20 files changed, 273 insertions, 93 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 274450efea90..9c51ec3f0f44 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3862,10 +3862,8 @@ static void _free_event(struct perf_event *event)
 	if (event->ctx)
 		put_ctx(event->ctx);
 
-	if (event->pmu) {
-		exclusive_event_destroy(event);
-		module_put(event->pmu->module);
-	}
+	exclusive_event_destroy(event);
+	module_put(event->pmu->module);
 
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 5c2c355aa97f..4a7ec0c6c88c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -148,18 +148,18 @@ static inline void free_task_struct(struct task_struct *tsk)
 }
 #endif
 
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
 {
 }
 
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
 
 /*
  * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
  * kmemcache based allocator.
  */
 # if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 						  int node)
 {
 	struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
@@ -172,33 +172,33 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 	return page ? page_address(page) : NULL;
 }
 
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
 {
-	struct page *page = virt_to_page(ti);
+	struct page *page = virt_to_page(stack);
 
 	memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
 				    -(1 << THREAD_SIZE_ORDER));
 	__free_kmem_pages(page, THREAD_SIZE_ORDER);
 }
 # else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
 
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 						  int node)
 {
-	return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+	return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
 }
 
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(unsigned long *stack)
 {
-	kmem_cache_free(thread_info_cache, ti);
+	kmem_cache_free(thread_stack_cache, stack);
 }
 
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
 {
-	thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+	thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
 					      THREAD_SIZE, 0, NULL);
-	BUG_ON(thread_info_cache == NULL);
+	BUG_ON(thread_stack_cache == NULL);
 }
 # endif
 #endif
@@ -221,9 +221,9 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
 {
-	struct zone *zone = page_zone(virt_to_page(ti));
+	struct zone *zone = page_zone(virt_to_page(stack));
 
 	mod_zone_page_state(zone, NR_KERNEL_STACK, account);
 }
@@ -231,8 +231,8 @@ static void account_kernel_stack(struct thread_info *ti, int account)
 void free_task(struct task_struct *tsk)
 {
 	account_kernel_stack(tsk->stack, -1);
-	arch_release_thread_info(tsk->stack);
-	free_thread_info(tsk->stack);
+	arch_release_thread_stack(tsk->stack);
+	free_thread_stack(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
 	put_seccomp_filter(tsk);
@@ -343,7 +343,7 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
-	struct thread_info *ti;
+	unsigned long *stack;
 	int err;
 
 	if (node == NUMA_NO_NODE)
@@ -352,15 +352,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	if (!tsk)
 		return NULL;
 
-	ti = alloc_thread_info_node(tsk, node);
-	if (!ti)
+	stack = alloc_thread_stack_node(tsk, node);
+	if (!stack)
 		goto free_tsk;
 
 	err = arch_dup_task_struct(tsk, orig);
 	if (err)
-		goto free_ti;
+		goto free_stack;
 
-	tsk->stack = ti;
+	tsk->stack = stack;
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -392,14 +392,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
 
-	account_kernel_stack(ti, 1);
+	account_kernel_stack(stack, 1);
 
 	kcov_task_init(tsk);
 
 	return tsk;
 
-free_ti:
-	free_thread_info(ti);
+free_stack:
+	free_thread_stack(stack);
 free_tsk:
 	free_task_struct(tsk);
 	return NULL;
diff --git a/kernel/futex.c b/kernel/futex.c
index ee25f5ba4aca..33664f70e2d2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -469,7 +469,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct page *page;
+	struct page *page, *tail;
 	struct address_space *mapping;
 	int err, ro = 0;
 
@@ -530,7 +530,15 @@ again:
 	 * considered here and page lock forces unnecessarily serialization
 	 * From this point on, mapping will be re-verified if necessary and
 	 * page lock will be acquired only if it is unavoidable
-	 */
+	 *
+	 * Mapping checks require the head page for any compound page so the
+	 * head page and mapping is looked up now. For anonymous pages, it
+	 * does not matter if the page splits in the future as the key is
+	 * based on the address. For filesystem-backed pages, the tail is
+	 * required as the index of the page determines the key. For
+	 * base pages, there is no tail page and tail == page.
+	 */
+	tail = page;
 	page = compound_head(page);
 	mapping = READ_ONCE(page->mapping);
 
@@ -654,7 +662,7 @@ again:
 
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
 		key->shared.inode = inode;
-		key->shared.pgoff = basepage_index(page);
+		key->shared.pgoff = basepage_index(tail);
 		rcu_read_unlock();
 	}
 
