1 files changed, 315 insertions, 109 deletions

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 291f03664552..7e2e7dd4cd2f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -8,16 +8,15 @@
  */
 
 #include <linux/irq.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 #include "internals.h"
 
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
-cpumask_var_t irq_default_affinity;
-
 /**
  *      synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *      @irq: interrupt number to wait for
@@ -53,9 +52,18 @@ void synchronize_irq(unsigned int irq)
 
                 /* Oops, that failed? */
         } while (status & IRQ_INPROGRESS);
+
+        /*
+         * We made sure that no hardirq handler is running. Now verify
+         * that no threaded handlers are active.
+         */
+        wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
 }
 EXPORT_SYMBOL(synchronize_irq);
 
+#ifdef CONFIG_SMP
+cpumask_var_t irq_default_affinity;
+
 /**
  *      irq_can_set_affinity - Check if the affinity of a given irq can be set
  *      @irq:           Interrupt to check
@@ -72,6 +80,18 @@ int irq_can_set_affinity(unsigned int irq)
         return 1;
 }
 
+static void
+irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
+{
+        struct irqaction *action = desc->action;
+
+        while (action) {
+                if (action->thread)
+                        set_cpus_allowed_ptr(action->thread, cpumask);
+                action = action->next;
+        }
+}
+
 /**
  *      irq_set_affinity - Set the irq affinity of a given irq
  *      @irq:           Interrupt to set affinity
@@ -90,16 +110,17 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-                cpumask_copy(&desc->affinity, cpumask);
+                cpumask_copy(desc->affinity, cpumask);
                 desc->chip->set_affinity(irq, cpumask);
         } else {
                 desc->status |= IRQ_MOVE_PENDING;
-                cpumask_copy(&desc->pending_mask, cpumask);
+                cpumask_copy(desc->pending_mask, cpumask);
         }
 #else
-        cpumask_copy(&desc->affinity, cpumask);
+        cpumask_copy(desc->affinity, cpumask);
         desc->chip->set_affinity(irq, cpumask);
 #endif
+        irq_set_thread_affinity(desc, cpumask);
         desc->status |= IRQ_AFFINITY_SET;
         spin_unlock_irqrestore(&desc->lock, flags);
         return 0;
@@ -109,7 +130,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 /*
  * Generic version of the affinity autoselector.
  */
-int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
+static int setup_affinity(unsigned int irq, struct irq_desc *desc)
 {
         if (!irq_can_set_affinity(irq))
                 return 0;
@@ -119,21 +140,21 @@ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
          * one of the targets is online.
          */
         if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-                if (cpumask_any_and(&desc->affinity, cpu_online_mask)
+                if (cpumask_any_and(desc->affinity, cpu_online_mask)
                     < nr_cpu_ids)
                         goto set_affinity;
                 else
                         desc->status &= ~IRQ_AFFINITY_SET;
         }
 
-        cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
+        cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-        desc->chip->set_affinity(irq, &desc->affinity);
+        desc->chip->set_affinity(irq, desc->affinity);
 
         return 0;
 }
 #else
-static inline int do_irq_select_affinity(unsigned int irq, struct irq_desc *d)
+static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
 {
         return irq_select_affinity(irq);
 }
@@ -149,19 +170,35 @@ int irq_select_affinity_usr(unsigned int irq)
         int ret;
 
         spin_lock_irqsave(&desc->lock, flags);
-        ret = do_irq_select_affinity(irq, desc);
+        ret = setup_affinity(irq, desc);
+        if (!ret)
+                irq_set_thread_affinity(desc, desc->affinity);
         spin_unlock_irqrestore(&desc->lock, flags);
 
         return ret;
 }
 
 #else
-static inline int do_irq_select_affinity(int irq, struct irq_desc *desc)
+static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
 {
         return 0;
 }
 #endif
 
+void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
+{
+        if (suspend) {
+                if (!desc->action || (desc->action->flags & IRQF_TIMER))
+                        return;
+                desc->status |= IRQ_SUSPENDED;
+        }
+
+        if (!desc->depth++) {
+                desc->status |= IRQ_DISABLED;
+                desc->chip->disable(irq);
+        }
+}
+
 /**
  *      disable_irq_nosync - disable an irq without waiting
  *      @irq: Interrupt to disable
@@ -182,10 +219,7 @@ void disable_irq_nosync(unsigned int irq)
                 return;
 
         spin_lock_irqsave(&desc->lock, flags);
-        if (!desc->depth++) {
-                desc->status |= IRQ_DISABLED;
-                desc->chip->disable(irq);
-        }
+        __disable_irq(desc, irq, false);
         spin_unlock_irqrestore(&desc->lock, flags);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
@@ -215,15 +249,21 @@ void disable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(disable_irq);
 
