Merge schedutil governor updates for v4.10.

17 files changed, 234 insertions, 110 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5df20d6..29de1a9 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -228,7 +228,7 @@ static struct {
 	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
 	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-	.dep_map = {.name = "cpu_hotplug.lock" },
+	.dep_map = STATIC_LOCKDEP_MAP_INIT("cpu_hotplug.dep_map", &cpu_hotplug.dep_map),
 #endif
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c6e47e9..0e29213 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/events/uprobes.c b/kernel/events/uprobes.c
index d4129bb..f9ec9ad 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -300,7 +300,8 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
 
 retry:
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
+	ret = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page,
+			&vma);
 	if (ret <= 0)
 		return ret;
 
@@ -1710,7 +1711,8 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	 * but we treat this as a 'remote' access since it is
 	 * essentially a kernel access to the memory.
 	 */
-	result = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
+	result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page,
+			NULL);
 	if (result < 0)
 		return result;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 623259f..997ac1d 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 0c5f1a5..9c4d304 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 8d44b3f..30e6d05 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 1e7f5da..6ccb08f 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/power/suspend_test.c b/kernel/power/suspend_test.c
index 084452e..bdff5ed 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -203,8 +203,10 @@ static int __init test_suspend(void)
 
 	/* RTCs have initialized by now too ... can we use one? */
 	dev = class_find_device(rtc_class, NULL, NULL, has_wakealarm);
-	if (dev)
+	if (dev) {
 		rtc = rtc_class_open(dev_name(dev));
+		put_device(dev);
+	}
 	if (!rtc) {
 		printk(warn_no_rtc);
 		return 0;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index d5e3973..5028f4f 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -253,17 +253,6 @@ static int preferred_console = -1;
 int console_set_on_cmdline;
 EXPORT_SYMBOL(console_set_on_cmdline);
 
-#ifdef CONFIG_OF
-static bool of_specified_console;
-
-void console_set_by_of(void)
-{
-	of_specified_console = true;
-}
-#else
-# define of_specified_console false
-#endif
-
 /* Flag: console code may call schedule() */
 static int console_may_schedule;
 
@@ -1769,6 +1758,10 @@ static size_t log_output(int facility, int level, enum log_flags lflags, const c
 		cont_flush();
 	}
 
+	/* Skip empty continuation lines that couldn't be added - they just flush */
+	if (!text_len && (lflags & LOG_CONT))
+		return 0;
+
 	/* If it doesn't end in a newline, try to buffer the current line */
 	if (!(lflags & LOG_NEWLINE)) {
 		if (cont_add(facility, level, lflags, text, text_len))
@@ -2653,7 +2646,7 @@ void register_console(struct console *newcon)
 	 *	didn't select a console we take the first one
 	 *	that registers here.
 	 */
-	if (preferred_console < 0 && !of_specified_console) {
+	if (preferred_console < 0) {
 		if (newcon->index < 0)
 			newcon->index = 0;
 		if (newcon->setup == NULL ||
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 2a99027..e6474f7 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -537,7 +537,7 @@ int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst
 		int this_len, retval;
 
 		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
-		retval = access_process_vm(tsk, src, buf, this_len, 0);
+		retval = access_process_vm(tsk, src, buf, this_len, FOLL_FORCE);
 		if (!retval) {
 			if (copied)
 				break;
@@ -564,7 +564,8 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
 		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
 		if (copy_from_user(buf, src, this_len))
 			return -EFAULT;
-		retval = access_process_vm(tsk, dst, buf, this_len, 1);
+		retval = access_process_vm(tsk, dst, buf, this_len,
+				FOLL_FORCE | FOLL_WRITE);
 		if (!retval) {
 			if (copied)
 				break;
@@ -1127,7 +1128,7 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
 	unsigned long tmp;
 	int copied;
 
-	copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), 0);
+	copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE);
 	if (copied != sizeof(tmp))
 		return -EIO;
 	return put_user(tmp, (unsigned long __user *)data);
@@ -1138,7 +1139,8 @@ int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
 {
 	int copied;
 
-	copied = access_process_vm(tsk, addr, &data, sizeof(data), 1);
+	copied = access_process_vm(tsk, addr, &data, sizeof(data),
+			FOLL_FORCE | FOLL_WRITE);
 	return (copied == sizeof(data)) ? 0 : -EIO;
 }
 
