24 files changed, 3087 insertions, 323 deletions

diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index 988573a9a38..277f494c2a9 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -105,14 +105,17 @@ static void cpu_idle_loop(void)
 				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
-			/*
-			 * We need to test and propagate the TIF_NEED_RESCHED
-			 * bit here because we might not have send the
-			 * reschedule IPI to idle tasks.
-			 */
-			if (tif_need_resched())
-				set_preempt_need_resched();
 		}
+
+		/*
+		 * Since we fell out of the loop above, we know
+		 * TIF_NEED_RESCHED must be set, propagate it into
+		 * PREEMPT_NEED_RESCHED.
+		 *
+		 * This is required because for polling idle loops we will
+		 * not have had an IPI to fold the state for us.
+		 */
+		preempt_set_need_resched();
 		tick_nohz_idle_exit();
 		schedule_preempt_disabled();
 	}
diff --git a/kernel/fork.c b/kernel/fork.c
index dfa736c98d1..294189fc7ac 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1087,8 +1087,10 @@ static void rt_mutex_init_task(struct task_struct *p)
 {
 	raw_spin_lock_init(&p->pi_lock);
 #ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&p->pi_waiters);
+	p->pi_waiters = RB_ROOT;
+	p->pi_waiters_leftmost = NULL;
 	p->pi_blocked_on = NULL;
+	p->pi_top_task = NULL;
 #endif
 }
 
@@ -1311,7 +1313,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(clone_flags, p);
+	retval = sched_fork(clone_flags, p);
+	if (retval)
+		goto bad_fork_cleanup_policy;
 
 	retval = perf_event_init_task(p);
 	if (retval)
@@ -1403,13 +1407,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->tgid = p->pid;
 	}
 
-	p->pdeath_signal = 0;
-	p->exit_state = 0;
-
 	p->nr_dirtied = 0;
 	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
 	p->dirty_paused_when = 0;
 
+	p->pdeath_signal = 0;
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 1ddc4498f1e..44a1261cb9f 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2426,6 +2426,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * code while we sleep on uaddr.
 	 */
 	debug_rt_mutex_init_waiter(&rt_waiter);
+	RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&rt_waiter.tree_entry);
 	rt_waiter.task = NULL;
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 383319bae3f..09094361dce 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -46,6 +46,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
@@ -1610,7 +1611,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	unsigned long slack;
 
 	slack = current->timer_slack_ns;
-	if (rt_task(current))
+	if (dl_task(current) || rt_task(current))
 		slack = 0;
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 13b243a323f..49b2ed3dced 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -24,7 +24,7 @@
 #include <linux/kallsyms.h>
 #include <linux/syscalls.h>
 #include <linux/interrupt.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
 #include <linux/fs.h>
 #include <linux/debug_locks.h>
 
@@ -57,7 +57,7 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
 
 void rt_mutex_debug_task_free(struct task_struct *task)
 {
-	DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters));
 	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
 }
 
@@ -154,16 +154,12 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
 void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 {
 	memset(waiter, 0x11, sizeof(*waiter));
-	plist_node_init(&waiter->list_entry, MAX_PRIO);
-	plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
 	waiter->deadlock_task_pid = NULL;
 }
 
 void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 {
 	put_pid(waiter->deadlock_task_pid);
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 	memset(waiter, 0x22, sizeof(*waiter));
 }
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec1cb6..2e960a2bab8 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 
 #include "rtmutex_common.h"
@@ -91,10 +92,107 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 }
 #endif
 