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 05254eeb4b4e..4b353e0be121 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key);
 
 void static_key_slow_inc(struct static_key *key)
 {
+	int v, v1;
+
 	STATIC_KEY_CHECK_USE();
-	if (atomic_inc_not_zero(&key->enabled))
-		return;
+
+	/*
+	 * Careful if we get concurrent static_key_slow_inc() calls;
+	 * later calls must wait for the first one to _finish_ the
+	 * jump_label_update() process.  At the same time, however,
+	 * the jump_label_update() call below wants to see
+	 * static_key_enabled(&key) for jumps to be updated properly.
+	 *
+	 * So give a special meaning to negative key->enabled: it sends
+	 * static_key_slow_inc() down the slow path, and it is non-zero
+	 * so it counts as "enabled" in jump_label_update().  Note that
+	 * atomic_inc_unless_negative() checks >= 0, so roll our own.
+	 */
+	for (v = atomic_read(&key->enabled); v > 0; v = v1) {
+		v1 = atomic_cmpxchg(&key->enabled, v, v + 1);
+		if (likely(v1 == v))
+			return;
+	}
 
 	jump_label_lock();
-	if (atomic_inc_return(&key->enabled) == 1)
+	if (atomic_read(&key->enabled) == 0) {
+		atomic_set(&key->enabled, -1);
 		jump_label_update(key);
+		atomic_set(&key->enabled, 1);
+	} else {
+		atomic_inc(&key->enabled);
+	}
 	jump_label_unlock();
 }
 EXPORT_SYMBOL_GPL(static_key_slow_inc);
@@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc);
 static void __static_key_slow_dec(struct static_key *key,
 		unsigned long rate_limit, struct delayed_work *work)
 {
+	/*
+	 * The negative count check is valid even when a negative
+	 * key->enabled is in use by static_key_slow_inc(); a
+	 * __static_key_slow_dec() before the first static_key_slow_inc()
+	 * returns is unbalanced, because all other static_key_slow_inc()
+	 * instances block while the update is in progress.
+	 */
 	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
 		WARN(atomic_read(&key->enabled) < 0,
 		     "jump label: negative count!\n");
diff --git a/kernel/kcov.c b/kernel/kcov.c
index a02f2dddd1d7..8d44b3fea9d0 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -264,7 +264,12 @@ static const struct file_operations kcov_fops = {
 
 static int __init kcov_init(void)
 {
-	if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) {
+	/*
+	 * The kcov debugfs file won't ever get removed and thus,
+	 * there is no need to protect it against removal races. The
+	 * use of debugfs_create_file_unsafe() is actually safe here.
+	 */
+	if (!debugfs_create_file_unsafe("kcov", 0600, NULL, NULL, &kcov_fops)) {
 		pr_err("failed to create kcov in debugfs\n");
 		return -ENOMEM;
 	}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 3ef3736002d8..9c951fade415 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -49,21 +49,21 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
 }
 
 void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
-			    struct thread_info *ti)
+			    struct task_struct *task)
 {
 	SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
 
 	/* Mark the current thread as blocked on the lock: */
-	ti->task->blocked_on = waiter;
+	task->blocked_on = waiter;
 }
 
 void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
-			 struct thread_info *ti)
+			 struct task_struct *task)
 {
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
-	DEBUG_LOCKS_WARN_ON(waiter->task != ti->task);
-	DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter);
-	ti->task->blocked_on = NULL;
+	DEBUG_LOCKS_WARN_ON(waiter->task != task);
+	DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
+	task->blocked_on = NULL;
 
 	list_del_init(&waiter->list);
 	waiter->task = NULL;
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 0799fd3e4cfa..d06ae3bb46c5 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -20,9 +20,9 @@ extern void debug_mutex_wake_waiter(struct mutex *lock,
 extern void debug_mutex_free_waiter(struct mutex_waiter *waiter);
 extern void debug_mutex_add_waiter(struct mutex *lock,
 				   struct mutex_waiter *waiter,
-				   struct thread_info *ti);
+				   struct task_struct *task);
 extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
-				struct thread_info *ti);
+				struct task_struct *task);
 extern void debug_mutex_unlock(struct mutex *lock);
 extern void debug_mutex_init(struct mutex *lock, const char *name,
 			     struct lock_class_key *key);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index e364b424b019..a70b90db3909 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
 	if (!hold_ctx)
 		return 0;
 