@@ -1155,7 +1157,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 	switch (request) {
 	case PTRACE_PEEKTEXT:
 	case PTRACE_PEEKDATA:
-		ret = access_process_vm(child, addr, &word, sizeof(word), 0);
+		ret = access_process_vm(child, addr, &word, sizeof(word),
+				FOLL_FORCE);
 		if (ret != sizeof(word))
 			ret = -EIO;
 		else
@@ -1164,7 +1167,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 
 	case PTRACE_POKETEXT:
 	case PTRACE_POKEDATA:
-		ret = access_process_vm(child, addr, &data, sizeof(data), 1);
+		ret = access_process_vm(child, addr, &data, sizeof(data),
+				FOLL_FORCE | FOLL_WRITE);
 		ret = (ret != sizeof(data) ? -EIO : 0);
 		break;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94732d1..154fd68 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5192,21 +5192,14 @@ 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
@@ -5221,6 +5214,7 @@ 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)
@@ -7515,11 +7509,27 @@ 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/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 69e0689..fd46593 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -12,11 +12,14 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/cpufreq.h>
+#include <linux/kthread.h>
 #include <linux/slab.h>
 #include <trace/events/power.h>
 
 #include "sched.h"
 
+#define SUGOV_KTHREAD_PRIORITY	50
+
 struct sugov_tunables {
 	struct gov_attr_set attr_set;
 	unsigned int rate_limit_us;
@@ -35,8 +38,10 @@ struct sugov_policy {
 
 	/* The next fields are only needed if fast switch cannot be used. */
 	struct irq_work irq_work;
-	struct work_struct work;
+	struct kthread_work work;
 	struct mutex work_lock;
+	struct kthread_worker worker;
+	struct task_struct *thread;
 	bool work_in_progress;
 
 	bool need_freq_update;
@@ -291,7 +296,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
 	raw_spin_unlock(&sg_policy->update_lock);
 }
 
-static void sugov_work(struct work_struct *work)
+static void sugov_work(struct kthread_work *work)
 {
 	struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
 
@@ -308,7 +313,21 @@ static void sugov_irq_work(struct irq_work *irq_work)
 	struct sugov_policy *sg_policy;
 
 	sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
-	schedule_work_on(smp_processor_id(), &sg_policy->work);
+
+	/*
+	 * For RT and deadline tasks, the schedutil governor shoots the
+	 * frequency to maximum. Special care must be taken to ensure that this
+	 * kthread doesn't result in the same behavior.
+	 *
+	 * This is (mostly) guaranteed by the work_in_progress flag. The flag is
+	 * updated only at the end of the sugov_work() function and before that
+	 * the schedutil governor rejects all other frequency scaling requests.
+	 *
+	 * There is a very rare case though, where the RT thread yields right
+	 * after the work_in_progress flag is cleared. The effects of that are
+	 * neglected for now.
+	 */
+	kthread_queue_work(&sg_policy->worker, &sg_policy->work);
 }
 
 /************************** sysfs interface ************************/
@@ -371,19 +390,64 @@ static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
 		return NULL;
 
 	sg_policy->policy = policy;
-	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
-	INIT_WORK(&sg_policy->work, sugov_work);
-	mutex_init(&sg_policy->work_lock);
 	raw_spin_lock_init(&sg_policy->update_lock);
 	return sg_policy;
 }
 
 static void sugov_policy_free(struct sugov_policy *sg_policy)
 {
-	mutex_destroy(&sg_policy->work_lock);
 	kfree(sg_policy);
 }
 
+static int sugov_kthread_create(struct sugov_policy *sg_policy)
+{
+	struct task_struct *thread;
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+	struct cpufreq_policy *policy = sg_policy->policy;
+	int ret;
+
+	/* kthread only required for slow path */
+	if (policy->fast_switch_enabled)
+		return 0;
+
+	kthread_init_work(&sg_policy->work, sugov_work);
+	kthread_init_worker(&sg_policy->worker);
+	thread = kthread_create(kthread_worker_fn, &sg_policy->worker,
+				"sugov:%d",
+				cpumask_first(policy->related_cpus));
+	if (IS_ERR(thread)) {
+		pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread));
+		return PTR_ERR(thread);
+	}
+
+	ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, &param);
+	if (ret) {
+		kthread_stop(thread);
+		pr_warn("%s: failed to set SCHED_FIFO\n", __func__);
+		return ret;
+	}
+
+	sg_policy->thread = thread;
+	kthread_bind_mask(thread, policy->related_cpus);
+	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
+	mutex_init(&sg_policy->work_lock);
+
+	wake_up_process(thread);
+
+	return 0;
+}
+
+static void sugov_kthread_stop(struct sugov_policy *sg_policy)
+{
+	/* kthread only required for slow path */
+	if (sg_policy->policy->fast_switch_enabled)
+		return;
+
+	kthread_flush_worker(&sg_policy->worker);
+	kthread_stop(sg_policy->thread);
+	mutex_destroy(&sg_policy->work_lock);
+}
+
 static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy)
 {
 	struct sugov_tunables *tunables;
@@ -416,16 +480,24 @@ static int sugov_init(struct cpufreq_policy *policy)
 	if (policy->governor_data)
 		return -EBUSY;
 