+static inline int
+rt_mutex_waiter_less(struct rt_mutex_waiter *left,
+		     struct rt_mutex_waiter *right)
+{
+	if (left->prio < right->prio)
+		return 1;
+
+	/*
+	 * If both waiters have dl_prio(), we check the deadlines of the
+	 * associated tasks.
+	 * If left waiter has a dl_prio(), and we didn't return 1 above,
+	 * then right waiter has a dl_prio() too.
+	 */
+	if (dl_prio(left->prio))
+		return (left->task->dl.deadline < right->task->dl.deadline);
+
+	return 0;
+}
+
+static void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &lock->waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		lock->waiters_leftmost = &waiter->tree_entry;
+
+	rb_link_node(&waiter->tree_entry, parent, link);
+	rb_insert_color(&waiter->tree_entry, &lock->waiters);
+}
+
+static void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->tree_entry))
+		return;
+
+	if (lock->waiters_leftmost == &waiter->tree_entry)
+		lock->waiters_leftmost = rb_next(&waiter->tree_entry);
+
+	rb_erase(&waiter->tree_entry, &lock->waiters);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+}
+
+static void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &task->pi_waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		task->pi_waiters_leftmost = &waiter->pi_tree_entry;
+
+	rb_link_node(&waiter->pi_tree_entry, parent, link);
+	rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
+}
+
+static void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+		return;
+
+	if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
+		task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);
+
+	rb_erase(&waiter->pi_tree_entry, &task->pi_waiters);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+}
+
 /*
- * Calculate task priority from the waiter list priority
+ * Calculate task priority from the waiter tree priority
  *
- * Return task->normal_prio when the waiter list is empty or when
+ * Return task->normal_prio when the waiter tree is empty or when
  * the waiter is not allowed to do priority boosting
  */
 int rt_mutex_getprio(struct task_struct *task)
@@ -102,10 +200,18 @@ int rt_mutex_getprio(struct task_struct *task)
 	if (likely(!task_has_pi_waiters(task)))
 		return task->normal_prio;
 
-	return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+	return min(task_top_pi_waiter(task)->prio,
 		   task->normal_prio);
 }
 
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+	if (likely(!task_has_pi_waiters(task)))
+		return NULL;
+
+	return task_top_pi_waiter(task)->task;
+}
+
 /*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *
@@ -115,7 +221,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task)
 {
 	int prio = rt_mutex_getprio(task);
 
-	if (task->prio != prio)
+	if (task->prio != prio || dl_prio(prio))
 		rt_mutex_setprio(task, prio);
 }
 
@@ -233,7 +339,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * When deadlock detection is off then we check, if further
 	 * priority adjustment is necessary.
 	 */
-	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+	if (!detect_deadlock && waiter->prio == task->prio)
 		goto out_unlock_pi;
 
 	lock = waiter->lock;
@@ -254,9 +360,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	top_waiter = rt_mutex_top_waiter(lock);
 
 	/* Requeue the waiter */
-	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->list_entry.prio = task->prio;
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
+	waiter->prio = task->prio;
+	rt_mutex_enqueue(lock, waiter);
 
 	/* Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -280,17 +386,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		/* Boost the owner */
-		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, top_waiter);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
 	} else if (top_waiter == waiter) {
 		/* Deboost the owner */
-		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 	}
 
@@ -355,7 +459,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	 * 3) it is top waiter
 	 */
 	if (rt_mutex_has_waiters(lock)) {
-		if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+		if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
 			if (!waiter || waiter != rt_mutex_top_waiter(lock))
 				return 0;
 		}
@@ -369,7 +473,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 
 		/* remove the queued waiter. */
 		if (waiter) {
-			plist_del(&waiter->list_entry, &lock->wait_list);
+			rt_mutex_dequeue(lock, waiter);
 			task->pi_blocked_on = NULL;
 		}
 
@@ -379,8 +483,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 		 */
 		if (rt_mutex_has_waiters(lock)) {
 			top = rt_mutex_top_waiter(lock);
-			top->pi_list_entry.prio = top->list_entry.prio;
-			plist_add(&top->pi_list_entry, &task->pi_waiters);
+			rt_mutex_enqueue_pi(task, top);
 		}
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
@@ -416,13 +519,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
-	plist_node_init(&waiter->list_entry, task->prio);
-	plist_node_init(&waiter->pi_list_entry, task->prio);
+	waiter->prio = task->prio;
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_enqueue(lock, waiter);
 
 	task->pi_blocked_on = waiter;
 
