1 files changed, 60 insertions, 156 deletions

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 74b9ff7341e..63ce838e5a5 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -16,6 +16,8 @@
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/uaccess.h>
+#include <linux/percpu.h>
+#include <linux/mm.h>
 
 #include <asm/apic.h>
 
@@ -26,6 +28,9 @@ DEFINE_PER_CPU(struct pt_regs *, irq_regs);
 EXPORT_PER_CPU_SYMBOL(irq_regs);
 
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
+
+int sysctl_panic_on_stackoverflow __read_mostly;
+
 /* Debugging check for stack overflow: is there less than 1KB free? */
 static int check_stack_overflow(void)
 {
@@ -41,6 +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
@@ -48,20 +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)
 {
@@ -74,14 +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
@@ -89,21 +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);
@@ -121,158 +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);
+	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
+					       THREADINFO_GFP,
+					       THREAD_SIZE_ORDER));
+	per_cpu(hardirq_stack, cpu) = irqstk;
 
-	hardirq_ctx[cpu] = irqctx;
-
-	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]);
-}
-
-void irq_ctx_exit(int cpu)
-{
-	hardirq_ctx[cpu] = NULL;
+	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
-asmlinkage void do_softirq(void)
+void do_softirq_own_stack(void)
 {
-	unsigned long flags;
-	struct thread_info *curctx;
-	union irq_ctx *irqctx;
-	u32 *isp;
+	struct thread_info *curstk;
+	struct irq_stack *irqstk;
+	u32 *isp, *prev_esp;
 
-	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;
+	/* Push the previous esp onto the stack */
+	prev_esp = (u32 *)irqstk;
+	*prev_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());
-	}
-
-	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;
-	unsigned vector = ~regs->orig_ax;
 	struct irq_desc *desc;
-	unsigned irq;
-
-
-	old_regs = set_irq_regs(regs);
-	irq_enter();
-	irq = __get_cpu_var(vector_irq)[vector];
+	int overflow;
 
 	overflow = check_stack_overflow();
 
 	desc = irq_to_desc(irq);
-	if (unlikely(!desc)) {
-		printk(KERN_EMERG "%s: cannot handle IRQ %d vector %#x cpu %d\n",
-					__func__, irq, vector, smp_processor_id());
-		BUG();
-	}
+	if (unlikely(!desc))
+		return false;
 
-	if (!execute_on_irq_stack(overflow, desc, irq)) {
+	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;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <mach_apic.h>
-
-/* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
-void fixup_irqs(void)
-{
-	unsigned int irq;
-	static int warned;
-	struct irq_desc *desc;
-
-	for_each_irq_desc(irq, desc) {
-		const struct cpumask *affinity;
-
-		if (!desc)
-			continue;
-		if (irq == 2)
-			continue;
-
-		affinity = &desc->affinity;
-		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
-			printk("Breaking affinity for irq %i\n", irq);
-			affinity = cpu_all_mask;
-		}
-		if (desc->chip->set_affinity)
-			desc->chip->set_affinity(irq, affinity);
-		else if (desc->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
+	return true;
 }
-#endif
-