1 files changed, 157 insertions, 97 deletions

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 147352df28b9..47a6f6f12478 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -48,6 +48,29 @@ void ack_bad_irq(unsigned int irq)
 #endif
 }
 
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+/* Debugging check for stack overflow: is there less than 1KB free? */
+static int check_stack_overflow(void)
+{
+        long sp;
+
+        __asm__ __volatile__("andl %%esp,%0" :
+                             "=r" (sp) : "0" (THREAD_SIZE - 1));
+
+        return sp < (sizeof(struct thread_info) + STACK_WARN);
+}
+
+static void print_stack_overflow(void)
+{
+        printk(KERN_WARNING "low stack detected by irq handler\n");
+        dump_stack();
+}
+
+#else
+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)
@@ -59,48 +82,29 @@ union irq_ctx {
 
 static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly;
 static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly;
-#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)
-{       
-        struct pt_regs *old_regs;
-        /* high bit used in ret_from_ code */
-        int irq = ~regs->orig_ax;
-        struct irq_desc *desc = irq_desc + irq;
-#ifdef CONFIG_4KSTACKS
-        union irq_ctx *curctx, *irqctx;
-        u32 *isp;
-#endif
+static char softirq_stack[NR_CPUS * THREAD_SIZE]
+                __attribute__((__section__(".bss.page_aligned")));
 
-        if (unlikely((unsigned)irq >= NR_IRQS)) {
-                printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
-                                        __func__, irq);
-                BUG();
-        }
+static char hardirq_stack[NR_CPUS * THREAD_SIZE]
+                __attribute__((__section__(".bss.page_aligned")));
 
-        old_regs = set_irq_regs(regs);
-        irq_enter();
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-        /* Debugging check for stack overflow: is there less than 1KB free? */
-        {
-                long sp;
-
-                __asm__ __volatile__("andl %%esp,%0" :
-                                        "=r" (sp) : "0" (THREAD_SIZE - 1));
-                if (unlikely(sp < (sizeof(struct thread_info) + STACK_WARN))) {
-                        printk("do_IRQ: stack overflow: %ld\n",
-                                sp - sizeof(struct thread_info));
-                        dump_stack();
-                }
-        }
-#endif
+static void call_on_stack(void *func, void *stack)
+{
+        asm volatile("xchgl     %%ebx,%%esp     \n"
+                     "call      *%%edi          \n"
+                     "movl      %%ebx,%%esp     \n"
+                     : "=b" (stack)
+                     : "0" (stack),
+                       "D"(func)
+                     : "memory", "cc", "edx", "ecx", "eax");
+}
 
-#ifdef CONFIG_4KSTACKS
+static inline int
+execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
+{
+        union irq_ctx *curctx, *irqctx;
+        u32 *isp, arg1, arg2;
 
         curctx = (union irq_ctx *) current_thread_info();
         irqctx = hardirq_ctx[smp_processor_id()];
@@ -111,52 +115,39 @@ unsigned int do_IRQ(struct pt_regs *regs)
          * handler) we can't do that and just have to keep using the
          * current stack (which is the irq stack already after all)
          */
-        if (curctx != irqctx) {
-                int arg1, arg2, bx;
-
-                /* 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;
+        if (unlikely(curctx == irqctx))
+                return 0;
 
-                /*
-                 * 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);
-
-                asm volatile(
-                        "       xchgl  %%ebx,%%esp    \n"
-                        "       call   *%%edi         \n"
-                        "       movl   %%ebx,%%esp    \n"
-                        : "=a" (arg1), "=d" (arg2), "=b" (bx)
-                        :  "0" (irq),   "1" (desc),  "2" (isp),
-                           "D" (desc->handle_irq)
-                        : "memory", "cc", "ecx"
-                );
-        } else
-#endif
-                desc->handle_irq(irq, desc);
+        /* 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;
 
-        irq_exit();
-        set_irq_regs(old_regs);
+        /*
+         * 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);
+
+        if (unlikely(overflow))
+                call_on_stack(print_stack_overflow, isp);
+
+        asm volatile("xchgl     %%ebx,%%esp     \n"
+                     "call      *%%edi          \n"
+                     "movl      %%ebx,%%esp     \n"
+                     : "=a" (arg1), "=d" (arg2), "=b" (isp)
+                     :  "0" (irq),   "1" (desc),  "2" (isp),
+                        "D" (desc->handle_irq)
+                     : "memory", "cc", "ecx");
         return 1;
 }
 
-#ifdef CONFIG_4KSTACKS
-
-static char softirq_stack[NR_CPUS * THREAD_SIZE]
-                __attribute__((__section__(".bss.page_aligned")));
-
-static char hardirq_stack[NR_CPUS * THREAD_SIZE]
-                __attribute__((__section__(".bss.page_aligned")));
-
 /*
  * allocate per-cpu stacks for hardirq and for softirq processing
  */
-void irq_ctx_init(int cpu)
+void __cpuinit irq_ctx_init(int cpu)
 {
         union irq_ctx *irqctx;
 
@@ -164,25 +155,25 @@ void irq_ctx_init(int 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);
+        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;
 
         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);
+        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;
 
-        printk("CPU %u irqstacks, hard=%p soft=%p\n",
-                cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
+        printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
+               cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
 }
 
 void irq_ctx_exit(int cpu)
@@ -211,25 +202,56 @@ asmlinkage void do_softirq(void)
                 /* build the stack frame on the softirq stack */
                 isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
 
-                asm volatile(
-                        "       xchgl   %%ebx,%%esp     \n"
-                        "       call    __do_softirq    \n"
-                        "       movl    %%ebx,%%esp     \n"
-                        : "=b"(isp)
-                        : "0"(isp)
-                        : "memory", "cc", "edx", "ecx", "eax"
-                );
+                call_on_stack(__do_softirq, isp);
                 /*
                  * Shouldnt happen, we returned above if in_interrupt():
-                 */
+                 */
                 WARN_ON_ONCE(softirq_count());
         }
 
         local_irq_restore(flags);
 }
+
+#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)
+{
+        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();
+
+        overflow = check_stack_overflow();
+
+        if (!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:
  */
 
@@ -313,16 +335,20 @@ skip:
                                 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));
@@ -331,6 +357,40 @@ skip:
         return 0;
 }
 
+/*
+ * /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>