1 files changed, 63 insertions, 312 deletions

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 1cf8c1fcc08..63ce838e5a5 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -15,9 +15,11 @@
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
+#include <linux/uaccess.h>
+#include <linux/percpu.h>
+#include <linux/mm.h>
 
 #include <asm/apic.h>
-#include <asm/uaccess.h>
 
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
@@ -25,30 +27,10 @@ EXPORT_PER_CPU_SYMBOL(irq_stat);
 DEFINE_PER_CPU(struct pt_regs *, irq_regs);
 EXPORT_PER_CPU_SYMBOL(irq_regs);
 
-/*
- * '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_ERR "unexpected IRQ trap at vector %02x\n", irq);
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
 
-#ifdef CONFIG_X86_LOCAL_APIC
-	/*
-	 * 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 only ack when the APIC is enabled -AK
-	 */
-	if (cpu_has_apic)
-		ack_APIC_irq();
-#endif
-}
+int sysctl_panic_on_stackoverflow __read_mostly;
 
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 /* Debugging check for stack overflow: is there less than 1KB free? */
 static int check_stack_overflow(void)
 {
@@ -64,6 +46,8 @@ static void print_stack_overflow(void)
 {
 	printk(KERN_WARNING "low stack detected by irq handler\n");
 	dump_stack();
+	if (sysctl_panic_on_stackoverflow)
+		panic("low stack detected by irq handler - check messages\n");
 }
 
 #else
@@ -71,20 +55,8 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-#ifdef CONFIG_4KSTACKS
-/*
- * per-CPU IRQ handling contexts (thread information and stack)
- */
-union irq_ctx {
-	struct thread_info      tinfo;
-	u32                     stack[THREAD_SIZE/sizeof(u32)];
-};
-
-static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly;
-static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly;
-
-static char softirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss;
-static char hardirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss;
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -97,14 +69,26 @@ static void call_on_stack(void *func, void *stack)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
+/* how to get the current stack pointer from C */
+#define current_stack_pointer ({		\
+	unsigned long sp;			\
+	asm("mov %%esp,%0" : "=g" (sp));	\
+	sp;					\
+})
+
+static inline void *current_stack(void)
+{
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
 static inline int
 execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 {
-	union irq_ctx *curctx, *irqctx;
-	u32 *isp, arg1, arg2;
+	struct irq_stack *curstk, *irqstk;
+	u32 *isp, *prev_esp, arg1, arg2;
 
-	curctx = (union irq_ctx *) current_thread_info();
-	irqctx = hardirq_ctx[smp_processor_id()];
+	curstk = (struct irq_stack *) current_stack();
+	irqstk = __this_cpu_read(hardirq_stack);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -112,21 +96,14 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 	 * handler) we can't do that and just have to keep using the
 	 * current stack (which is the irq stack already after all)
 	 */
-	if (unlikely(curctx == irqctx))
+	if (unlikely(curstk == irqstk))
 		return 0;
 
-	/* build the stack frame on the IRQ stack */
-	isp = (u32 *) ((char*)irqctx + sizeof(*irqctx));
-	irqctx->tinfo.task = curctx->tinfo.task;
-	irqctx->tinfo.previous_esp = current_stack_pointer;
+	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
 
-	/*
-	 * Copy the softirq bits in preempt_count so that the
-	 * softirq checks work in the hardirq context.
-	 */
-	irqctx->tinfo.preempt_count =
-		(irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
-		(curctx->tinfo.preempt_count & SOFTIRQ_MASK);
+	/* Save the next esp at the bottom of the stack */
+	prev_esp = (u32 *)irqstk;
+	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -144,288 +121,62 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 /*
  * allocate per-cpu stacks for hardirq and for softirq processing
  */
-void __cpuinit irq_ctx_init(int cpu)
+void irq_ctx_init(int cpu)
 {
-	union irq_ctx *irqctx;
+	struct irq_stack *irqstk;
 
-	if (hardirq_ctx[cpu])
+	if (per_cpu(hardirq_stack, cpu))
 		return;
 
-	irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE];
-	irqctx->tinfo.task		= NULL;
-	irqctx->tinfo.exec_domain	= NULL;
-	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
-	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
-
-	hardirq_ctx[cpu] = irqctx;
+	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
+					       THREADINFO_GFP,
+					       THREAD_SIZE_ORDER));
+	per_cpu(hardirq_stack, cpu) = irqstk;
 
-	irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE];
-	irqctx->tinfo.task		= NULL;
-	irqctx->tinfo.exec_domain	= NULL;
-	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.preempt_count	= 0;
-	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
-
-	softirq_ctx[cpu] = irqctx;
+	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
+					       THREADINFO_GFP,
+					       THREAD_SIZE_ORDER));
+	per_cpu(softirq_stack, cpu) = irqstk;
 
 	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-	       cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
+	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
-void irq_ctx_exit(int cpu)
+void do_softirq_own_stack(void)
 {
-	hardirq_ctx[cpu] = NULL;
-}
+	struct thread_info *curstk;
+	struct irq_stack *irqstk;
+	u32 *isp, *prev_esp;
 
-asmlinkage void do_softirq(void)
-{
-	unsigned long flags;
-	struct thread_info *curctx;
-	union irq_ctx *irqctx;
-	u32 *isp;
-
-	if (in_interrupt())
-		return;
+	curstk = current_stack();
+	irqstk = __this_cpu_read(softirq_stack);
 
-	local_irq_save(flags);
+	/* build the stack frame on the softirq stack */
+	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
 
