[ANNOUNCE] 3.14.72-rt76

@@ -234,7 +234,11 @@ svc_preempt:
 	bne	1b
 	tst	r0, #_TIF_NEED_RESCHED_LAZY
 	moveq	pc, r8				@ go again
-	b	1b
+	ldr	r0, [tsk, #TI_PREEMPT_LAZY]	@ get preempt lazy count
+	teq	r0, #0				@ if preempt lazy count != 0
+	beq	1b
+	mov	pc, r8				@ go again
+
 #endif
 
 __und_fault:

@@ -1403,7 +1403,8 @@ static int mce_notify_work_init(void)
 
 static void mce_notify_work(void)
 {
-	wake_up_process(mce_notify_helper);
+	if (mce_notify_helper)
+		wake_up_process(mce_notify_helper);
 }
 #else
 static void mce_notify_work(void)

@@ -98,7 +98,7 @@ static struct kobj_attribute format_attr_##_var =		\
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
 struct rapl_pmu {
-	spinlock_t	 lock;
+	raw_spinlock_t	 lock;
 	int		 hw_unit;  /* 1/2^hw_unit Joule */
 	int		 n_active; /* number of active events */
 	struct list_head active_list;

@@ -188,13 +188,13 @@ static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 	if (!pmu->n_active)
 		return HRTIMER_NORESTART;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	list_for_each_entry(event, &pmu->active_list, active_entry) {
 		rapl_event_update(event);
 	}
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 
 	hrtimer_forward_now(hrtimer, pmu->timer_interval);
 

@@ -231,9 +231,9 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
 	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 	__rapl_pmu_event_start(pmu, event);
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 }
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)

@@ -242,7 +242,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	/* mark event as deactivated and stopped */
 	if (!(hwc->state & PERF_HES_STOPPED)) {

@@ -267,7 +267,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 }
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)

@@ -276,14 +276,14 @@ static int rapl_pmu_event_add(struct perf_event *event, int mode)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_START)
 		__rapl_pmu_event_start(pmu, event);
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 
 	return 0;
 }

@@ -526,7 +526,7 @@ static int rapl_cpu_prepare(int cpu)
 	if (!pmu)
 		return -1;
 
-	spin_lock_init(&pmu->lock);
+	raw_spin_lock_init(&pmu->lock);
 
 	INIT_LIST_HEAD(&pmu->active_list);
 

@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/kprobes.h>
 #include <linux/debugfs.h>
+#include <linux/wait-simple.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>

@@ -90,14 +91,14 @@ static void kvm_io_delay(void)
 
 struct kvm_task_sleep_node {
 	struct hlist_node link;
-	wait_queue_head_t wq;
+	struct swait_head wq;
 	u32 token;
 	int cpu;
 	bool halted;
 };
 
 static struct kvm_task_sleep_head {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct hlist_head list;
 } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];
 

@@ -121,17 +122,17 @@ void kvm_async_pf_task_wait(u32 token)
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
 	struct kvm_task_sleep_node n, *e;
-	DEFINE_WAIT(wait);
+	DEFINE_SWAITER(wait);
 
 	rcu_irq_enter();
 
-	spin_lock(&b->lock);
+	raw_spin_lock(&b->lock);
 	e = _find_apf_task(b, token);
 	if (e) {
 		/* dummy entry exist -> wake up was delivered ahead of PF */
 		hlist_del(&e->link);
 		kfree(e);
-		spin_unlock(&b->lock);
+		raw_spin_unlock(&b->lock);
 
 		rcu_irq_exit();
 		return;

@@ -140,13 +141,13 @@ void kvm_async_pf_task_wait(u32 token)
 	n.token = token;
 	n.cpu = smp_processor_id();
 	n.halted = is_idle_task(current) || preempt_count() > 1;
-	init_waitqueue_head(&n.wq);
+	init_swait_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
-	spin_unlock(&b->lock);
+	raw_spin_unlock(&b->lock);
 
 	for (;;) {
 		if (!n.halted)
-			prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+			swait_prepare(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
 		if (hlist_unhashed(&n.link))
 			break;
 

@@ -165,7 +166,7 @@ void kvm_async_pf_task_wait(u32 token)
 		}
 	}
 	if (!n.halted)
-		finish_wait(&n.wq, &wait);
+		swait_finish(&n.wq, &wait);
 
 	rcu_irq_exit();
 	return;

