Merge branch 'nohz/printk-v8' into irq/core

Conflicts:
	kernel/irq_work.c

Add support for printk in full dynticks CPU.

* Don't stop tick with irq works pending. This
fix is generally useful and concerns archs that
can't raise self IPIs.

* Flush irq works before CPU offlining.

* Introduce "lazy" irq works that can wait for the
next tick to be executed, unless it's stopped.

* Implement klogd wake up using irq work. This
removes the ad-hoc printk_tick()/printk_needs_cpu()
hooks and make it working even in dynticks mode.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

8 files changed, 147 insertions, 50 deletions

diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index ce60c084635b..f5dbce50466e 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -3,6 +3,20 @@
 
 #include <linux/llist.h>
 
+/*
+ * An entry can be in one of four states:
+ *
+ * free	     NULL, 0 -> {claimed}       : free to be used
+ * claimed   NULL, 3 -> {pending}       : claimed to be enqueued
+ * pending   next, 3 -> {busy}          : queued, pending callback
+ * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
+ */
+
+#define IRQ_WORK_PENDING	1UL
+#define IRQ_WORK_BUSY		2UL
+#define IRQ_WORK_FLAGS		3UL
+#define IRQ_WORK_LAZY		4UL /* Doesn't want IPI, wait for tick */
+
 struct irq_work {
 	unsigned long flags;
 	struct llist_node llnode;
@@ -20,4 +34,10 @@ void irq_work_queue(struct irq_work *work);
 void irq_work_run(void);
 void irq_work_sync(struct irq_work *work);
 
+#ifdef CONFIG_IRQ_WORK
+bool irq_work_needs_cpu(void);
+#else
+static bool irq_work_needs_cpu(void) { return false; }
+#endif
+
 #endif /* _LINUX_IRQ_WORK_H */
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 9afc01e5a0a6..86c4b6294713 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -98,9 +98,6 @@ int no_printk(const char *fmt, ...)
 extern asmlinkage __printf(1, 2)
 void early_printk(const char *fmt, ...);
 
-extern int printk_needs_cpu(int cpu);
-extern void printk_tick(void);
-
 #ifdef CONFIG_PRINTK
 asmlinkage __printf(5, 0)
 int vprintk_emit(int facility, int level,
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 1a6567b48492..553272e6af55 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -8,6 +8,8 @@
 
 #include <linux/clockchips.h>
 #include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/hrtimer.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
@@ -122,13 +124,26 @@ static inline int tick_oneshot_mode_active(void) { return 0; }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
 # ifdef CONFIG_NO_HZ
+DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched);
+
+static inline int tick_nohz_tick_stopped(void)
+{
+	return __this_cpu_read(tick_cpu_sched.tick_stopped);
+}
+
 extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
-# else
+
+# else /* !CONFIG_NO_HZ */
+static inline int tick_nohz_tick_stopped(void)
+{
+	return 0;
+}
+
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }
 
diff --git a/init/Kconfig b/init/Kconfig
index e3227d7ba35d..a98e1acc122d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1259,6 +1259,7 @@ config HOTPLUG
 config PRINTK
 	default y
 	bool "Enable support for printk" if EXPERT
+	select IRQ_WORK
 	help
 	  This option enables normal printk support. Removing it
 	  eliminates most of the message strings from the kernel image
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index c9d7478e4889..55fcce6065cf 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -12,22 +12,15 @@
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+#include <linux/cpu.h>
+#include <linux/notifier.h>
 #include <asm/processor.h>
 
-/*
- * An entry can be in one of four states:
- *
- * free	     NULL, 0 -> {claimed}       : free to be used
- * claimed   NULL, 3 -> {pending}       : claimed to be enqueued
- * pending   next, 3 -> {busy}          : queued, pending callback
- * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
- */
-
-#define IRQ_WORK_PENDING	1UL
-#define IRQ_WORK_BUSY		2UL
-#define IRQ_WORK_FLAGS		3UL
 
 static DEFINE_PER_CPU(struct llist_head, irq_work_list);
+static DEFINE_PER_CPU(int, irq_work_raised);
 
 /*
  * Claim the entry so that no one else will poke at it.
@@ -70,8 +63,6 @@ void __weak arch_irq_work_raise(void)
  */
 void irq_work_queue(struct irq_work *work)
 {
-	bool empty;
-
 	/* Only queue if not already pending */
 	if (!irq_work_claim(work))
 		return;
@@ -79,30 +70,55 @@ void irq_work_queue(struct irq_work *work)
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 
-	empty = llist_add(&work->llnode, &__get_cpu_var(irq_work_list));
-	/* The list was empty, raise self-interrupt to start processing. */
-	if (empty)
-		arch_irq_work_raise();
+	llist_add(&work->llnode, &__get_cpu_var(irq_work_list));
+
+	/*
+	 * If the work is not "lazy" or the tick is stopped, raise the irq
+	 * work interrupt (if supported by the arch), otherwise, just wait
+	 * for the next tick.
+	 */
+	if (!(work->flags & IRQ_WORK_LAZY) || tick_nohz_tick_stopped()) {
+		if (!this_cpu_cmpxchg(irq_work_raised, 0, 1))
+			arch_irq_work_raise();
+	}
 
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(irq_work_queue);
 
-/*
- * Run the irq_work entries on this cpu. Requires to be ran from hardirq
- * context with local IRQs disabled.
- */
-void irq_work_run(void)
+bool irq_work_needs_cpu(void)
+{
+	struct llist_head *this_list;
+
+	this_list = &__get_cpu_var(irq_work_list);
+	if (llist_empty(this_list))
+		return false;
+
+	/* All work should have been flushed before going offline */
+	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
+
+	return true;
+}
+
+static void __irq_work_run(void)
 {
+	unsigned long flags;
 	struct irq_work *work;
 	struct llist_head *this_list;
 	struct llist_node *llnode;
 
