Merge branch 'sched/urgent' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

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);
 }

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();
 	}
 

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);
 

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 */
 
 /**

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);

kernel/sched/core.c

@@ -2535,10 +2535,9 @@ 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);
@@ -3170,7 +3169,8 @@ 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())) {

kernel/sched/fair.c

@@ -8468,8 +8468,9 @@ 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);
@@ -8484,6 +8485,8 @@ 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)
@@ -8497,7 +8500,10 @@ 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;

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;
 

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;