-static void __enable_irq(struct irq_desc *desc, unsigned int irq)
+void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
+        if (resume)
+                desc->status &= ~IRQ_SUSPENDED;
+
         switch (desc->depth) {
         case 0:
+ err_out:
                 WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
                 break;
         case 1: {
                 unsigned int status = desc->status & ~IRQ_DISABLED;
 
+                if (desc->status & IRQ_SUSPENDED)
+                        goto err_out;
                 /* Prevent probing on this irq: */
                 desc->status = status | IRQ_NOPROBE;
                 check_irq_resend(desc, irq);
@@ -253,7 +293,7 @@ void enable_irq(unsigned int irq)
                 return;
 
         spin_lock_irqsave(&desc->lock, flags);
-        __enable_irq(desc, irq);
+        __enable_irq(desc, irq, false);
         spin_unlock_irqrestore(&desc->lock, flags);
 }
 EXPORT_SYMBOL(enable_irq);
@@ -384,14 +424,98 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
         return ret;
 }
 
+static int irq_wait_for_interrupt(struct irqaction *action)
+{
+        while (!kthread_should_stop()) {
+                set_current_state(TASK_INTERRUPTIBLE);
+
+                if (test_and_clear_bit(IRQTF_RUNTHREAD,
+                                       &action->thread_flags)) {
+                        __set_current_state(TASK_RUNNING);
+                        return 0;
+                }
+                schedule();
+        }
+        return -1;
+}
+
+/*
+ * Interrupt handler thread
+ */
+static int irq_thread(void *data)
+{
+        struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
+        struct irqaction *action = data;
+        struct irq_desc *desc = irq_to_desc(action->irq);
+        int wake;
+
+        sched_setscheduler(current, SCHED_FIFO, &param);
+        current->irqaction = action;
+
+        while (!irq_wait_for_interrupt(action)) {
+
+                atomic_inc(&desc->threads_active);
+
+                spin_lock_irq(&desc->lock);
+                if (unlikely(desc->status & IRQ_DISABLED)) {
+                        /*
+                         * CHECKME: We might need a dedicated
+                         * IRQ_THREAD_PENDING flag here, which
+                         * retriggers the thread in check_irq_resend()
+                         * but AFAICT IRQ_PENDING should be fine as it
+                         * retriggers the interrupt itself --- tglx
+                         */
+                        desc->status |= IRQ_PENDING;
+                        spin_unlock_irq(&desc->lock);
+                } else {
+                        spin_unlock_irq(&desc->lock);
+
+                        action->thread_fn(action->irq, action->dev_id);
+                }
+
+                wake = atomic_dec_and_test(&desc->threads_active);
+
+                if (wake && waitqueue_active(&desc->wait_for_threads))
+                        wake_up(&desc->wait_for_threads);
+        }
+
+        /*
+         * Clear irqaction. Otherwise exit_irq_thread() would make
+         * fuzz about an active irq thread going into nirvana.
+         */
+        current->irqaction = NULL;
+        return 0;
+}
+
+/*
+ * Called from do_exit()
+ */
+void exit_irq_thread(void)
+{
+        struct task_struct *tsk = current;
+
+        if (!tsk->irqaction)
+                return;
+
+        printk(KERN_ERR
+               "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
+               tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
+
+        /*
+         * Set the THREAD DIED flag to prevent further wakeups of the
+         * soon to be gone threaded handler.
+         */
+        set_bit(IRQTF_DIED, &tsk->irqaction->flags);
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
  */
 static int
-__setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
+__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 {
-        struct irqaction *old, **p;
+        struct irqaction *old, **old_ptr;
         const char *old_name = NULL;
         unsigned long flags;
         int shared = 0;
@@ -420,11 +544,31 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
         }
 