@@ -433,8 +535,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
-		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
-		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, top_waiter);
+		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
@@ -486,7 +588,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 * boosted mode and go back to normal after releasing
 	 * lock->wait_lock.
 	 */
-	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+	rt_mutex_dequeue_pi(current, waiter);
 
 	rt_mutex_set_owner(lock, NULL);
 
@@ -510,7 +612,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
-	plist_del(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
@@ -521,13 +623,13 @@ static void remove_waiter(struct rt_mutex *lock,
 
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, waiter);
 
 		if (rt_mutex_has_waiters(lock)) {
 			struct rt_mutex_waiter *next;
 
 			next = rt_mutex_top_waiter(lock);
-			plist_add(&next->pi_list_entry, &owner->pi_waiters);
+			rt_mutex_enqueue_pi(owner, next);
 		}
 		__rt_mutex_adjust_prio(owner);
 
@@ -537,8 +639,6 @@ static void remove_waiter(struct rt_mutex *lock,
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
-	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
 	if (!chain_walk)
 		return;
 
@@ -565,7 +665,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->list_entry.prio == task->prio) {
+	if (!waiter || (waiter->prio == task->prio &&
+			!dl_prio(task->prio))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
@@ -638,6 +739,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	int ret = 0;
 
 	debug_rt_mutex_init_waiter(&waiter);
+	RB_CLEAR_NODE(&waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&waiter.tree_entry);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -904,7 +1007,8 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name)
 {
 	lock->owner = NULL;
 	raw_spin_lock_init(&lock->wait_lock);
-	plist_head_init(&lock->wait_list);
+	lock->waiters = RB_ROOT;
+	lock->waiters_leftmost = NULL;
 
 	debug_rt_mutex_init(lock, name);
 }
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 53a66c85261..7431a9c86f3 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -40,13 +40,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock);
  * This is the control structure for tasks blocked on a rt_mutex,
  * which is allocated on the kernel stack on of the blocked task.
  *
- * @list_entry:		pi node to enqueue into the mutex waiters list
- * @pi_list_entry:	pi node to enqueue into the mutex owner waiters list
+ * @tree_entry:		pi node to enqueue into the mutex waiters tree
+ * @pi_tree_entry:	pi node to enqueue into the mutex owner waiters tree
  * @task:		task reference to the blocked task
  */
 struct rt_mutex_waiter {
-	struct plist_node	list_entry;
-	struct plist_node	pi_list_entry;
+	struct rb_node          tree_entry;
+	struct rb_node          pi_tree_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
@@ -54,14 +54,15 @@ struct rt_mutex_waiter {
 	struct pid		*deadlock_task_pid;
 	struct rt_mutex		*deadlock_lock;
 #endif
+	int prio;
 };
 
 /*
- * Various helpers to access the waiters-plist:
+ * Various helpers to access the waiters-tree:
  */
 static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
 {
-	return !plist_head_empty(&lock->wait_list);
+	return !RB_EMPTY_ROOT(&lock->waiters);
 }
 
 static inline struct rt_mutex_waiter *
@@ -69,8 +70,8 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *w;
 
-	w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
-			       list_entry);
+	w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
+		     tree_entry);
 	BUG_ON(w->lock != lock);
 
 	return w;
@@ -78,14 +79,14 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 
 static inline int task_has_pi_waiters(struct task_struct *p)
 {
-	return !plist_head_empty(&p->pi_waiters);
+	return !RB_EMPTY_ROOT(&p->pi_waiters);
 }
 
 static inline struct rt_mutex_waiter *
 task_top_pi_waiter(struct task_struct *p)
 {
-	return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
-				  pi_list_entry);
+	return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
+			pi_tree_entry);
 }
 
