From f84dbb912f344270f31d5cce974f12908a47798d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 10 Jul 2008 14:48:54 -0700 Subject: [PATCH] genirq: enable polling for disabled screaming irqs When we disable a screaming irq we never see it again. If the irq line is shared or if the driver half works this is a real pain. So periodically poll the handlers for screaming interrupts. I use a timer instead of the classic irq poll technique of working off the timer interrupt because when we use the local apic timers note_interrupt is never called (bug?). Further on a system with dynamic ticks the timer interrupt might not even fire unless there is a timer telling it it needs to. I forced this case on my test system with an e1000 nic and my ssh session remained responsive despite the interrupt handler only being called every 10th of a second. Signed-off-by: Eric W. Biederman Signed-off-by: Ingo Molnar --- kernel/irq/spurious.c | 146 ++++++++++++++++++++++++++---------------- 1 file changed, 91 insertions(+), 55 deletions(-) diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index c66d3f10e853..19fe9d6ebfe8 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -12,83 +12,117 @@ #include #include #include +#include static int irqfixup __read_mostly; +#define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10) +static void poll_spurious_irqs(unsigned long dummy); +static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0); + /* * Recovery handler for misrouted interrupts. */ +static int try_one_irq(int irq, struct irq_desc *desc) +{ + struct irqaction *action; + int ok = 0; + int work = 0; /* Did we do work for a real IRQ */ + + spin_lock(&desc->lock); + /* Already running on another processor */ + if (desc->status & IRQ_INPROGRESS) { + /* + * Already running: If it is shared get the other + * CPU to go looking for our mystery interrupt too + */ + if (desc->action && (desc->action->flags & IRQF_SHARED)) + desc->status |= IRQ_PENDING; + spin_unlock(&desc->lock); + return ok; + } + /* Honour the normal IRQ locking */ + desc->status |= IRQ_INPROGRESS; + action = desc->action; + spin_unlock(&desc->lock); + + while (action) { + /* Only shared IRQ handlers are safe to call */ + if (action->flags & IRQF_SHARED) { + if (action->handler(irq, action->dev_id) == + IRQ_HANDLED) + ok = 1; + } + action = action->next; + } + local_irq_disable(); + /* Now clean up the flags */ + spin_lock(&desc->lock); + action = desc->action; + + /* + * While we were looking for a fixup someone queued a real + * IRQ clashing with our walk: + */ + while ((desc->status & IRQ_PENDING) && action) { + /* + * Perform real IRQ processing for the IRQ we deferred + */ + work = 1; + spin_unlock(&desc->lock); + handle_IRQ_event(irq, action); + spin_lock(&desc->lock); + desc->status &= ~IRQ_PENDING; + } + desc->status &= ~IRQ_INPROGRESS; + /* + * If we did actual work for the real IRQ line we must let the + * IRQ controller clean up too + */ + if (work && desc->chip && desc->chip->end) + desc->chip->end(irq); + spin_unlock(&desc->lock); + + return ok; +} + static int misrouted_irq(int irq) { int i; int ok = 0; - int work = 0; /* Did we do work for a real IRQ */ for (i = 1; i < NR_IRQS; i++) { struct irq_desc *desc = irq_desc + i; - struct irqaction *action; if (i == irq) /* Already tried */ continue; - spin_lock(&desc->lock); - /* Already running on another processor */ - if (desc->status & IRQ_INPROGRESS) { - /* - * Already running: If it is shared get the other - * CPU to go looking for our mystery interrupt too - */ - if (desc->action && (desc->action->flags & IRQF_SHARED)) - desc->status |= IRQ_PENDING; - spin_unlock(&desc->lock); - continue; - } - /* Honour the normal IRQ locking */ - desc->status |= IRQ_INPROGRESS; - action = desc->action; - spin_unlock(&desc->lock); - - while (action) { - /* Only shared IRQ handlers are safe to call */ - if (action->flags & IRQF_SHARED) { - if (action->handler(i, action->dev_id) == - IRQ_HANDLED) - ok = 1; - } - action = action->next; - } - local_irq_disable(); - /* Now clean up the flags */ - spin_lock(&desc->lock); - action = desc->action; - - /* - * While we were looking for a fixup someone queued a real - * IRQ clashing with our walk: - */ - while ((desc->status & IRQ_PENDING) && action) { - /* - * Perform real IRQ processing for the IRQ we deferred - */ - work = 1; - spin_unlock(&desc->lock); - handle_IRQ_event(i, action); - spin_lock(&desc->lock); - desc->status &= ~IRQ_PENDING; - } - desc->status &= ~IRQ_INPROGRESS; - /* - * If we did actual work for the real IRQ line we must let the - * IRQ controller clean up too - */ - if (work && desc->chip && desc->chip->end) - desc->chip->end(i); - spin_unlock(&desc->lock); + if (try_one_irq(i, desc)) + ok = 1; } /* So the caller can adjust the irq error counts */ return ok; } +static void poll_spurious_irqs(unsigned long dummy) +{ + int i; + for (i = 1; i < NR_IRQS; i++) { + struct irq_desc *desc = irq_desc + i; + unsigned int status; + + /* Racy but it doesn't matter */ + status = desc->status; + barrier(); + if (!(status & IRQ_SPURIOUS_DISABLED)) + continue; + + try_one_irq(i, desc); + } + + mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); +} + /* * If 99,900 of the previous 100,000 interrupts have not been handled * then assume that the IRQ is stuck in some manner. Drop a diagnostic @@ -212,6 +246,8 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED; desc->depth++; desc->chip->disable(irq); + + mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); } desc->irqs_unhandled = 0; }