         /*
+         * Threaded handler ?
+         */
+        if (new->thread_fn) {
+                struct task_struct *t;
+
+                t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
+                                   new->name);
+                if (IS_ERR(t))
+                        return PTR_ERR(t);
+                /*
+                 * We keep the reference to the task struct even if
+                 * the thread dies to avoid that the interrupt code
+                 * references an already freed task_struct.
+                 */
+                get_task_struct(t);
+                new->thread = t;
+                wake_up_process(t);
+        }
+
+        /*
          * The following block of code has to be executed atomically
          */
         spin_lock_irqsave(&desc->lock, flags);
-        p = &desc->action;
-        old = *p;
+        old_ptr = &desc->action;
+        old = *old_ptr;
         if (old) {
                 /*
                  * Can't share interrupts unless both agree to and are
@@ -447,8 +591,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 
                 /* add new interrupt at end of irq queue */
                 do {
-                        p = &old->next;
-                        old = *p;
+                        old_ptr = &old->next;
+                        old = *old_ptr;
                 } while (old);
                 shared = 1;
         }
@@ -456,15 +600,15 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
         if (!shared) {
                 irq_chip_set_defaults(desc->chip);
 
+                init_waitqueue_head(&desc->wait_for_threads);
+
                 /* Setup the type (level, edge polarity) if configured: */
                 if (new->flags & IRQF_TRIGGER_MASK) {
                         ret = __irq_set_trigger(desc, irq,
                                         new->flags & IRQF_TRIGGER_MASK);
 
-                        if (ret) {
-                                spin_unlock_irqrestore(&desc->lock, flags);
-                                return ret;
-                        }
+                        if (ret)
+                                goto out_thread;
                 } else
                         compat_irq_chip_set_default_handler(desc);
 #if defined(CONFIG_IRQ_PER_CPU)
@@ -488,7 +632,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
                         desc->status |= IRQ_NO_BALANCING;
 
                 /* Set default affinity mask once everything is setup */
-                do_irq_select_affinity(irq, desc);
+                setup_affinity(irq, desc);
 
         } else if ((new->flags & IRQF_TRIGGER_MASK)
                         && (new->flags & IRQF_TRIGGER_MASK)
@@ -499,7 +643,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
                                 (int)(new->flags & IRQF_TRIGGER_MASK));
         }
 
-        *p = new;
+        *old_ptr = new;
 
         /* Reset broken irq detection when installing new handler */
         desc->irq_count = 0;
@@ -511,7 +655,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
          */
         if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
                 desc->status &= ~IRQ_SPURIOUS_DISABLED;
-                __enable_irq(desc, irq);
+                __enable_irq(desc, irq, false);
         }
 
         spin_unlock_irqrestore(&desc->lock, flags);
@@ -532,8 +676,19 @@ mismatch:
                 dump_stack();
         }
 #endif
+        ret = -EBUSY;
+
+out_thread:
         spin_unlock_irqrestore(&desc->lock, flags);
-        return -EBUSY;
+        if (new->thread) {
+                struct task_struct *t = new->thread;
+
+                new->thread = NULL;
+                if (likely(!test_bit(IRQTF_DIED, &new->thread_flags)))
+                        kthread_stop(t);
+                put_task_struct(t);
+        }
+        return ret;
 }
 
 /**
@@ -549,97 +704,138 @@ int setup_irq(unsigned int irq, struct irqaction *act)
 
         return __setup_irq(irq, desc, act);
 }
+EXPORT_SYMBOL_GPL(setup_irq);
 
-/**
- *      free_irq - free an interrupt
- *      @irq: Interrupt line to free
- *      @dev_id: Device identity to free
- *
- *      Remove an interrupt handler. The handler is removed and if the
- *      interrupt line is no longer in use by any driver it is disabled.
- *      On a shared IRQ the caller must ensure the interrupt is disabled
- *      on the card it drives before calling this function. The function
- *      does not return until any executing interrupts for this IRQ
- *      have completed.
- *
- *      This function must not be called from interrupt context.
+ /*
+ * Internal function to unregister an irqaction - used to free
+ * regular and special interrupts that are part of the architecture.
  */
-void free_irq(unsigned int irq, void *dev_id)
+static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 {
         struct irq_desc *desc = irq_to_desc(irq);
-        struct irqaction **p;
+        struct irqaction *action, **action_ptr;
+        struct task_struct *irqthread;
         unsigned long flags;
 
