Merge branch 'irq/core' into auto-latest

6 files changed, 202 insertions, 32 deletions

diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 355b8c7957f5..144db9dcfcde 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -38,6 +38,9 @@ config HARDIRQS_SW_RESEND
 config IRQ_PREFLOW_FASTEOI
        bool
 
+config IRQ_FORCED_THREADING
+       bool
+
 config SPARSE_IRQ
 	bool "Support sparse irq numbering"
 	depends on HAVE_SPARSE_IRQ
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index e099e9e9de0b..517561fc7317 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -51,6 +51,68 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 	       "but no thread function available.", irq, action->name);
 }
 
+static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
+{
+	/*
+	 * Wake up the handler thread for this action. In case the
+	 * thread crashed and was killed we just pretend that we
+	 * handled the interrupt. The hardirq handler has disabled the
+	 * device interrupt, so no irq storm is lurking. If the
+	 * RUNTHREAD bit is already set, nothing to do.
+	 */
+	if (test_bit(IRQTF_DIED, &action->thread_flags) ||
+	    test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		return;
+
+	/*
+	 * It's safe to OR the mask lockless here. We have only two
+	 * places which write to threads_oneshot: This code and the
+	 * irq thread.
+	 *
+	 * This code is the hard irq context and can never run on two
+	 * cpus in parallel. If it ever does we have more serious
+	 * problems than this bitmask.
+	 *
+	 * The irq threads of this irq which clear their "running" bit
+	 * in threads_oneshot are serialized via desc->lock against
+	 * each other and they are serialized against this code by
+	 * IRQS_INPROGRESS.
+	 *
+	 * Hard irq handler:
+	 *
+	 *	spin_lock(desc->lock);
+	 *	desc->state |= IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *	set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
+	 *	desc->threads_oneshot |= mask;
+	 *	spin_lock(desc->lock);
+	 *	desc->state &= ~IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * irq thread:
+	 *
+	 * again:
+	 *	spin_lock(desc->lock);
+	 *	if (desc->state & IRQS_INPROGRESS) {
+	 *		spin_unlock(desc->lock);
+	 *		while(desc->state & IRQS_INPROGRESS)
+	 *			cpu_relax();
+	 *		goto again;
+	 *	}
+	 *	if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	 *		desc->threads_oneshot &= ~mask;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * So either the thread waits for us to clear IRQS_INPROGRESS
+	 * or we are waiting in the flow handler for desc->lock to be
+	 * released before we reach this point. The thread also checks
+	 * IRQTF_RUNTHREAD under desc->lock. If set it leaves
+	 * threads_oneshot untouched and runs the thread another time.
+	 */
+	desc->threads_oneshot |= action->thread_mask;
+	wake_up_process(action->thread);
+}
+
 irqreturn_t
 handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
@@ -64,7 +126,8 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 		res = action->handler(irq, action->dev_id);
 		trace_irq_handler_exit(irq, action, res);
 
-		if (WARN_ON_ONCE(!irqs_disabled()))
+		if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pF enabled interrupts\n",
+			      irq, action->handler))
 			local_irq_disable();
 
 		switch (res) {
@@ -84,19 +147,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 				break;
 			}
 
-			/*
-			 * Wake up the handler thread for this
-			 * action. In case the thread crashed and was
-			 * killed we just pretend that we handled the
-			 * interrupt. The hardirq handler above has
-			 * disabled the device interrupt, so no irq
-			 * storm is lurking.
-			 */
-			if (likely(!test_bit(IRQTF_DIED,
-					     &action->thread_flags))) {
-				set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
-				wake_up_process(action->thread);
-			}
+			irq_wake_thread(desc, action);
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 935bec4bfa87..6c6ec9a49027 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -27,12 +27,14 @@ extern int noirqdebug;
  * IRQTF_DIED      - handler thread died
  * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
  * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
+ * IRQTF_FORCED_THREAD  - irq action is force threaded
  */
 enum {
 	IRQTF_RUNTHREAD,
 	IRQTF_DIED,
 	IRQTF_WARNED,
 	IRQTF_AFFINITY,
+	IRQTF_FORCED_THREAD,
 };
 
