
+				   struct cgroup_subsys_state *css);
 
 	int (*can_attach)(struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_taskset *tset);

include/linux/rbtree_augmented.h

@@ -60,6 +60,32 @@ rb_insert_augmented_cached(struct rb_node *node,
 	rb_insert_augmented(node, &root->rb_root, augment);
 }
 
+static __always_inline struct rb_node *
+rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree,
+			bool (*less)(struct rb_node *, const struct rb_node *),
+			const struct rb_augment_callbacks *augment)
+{
+	struct rb_node **link = &tree->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	bool leftmost = true;
+
+	while (*link) {
+		parent = *link;
+		if (less(node, parent)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = false;
+		}
+	}
+
+	rb_link_node(node, parent, link);
+	augment->propagate(parent, NULL); /* suboptimal */
+	rb_insert_augmented_cached(node, tree, leftmost, augment);
+
+	return leftmost ? node : NULL;
+}
+
 /*
  * Template for declaring augmented rbtree callbacks (generic case)
  *

include/linux/sched.h

@@ -75,14 +75,14 @@ struct user_event_mm;
  * Task state bitmask. NOTE! These bits are also
  * encoded in fs/proc/array.c: get_task_state().
  *
- * We have two separate sets of flags: task->state
+ * We have two separate sets of flags: task->__state
  * is about runnability, while task->exit_state are
  * about the task exiting. Confusing, but this way
  * modifying one set can't modify the other one by
  * mistake.
  */
 
-/* Used in tsk->state: */
+/* Used in tsk->__state: */
 #define TASK_RUNNING			0x00000000
 #define TASK_INTERRUPTIBLE		0x00000001
 #define TASK_UNINTERRUPTIBLE		0x00000002
@@ -92,7 +92,7 @@ struct user_event_mm;
 #define EXIT_DEAD			0x00000010
 #define EXIT_ZOMBIE			0x00000020
 #define EXIT_TRACE			(EXIT_ZOMBIE | EXIT_DEAD)
-/* Used in tsk->state again: */
+/* Used in tsk->__state again: */
 #define TASK_PARKED			0x00000040
 #define TASK_DEAD			0x00000080
 #define TASK_WAKEKILL			0x00000100
@@ -173,7 +173,7 @@ struct user_event_mm;
 #endif
 
 /*
- * set_current_state() includes a barrier so that the write of current->state
+ * set_current_state() includes a barrier so that the write of current->__state
  * is correctly serialised wrt the caller's subsequent test of whether to
  * actually sleep:
  *
@@ -196,9 +196,9 @@ struct user_event_mm;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
  * where wake_up_state()/try_to_wake_up() executes a full memory barrier before
- * accessing p->state.
+ * accessing p->__state.
  *
- * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
+ * Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
  * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
  *
@@ -549,13 +549,18 @@ struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
 	struct rb_node			run_node;
+	u64				deadline;
+	u64				min_deadline;
+
 	struct list_head		group_node;
 	unsigned int			on_rq;
 
 	u64				exec_start;
 	u64				sum_exec_runtime;
-	u64				vruntime;
 	u64				prev_sum_exec_runtime;
+	u64				vruntime;
+	s64				vlag;
+	u64				slice;
 
 	u64				nr_migrations;
 
@@ -2433,9 +2438,11 @@ extern void sched_core_free(struct task_struct *tsk);
 extern void sched_core_fork(struct task_struct *p);
 extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type,
 				unsigned long uaddr);
+extern int sched_core_idle_cpu(int cpu);
 #else
 static inline void sched_core_free(struct task_struct *tsk) { }
 static inline void sched_core_fork(struct task_struct *p) { }
+static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); }
 #endif
 
 extern void sched_set_stop_task(int cpu, struct task_struct *stop);

include/linux/sched/task.h

@@ -118,11 +118,47 @@ static inline struct task_struct *get_task_struct(struct task_struct *t)
 }
 
 extern void __put_task_struct(struct task_struct *t);
+extern void __put_task_struct_rcu_cb(struct rcu_head *rhp);
 
 static inline void put_task_struct(struct task_struct *t)
 {
-	if (refcount_dec_and_test(&t->usage))
+	if (!refcount_dec_and_test(&t->usage))
+		return;
+
+	/*
+	 * In !RT, it is always safe to call __put_task_struct().
+	 * Under RT, we can only call it in preemptible context.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
+		static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP);
+
+		lock_map_acquire_try(&put_task_map);
 		__put_task_struct(t);
+		lock_map_release(&put_task_map);
+		return;
+	}
+
+	/*
+	 * under PREEMPT_RT, we can't call put_task_struct
+	 * in atomic context because it will indirectly
+	 * acquire sleeping locks.
+	 *
+	 * call_rcu() will schedule delayed_put_task_struct_rcu()
+	 * to be called in process context.
+	 *
+	 * __put_task_struct() is called when
+	 * refcount_dec_and_test(&t->usage) succeeds.
+	 *
+	 * This means that it can't "conflict" with
+	 * put_task_struct_rcu_user() which abuses ->rcu the same
+	 * way; rcu_users has a reference so task->usage can't be
+	 * zero after rcu_users 1 -> 0 transition.
+	 *
+	 * delayed_free_task() also uses ->rcu, but it is only called
+	 * when it fails to fork a process. Therefore, there is no
+	 * way it can conflict with put_task_struct().
+	 */
+	call_rcu(&t->rcu, __put_task_struct_rcu_cb);
 }
 
 DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T))

init/Kconfig

@@ -629,6 +629,7 @@ config TASK_IO_ACCOUNTING
 
 config PSI
 	bool "Pressure stall information tracking"
+	select KERNFS
 	help
 	  Collect metrics that indicate how overcommitted the CPU, memory,
 	  and IO capacity are in the system.

kernel/cgroup/cgroup.c

@@ -3685,6 +3685,36 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 	return ret;
 }
 
+static int __maybe_unused cgroup_local_stat_show(struct seq_file *seq,
+						 struct cgroup *cgrp, int ssid)
+{
+	struct cgroup_subsys *ss = cgroup_subsys[ssid];
+	struct cgroup_subsys_state *css;
+	int ret;
+
+	if (!ss->css_local_stat_show)
+		return 0;
+
+	css = cgroup_tryget_css(cgrp, ss);
+	if (!css)
+		return 0;
+
+	ret = ss->css_local_stat_show(seq, css);
+	css_put(css);
+	return ret;
+}
+
+static int cpu_local_stat_show(struct seq_file *seq, void *v)
+{
+	struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
+	int ret = 0;
+
+#ifdef CONFIG_CGROUP_SCHED
+	ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id);
+#endif
+	return ret;
+}
+
 #ifdef CONFIG_PSI
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
@@ -5235,6 +5265,10 @@ static struct cftype cgroup_base_files[] = {
 		.name = "cpu.stat",
 		.seq_show = cpu_stat_show,
 	},
+	{
+		.name = "cpu.stat.local",
+		.seq_show = cpu_local_stat_show,
+	},
 	{ }	/* terminate */
 };
 

kernel/fork.c

@@ -985,6 +985,14 @@ void __put_task_struct(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(__put_task_struct);
 
+void __put_task_struct_rcu_cb(struct rcu_head *rhp)
+{
+	struct task_struct *task = container_of(rhp, struct task_struct, rcu);
+
+	__put_task_struct(task);
+}
+EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb);
+
 void __init __weak arch_task_cache_init(void) { }
 
 /*