@@ -177,8 +178,8 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 	hlist_del_init(&n->link);
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
-	else if (waitqueue_active(&n->wq))
-		wake_up(&n->wq);
+	else if (swaitqueue_active(&n->wq))
+		swait_wake(&n->wq);
 }
 
 static void apf_task_wake_all(void)

@@ -188,14 +189,14 @@ static void apf_task_wake_all(void)
 	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
 		struct hlist_node *p, *next;
 		struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
-		spin_lock(&b->lock);
+		raw_spin_lock(&b->lock);
 		hlist_for_each_safe(p, next, &b->list) {
 			struct kvm_task_sleep_node *n =
 				hlist_entry(p, typeof(*n), link);
 			if (n->cpu == smp_processor_id())
 				apf_task_wake_one(n);
 		}
-		spin_unlock(&b->lock);
+		raw_spin_unlock(&b->lock);
 	}
 }
 

@@ -211,7 +212,7 @@ void kvm_async_pf_task_wake(u32 token)
 	}
 
 again:
-	spin_lock(&b->lock);
+	raw_spin_lock(&b->lock);
 	n = _find_apf_task(b, token);
 	if (!n) {
 		/*

@@ -224,17 +225,17 @@ again:
 			 * Allocation failed! Busy wait while other cpu
 			 * handles async PF.
 			 */
-			spin_unlock(&b->lock);
+			raw_spin_unlock(&b->lock);
 			cpu_relax();
 			goto again;
 		}
 		n->token = token;
 		n->cpu = smp_processor_id();
-		init_waitqueue_head(&n->wq);
+		init_swait_head(&n->wq);
 		hlist_add_head(&n->link, &b->list);
 	} else
 		apf_task_wake_one(n);
-	spin_unlock(&b->lock);
+	raw_spin_unlock(&b->lock);
 	return;
 }
 EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);

@@ -484,7 +485,7 @@ void __init kvm_guest_init(void)
 	paravirt_ops_setup();
 	register_reboot_notifier(&kvm_pv_reboot_nb);
 	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
-		spin_lock_init(&async_pf_sleepers[i].lock);
+		raw_spin_lock_init(&async_pf_sleepers[i].lock);
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
 		x86_init.irqs.trap_init = kvm_apf_trap_init;
 

@@ -7,10 +7,10 @@
 
 static __always_inline int preempt_count(void)
 {
-	return current_thread_info()->preempt_count;
+	return READ_ONCE(current_thread_info()->preempt_count);
 }
 
-static __always_inline int *preempt_count_ptr(void)
+static __always_inline volatile int *preempt_count_ptr(void)
 {
 	return &current_thread_info()->preempt_count;
 }

@@ -42,13 +42,15 @@ struct hlist_bl_node {
 	struct hlist_bl_node *next, **pprev;
 };
 
-static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h)
-{
-	h->first = NULL;
 #ifdef CONFIG_PREEMPT_RT_BASE
-	raw_spin_lock_init(&h->lock);
+#define INIT_HLIST_BL_HEAD(h)		\
+do {					\
+	(h)->first = NULL;		\
+	raw_spin_lock_init(&(h)->lock);	\
+} while (0)
+#else
+#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL
 #endif
-}
 
 static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
 {

@@ -66,6 +66,9 @@ static inline void __local_lock(struct local_irq_lock *lv)
 #define local_lock(lvar)					\
 	do { __local_lock(&get_local_var(lvar)); } while (0)
 
+#define local_lock_on(lvar, cpu)				\
+	do { __local_lock(&per_cpu(lvar, cpu)); } while (0)
+
 static inline int __local_trylock(struct local_irq_lock *lv)
 {
 	if (lv->owner != current && spin_trylock_local(&lv->lock)) {

@@ -104,6 +107,9 @@ static inline void __local_unlock(struct local_irq_lock *lv)
 		put_local_var(lvar);				\
 	} while (0)
 
+#define local_unlock_on(lvar, cpu)                       \
+	do { __local_unlock(&per_cpu(lvar, cpu)); } while (0)
+
 static inline void __local_lock_irq(struct local_irq_lock *lv)
 {
 	spin_lock_irqsave(&lv->lock, lv->flags);