 /*
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 7b621409cf1..9a95c8c2af2 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,9 +11,10 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c3ae1446461..6bd6a6731b2 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -26,9 +26,10 @@
  * at 0 on boot (but people really shouldn't rely on that).
  *
  * cpu_clock(i)       -- can be used from any context, including NMI.
- * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
  * local_clock()      -- is cpu_clock() on the current cpu.
  *
+ * sched_clock_cpu(i)
+ *
  * How:
  *
  * The implementation either uses sched_clock() when
@@ -50,15 +51,6 @@
  * Furthermore, explicit sleep and wakeup hooks allow us to account for time
  * that is otherwise invisible (TSC gets stopped).
  *
- *
- * Notes:
- *
- * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
- * like cpufreq interrupts that can change the base clock (TSC) multiplier
- * and cause funny jumps in time -- although the filtering provided by
- * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
- * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
- * sched_clock().
  */
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
@@ -66,6 +58,8 @@
 #include <linux/percpu.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/static_key.h>
+#include <linux/workqueue.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -82,7 +76,37 @@ EXPORT_SYMBOL_GPL(sched_clock);
 __read_mostly int sched_clock_running;
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__read_mostly int sched_clock_stable;
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+
+int sched_clock_stable(void)
+{
+	if (static_key_false(&__sched_clock_stable))
+		return false;
+	return true;
+}
+
+void set_sched_clock_stable(void)
+{
+	if (!sched_clock_stable())
+		static_key_slow_dec(&__sched_clock_stable);
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+	/* XXX worry about clock continuity */
+	if (sched_clock_stable())
+		static_key_slow_inc(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+	if (keventd_up())
+		schedule_work(&sched_clock_work);
+	else
+		__clear_sched_clock_stable(&sched_clock_work);
+}
 
 struct sched_clock_data {
 	u64			tick_raw;
@@ -242,20 +266,20 @@ u64 sched_clock_cpu(int cpu)
 	struct sched_clock_data *scd;
 	u64 clock;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return sched_clock();
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
+	preempt_disable();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
+	preempt_enable();
 
 	return clock;
 }
@@ -265,7 +289,7 @@ void sched_clock_tick(void)
 	struct sched_clock_data *scd;
 	u64 now, now_gtod;
 
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return;
 
 	if (unlikely(!sched_clock_running))
@@ -316,14 +340,10 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
  */
 u64 cpu_clock(int cpu)
 {
-	u64 clock;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	clock = sched_clock_cpu(cpu);
-	local_irq_restore(flags);
+	if (static_key_false(&__sched_clock_stable))
+		return sched_clock_cpu(cpu);
 
-	return clock;
+	return sched_clock();
 }
 
 /*
@@ -335,14 +355,10 @@ u64 cpu_clock(int cpu)
  */
 u64 local_clock(void)
 {
-	u64 clock;
-	unsigned long flags;
+	if (static_key_false(&__sched_clock_stable))
+		return sched_clock_cpu(raw_smp_processor_id());
 
-	local_irq_save(flags);
-	clock = sched_clock_cpu(smp_processor_id());
-	local_irq_restore(flags);
-
-	return clock;
+	return sched_clock();
 }
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
@@ -362,12 +378,12 @@ u64 sched_clock_cpu(int cpu)
 
 u64 cpu_clock(int cpu)
 {
-	return sched_clock_cpu(cpu);
+	return sched_clock();
 }
 
 u64 local_clock(void)
 {
-	return sched_clock_cpu(0);
+	return sched_clock();
 }
 
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a88f4a485c5..36c951b7eef 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -296,8 +296,6 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
-
-
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -899,7 +897,9 @@ static inline int normal_prio(struct task_struct *p)
 {
 	int prio;
 
