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

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

10 files changed, 96 insertions, 62 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index c6e47e97b33f..0e292132efac 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1960,6 +1960,12 @@ void perf_event_disable(struct perf_event *event)
 }
 EXPORT_SYMBOL_GPL(perf_event_disable);
 
+void perf_event_disable_inatomic(struct perf_event *event)
+{
+	event->pending_disable = 1;
+	irq_work_queue(&event->pending);
+}
+
 static void perf_set_shadow_time(struct perf_event *event,
 				 struct perf_event_context *ctx,
 				 u64 tstamp)
@@ -7075,8 +7081,8 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (events && atomic_dec_and_test(&event->event_limit)) {
 		ret = 1;
 		event->pending_kill = POLL_HUP;
-		event->pending_disable = 1;
-		irq_work_queue(&event->pending);
+
+		perf_event_disable_inatomic(event);
 	}
 
 	READ_ONCE(event->overflow_handler)(event, data, regs);
@@ -8855,7 +8861,10 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
+	int remove_device;
+
 	mutex_lock(&pmus_lock);
+	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
 	mutex_unlock(&pmus_lock);
 
@@ -8869,10 +8878,12 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (pmu->nr_addr_filters)
-		device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
-	device_del(pmu->dev);
-	put_device(pmu->dev);
+	if (remove_device) {
+		if (pmu->nr_addr_filters)
+			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
+		device_del(pmu->dev);
+		put_device(pmu->dev);
+	}
 	free_pmu_context(pmu);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
diff --git a/kernel/fork.c b/kernel/fork.c
index 623259fc794d..997ac1d584f7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -315,6 +315,9 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 
 static void release_task_stack(struct task_struct *tsk)
 {
+	if (WARN_ON(tsk->state != TASK_DEAD))
+		return;  /* Better to leak the stack than to free prematurely */
+
 	account_kernel_stack(tsk, -1);
 	arch_release_thread_stack(tsk->stack);
 	free_thread_stack(tsk);
@@ -1862,6 +1865,7 @@ bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
 	exit_creds(p);
 bad_fork_free:
+	p->state = TASK_DEAD;
 	put_task_stack(p);
 	free_task(p);
 fork_out:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0c5f1a5db654..9c4d30483264 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -721,6 +721,7 @@ int irq_set_parent(int irq, int parent_irq)
 	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(irq_set_parent);
 #endif
 
 /*
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 8d44b3fea9d0..30e6d05aa5a9 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -53,8 +53,15 @@ void notrace __sanitizer_cov_trace_pc(void)
 	/*
 	 * We are interested in code coverage as a function of a syscall inputs,
 	 * so we ignore code executed in interrupts.
+	 * The checks for whether we are in an interrupt are open-coded, because
+	 * 1. We can't use in_interrupt() here, since it also returns true
+	 *    when we are inside local_bh_disable() section.
+	 * 2. We don't want to use (in_irq() | in_serving_softirq() | in_nmi()),
+	 *    since that leads to slower generated code (three separate tests,
+	 *    one for each of the flags).
 	 */
-	if (!t || in_interrupt())
+	if (!t || (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET
+							| NMI_MASK)))
 		return;
 	mode = READ_ONCE(t->kcov_mode);
 	if (mode == KCOV_MODE_TRACE) {
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 1e7f5da648d9..6ccb08f57fcb 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -498,9 +498,9 @@ static int enter_state(suspend_state_t state)
 
 #ifndef CONFIG_SUSPEND_SKIP_SYNC
 	trace_suspend_resume(TPS("sync_filesystems"), 0, true);
-	printk(KERN_INFO "PM: Syncing filesystems ... ");
+	pr_info("PM: Syncing filesystems ... ");
 	sys_sync();
-	printk("done.\n");
+	pr_cont("done.\n");
 	trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 #endif
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b8c86ba44ca9..f3cfa0dd5b34 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5193,21 +5193,14 @@ void sched_show_task(struct task_struct *p)
 	int ppid;
 	unsigned long state = p->state;
 
