1 files changed, 49 insertions, 226 deletions

diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 3aac15466a9..4d1c746892e 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -13,34 +13,21 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/delay.h>
-#include <asm/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <linux/smp.h>
 #include <asm/io_apic.h>
 #include <asm/idle.h>
-#include <asm/smp.h>
+#include <asm/apic.h>
 
-atomic_t irq_err_count;
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
 
-/*
- * 'what should we do if we get a hw irq event on an illegal vector'.
- * each architecture has to answer this themselves.
- */
-void ack_bad_irq(unsigned int irq)
-{
-	printk(KERN_WARNING "unexpected IRQ trap at vector %02x\n", irq);
-	/*
-	 * Currently unexpected vectors happen only on SMP and APIC.
-	 * We _must_ ack these because every local APIC has only N
-	 * irq slots per priority level, and a 'hanging, unacked' IRQ
-	 * holds up an irq slot - in excessive cases (when multiple
-	 * unexpected vectors occur) that might lock up the APIC
-	 * completely.
-	 * But don't ack when the APIC is disabled. -AK
-	 */
-	if (!disable_apic)
-		ack_APIC_irq();
-}
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
+int sysctl_panic_on_stackoverflow;
 
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 /*
  * Probabilistic stack overflow check:
  *
@@ -50,217 +37,53 @@ void ack_bad_irq(unsigned int irq)
  */
 static inline void stack_overflow_check(struct pt_regs *regs)
 {
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+#define STACK_TOP_MARGIN	128
+	struct orig_ist *oist;
+	u64 irq_stack_top, irq_stack_bottom;
+	u64 estack_top, estack_bottom;
 	u64 curbase = (u64)task_stack_page(current);
-	static unsigned long warned = -60*HZ;
 
-	if (regs->sp >= curbase && regs->sp <= curbase + THREAD_SIZE &&
-	    regs->sp <  curbase + sizeof(struct thread_info) + 128 &&
-	    time_after(jiffies, warned + 60*HZ)) {
-		printk("do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-		       current->comm, curbase, regs->sp);
-		show_stack(NULL,NULL);
-		warned = jiffies;
-	}
-}
+	if (user_mode_vm(regs))
+		return;
+
+	if (regs->sp >= curbase + sizeof(struct thread_info) +
+				  sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
+	    regs->sp <= curbase + THREAD_SIZE)
+		return;
+
+	irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) +
+			STACK_TOP_MARGIN;
+	irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
+		return;
+
+	oist = &__get_cpu_var(orig_ist);
+	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
+	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
+	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
+		return;
+
+	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+		current->comm, curbase, regs->sp,
+		irq_stack_top, irq_stack_bottom,
+		estack_top, estack_bottom);
+
+	if (sysctl_panic_on_stackoverflow)
+		panic("low stack detected by irq handler - check messages\n");
 #endif
-
-/*
- * Generic, controller-independent functions:
- */
-
-int show_interrupts(struct seq_file *p, void *v)
-{
-	int i = *(loff_t *) v, j;
-	struct irqaction * action;
-	unsigned long flags;
-
-	if (i == 0) {
-		seq_printf(p, "           ");
-		for_each_online_cpu(j)
-			seq_printf(p, "CPU%-8d",j);
-		seq_putc(p, '\n');
-	}
-
-	if (i < NR_IRQS) {
-		unsigned any_count = 0;
-
-		spin_lock_irqsave(&irq_desc[i].lock, flags);
-#ifndef CONFIG_SMP
-		any_count = kstat_irqs(i);
-#else
-		for_each_online_cpu(j)
-			any_count |= kstat_cpu(j).irqs[i];
-#endif
-		action = irq_desc[i].action;
-		if (!action && !any_count)
-			goto skip;
-		seq_printf(p, "%3d: ",i);
-#ifndef CONFIG_SMP
-		seq_printf(p, "%10u ", kstat_irqs(i));
-#else
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
-#endif
-		seq_printf(p, " %8s", irq_desc[i].chip->name);
-		seq_printf(p, "-%-8s", irq_desc[i].name);
-
-		if (action) {
-			seq_printf(p, "  %s", action->name);
-			while ((action = action->next) != NULL)
-				seq_printf(p, ", %s", action->name);
-		}
-		seq_putc(p, '\n');
-skip:
-		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
-	} else if (i == NR_IRQS) {
-		seq_printf(p, "NMI: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
-		seq_printf(p, "  Non-maskable interrupts\n");
-		seq_printf(p, "LOC: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs);
-		seq_printf(p, "  Local timer interrupts\n");
-#ifdef CONFIG_SMP
-		seq_printf(p, "RES: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->irq_resched_count);
-		seq_printf(p, "  Rescheduling interrupts\n");
-		seq_printf(p, "CAL: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->irq_call_count);
-		seq_printf(p, "  function call interrupts\n");
-		seq_printf(p, "TLB: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
-		seq_printf(p, "  TLB shootdowns\n");
-#endif
-		seq_printf(p, "TRM: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count);
-		seq_printf(p, "  Thermal event interrupts\n");
-		seq_printf(p, "THR: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count);
-		seq_printf(p, "  Threshold APIC interrupts\n");
-		seq_printf(p, "SPU: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count);
-		seq_printf(p, "  Spurious interrupts\n");
-		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
-	}
-	return 0;
 }
 