+	cpufreq_enable_fast_switch(policy);
+
 	sg_policy = sugov_policy_alloc(policy);
-	if (!sg_policy)
-		return -ENOMEM;
+	if (!sg_policy) {
+		ret = -ENOMEM;
+		goto disable_fast_switch;
+	}
+
+	ret = sugov_kthread_create(sg_policy);
+	if (ret)
+		goto free_sg_policy;
 
 	mutex_lock(&global_tunables_lock);
 
 	if (global_tunables) {
 		if (WARN_ON(have_governor_per_policy())) {
 			ret = -EINVAL;
-			goto free_sg_policy;
+			goto stop_kthread;
 		}
 		policy->governor_data = sg_policy;
 		sg_policy->tunables = global_tunables;
@@ -437,7 +509,7 @@ static int sugov_init(struct cpufreq_policy *policy)
 	tunables = sugov_tunables_alloc(sg_policy);
 	if (!tunables) {
 		ret = -ENOMEM;
-		goto free_sg_policy;
+		goto stop_kthread;
 	}
 
 	tunables->rate_limit_us = LATENCY_MULTIPLIER;
@@ -454,20 +526,25 @@ static int sugov_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto fail;
 
- out:
+out:
 	mutex_unlock(&global_tunables_lock);
-
-	cpufreq_enable_fast_switch(policy);
 	return 0;
 
- fail:
+fail:
 	policy->governor_data = NULL;
 	sugov_tunables_free(tunables);
 
- free_sg_policy:
+stop_kthread:
+	sugov_kthread_stop(sg_policy);
+
+free_sg_policy:
 	mutex_unlock(&global_tunables_lock);
 
 	sugov_policy_free(sg_policy);
+
+disable_fast_switch:
+	cpufreq_disable_fast_switch(policy);
+
 	pr_err("initialization failed (error %d)\n", ret);
 	return ret;
 }
@@ -478,8 +555,6 @@ static void sugov_exit(struct cpufreq_policy *policy)
 	struct sugov_tunables *tunables = sg_policy->tunables;
 	unsigned int count;
 
-	cpufreq_disable_fast_switch(policy);
-
 	mutex_lock(&global_tunables_lock);
 
 	count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
@@ -489,7 +564,9 @@ static void sugov_exit(struct cpufreq_policy *policy)
 
 	mutex_unlock(&global_tunables_lock);
 
+	sugov_kthread_stop(sg_policy);
 	sugov_policy_free(sg_policy);
+	cpufreq_disable_fast_switch(policy);
 }
 
 static int sugov_start(struct cpufreq_policy *policy)
@@ -535,8 +612,10 @@ static void sugov_stop(struct cpufreq_policy *policy)
 
 	synchronize_sched();
 
-	irq_work_sync(&sg_policy->irq_work);
-	cancel_work_sync(&sg_policy->work);
+	if (!policy->fast_switch_enabled) {
+		irq_work_sync(&sg_policy->irq_work);
+		kthread_cancel_work_sync(&sg_policy->work);
+	}
 }
 
 static void sugov_limits(struct cpufreq_policy *policy)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2d4ad72..c242944 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -690,7 +690,14 @@ void init_entity_runnable_average(struct sched_entity *se)
 	 * will definitely be update (after enqueue).
 	 */
 	sa->period_contrib = 1023;
-	sa->load_avg = scale_load_down(se->load.weight);
+	/*
+	 * Tasks are intialized with full load to be seen as heavy tasks until
+	 * they get a chance to stabilize to their real load level.
+	 * Group entities are intialized with zero load to reflect the fact that
+	 * nothing has been attached to the task group yet.
+	 */
+	if (entity_is_task(se))
+		sa->load_avg = scale_load_down(se->load.weight);
 	sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
 	/*
 	 * At this point, util_avg won't be used in select_task_rq_fair anyway
@@ -5471,13 +5478,18 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
  */
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	struct sched_domain *this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
-	u64 avg_idle = this_rq()->avg_idle;
-	u64 avg_cost = this_sd->avg_scan_cost;
+	struct sched_domain *this_sd;
+	u64 avg_cost, avg_idle = this_rq()->avg_idle;
 	u64 time, cost;
 	s64 delta;
 	int cpu, wrap;
 
+	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
+	if (!this_sd)
+		return -1;
+
+	avg_cost = this_sd->avg_scan_cost;
+
 	/*
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
@@ -8827,7 +8839,6 @@ 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);
@@ -8842,8 +8853,6 @@ 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 4f70535..9453efe 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 1bf81ef..744fa61 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/alarmtimer.c b/kernel/time/alarmtimer.c
index c3aad68..12dd190 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -542,7 +542,6 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
 static int alarm_timer_create(struct k_itimer *new_timer)
 {
 	enum  alarmtimer_type type;
-	struct alarm_base *base;
 
 	if (!alarmtimer_get_rtcdev())
 		return -ENOTSUPP;
@@ -551,7 +550,6 @@ static int alarm_timer_create(struct k_itimer *new_timer)
 		return -EPERM;
 
 	type = clock2alarm(new_timer->it_clock);
-	base = &alarm_bases[type];
 	alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer);
 	return 0;
 }
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 2d47980..c611c47 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;