+	if (!try_get_task_stack(p))
+		return;
 	if (state)
 		state = __ffs(state) + 1;
 	printk(KERN_INFO "%-15.15s %c", p->comm,
 		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
-#if BITS_PER_LONG == 32
-	if (state == TASK_RUNNING)
-		printk(KERN_CONT " running  ");
-	else
-		printk(KERN_CONT " %08lx ", thread_saved_pc(p));
-#else
 	if (state == TASK_RUNNING)
 		printk(KERN_CONT "  running task    ");
-	else
-		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
-#endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
@@ -5222,6 +5215,7 @@ void sched_show_task(struct task_struct *p)
 
 	print_worker_info(KERN_INFO, p);
 	show_stack(p, NULL);
+	put_task_stack(p);
 }
 
 void show_state_filter(unsigned long state_filter)
@@ -7516,11 +7510,27 @@ static struct kmem_cache *task_group_cache __read_mostly;
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
 DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
+#define WAIT_TABLE_BITS 8
+#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
+static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+	unsigned long val = (unsigned long)word << shift | bit;
+
+	return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
+}
+EXPORT_SYMBOL(bit_waitqueue);
+
 void __init sched_init(void)
 {
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
+	for (i = 0; i < WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(bit_wait_table + i);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 79d464a04417..3cf446c53043 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8832,7 +8832,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	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);
@@ -8847,8 +8846,6 @@ 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)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4f7053579fe3..9453efe9b25a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -480,16 +480,6 @@ void wake_up_bit(void *word, int bit)
 }
 EXPORT_SYMBOL(wake_up_bit);
 
-wait_queue_head_t *bit_waitqueue(void *word, int bit)
-{
-	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
-	const struct zone *zone = page_zone(virt_to_page(word));
-	unsigned long val = (unsigned long)word << shift | bit;
-
-	return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
-}
-EXPORT_SYMBOL(bit_waitqueue);
-
 /*
  * Manipulate the atomic_t address to produce a better bit waitqueue table hash
  * index (we're keying off bit -1, but that would produce a horrible hash
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 1bf81ef91375..744fa611cae0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -58,7 +58,7 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
 DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 const char * const softirq_to_name[NR_SOFTIRQS] = {
-	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
+	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL",
 	"TASKLET", "SCHED", "HRTIMER", "RCU"
 };
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 2d47980a1bc4..c611c47de884 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -878,7 +878,7 @@ static inline struct timer_base *get_timer_base(u32 tflags)
 
 #ifdef CONFIG_NO_HZ_COMMON
 static inline struct timer_base *
-__get_target_base(struct timer_base *base, unsigned tflags)
+get_target_base(struct timer_base *base, unsigned tflags)
 {
 #ifdef CONFIG_SMP
 	if ((tflags & TIMER_PINNED) || !base->migration_enabled)
@@ -891,25 +891,27 @@ __get_target_base(struct timer_base *base, unsigned tflags)
 
 static inline void forward_timer_base(struct timer_base *base)
 {
+	unsigned long jnow = READ_ONCE(jiffies);
+
 	/*
 	 * We only forward the base when it's idle and we have a delta between
 	 * base clock and jiffies.
 	 */
-	if (!base->is_idle || (long) (jiffies - base->clk) < 2)
+	if (!base->is_idle || (long) (jnow - base->clk) < 2)
 		return;
 
 	/*
 	 * If the next expiry value is > jiffies, then we fast forward to
 	 * jiffies otherwise we forward to the next expiry value.
 	 */
-	if (time_after(base->next_expiry, jiffies))
-		base->clk = jiffies;
+	if (time_after(base->next_expiry, jnow))
+		base->clk = jnow;
 	else
 		base->clk = base->next_expiry;
 }
 #else
 static inline struct timer_base *
-__get_target_base(struct timer_base *base, unsigned tflags)
+get_target_base(struct timer_base *base, unsigned tflags)
 {
 	return get_timer_this_cpu_base(tflags);
 }
@@ -917,14 +919,6 @@ __get_target_base(struct timer_base *base, unsigned tflags)
 static inline void forward_timer_base(struct timer_base *base) { }
 #endif
 
