Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
  x86, apic: Enable lapic nmi watchdog on AMD Family 11h
  x86: Remove unnecessary mdelay() from cpu_disable_common()
  x86, ioapic: Document another case when level irq is seen as an edge
  x86, ioapic: Fix the EOI register detection mechanism
  x86, io-apic: Move the effort of clearing remoteIRR explicitly before migrating the irq
  x86: SGI UV: Map low MMR ranges
  x86: apic: Print out SRAT table APIC id in hex
  x86: Re-get cfg_new in case reuse/move irq_desc
  x86: apic: Remove not needed #ifdef
  x86: io-apic: IO-APIC MMIO should not fail on resource insertion
  x86: Remove asm/apicnum.h
  x86: apic: Do not use stacked physid_mask_t
  x86, apic: Get rid of apicid_to_cpu_present assign on 64-bit
  x86, ioapic: Use snrpintf while set names for IO-APIC resourses
  x86, apic: Use PAGE_SIZE instead of numbers
  x86: Remove local_irq_enable()/local_irq_disable() in fixup_irqs()
  x86: Use EOI register in io-apic on intel platforms
  x86: Force irq complete move during cpu offline
  x86: Remove move_cleanup_count from irq_cfg
  x86, intr-remap: Avoid irq_chip mask/unmask in fixup_irqs() for intr-remapping
  ...

1 files changed, 90 insertions, 0 deletions

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 19212cb01558..fee6cc2b2079 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -274,3 +274,93 @@ void smp_generic_interrupt(struct pt_regs *regs)
 }
 
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
+void fixup_irqs(void)
+{
+        unsigned int irq, vector;
+        static int warned;
+        struct irq_desc *desc;
+
+        for_each_irq_desc(irq, desc) {
+                int break_affinity = 0;
+                int set_affinity = 1;
+                const struct cpumask *affinity;
+
+                if (!desc)
+                        continue;
+                if (irq == 2)
+                        continue;
+
+                /* interrupt's are disabled at this point */
+                spin_lock(&desc->lock);
+
+                affinity = desc->affinity;
+                if (!irq_has_action(irq) ||
+                    cpumask_equal(affinity, cpu_online_mask)) {
+                        spin_unlock(&desc->lock);
+                        continue;
+                }
+
+                /*
+                 * Complete the irq move. This cpu is going down and for
+                 * non intr-remapping case, we can't wait till this interrupt
+                 * arrives at this cpu before completing the irq move.
+                 */
+                irq_force_complete_move(irq);
+
+                if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+                        break_affinity = 1;
+                        affinity = cpu_all_mask;
+                }
+
+                if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->mask)
+                        desc->chip->mask(irq);
+
+                if (desc->chip->set_affinity)
+                        desc->chip->set_affinity(irq, affinity);
+                else if (!(warned++))
+                        set_affinity = 0;
+
+                if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->unmask)
+                        desc->chip->unmask(irq);
+
+                spin_unlock(&desc->lock);
+
+                if (break_affinity && set_affinity)
+                        printk("Broke affinity for irq %i\n", irq);
+                else if (!set_affinity)
+                        printk("Cannot set affinity for irq %i\n", irq);
+        }
+
+        /*
+         * We can remove mdelay() and then send spuriuous interrupts to
+         * new cpu targets for all the irqs that were handled previously by
+         * this cpu. While it works, I have seen spurious interrupt messages
+         * (nothing wrong but still...).
+         *
+         * So for now, retain mdelay(1) and check the IRR and then send those
+         * interrupts to new targets as this cpu is already offlined...
+         */
+        mdelay(1);
+
+        for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+                unsigned int irr;
+
+                if (__get_cpu_var(vector_irq)[vector] < 0)
+                        continue;
+
+                irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+                if (irr  & (1 << (vector % 32))) {
+                        irq = __get_cpu_var(vector_irq)[vector];
+
+                        desc = irq_to_desc(irq);
+                        spin_lock(&desc->lock);
+                        if (desc->chip->retrigger)
+                                desc->chip->retrigger(irq);
+                        spin_unlock(&desc->lock);
+                }
+        }
+}
+#endif