12 files changed, 337 insertions, 10 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a8d389d72405..eb93fd0ec734 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1824,6 +1824,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
         nomfgpt         [X86-32] Disable Multi-Function General Purpose
                         Timer usage (for AMD Geode machines).
 
+        nonmi_ipi       [X86] Disable using NMI IPIs during panic/reboot to
+                        shutdown the other cpus.  Instead use the REBOOT_VECTOR
+                        irq.
+
         nopat           [X86] Disable PAT (page attribute table extension of
                         pagetables) support.
 
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 1f2463671a1a..6d8cd8b2c30d 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -49,6 +49,7 @@ show up in /proc/sys/kernel:
 - panic
 - panic_on_oops
 - panic_on_unrecovered_nmi
+- panic_on_stackoverflow
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
@@ -393,6 +394,19 @@ Controls the kernel's behaviour when an oops or BUG is encountered.
 
 ==============================================================
 
+panic_on_stackoverflow:
+
+Controls the kernel's behavior when detecting the overflows of
+kernel, IRQ and exception stacks except a user stack.
+This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.
+
+0: try to continue operation.
+
+1: panic immediately.
+
+==============================================================
+
+
 pid_max:
 
 PID allocation wrap value.  When the kernel's next PID value
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index bf56e1793272..aa4158f3ce62 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -63,8 +63,11 @@ config DEBUG_STACKOVERFLOW
         bool "Check for stack overflows"
         depends on DEBUG_KERNEL
         ---help---
-          This option will cause messages to be printed if free stack space
-          drops below a certain limit.
+          Say Y here if you want to check the overflows of kernel, IRQ
+          and exception stacks. This option will cause messages of the
+          stacks in detail when free stack space drops below a certain
+          limit.
+          If in doubt, say "N".
 
 config X86_PTDUMP
         bool "Export kernel pagetable layout to userspace via debugfs"
@@ -284,4 +287,16 @@ config DEBUG_STRICT_USER_COPY_CHECKS
 
           If unsure, or if you run an older (pre 4.4) gcc, say N.
 
+config DEBUG_NMI_SELFTEST
+        bool "NMI Selftest"
+        depends on DEBUG_KERNEL && X86_LOCAL_APIC
+        ---help---
+          Enabling this option turns on a quick NMI selftest to verify
+          that the NMI behaves correctly.
+
+          This might help diagnose strange hangs that rely on NMI to
+          function properly.
+
+          If unsure, say N.
+
 endmenu
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 73b11bc0ae6f..0434c400287c 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -225,5 +225,11 @@ extern int hard_smp_processor_id(void);
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_DEBUG_NMI_SELFTEST
+extern void nmi_selftest(void);
+#else
+#define nmi_selftest() do { } while (0)
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8baca3c4871c..02b2f05b371e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -80,6 +80,7 @@ obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
 obj-$(CONFIG_AMD_NB)            += amd_nb.o
 obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
 obj-$(CONFIG_DEBUG_NX_TEST)     += test_nx.o
+obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
 obj-$(CONFIG_KVM_GUEST)         += kvm.o
 obj-$(CONFIG_KVM_CLOCK)         += kvmclock.o
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 72090705a656..40fc86161d92 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -28,6 +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)
 {
@@ -43,6 +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
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 69bca468c47a..d04d3ecded62 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,6 +26,8 @@ EXPORT_PER_CPU_SYMBOL(irq_stat);
 DEFINE_PER_CPU(struct pt_regs *, irq_regs);
 EXPORT_PER_CPU_SYMBOL(irq_regs);
 
+int sysctl_panic_on_stackoverflow;
+
 /*
  * Probabilistic stack overflow check:
  *
@@ -36,18 +38,39 @@ EXPORT_PER_CPU_SYMBOL(irq_regs);
 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);
 
         if (user_mode_vm(regs))
                 return;
 
-        WARN_ONCE(regs->sp >= curbase &&
-                  regs->sp <= curbase + THREAD_SIZE &&
-                  regs->sp <  curbase + sizeof(struct thread_info) +
-                                        sizeof(struct pt_regs) + 128,
+        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);
 
-                  "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-                        current->comm, curbase, regs->sp);
+        if (sysctl_panic_on_stackoverflow)
+                panic("low stack detected by irq handler - check messages\n");
 #endif
 }
 
