diff --git a/arch/x86_64/kernel/crash.c b/arch/x86_64/kernel/crash.c index efe450760bbc..abc601f36b6e 100644 --- a/arch/x86_64/kernel/crash.c +++ b/arch/x86_64/kernel/crash.c @@ -13,15 +13,85 @@ #include #include #include +#include #include #include #include #include +#include + +/* This keeps a track of which one is crashing cpu. */ +static int crashing_cpu; + +#ifdef CONFIG_SMP +static atomic_t waiting_for_crash_ipi; + +static int crash_nmi_callback(struct pt_regs *regs, int cpu) +{ + /* + * Don't do anything if this handler is invoked on crashing cpu. + * Otherwise, system will completely hang. Crashing cpu can get + * an NMI if system was initially booted with nmi_watchdog parameter. + */ + if (cpu == crashing_cpu) + return 1; + local_irq_disable(); + + disable_local_APIC(); + atomic_dec(&waiting_for_crash_ipi); + /* Assume hlt works */ + for(;;) + asm("hlt"); + + return 1; +} + +static void smp_send_nmi_allbutself(void) +{ + send_IPI_allbutself(APIC_DM_NMI); +} + +/* + * This code is a best effort heuristic to get the + * other cpus to stop executing. So races with + * cpu hotplug shouldn't matter. + */ + +static void nmi_shootdown_cpus(void) +{ + unsigned long msecs; + + atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + set_nmi_callback(crash_nmi_callback); + + /* + * Ensure the new callback function is set before sending + * out the NMI + */ + wmb(); + + smp_send_nmi_allbutself(); + + msecs = 1000; /* Wait at most a second for the other cpus to stop */ + while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { + mdelay(1); + msecs--; + } + /* Leave the nmi callback set */ + disable_local_APIC(); +} +#else +static void nmi_shootdown_cpus(void) +{ + /* There are no cpus to shootdown */ +} +#endif void machine_crash_shutdown(struct pt_regs *regs) { - /* This function is only called after the system + /* + * This function is only called after the system * has paniced or is otherwise in a critical state. * The minimum amount of code to allow a kexec'd kernel * to run successfully needs to happen here. @@ -29,4 +99,18 @@ void machine_crash_shutdown(struct pt_regs *regs) * In practice this means shooting down the other cpus in * an SMP system. */ + /* The kernel is broken so disable interrupts */ + local_irq_disable(); + + /* Make a note of crashing cpu. Will be used in NMI callback.*/ + crashing_cpu = smp_processor_id(); + nmi_shootdown_cpus(); + + if(cpu_has_apic) + disable_local_APIC(); + +#if defined(CONFIG_X86_IO_APIC) + disable_IO_APIC(); +#endif + }