-	if (local_softirq_pending()) {
-		curctx = current_thread_info();
-		irqctx = softirq_ctx[smp_processor_id()];
-		irqctx->tinfo.task = curctx->task;
-		irqctx->tinfo.previous_esp = current_stack_pointer;
-
-		/* build the stack frame on the softirq stack */
-		isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
-
-		call_on_stack(__do_softirq, isp);
-		/*
-		 * Shouldnt happen, we returned above if in_interrupt():
-		 */
-		WARN_ON_ONCE(softirq_count());
-	}
+	/* Push the previous esp onto the stack */
+	prev_esp = (u32 *)irqstk;
+	*prev_esp = current_stack_pointer;
 
-	local_irq_restore(flags);
+	call_on_stack(__do_softirq, isp);
 }
 
-#else
-static inline int
-execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
-#endif
-
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
-unsigned int do_IRQ(struct pt_regs *regs)
+bool handle_irq(unsigned irq, struct pt_regs *regs)
 {
-	struct pt_regs *old_regs;
-	/* high bit used in ret_from_ code */
-	int overflow, irq = ~regs->orig_ax;
-	struct irq_desc *desc = irq_desc + irq;
-
-	if (unlikely((unsigned)irq >= NR_IRQS)) {
-		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
-					__func__, irq);
-		BUG();
-	}
-
-	old_regs = set_irq_regs(regs);
-	irq_enter();
+	struct irq_desc *desc;
+	int overflow;
 
 	overflow = check_stack_overflow();
 
-	if (!execute_on_irq_stack(overflow, desc, irq)) {
+	desc = irq_to_desc(irq);
+	if (unlikely(!desc))
+		return false;
+
+	if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
 		if (unlikely(overflow))
 			print_stack_overflow();
 		desc->handle_irq(irq, desc);
 	}
 
-	irq_exit();
-	set_irq_regs(old_regs);
-	return 1;
-}
-
-/*
- * Interrupt statistics:
- */
-
-atomic_t irq_err_count;
-
-/*
- * /proc/interrupts printing:
- */
-
-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 ", nmi_count(j));
-		seq_printf(p, "  Non-maskable interrupts\n");
-#ifdef CONFIG_X86_LOCAL_APIC
-		seq_printf(p, "LOC: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ",
-				per_cpu(irq_stat,j).apic_timer_irqs);
-		seq_printf(p, "  Local timer interrupts\n");
-#endif
-#ifdef CONFIG_SMP
-		seq_printf(p, "RES: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ",
-				per_cpu(irq_stat,j).irq_resched_count);
-		seq_printf(p, "  Rescheduling interrupts\n");
-		seq_printf(p, "CAL: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ",
-				per_cpu(irq_stat,j).irq_call_count);
-		seq_printf(p, "  function call interrupts\n");
-		seq_printf(p, "TLB: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ",
-				per_cpu(irq_stat,j).irq_tlb_count);
-		seq_printf(p, "  TLB shootdowns\n");
-#endif
-#ifdef CONFIG_X86_MCE
-		seq_printf(p, "TRM: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ",
-				per_cpu(irq_stat,j).irq_thermal_count);
-		seq_printf(p, "  Thermal event interrupts\n");
-#endif
-#ifdef CONFIG_X86_LOCAL_APIC
-		seq_printf(p, "SPU: ");
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ",
-				per_cpu(irq_stat,j).irq_spurious_count);
-		seq_printf(p, "  Spurious interrupts\n");
-#endif
-		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
-#if defined(CONFIG_X86_IO_APIC)
-		seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
-#endif
-	}
-	return 0;
+	return true;
 }
-
-/*
- * /proc/stat helpers
- */
-u64 arch_irq_stat_cpu(unsigned int cpu)
-{
-	u64 sum = nmi_count(cpu);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	sum += per_cpu(irq_stat, cpu).apic_timer_irqs;
-#endif
-#ifdef CONFIG_SMP
-	sum += per_cpu(irq_stat, cpu).irq_resched_count;
-	sum += per_cpu(irq_stat, cpu).irq_call_count;
-	sum += per_cpu(irq_stat, cpu).irq_tlb_count;
-#endif
-#ifdef CONFIG_X86_MCE
-	sum += per_cpu(irq_stat, cpu).irq_thermal_count;
-#endif
-#ifdef CONFIG_X86_LOCAL_APIC
-	sum += per_cpu(irq_stat, cpu).irq_spurious_count;
-#endif
-	return sum;
-}
-
-u64 arch_irq_stat(void)
-{
-	u64 sum = atomic_read(&irq_err_count);
-
-#ifdef CONFIG_X86_IO_APIC
-	sum += atomic_read(&irq_mis_count);
-#endif
-	return sum;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <mach_apic.h>
-
-void fixup_irqs(cpumask_t map)
-{
-	unsigned int irq;
-	static int warned;
-
-	for (irq = 0; irq < NR_IRQS; irq++) {
-		cpumask_t mask;
-		if (irq == 2)
-			continue;
-
-		cpus_and(mask, irq_desc[irq].affinity, map);
-		if (any_online_cpu(mask) == NR_CPUS) {
-			printk("Breaking affinity for irq %i\n", irq);
-			mask = map;
-		}
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, mask);
-		else if (irq_desc[irq].action && !(warned++))
-			printk("Cannot set affinity for irq %i\n", irq);
-	}
-
-#if 0
-	barrier();
-	/* Ingo Molnar says: "after the IO-APIC masks have been redirected
-	   [note the nop - the interrupt-enable boundary on x86 is two
-	   instructions from sti] - to flush out pending hardirqs and
-	   IPIs. After this point nothing is supposed to reach this CPU." */
-	__asm__ __volatile__("sti; nop; cli");
-	barrier();
-#else
-	/* That doesn't seem sufficient.  Give it 1ms. */
-	local_irq_enable();
-	mdelay(1);
-	local_irq_disable();
-#endif
-}
-#endif
-