-        WARN_ON(in_interrupt());
+        WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
         if (!desc)
-                return;
+                return NULL;
 
         spin_lock_irqsave(&desc->lock, flags);
-        p = &desc->action;
+
+        /*
+         * There can be multiple actions per IRQ descriptor, find the right
+         * one based on the dev_id:
+         */
+        action_ptr = &desc->action;
         for (;;) {
-                struct irqaction *action = *p;
+                action = *action_ptr;
+
+                if (!action) {
+                        WARN(1, "Trying to free already-free IRQ %d\n", irq);
+                        spin_unlock_irqrestore(&desc->lock, flags);
 
-                if (action) {
-                        struct irqaction **pp = p;
+                        return NULL;
+                }
 
-                        p = &action->next;
-                        if (action->dev_id != dev_id)
-                                continue;
+                if (action->dev_id == dev_id)
+                        break;
+                action_ptr = &action->next;
+        }
 
-                        /* Found it - now remove it from the list of entries */
-                        *pp = action->next;
+        /* Found it - now remove it from the list of entries: */
+        *action_ptr = action->next;
 
-                        /* Currently used only by UML, might disappear one day.*/
+        /* Currently used only by UML, might disappear one day: */
 #ifdef CONFIG_IRQ_RELEASE_METHOD
-                        if (desc->chip->release)
-                                desc->chip->release(irq, dev_id);
+        if (desc->chip->release)
+                desc->chip->release(irq, dev_id);
 #endif
 
-                        if (!desc->action) {
-                                desc->status |= IRQ_DISABLED;
-                                if (desc->chip->shutdown)
-                                        desc->chip->shutdown(irq);
-                                else
-                                        desc->chip->disable(irq);
-                        }
-                        spin_unlock_irqrestore(&desc->lock, flags);
-                        unregister_handler_proc(irq, action);
+        /* If this was the last handler, shut down the IRQ line: */
+        if (!desc->action) {
+                desc->status |= IRQ_DISABLED;
+                if (desc->chip->shutdown)
+                        desc->chip->shutdown(irq);
+                else
+                        desc->chip->disable(irq);
+        }
+
+        irqthread = action->thread;
+        action->thread = NULL;
+
+        spin_unlock_irqrestore(&desc->lock, flags);
+
+        unregister_handler_proc(irq, action);
+
+        /* Make sure it's not being used on another CPU: */
+        synchronize_irq(irq);
+
+        if (irqthread) {
+                if (!test_bit(IRQTF_DIED, &action->thread_flags))
+                        kthread_stop(irqthread);
+                put_task_struct(irqthread);
+        }
 
-                        /* Make sure it's not being used on another CPU */
-                        synchronize_irq(irq);
-#ifdef CONFIG_DEBUG_SHIRQ
-                        /*
-                         * It's a shared IRQ -- the driver ought to be
-                         * prepared for it to happen even now it's
-                         * being freed, so let's make sure....  We do
-                         * this after actually deregistering it, to
-                         * make sure that a 'real' IRQ doesn't run in
-                         * parallel with our fake
-                         */
-                        if (action->flags & IRQF_SHARED) {
-                                local_irq_save(flags);
-                                action->handler(irq, dev_id);
-                                local_irq_restore(flags);
-                        }
-#endif
-                        kfree(action);
-                        return;
-                }
-                printk(KERN_ERR "Trying to free already-free IRQ %d\n", irq);
 #ifdef CONFIG_DEBUG_SHIRQ
-                dump_stack();
-#endif
-                spin_unlock_irqrestore(&desc->lock, flags);
-                return;
+        /*
+         * It's a shared IRQ -- the driver ought to be prepared for an IRQ
+         * event to happen even now it's being freed, so let's make sure that
+         * is so by doing an extra call to the handler ....
+         *
+         * ( We do this after actually deregistering it, to make sure that a
+         *   'real' IRQ doesn't run in * parallel with our fake. )
+         */
+        if (action->flags & IRQF_SHARED) {
+                local_irq_save(flags);
+                action->handler(irq, dev_id);
+                local_irq_restore(flags);
         }
+#endif
+        return action;
+}
+
+/**
+ *      remove_irq - free an interrupt
+ *      @irq: Interrupt line to free
+ *      @act: irqaction for the interrupt
+ *
+ * Used to remove interrupts statically setup by the early boot process.
+ */
+void remove_irq(unsigned int irq, struct irqaction *act)
+{
+        __free_irq(irq, act->dev_id);
+}
+EXPORT_SYMBOL_GPL(remove_irq);
+
+/**
+ *      free_irq - free an interrupt allocated with request_irq
+ *      @irq: Interrupt line to free
+ *      @dev_id: Device identity to free
+ *
+ *      Remove an interrupt handler. The handler is removed and if the
+ *      interrupt line is no longer in use by any driver it is disabled.
+ *      On a shared IRQ the caller must ensure the interrupt is disabled
+ *      on the card it drives before calling this function. The function
+ *      does not return until any executing interrupts for this IRQ
+ *      have completed.
+ *
+ *      This function must not be called from interrupt context.
+ */
+void free_irq(unsigned int irq, void *dev_id)
+{
+        kfree(__free_irq(irq, dev_id));
 }
 EXPORT_SYMBOL(free_irq);
 