-static inline struct timer_base *
-get_target_base(struct timer_base *base, unsigned tflags)
-{
-	struct timer_base *target = __get_target_base(base, tflags);
-
-	forward_timer_base(target);
-	return target;
-}
 
 /*
  * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
@@ -943,7 +937,14 @@ static struct timer_base *lock_timer_base(struct timer_list *timer,
 {
 	for (;;) {
 		struct timer_base *base;
-		u32 tf = timer->flags;
+		u32 tf;
+
+		/*
+		 * We need to use READ_ONCE() here, otherwise the compiler
+		 * might re-read @tf between the check for TIMER_MIGRATING
+		 * and spin_lock().
+		 */
+		tf = READ_ONCE(timer->flags);
 
 		if (!(tf & TIMER_MIGRATING)) {
 			base = get_timer_base(tf);
@@ -964,6 +965,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	unsigned long clk = 0, flags;
 	int ret = 0;
 
+	BUG_ON(!timer->function);
+
 	/*
 	 * This is a common optimization triggered by the networking code - if
 	 * the timer is re-modified to have the same timeout or ends up in the
@@ -972,13 +975,16 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	if (timer_pending(timer)) {
 		if (timer->expires == expires)
 			return 1;
+
 		/*
-		 * Take the current timer_jiffies of base, but without holding
-		 * the lock!
+		 * We lock timer base and calculate the bucket index right
+		 * here. If the timer ends up in the same bucket, then we
+		 * just update the expiry time and avoid the whole
+		 * dequeue/enqueue dance.
 		 */
-		base = get_timer_base(timer->flags);
-		clk = base->clk;
+		base = lock_timer_base(timer, &flags);
 
+		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);
 
 		/*
@@ -988,14 +994,14 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 */
 		if (idx == timer_get_idx(timer)) {
 			timer->expires = expires;
-			return 1;
+			ret = 1;
+			goto out_unlock;
 		}
+	} else {
+		base = lock_timer_base(timer, &flags);
 	}
 
 	timer_stats_timer_set_start_info(timer);
-	BUG_ON(!timer->function);
-
-	base = lock_timer_base(timer, &flags);
 
 	ret = detach_if_pending(timer, base, false);
 	if (!ret && pending_only)
@@ -1025,12 +1031,16 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		}
 	}
 
+	/* Try to forward a stale timer base clock */
+	forward_timer_base(base);
+
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
-	 * between calculating 'idx' and taking the lock, only enqueue_timer()
-	 * and trigger_dyntick_cpu() is required. Otherwise we need to
-	 * (re)calculate the wheel index via internal_add_timer().
+	 * between calculating 'idx' and possibly switching the base, only
+	 * enqueue_timer() and trigger_dyntick_cpu() is required. Otherwise
+	 * we need to (re)calculate the wheel index via
+	 * internal_add_timer().
 	 */
 	if (idx != UINT_MAX && clk == base->clk) {
 		enqueue_timer(base, timer, idx);
@@ -1510,12 +1520,16 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 	is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
 	base->next_expiry = nextevt;
 	/*
-	 * We have a fresh next event. Check whether we can forward the base:
+	 * We have a fresh next event. Check whether we can forward the
+	 * base. We can only do that when @basej is past base->clk
+	 * otherwise we might rewind base->clk.
 	 */
-	if (time_after(nextevt, jiffies))
-		base->clk = jiffies;
-	else if (time_after(nextevt, base->clk))
-		base->clk = nextevt;
+	if (time_after(basej, base->clk)) {
+		if (time_after(nextevt, basej))
+			base->clk = basej;
+		else if (time_after(nextevt, base->clk))
+			base->clk = nextevt;
+	}
 
 	if (time_before_eq(nextevt, basej)) {
 		expires = basem;