+
+	/*
+	 * Reset the "raised" state right before we check the list because
+	 * an NMI may enqueue after we find the list empty from the runner.
+	 */
+	__this_cpu_write(irq_work_raised, 0);
+	barrier();
+
 	this_list = &__get_cpu_var(irq_work_list);
 	if (llist_empty(this_list))
 		return;
 
-	BUG_ON(!in_irq());
 	BUG_ON(!irqs_disabled());
 
 	llnode = llist_del_all(this_list);
@@ -118,15 +134,27 @@ void irq_work_run(void)
 		 * to claim that work don't rely on us to handle their data
 		 * while we are in the middle of the func.
 		 */
-		xchg(&work->flags, IRQ_WORK_BUSY);
+		flags = work->flags & ~IRQ_WORK_PENDING;
+		xchg(&work->flags, flags);
+
 		work->func(work);
 		/*
 		 * Clear the BUSY bit and return to the free state if
 		 * no-one else claimed it meanwhile.
 		 */
-		(void)cmpxchg(&work->flags, IRQ_WORK_BUSY, 0);
+		(void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
 	}
 }
+
+/*
+ * Run the irq_work entries on this cpu. Requires to be ran from hardirq
+ * context with local IRQs disabled.
+ */
+void irq_work_run(void)
+{
+	BUG_ON(!in_irq());
+	__irq_work_run();
+}
 EXPORT_SYMBOL_GPL(irq_work_run);
 
 /*
@@ -141,3 +169,35 @@ void irq_work_sync(struct irq_work *work)
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int irq_work_cpu_notify(struct notifier_block *self,
+			       unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_DYING:
+		/* Called from stop_machine */
+		if (WARN_ON_ONCE(cpu != smp_processor_id()))
+			break;
+		__irq_work_run();
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cpu_notify;
+
+static __init int irq_work_init_cpu_notifier(void)
+{
+	cpu_notify.notifier_call = irq_work_cpu_notify;
+	cpu_notify.priority = 0;
+	register_cpu_notifier(&cpu_notify);
+	return 0;
+}
+device_initcall(irq_work_init_cpu_notifier);
+
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/kernel/printk.c b/kernel/printk.c
index 357f714ddd49..0b31715f335a 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -42,6 +42,7 @@
 #include <linux/notifier.h>
 #include <linux/rculist.h>
 #include <linux/poll.h>
+#include <linux/irq_work.h>
 
 #include <asm/uaccess.h>
 
@@ -1967,30 +1968,32 @@ int is_console_locked(void)
 static DEFINE_PER_CPU(int, printk_pending);
 static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
 
-void printk_tick(void)
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
 {
-	if (__this_cpu_read(printk_pending)) {
-		int pending = __this_cpu_xchg(printk_pending, 0);
-		if (pending & PRINTK_PENDING_SCHED) {
-			char *buf = __get_cpu_var(printk_sched_buf);
-			printk(KERN_WARNING "[sched_delayed] %s", buf);
-		}
-		if (pending & PRINTK_PENDING_WAKEUP)
-			wake_up_interruptible(&log_wait);
+	int pending = __this_cpu_xchg(printk_pending, 0);
+
+	if (pending & PRINTK_PENDING_SCHED) {
+		char *buf = __get_cpu_var(printk_sched_buf);
+		printk(KERN_WARNING "[sched_delayed] %s", buf);
 	}
-}
 
-int printk_needs_cpu(int cpu)
-{
-	if (cpu_is_offline(cpu))
-		printk_tick();
-	return __this_cpu_read(printk_pending);
+	if (pending & PRINTK_PENDING_WAKEUP)
+		wake_up_interruptible(&log_wait);
 }
 
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+	.func = wake_up_klogd_work_func,
+	.flags = IRQ_WORK_LAZY,
+};
+
 void wake_up_klogd(void)
 {
-	if (waitqueue_active(&log_wait))
+	preempt_disable();
+	if (waitqueue_active(&log_wait)) {
 		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+	}
+	preempt_enable();
 }
 
 static void console_cont_flush(char *text, size_t size)
@@ -2471,6 +2474,7 @@ int printk_sched(const char *fmt, ...)
 	va_end(args);
 
 	__this_cpu_or(printk_pending, PRINTK_PENDING_SCHED);
+	irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
 	local_irq_restore(flags);
 
 	return r;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index d58e552d9fd1..fb8e5e469d1c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -20,6 +20,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <linux/irq_work.h>
 
 #include <asm/irq_regs.h>
 
@@ -28,7 +29,7 @@
 /*
  * Per cpu nohz control structure
  */
-static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
 /*
  * The time, when the last jiffy update happened. Protected by jiffies_lock.
@@ -331,8 +332,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		time_delta = timekeeping_max_deferment();
 	} while (read_seqretry(&jiffies_lock, seq));
 
-	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
-	    arch_needs_cpu(cpu)) {
+	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
+	    arch_needs_cpu(cpu) || irq_work_needs_cpu()) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
 	} else {
diff --git a/kernel/timer.c b/kernel/timer.c
index 367d00858482..ff3b5165737b 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1351,7 +1351,6 @@ void update_process_times(int user_tick)
 	account_process_tick(p, user_tick);
 	run_local_timers();
 	rcu_check_callbacks(cpu, user_tick);
-	printk_tick();
 #ifdef CONFIG_IRQ_WORK
 	if (in_irq())
 		irq_work_run();