6 files changed, 133 insertions, 70 deletions

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e49a288fa479..88e7bed62711 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1524,6 +1524,7 @@ void enable_percpu_irq(unsigned int irq, unsigned int type)
 out:
         irq_put_desc_unlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(enable_percpu_irq);
 
 void disable_percpu_irq(unsigned int irq)
 {
@@ -1537,6 +1538,7 @@ void disable_percpu_irq(unsigned int irq)
         irq_percpu_disable(desc, cpu);
         irq_put_desc_unlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(disable_percpu_irq);
 
 /*
  * Internal function to unregister a percpu irqaction.
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 611cd6003c45..7b5f012bde9d 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -80,13 +80,11 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 
         /*
          * All handlers must agree on IRQF_SHARED, so we test just the
-         * first. Check for action->next as well.
+         * first.
          */
         action = desc->action;
         if (!action || !(action->flags & IRQF_SHARED) ||
-            (action->flags & __IRQF_TIMER) ||
-            (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
-            !action->next)
+            (action->flags & __IRQF_TIMER))
                 goto out;
 
         /* Already running on another processor */
@@ -104,6 +102,7 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
         do {
                 if (handle_irq_event(desc) == IRQ_HANDLED)
                         ret = IRQ_HANDLED;
+                /* Make sure that there is still a valid action */
                 action = desc->action;
         } while ((desc->istate & IRQS_PENDING) && action);
         desc->istate &= ~IRQS_POLL_INPROGRESS;
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 1588e3b2871b..55fcce6065cf 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -12,37 +12,36 @@
 #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.
  */
 static bool irq_work_claim(struct irq_work *work)
 {
-        unsigned long flags, nflags;
+        unsigned long flags, oflags, nflags;
 
+        /*
+         * Start with our best wish as a premise but only trust any
+         * flag value after cmpxchg() result.
+         */
+        flags = work->flags & ~IRQ_WORK_PENDING;
         for (;;) {
-                flags = work->flags;
-                if (flags & IRQ_WORK_PENDING)
-                        return false;
                 nflags = flags | IRQ_WORK_FLAGS;
-                if (cmpxchg(&work->flags, flags, nflags) == flags)
+                oflags = cmpxchg(&work->flags, flags, nflags);
+                if (oflags == flags)
                         break;
+                if (oflags & IRQ_WORK_PENDING)
+                        return false;
+                flags = oflags;
                 cpu_relax();
         }
 
@@ -57,57 +56,69 @@ void __weak arch_irq_work_raise(void)
 }
 
 /*
- * Queue the entry and raise the IPI if needed.
+ * Enqueue the irq_work @entry unless it's already pending
+ * somewhere.
+ *
+ * Can be re-enqueued while the callback is still in progress.
  */
-static void __irq_work_queue(struct irq_work *work)
+void irq_work_queue(struct irq_work *work)
 {
-        bool empty;
+        /* Only queue if not already pending */
+        if (!irq_work_claim(work))
+                return;
 
+        /* 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);
 
-/*
- * Enqueue the irq_work @entry, returns true on success, failure when the
- * @entry was already enqueued by someone else.
- *
- * Can be re-enqueued while the callback is still in progress.
- */
-bool irq_work_queue(struct irq_work *work)
+bool irq_work_needs_cpu(void)
 {
-        if (!irq_work_claim(work)) {
-                /*
-                 * Already enqueued, can't do!
-                 */
+        struct llist_head *this_list;
+
+        this_list = &__get_cpu_var(irq_work_list);
+        if (llist_empty(this_list))
                 return false;
-        }
 
-        __irq_work_queue(work);
+        /* All work should have been flushed before going offline */
+        WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
+
         return true;
 }
-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)
+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);
@@ -119,16 +130,31 @@ void irq_work_run(void)
                 /*
                  * Clear the PENDING bit, after this point the @work
                  * can be re-used.
+                 * Make it immediately visible so that other CPUs trying
+                 * to claim that work don't rely on us to handle their data
+                 * while we are in the middle of the func.
                  */
-                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);
 
 /*
@@ -143,3 +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 267ce780abe8..f24633afa46a 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>
 
@@ -1959,30 +1960,32 @@ 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)
@@ -2462,6 +2465,7 @@ 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();