 /*
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 01f8a9519e63..acd599a43bfb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -17,6 +17,17 @@
 
 #include "internals.h"
 
+#ifdef CONFIG_IRQ_FORCED_THREADING
+__read_mostly bool force_irqthreads;
+
+static int __init setup_forced_irqthreads(char *arg)
+{
+	force_irqthreads = true;
+	return 0;
+}
+early_param("threadirqs", setup_forced_irqthreads);
+#endif
+
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -617,8 +628,11 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  * handler finished. unmask if the interrupt has not been disabled and
  * is marked MASKED.
  */
-static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
+static void irq_finalize_oneshot(struct irq_desc *desc,
+				 struct irqaction *action, bool force)
 {
+	if (!(desc->istate & IRQS_ONESHOT))
+		return;
 again:
 	chip_bus_lock(desc);
 	raw_spin_lock_irq(&desc->lock);
@@ -631,6 +645,11 @@ again:
 	 * on the other CPU. If we unmask the irq line then the
 	 * interrupt can come in again and masks the line, leaves due
 	 * to IRQS_INPROGRESS and the irq line is masked forever.
+	 *
+	 * This also serializes the state of shared oneshot handlers
+	 * versus "desc->threads_onehsot |= action->thread_mask;" in
+	 * irq_wake_thread(). See the comment there which explains the
+	 * serialization.
 	 */
 	if (unlikely(desc->istate & IRQS_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
@@ -639,11 +658,23 @@ again:
 		goto again;
 	}
 
-	if (!(desc->istate & IRQS_DISABLED) && (desc->istate & IRQS_MASKED)) {
+	/*
+	 * Now check again, whether the thread should run. Otherwise
+	 * we would clear the threads_oneshot bit of this thread which
+	 * was just set.
+	 */
+	if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		goto out_unlock;
+
+	desc->threads_oneshot &= ~action->thread_mask;
+
+	if (!desc->threads_oneshot && !(desc->istate & IRQS_DISABLED) &&
+	    (desc->istate & IRQS_MASKED)) {
 		irq_compat_clr_masked(desc);
 		desc->istate &= ~IRQS_MASKED;
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
+out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
 	chip_bus_sync_unlock(desc);
 }
@@ -682,6 +713,32 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
 #endif
 
 /*
+ * Interrupts which are not explicitely requested as threaded
+ * interrupts rely on the implicit bh/preempt disable of the hard irq
+ * context. So we need to disable bh here to avoid deadlocks and other
+ * side effects.
+ */
+static void
+irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	local_bh_disable();
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+	local_bh_enable();
+}
+
+/*
+ * Interrupts explicitely requested as threaded interupts want to be
+ * preemtible - many of them need to sleep and wait for slow busses to
+ * complete.
+ */
+static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+}
+
+/*
  * Interrupt handler thread
  */
 static int irq_thread(void *data)
@@ -691,7 +748,14 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	int wake, oneshot = desc->istate & IRQS_ONESHOT;
+	void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
+	int wake;
+
+	if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
+					&action->thread_flags))
+		handler_fn = irq_forced_thread_fn;
+	else
+		handler_fn = irq_thread_fn;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
@@ -716,11 +780,7 @@ static int irq_thread(void *data)
 			raw_spin_unlock_irq(&desc->lock);
 		} else {
 			raw_spin_unlock_irq(&desc->lock);
-
-			action->thread_fn(action->irq, action->dev_id);
-
-			if (oneshot)
-				irq_finalize_oneshot(action->irq, desc);
+			handler_fn(desc, action);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -729,6 +789,9 @@ static int irq_thread(void *data)
 			wake_up(&desc->wait_for_threads);
 	}
 