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
new file mode 100644
index 000000000000..0d01a8ea4e11
--- /dev/null
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -0,0 +1,180 @@
+/*
+ * arch/x86/kernel/nmi-selftest.c
+ *
+ * Testsuite for NMI: IPIs
+ *
+ * Started by Don Zickus:
+ * (using lib/locking-selftest.c as a guide)
+ *
+ *   Copyright (C) 2011 Red Hat, Inc., Don Zickus <dzickus@redhat.com>
+ */
+
+#include <linux/smp.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+
+#include <asm/apic.h>
+#include <asm/nmi.h>
+
+#define SUCCESS         0
+#define FAILURE         1
+#define TIMEOUT         2
+
+static int nmi_fail;
+
+/* check to see if NMI IPIs work on this machine */
+static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __read_mostly;
+
+static int testcase_total;
+static int testcase_successes;
+static int expected_testcase_failures;
+static int unexpected_testcase_failures;
+static int unexpected_testcase_unknowns;
+
+static int nmi_unk_cb(unsigned int val, struct pt_regs *regs)
+{
+        unexpected_testcase_unknowns++;
+        return NMI_HANDLED;
+}
+
+static void init_nmi_testsuite(void)
+{
+        /* trap all the unknown NMIs we may generate */
+        register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+}
+
+static void cleanup_nmi_testsuite(void)
+{
+        unregister_nmi_handler(NMI_UNKNOWN, "nmi_selftest_unk");
+}
+
+static int test_nmi_ipi_callback(unsigned int val, struct pt_regs *regs)
+{
+        int cpu = raw_smp_processor_id();
+
+        if (cpumask_test_and_clear_cpu(cpu, to_cpumask(nmi_ipi_mask)))
+                return NMI_HANDLED;
+
+        return NMI_DONE;
+}
+
+static void test_nmi_ipi(struct cpumask *mask)
+{
+        unsigned long timeout;
+
+        if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+                                 NMI_FLAG_FIRST, "nmi_selftest")) {
+                nmi_fail = FAILURE;
+                return;
+        }
+
+        /* sync above data before sending NMI */
+        wmb();
+
+        apic->send_IPI_mask(mask, NMI_VECTOR);
+
+        /* Don't wait longer than a second */
+        timeout = USEC_PER_SEC;
+        while (!cpumask_empty(mask) && timeout--)
+                udelay(1);
+
+        /* What happens if we timeout, do we still unregister?? */
+        unregister_nmi_handler(NMI_LOCAL, "nmi_selftest");
+
+        if (!timeout)
+                nmi_fail = TIMEOUT;
+        return;
+}
+
+static void remote_ipi(void)
+{
+        cpumask_copy(to_cpumask(nmi_ipi_mask), cpu_online_mask);
+        cpumask_clear_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask));
+        if (!cpumask_empty(to_cpumask(nmi_ipi_mask)))
+                test_nmi_ipi(to_cpumask(nmi_ipi_mask));
+}
+
+static void local_ipi(void)
+{
+        cpumask_clear(to_cpumask(nmi_ipi_mask));
+        cpumask_set_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask));
+        test_nmi_ipi(to_cpumask(nmi_ipi_mask));
+}
+
+static void reset_nmi(void)
+{
+        nmi_fail = 0;
+}
+
+static void dotest(void (*testcase_fn)(void), int expected)
+{
+        testcase_fn();
+        /*
+         * Filter out expected failures:
+         */
+        if (nmi_fail != expected) {
+                unexpected_testcase_failures++;
+
+                if (nmi_fail == FAILURE)
+                        printk("FAILED |");
+                else if (nmi_fail == TIMEOUT)
+                        printk("TIMEOUT|");
+                else
+                        printk("ERROR  |");
+                dump_stack();
+        } else {
+                testcase_successes++;
+                printk("  ok  |");
+        }
+        testcase_total++;
+
+        reset_nmi();
+}
+
+static inline void print_testname(const char *testname)
+{
+        printk("%12s:", testname);
+}
+
+void nmi_selftest(void)
+{
+        init_nmi_testsuite();
+
+        /*
+         * Run the testsuite:
+         */
+        printk("----------------\n");
+        printk("| NMI testsuite:\n");
+        printk("--------------------\n");
+
+        print_testname("remote IPI");
+        dotest(remote_ipi, SUCCESS);
+        printk("\n");
+        print_testname("local IPI");
+        dotest(local_ipi, SUCCESS);
+        printk("\n");
+
+        cleanup_nmi_testsuite();
+
+        if (unexpected_testcase_failures) {
+                printk("--------------------\n");
+                printk("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
+                        unexpected_testcase_failures, testcase_total);
+                printk("-----------------------------------------------------------------\n");
+        } else if (expected_testcase_failures && testcase_successes) {
+                printk("--------------------\n");
+                printk("%3d out of %3d testcases failed, as expected. |\n",
+                        expected_testcase_failures, testcase_total);
+                printk("----------------------------------------------------\n");
+        } else if (expected_testcase_failures && !testcase_successes) {
+                printk("--------------------\n");
+                printk("All %3d testcases failed, as expected. |\n",
+                        expected_testcase_failures);
+                printk("----------------------------------------\n");
+        } else {
+                printk("--------------------\n");
+                printk("Good, all %3d testcases passed! |\n",
+                        testcase_successes);
+                printk("---------------------------------\n");
+        }
+}
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 16204dc15484..66c74f481cab 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -29,6 +29,7 @@
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 /*
  *      Some notes on x86 processor bugs affecting SMP operation:
  *
@@ -148,6 +149,60 @@ void native_send_call_func_ipi(const struct cpumask *mask)
         free_cpumask_var(allbutself);
 }
 
