4 files changed, 79 insertions, 8 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8a0d5466c7be..ae20dbb885d6 100644
--- a/include/linux/cgroup-defs.h
+++ b/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);
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 7ee7ed5de722..6dbc5a1bf6a8 100644
--- a/include/linux/rbtree_augmented.h
+++ b/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)
  *
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 609bde814cb0..177b3f3676ef 100644
--- a/include/linux/sched.h
+++ b/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);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index dd35ce28bb90..a23af225c898 100644
--- a/include/linux/sched/task.h
+++ b/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))