-	if (unlikely(ctx == hold_ctx))
-		return -EALREADY;
-
 	if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
 	    (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	unsigned long flags;
 	int ret;
 
+	if (use_ww_ctx) {
+		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+			return -EALREADY;
+	}
+
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
@@ -534,7 +537,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
-	debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
+	debug_mutex_add_waiter(lock, &waiter, task);
 
 	/* add waiting tasks to the end of the waitqueue (FIFO): */
 	list_add_tail(&waiter.list, &lock->wait_list);
@@ -581,7 +584,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	}
 	__set_task_state(task, TASK_RUNNING);
 
-	mutex_remove_waiter(lock, &waiter, current_thread_info());
+	mutex_remove_waiter(lock, &waiter, task);
 	/* set it to 0 if there are no waiters left: */
 	if (likely(list_empty(&lock->wait_list)))
 		atomic_set(&lock->count, 0);
@@ -602,7 +605,7 @@ skip_wait:
 	return 0;
 
 err:
-	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
+	mutex_remove_waiter(lock, &waiter, task);
 	spin_unlock_mutex(&lock->wait_lock, flags);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, 1, ip);
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 5cda397607f2..a68bae5e852a 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -13,7 +13,7 @@
 		do { spin_lock(lock); (void)(flags); } while (0)
 #define spin_unlock_mutex(lock, flags) \
 		do { spin_unlock(lock); (void)(flags); } while (0)
-#define mutex_remove_waiter(lock, waiter, ti) \
+#define mutex_remove_waiter(lock, waiter, task) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ce2f75e32ae1..5fc8c311b8fe 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -267,6 +267,66 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ *  (1) clear_pending_set_locked():	*,1,0 -> *,0,1
+ *
+ *  (2) set_locked():			t,0,0 -> t,0,1 ; t != 0
+ *      atomic_cmpxchg_relaxed():	t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+	u32 val;
+
+	for (;;) {
+		val = atomic_read(&lock->val);
+
+		if (!val) /* not locked, we're done */
+			goto done;
+
+		if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+			break;
+
+		/* not locked, but pending, wait until we observe the lock */
+		cpu_relax();
+	}
+
+	/* any unlock is good */
+	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+		cpu_relax();
+
+done:
+	smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**
diff --git a/kernel/power/process.c b/kernel/power/process.c
index df058bed53ce..0c2ee9761d57 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -146,6 +146,18 @@ int freeze_processes(void)
 	if (!error && !oom_killer_disable())
 		error = -EBUSY;
 
+	/*
+	 * There is a hard to fix race between oom_reaper kernel thread
+	 * and oom_killer_disable. oom_reaper calls exit_oom_victim
+	 * before the victim reaches exit_mm so try to freeze all the tasks
+	 * again and catch such a left over task.
+	 */
+	if (!error) {
+		pr_info("Double checking all user space processes after OOM killer disable... ");
+		error = try_to_freeze_tasks(true);
+		pr_cont("\n");
+	}
+
 	if (error)
 		thaw_processes();
 	return error;
diff --git a/kernel/relay.c b/kernel/relay.c
index 074994bcfa9b..04d7cf3ef8cf 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -614,6 +614,7 @@ free_bufs:
 
 	kref_put(&chan->kref, relay_destroy_channel);
 	mutex_unlock(&relay_channels_mutex);
+	kfree(chan);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(relay_open);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f2cae4620c7..51d7105f529a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1536,7 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	for (;;) {
 		/* Any allowed, online CPU? */
 		for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
-			if (!cpu_active(dest_cpu))
+			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
+				continue;
+			if (!cpu_online(dest_cpu))
 				continue;
 			goto out;
 		}
@@ -2253,9 +2255,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 #endif
 #endif
 
+#ifdef CONFIG_SCHEDSTATS
+
 DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+static bool __initdata __sched_schedstats = false;
 
-#ifdef CONFIG_SCHEDSTATS
 static void set_schedstats(bool enabled)
 {
 	if (enabled)
@@ -2278,11 +2282,16 @@ static int __init setup_schedstats(char *str)
 	if (!str)
 		goto out;
 
+	/*
+	 * This code is called before jump labels have been set up, so we can't
+	 * change the static branch directly just yet.  Instead set a temporary
+	 * variable so init_schedstats() can do it later.
+	 */
 	if (!strcmp(str, "enable")) {
-		set_schedstats(true);
+		__sched_schedstats = true;
 		ret = 1;
 	} else if (!strcmp(str, "disable")) {
-		set_schedstats(false);
+		__sched_schedstats = false;
 		ret = 1;
 	}
 out:
@@ -2293,6 +2302,11 @@ out:
 }
 __setup("schedstats=", setup_schedstats);
 