+static atomic_t stopping_cpu = ATOMIC_INIT(-1);
+
+static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
+{
+        /* We are registered on stopping cpu too, avoid spurious NMI */
+        if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
+                return NMI_HANDLED;
+
+        stop_this_cpu(NULL);
+
+        return NMI_HANDLED;
+}
+
+static void native_nmi_stop_other_cpus(int wait)
+{
+        unsigned long flags;
+        unsigned long timeout;
+
+        if (reboot_force)
+                return;
+
+        /*
+         * Use an own vector here because smp_call_function
+         * does lots of things not suitable in a panic situation.
+         */
+        if (num_online_cpus() > 1) {
+                /* did someone beat us here? */
+                if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1)
+                        return;
+
+                if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
+                                         NMI_FLAG_FIRST, "smp_stop"))
+                        /* Note: we ignore failures here */
+                        return;
+
+                /* sync above data before sending NMI */
+                wmb();
+
+                apic->send_IPI_allbutself(NMI_VECTOR);
+
+                /*
+                 * Don't wait longer than a second if the caller
+                 * didn't ask us to wait.
+                 */
+                timeout = USEC_PER_SEC;
+                while (num_online_cpus() > 1 && (wait || timeout--))
+                        udelay(1);
+        }
+
+        local_irq_save(flags);
+        disable_local_APIC();
+        local_irq_restore(flags);
+}
+
 /*
  * this function calls the 'stop' function on all other CPUs in the system.
  */
@@ -160,7 +215,7 @@ asmlinkage void smp_reboot_interrupt(void)
         irq_exit();
 }
 
-static void native_stop_other_cpus(int wait)
+static void native_irq_stop_other_cpus(int wait)
 {
         unsigned long flags;
         unsigned long timeout;
@@ -194,6 +249,11 @@ static void native_stop_other_cpus(int wait)
         local_irq_restore(flags);
 }
 
+static void native_smp_disable_nmi_ipi(void)
+{
+        smp_ops.stop_other_cpus = native_irq_stop_other_cpus;
+}
+
 /*
  * Reschedule call back.
  */
@@ -225,12 +285,20 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
         irq_exit();
 }
 
+static int __init nonmi_ipi_setup(char *str)
+{
+        native_smp_disable_nmi_ipi();
+        return 1;
+}
+
+__setup("nonmi_ipi", nonmi_ipi_setup);
+
 struct smp_ops smp_ops = {
         .smp_prepare_boot_cpu   = native_smp_prepare_boot_cpu,
         .smp_prepare_cpus       = native_smp_prepare_cpus,
         .smp_cpus_done          = native_smp_cpus_done,
 
-        .stop_other_cpus        = native_stop_other_cpus,
+        .stop_other_cpus        = native_nmi_stop_other_cpus,
         .smp_send_reschedule    = native_smp_send_reschedule,
 
         .cpu_up                 = native_cpu_up,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e38e21754eea..79f636bc44c6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1143,6 +1143,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 {
         pr_debug("Boot done.\n");
 
+        nmi_selftest();
         impress_friends();
 #ifdef CONFIG_X86_IO_APIC
         setup_ioapic_dest();
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index f48e8a528544..d0a7a0c71661 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -341,6 +341,7 @@ extern int panic_timeout;
 extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
+extern int sysctl_panic_on_stackoverflow;
 extern const char *print_tainted(void);
 extern void add_taint(unsigned flag);
 extern int test_taint(unsigned flag);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ae2719643854..f487f257e05e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -803,6 +803,15 @@ static struct ctl_table kern_table[] = {
                 .mode           = 0644,
                 .proc_handler   = proc_dointvec,
         },
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+        {
+                .procname       = "panic_on_stackoverflow",
+                .data           = &sysctl_panic_on_stackoverflow,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = proc_dointvec,
+        },
+#endif
         {
                 .procname       = "bootloader_type",
                 .data           = &bootloader_type,