@@ -555,6 +555,9 @@ ftrace_raw_event_##call(void *__data, proto)				\
 									\
 	local_save_flags(irq_flags);					\
 	pc = preempt_count();						\
+	/* Account for tracepoint preempt disable */			\
+	if (IS_ENABLED(CONFIG_PREEMPT))					\
+		pc--;							\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\

@@ -1289,6 +1289,11 @@ static void call_console_drivers(int level, const char *text, size_t len)
 	if (!console_drivers)
 		return;
 
+	if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) {
+		if (in_irq() || in_nmi())
+			return;
+	}
+
 	migrate_disable();
 	for_each_console(con) {
 		if (exclusive_console && con != exclusive_console)

@@ -2214,6 +2219,11 @@ void console_unblank(void)
 {
 	struct console *c;
 
+	if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) {
+		if (in_irq() || in_nmi())
+			return;
+	}
+
 	/*
 	 * console_unblank can no longer be called in interrupt context unless
 	 * oops_in_progress is set to 1..

@@ -1 +1 @@
--rt75
+-rt76

@@ -750,9 +750,15 @@ void lru_add_drain_cpu(int cpu)
 		unsigned long flags;
 
 		/* No harm done if a racing interrupt already did this */
+#ifdef CONFIG_PREEMPT_RT_BASE
+		local_lock_irqsave_on(rotate_lock, flags, cpu);
+		pagevec_move_tail(pvec);
+		local_unlock_irqrestore_on(rotate_lock, flags, cpu);
+#else
 		local_lock_irqsave(rotate_lock, flags);
 		pagevec_move_tail(pvec);
 		local_unlock_irqrestore(rotate_lock, flags);
+#endif
 	}
 
 	pvec = &per_cpu(lru_deactivate_pvecs, cpu);

@@ -795,12 +801,32 @@ void lru_add_drain(void)
 	local_unlock_cpu(swapvec_lock);
 }
 
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work)
+{
+	local_lock_on(swapvec_lock, cpu);
+	lru_add_drain_cpu(cpu);
+	local_unlock_on(swapvec_lock, cpu);
+}
+
+#else
+
 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
 	lru_add_drain();
 }
 
 static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
+static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work)
+{
+	struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
+
+	INIT_WORK(work, lru_add_drain_per_cpu);
+	schedule_work_on(cpu, work);
+	cpumask_set_cpu(cpu, has_work);
+}
+#endif
 
 void lru_add_drain_all(void)
 {

@@ -813,20 +839,17 @@ void lru_add_drain_all(void)
 	cpumask_clear(&has_work);
 
 	for_each_online_cpu(cpu) {
-		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
-
 		if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
 		    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
 		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
-		    need_activate_page_drain(cpu)) {
-			INIT_WORK(work, lru_add_drain_per_cpu);
-			schedule_work_on(cpu, work);
-			cpumask_set_cpu(cpu, &has_work);
-		}
+		    need_activate_page_drain(cpu))
+			remote_lru_add_drain(cpu, &has_work);
 	}
 
+#ifndef CONFIG_PREEMPT_RT_BASE
 	for_each_cpu(cpu, &has_work)
 		flush_work(&per_cpu(lru_add_drain_work, cpu));
+#endif
 
 	put_online_cpus();
 	mutex_unlock(&lock);

@@ -1037,7 +1037,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 	class = &pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
-	area = &get_cpu_var(zs_map_area);
+	area = per_cpu_ptr(&zs_map_area, get_cpu_light());
 	area->vm_mm = mm;
 	if (off + class->size <= PAGE_SIZE) {
 		/* this object is contained entirely within a page */

@@ -1083,7 +1083,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 
 		__zs_unmap_object(area, pages, off, class->size);
 	}
-	put_cpu_var(zs_map_area);
+	put_cpu_light();
 }
 EXPORT_SYMBOL_GPL(zs_unmap_object);
 

@@ -2720,7 +2720,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	 * This permits __QDISC_STATE_RUNNING owner to get the lock more often
 	 * and dequeue packets faster.
 	 */
+#ifdef CONFIG_PREEMPT_RT_FULL
+	contended = true;
+#else
 	contended = qdisc_is_running(q);
+#endif
 	if (unlikely(contended))
 		spin_lock(&q->busylock);