 /**
- *      request_irq - allocate an interrupt line
+ *      request_threaded_irq - allocate an interrupt line
  *      @irq: Interrupt line to allocate
- *      @handler: Function to be called when the IRQ occurs
+ *      @handler: Function to be called when the IRQ occurs.
+ *                Primary handler for threaded interrupts
+ *      @thread_fn: Function called from the irq handler thread
+ *                  If NULL, no irq thread is created
  *      @irqflags: Interrupt type flags
  *      @devname: An ascii name for the claiming device
  *      @dev_id: A cookie passed back to the handler function
@@ -651,6 +847,15 @@ EXPORT_SYMBOL(free_irq);
  *      raises, you must take care both to initialise your hardware
  *      and to set up the interrupt handler in the right order.
  *
+ *      If you want to set up a threaded irq handler for your device
+ *      then you need to supply @handler and @thread_fn. @handler ist
+ *      still called in hard interrupt context and has to check
+ *      whether the interrupt originates from the device. If yes it
+ *      needs to disable the interrupt on the device and return
+ *      IRQ_THREAD_WAKE which will wake up the handler thread and run
+ *      @thread_fn. This split handler design is necessary to support
+ *      shared interrupts.
+ *
  *      Dev_id must be globally unique. Normally the address of the
  *      device data structure is used as the cookie. Since the handler
  *      receives this value it makes sense to use it.
@@ -666,8 +871,9 @@ EXPORT_SYMBOL(free_irq);
  *      IRQF_TRIGGER_*          Specify active edge(s) or level
  *
  */
-int request_irq(unsigned int irq, irq_handler_t handler,
-                unsigned long irqflags, const char *devname, void *dev_id)
+int request_threaded_irq(unsigned int irq, irq_handler_t handler,
+                         irq_handler_t thread_fn, unsigned long irqflags,
+                         const char *devname, void *dev_id)
 {
         struct irqaction *action;
         struct irq_desc *desc;
@@ -679,11 +885,12 @@ int request_irq(unsigned int irq, irq_handler_t handler,
          * the behavior is classified as "will not fix" so we need to
          * start nudging drivers away from using that idiom.
          */
-        if ((irqflags & (IRQF_SHARED|IRQF_DISABLED))
-                        == (IRQF_SHARED|IRQF_DISABLED))
-                pr_warning("IRQ %d/%s: IRQF_DISABLED is not "
-                                "guaranteed on shared IRQs\n",
-                                irq, devname);
+        if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) ==
+                                        (IRQF_SHARED|IRQF_DISABLED)) {
+                pr_warning(
+                  "IRQ %d/%s: IRQF_DISABLED is not guaranteed on shared IRQs\n",
+                        irq, devname);
+        }
 
 #ifdef CONFIG_LOCKDEP
         /*
@@ -709,15 +916,14 @@ int request_irq(unsigned int irq, irq_handler_t handler,
         if (!handler)
                 return -EINVAL;
 
-        action = kmalloc(sizeof(struct irqaction), GFP_ATOMIC);
+        action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
         if (!action)
                 return -ENOMEM;
 
         action->handler = handler;
+        action->thread_fn = thread_fn;
         action->flags = irqflags;
-        cpus_clear(action->mask);
         action->name = devname;
-        action->next = NULL;
         action->dev_id = dev_id;
 
         retval = __setup_irq(irq, desc, action);
@@ -745,4 +951,4 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 #endif
         return retval;
 }
-EXPORT_SYMBOL(request_irq);
+EXPORT_SYMBOL(request_threaded_irq);