+static void __init init_schedstats(void)
+{
+	set_schedstats(__sched_schedstats);
+}
+
 #ifdef CONFIG_PROC_SYSCTL
 int sysctl_schedstats(struct ctl_table *table, int write,
 			 void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -2313,8 +2327,10 @@ int sysctl_schedstats(struct ctl_table *table, int write,
 		set_schedstats(state);
 	return err;
 }
-#endif
-#endif
+#endif /* CONFIG_PROC_SYSCTL */
+#else  /* !CONFIG_SCHEDSTATS */
+static inline void init_schedstats(void) {}
+#endif /* CONFIG_SCHEDSTATS */
 
 /*
  * fork()/clone()-time setup:
@@ -2521,10 +2537,9 @@ void wake_up_new_task(struct task_struct *p)
 	 */
 	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
-	/* Post initialize new task's util average when its cfs_rq is set */
+	rq = __task_rq_lock(p, &rf);
 	post_init_entity_util_avg(&p->se);
 
-	rq = __task_rq_lock(p, &rf);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
@@ -3156,7 +3171,8 @@ static noinline void __schedule_bug(struct task_struct *prev)
 static inline void schedule_debug(struct task_struct *prev)
 {
 #ifdef CONFIG_SCHED_STACK_END_CHECK
-	BUG_ON(task_stack_end_corrupted(prev));
+	if (task_stack_end_corrupted(prev))
+		panic("corrupted stack end detected inside scheduler\n");
 #endif
 
 	if (unlikely(in_atomic_preempt_off())) {
@@ -5133,14 +5149,16 @@ void show_state_filter(unsigned long state_filter)
 		/*
 		 * reset the NMI-timeout, listing all files on a slow
 		 * console might take a lot of time:
+		 * Also, reset softlockup watchdogs on all CPUs, because
+		 * another CPU might be blocked waiting for us to process
+		 * an IPI.
 		 */
 		touch_nmi_watchdog();
+		touch_all_softlockup_watchdogs();
 		if (!state_filter || (p->state & state_filter))
 			sched_show_task(p);
 	}
 
-	touch_all_softlockup_watchdogs();
-
 #ifdef CONFIG_SCHED_DEBUG
 	if (!state_filter)
 		sysrq_sched_debug_show();
@@ -7487,6 +7505,8 @@ void __init sched_init(void)
 #endif
 	init_sched_fair_class();
 
+	init_schedstats();
+
 	scheduler_running = 1;
 }
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index cf905f655ba1..0368c393a336 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -427,19 +427,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		SPLIT_NS(p->se.vruntime),
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
-#ifdef CONFIG_SCHEDSTATS
-	if (schedstat_enabled()) {
-		SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-			SPLIT_NS(p->se.statistics.wait_sum),
-			SPLIT_NS(p->se.sum_exec_runtime),
-			SPLIT_NS(p->se.statistics.sum_sleep_runtime));
-	}
-#else
+
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		0LL, 0L,
+		SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		0LL, 0L);
-#endif
+		SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime)));
+
 #ifdef CONFIG_NUMA_BALANCING
 	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 218f8e83db73..bdcbeea90c95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2904,6 +2904,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 	}
 }
 
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(*ptr) val = (_val);				\
+	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
+	res = var - val;					\
+	if (res > var)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
@@ -2913,15 +2930,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
-		sa->load_avg = max_t(long, sa->load_avg - r, 0);
-		sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->load_avg, r);
+		sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
 		removed_load = 1;
 	}
 
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
 		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
-		sa->util_avg = max_t(long, sa->util_avg - r, 0);
-		sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->util_avg, r);
+		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
 		removed_util = 1;
 	}
 
@@ -2994,10 +3011,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 			  &se->avg, se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
-	cfs_rq->avg.load_sum = max_t(s64,  cfs_rq->avg.load_sum - se->avg.load_sum, 0);
-	cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
-	cfs_rq->avg.util_sum = max_t(s32,  cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -3246,7 +3263,7 @@ static inline void check_schedstat_required(void)
 			trace_sched_stat_iowait_enabled()  ||
 			trace_sched_stat_blocked_enabled() ||
 			trace_sched_stat_runtime_enabled())  {
-		pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
 			     "stat_blocked and stat_runtime require the "
 			     "kernel parameter schedstats=enabled or "
 			     "kernel.sched_schedstats=1\n");
@@ -4185,6 +4202,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 	if (!cfs_bandwidth_used())
 		return;
 