-	if (task_has_rt_policy(p))
+	if (task_has_dl_policy(p))
+		prio = MAX_DL_PRIO-1;
+	else if (task_has_rt_policy(p))
 		prio = MAX_RT_PRIO-1 - p->rt_priority;
 	else
 		prio = __normal_prio(p);
@@ -945,7 +945,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		if (prev_class->switched_from)
 			prev_class->switched_from(rq, p);
 		p->sched_class->switched_to(rq, p);
-	} else if (oldprio != p->prio)
+	} else if (oldprio != p->prio || dl_task(p))
 		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
@@ -1499,8 +1499,7 @@ void scheduler_ipi(void)
 	 * TIF_NEED_RESCHED remotely (for the first time) will also send
 	 * this IPI.
 	 */
-	if (tif_need_resched())
-		set_preempt_need_resched();
+	preempt_fold_need_resched();
 
 	if (llist_empty(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
@@ -1717,6 +1716,13 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
+	RB_CLEAR_NODE(&p->dl.rb_node);
+	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	p->dl.dl_runtime = p->dl.runtime = 0;
+	p->dl.dl_deadline = p->dl.deadline = 0;
+	p->dl.dl_period = 0;
+	p->dl.flags = 0;
+
 	INIT_LIST_HEAD(&p->rt.run_list);
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -1768,7 +1774,7 @@ void set_numabalancing_state(bool enabled)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(unsigned long clone_flags, struct task_struct *p)
+int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
 	int cpu = get_cpu();
@@ -1790,7 +1796,7 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Revert to default priority/policy on fork if requested.
 	 */
 	if (unlikely(p->sched_reset_on_fork)) {
-		if (task_has_rt_policy(p)) {
+		if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
 			p->policy = SCHED_NORMAL;
 			p->static_prio = NICE_TO_PRIO(0);
 			p->rt_priority = 0;
@@ -1807,8 +1813,14 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	if (!rt_prio(p->prio))
+	if (dl_prio(p->prio)) {
+		put_cpu();
+		return -EAGAIN;
+	} else if (rt_prio(p->prio)) {
+		p->sched_class = &rt_sched_class;
+	} else {
 		p->sched_class = &fair_sched_class;
+	}
 
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
@@ -1834,11 +1846,124 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 	init_task_preempt_count(p);
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
 
 	put_cpu();
+	return 0;
+}
+
+unsigned long to_ratio(u64 period, u64 runtime)
+{
+	if (runtime == RUNTIME_INF)
+		return 1ULL << 20;
+
+	/*
+	 * Doing this here saves a lot of checks in all
+	 * the calling paths, and returning zero seems
+	 * safe for them anyway.
+	 */
+	if (period == 0)
+		return 0;
+
+	return div64_u64(runtime << 20, period);
+}
+
+#ifdef CONFIG_SMP
+inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->rd->dl_bw;
 }
 
+static inline int dl_bw_cpus(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	int cpus = 0;
+
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cpus++;
+
+	return cpus;
+}
+#else
+inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	return 1;
+}
+#endif
+
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+}
+
+/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+static int dl_overflow(struct task_struct *p, int policy,
+		       const struct sched_attr *attr)
+{
+
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	u64 period = attr->sched_period;
+	u64 runtime = attr->sched_runtime;
+	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+	int cpus, err = -1;
+
+	if (new_bw == p->dl.dl_bw)
+		return 0;
+
+	/*
+	 * Either if a task, enters, leave, or stays -deadline but changes
+	 * its parameters, we may need to update accordingly the total
+	 * allocated bandwidth of the container.
+	 */
+	raw_spin_lock(&dl_b->lock);
+	cpus = dl_bw_cpus(task_cpu(p));
+	if (dl_policy(policy) && !task_has_dl_policy(p) &&
+	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
+		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		err = 0;
+	}
+	raw_spin_unlock(&dl_b->lock);
+
+	return err;
+}
+
+extern void init_dl_bw(struct dl_bw *dl_b);
+
 /*
  * wake_up_new_task - wake up a newly created task for the first time.
  *
@@ -2003,6 +2128,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (unlikely(prev_state == TASK_DEAD)) {
 		task_numa_free(prev);
 
+		if (prev->sched_class->task_dead)
+			prev->sched_class->task_dead(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
@@ -2296,7 +2424,7 @@ void scheduler_tic