+	/* Prevent a stale desc->threads_oneshot */
+	irq_finalize_oneshot(desc, action, true);
+
 	/*
 	 * Clear irqaction. Otherwise exit_irq_thread() would make
 	 * fuzz about an active irq thread going into nirvana.
@@ -743,6 +806,7 @@ static int irq_thread(void *data)
 void exit_irq_thread(void)
 {
 	struct task_struct *tsk = current;
+	struct irq_desc *desc;
 
 	if (!tsk->irqaction)
 		return;
@@ -751,6 +815,14 @@ void exit_irq_thread(void)
 	       "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
 	       tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
 
+	desc = irq_to_desc(tsk->irqaction->irq);
+
+	/*
+	 * Prevent a stale desc->threads_oneshot. Must be called
+	 * before setting the IRQTF_DIED flag.
+	 */
+	irq_finalize_oneshot(desc, tsk->irqaction, true);
+
 	/*
 	 * Set the THREAD DIED flag to prevent further wakeups of the
 	 * soon to be gone threaded handler.
@@ -758,6 +830,22 @@ void exit_irq_thread(void)
 	set_bit(IRQTF_DIED, &tsk->irqaction->flags);
 }
 
+static void irq_setup_forced_threading(struct irqaction *new)
+{
+	if (!force_irqthreads)
+		return;
+	if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
+		return;
+
+	new->flags |= IRQF_ONESHOT;
+
+	if (!new->thread_fn) {
+		set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
+		new->thread_fn = new->handler;
+		new->handler = irq_default_primary_handler;
+	}
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -767,7 +855,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 {
 	struct irqaction *old, **old_ptr;
 	const char *old_name = NULL;
-	unsigned long flags;
+	unsigned long flags, thread_mask = 0;
 	int ret, nested, shared = 0;
 	cpumask_var_t mask;
 
@@ -793,10 +881,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		rand_initialize_irq(irq);
 	}
 
-	/* Oneshot interrupts are not allowed with shared */
-	if ((new->flags & IRQF_ONESHOT) && (new->flags & IRQF_SHARED))
-		return -EINVAL;
-
 	/*
 	 * Check whether the interrupt nests into another interrupt
 	 * thread.
@@ -811,6 +895,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * dummy function which warns when called.
 		 */
 		new->handler = irq_nested_primary_handler;
+	} else {
+		irq_setup_forced_threading(new);
 	}
 
 	/*
@@ -850,10 +936,12 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * Can't share interrupts unless both agree to and are
 		 * the same type (level, edge, polarity). So both flag
 		 * fields must have IRQF_SHARED set and the bits which
-		 * set the trigger type must match.
+		 * set the trigger type must match. Also all must
+		 * agree on ONESHOT.
 		 */
 		if (!((old->flags & new->flags) & IRQF_SHARED) ||
-		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK)) {
+		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
+		    ((old->flags ^ new->flags) & IRQF_ONESHOT)) {
 			old_name = old->name;
 			goto mismatch;
 		}
@@ -865,12 +953,23 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 		/* add new interrupt at end of irq queue */
 		do {
+			thread_mask |= old->thread_mask;
 			old_ptr = &old->next;
 			old = *old_ptr;
 		} while (old);
 		shared = 1;
 	}
 
+	/*
+	 * Setup the thread mask for this irqaction. Unlikely to have
+	 * 32 resp 64 irqs sharing one line, but who knows.
+	 */
+	if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) {
+		ret = -EBUSY;
+		goto out_mask;
+	}
+	new->thread_mask = 1 << ffz(thread_mask);
+
 	if (!shared) {
 		irq_chip_set_defaults(desc->irq_data.chip);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 36e936da9969..b9f28904f558 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2286,7 +2286,10 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * yield - it could be a while.
 		 */
 		if (unlikely(on_rq)) {
-			schedule_timeout_uninterruptible(1);
+			ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
+
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
 			continue;
 		}
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3e757e60f45d..56e5dec837f0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -311,9 +311,21 @@ void irq_enter(void)
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
-# define invoke_softirq()	__do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		__do_softirq();
+	else
+		wakeup_softirqd();
+}
 #else
-# define invoke_softirq()	do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		do_softirq();
+	else
+		wakeup_softirqd();
+}
 #endif
 
 /*