+	/* Synchronize hierarchical throttle counter: */
+	if (unlikely(!cfs_rq->throttle_uptodate)) {
+		struct rq *rq = rq_of(cfs_rq);
+		struct cfs_rq *pcfs_rq;
+		struct task_group *tg;
+
+		cfs_rq->throttle_uptodate = 1;
+
+		/* Get closest up-to-date node, because leaves go first: */
+		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+			if (pcfs_rq->throttle_uptodate)
+				break;
+		}
+		if (tg) {
+			cfs_rq->throttle_count = pcfs_rq->throttle_count;
+			cfs_rq->throttled_clock_task = rq_clock_task(rq);
+		}
+	}
+
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
@@ -4500,15 +4537,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
 			/*
 			 * Bias pick_next to pick a task from this cfs_rq, as
 			 * p is sleeping when it is within its sched_slice.
 			 */
-			if (task_sleep && parent_entity(se))
-				set_next_buddy(parent_entity(se));
-
-			/* avoid re-evaluating load for this entity */
-			se = parent_entity(se);
+			if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+				set_next_buddy(se);
 			break;
 		}
 		flags |= DEQUEUE_SLEEP;
@@ -8496,8 +8532,9 @@ void free_fair_sched_group(struct task_group *tg)
 
 int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
-	struct cfs_rq *cfs_rq;
 	struct sched_entity *se;
+	struct cfs_rq *cfs_rq;
+	struct rq *rq;
 	int i;
 
 	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8512,6 +8549,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
@@ -8525,7 +8564,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
+
+		raw_spin_lock_irq(&rq->lock);
 		post_init_entity_util_avg(se);
+		raw_spin_unlock_irq(&rq->lock);
 	}
 
 	return 1;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index bd12c6c714ec..c5aeedf4e93a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -127,7 +127,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  */
 static void cpuidle_idle_call(void)
 {
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_device *dev = cpuidle_get_device();
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int next_state, entered_state;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 72f1f3087b04..7cbeb92a1cb9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -437,7 +437,7 @@ struct cfs_rq {
 
 	u64 throttled_clock, throttled_clock_task;
 	u64 throttled_clock_task_time;
-	int throttled, throttle_count;
+	int throttled, throttle_count, throttle_uptodate;
 	struct list_head throttled_list;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 70b3b6a20fb0..78955cbea31c 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -33,6 +33,8 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 # define schedstat_inc(rq, field)	do { if (schedstat_enabled()) { (rq)->field++; } } while (0)
 # define schedstat_add(rq, field, amt)	do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0)
 # define schedstat_set(var, val)	do { if (schedstat_enabled()) { var = (val); } } while (0)
+# define schedstat_val(rq, field)	((schedstat_enabled()) ? (rq)->field : 0)
+
 #else /* !CONFIG_SCHEDSTATS */
 static inline void
 rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
@@ -47,6 +49,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 # define schedstat_inc(rq, field)	do { } while (0)
 # define schedstat_add(rq, field, amt)	do { } while (0)
 # define schedstat_set(var, val)	do { } while (0)
+# define schedstat_val(rq, field)	0
 #endif
 
 #ifdef CONFIG_SCHED_INFO
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 780bcbe1d4de..720b7bb01d43 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -198,7 +198,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
+	file = READ_ONCE(array->ptrs[index]);
 	if (unlikely(!file))
 		return -ENOENT;
 
@@ -247,7 +247,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
+	file = READ_ONCE(array->ptrs[index]);
 	if (unlikely(!file))
 		return -ENOENT;
 
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index f96f0383f6c6..ad1d6164e946 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -36,6 +36,10 @@ struct trace_bprintk_fmt {
 static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
 {
 	struct trace_bprintk_fmt *pos;
+
+	if (!fmt)
+		return ERR_PTR(-EINVAL);
+
 	list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
 		if (!strcmp(pos->fmt, fmt))
 			return pos;
@@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 	for (iter = start; iter < end; iter++) {
 		struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
 		if (tb_fmt) {
-			*iter = tb_fmt->fmt;
+			if (!IS_ERR(tb_fmt))
+				*iter = tb_fmt->fmt;
 			continue;
 		}