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
-asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
+bool handle_irq(unsigned irq, struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct irq_desc *desc;
 
-	/* high bit used in ret_from_ code  */
-	unsigned vector = ~regs->orig_ax;
-	unsigned irq;
-
-	exit_idle();
-	irq_enter();
-	irq = __get_cpu_var(vector_irq)[vector];
-
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 	stack_overflow_check(regs);
-#endif
-
-	if (likely(irq < NR_IRQS))
-		generic_handle_irq(irq);
-	else {
-		if (!disable_apic)
-			ack_APIC_irq();
-
-		if (printk_ratelimit())
-			printk(KERN_EMERG "%s: %d.%d No irq handler for vector\n",
-				__func__, smp_processor_id(), vector);
-	}
-
-	irq_exit();
-
-	set_irq_regs(old_regs);
-	return 1;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-void fixup_irqs(cpumask_t map)
-{
-	unsigned int irq;
-	static int warned;
-
-	for (irq = 0; irq < NR_IRQS; irq++) {
-		cpumask_t mask;
-		int break_affinity = 0;
-		int set_affinity = 1;
-
-		if (irq == 2)
-			continue;
-
-		/* interrupt's are disabled at this point */
-		spin_lock(&irq_desc[irq].lock);
-
-		if (!irq_has_action(irq) ||
-		    cpus_equal(irq_desc[irq].affinity, map)) {
-			spin_unlock(&irq_desc[irq].lock);
-			continue;
-		}
-
-		cpus_and(mask, irq_desc[irq].affinity, map);
-		if (cpus_empty(mask)) {
-			break_affinity = 1;
-			mask = map;
-		}
-
-		if (irq_desc[irq].chip->mask)
-			irq_desc[irq].chip->mask(irq);
-
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, mask);
-		else if (!(warned++))
-			set_affinity = 0;
-
-		if (irq_desc[irq].chip->unmask)
-			irq_desc[irq].chip->unmask(irq);
-
-		spin_unlock(&irq_desc[irq].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);
-	}
-
-	/* That doesn't seem sufficient.  Give it 1ms. */
-	local_irq_enable();
-	mdelay(1);
-	local_irq_disable();
-}
-#endif
-
-extern void call_softirq(void);
-
-asmlinkage void do_softirq(void)
-{
- 	__u32 pending;
- 	unsigned long flags;
 
- 	if (in_interrupt())
- 		return;
+	desc = irq_to_desc(irq);
+	if (unlikely(!desc))
+		return false;
 
- 	local_irq_save(flags);
- 	pending = local_softirq_pending();
- 	/* Switch to interrupt stack */
- 	if (pending) {
-		call_softirq();
-		WARN_ON_ONCE(softirq_count());
-	}
- 	local_irq_restore(flags);
+	generic_handle_irq_desc(irq, desc);
+	return true;
 }