diff options
Diffstat (limited to 'arch/x86/kernel/crash.c')
| -rw-r--r-- | arch/x86/kernel/crash.c | 139 |
1 files changed, 64 insertions, 75 deletions
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9a5fa0abfcc..507de806659 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -7,7 +7,6 @@ * */ -#include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/smp.h> @@ -16,6 +15,7 @@ #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/module.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -24,104 +24,80 @@ #include <asm/apic.h> #include <asm/hpet.h> #include <linux/kdebug.h> -#include <asm/smp.h> +#include <asm/cpu.h> +#include <asm/reboot.h> +#include <asm/virtext.h> -#ifdef CONFIG_X86_32 -#include <mach_ipi.h> -#else -#include <asm/mach_apic.h> -#endif +int in_crash_kexec; + +/* + * This is used to VMCLEAR all VMCSs loaded on the + * processor. And when loading kvm_intel module, the + * callback function pointer will be assigned. + * + * protected by rcu. + */ +crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL; +EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); -/* This keeps a track of which one is crashing cpu. */ -static int crashing_cpu; +static inline void cpu_crash_vmclear_loaded_vmcss(void) +{ + crash_vmclear_fn *do_vmclear_operation = NULL; + + rcu_read_lock(); + do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); + if (do_vmclear_operation) + do_vmclear_operation(); + rcu_read_unlock(); +} #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) -static atomic_t waiting_for_crash_ipi; -static int crash_nmi_callback(struct notifier_block *self, - unsigned long val, void *data) +static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { - struct pt_regs *regs; #ifdef CONFIG_X86_32 struct pt_regs fixed_regs; -#endif - int cpu; - - if (val != DIE_NMI_IPI) - return NOTIFY_OK; - - regs = ((struct die_args *)data)->regs; - cpu = raw_smp_processor_id(); - /* 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 NOTIFY_STOP; - local_irq_disable(); - -#ifdef CONFIG_X86_32 if (!user_mode_vm(regs)) { crash_fixup_ss_esp(&fixed_regs, regs); regs = &fixed_regs; } #endif crash_save_cpu(regs, cpu); - disable_local_APIC(); - atomic_dec(&waiting_for_crash_ipi); - /* Assume hlt works */ - halt(); - for (;;) - cpu_relax(); - - return 1; -} -static void smp_send_nmi_allbutself(void) -{ - cpumask_t mask = cpu_online_map; - cpu_clear(safe_smp_processor_id(), mask); - if (!cpus_empty(mask)) - send_IPI_mask(mask, NMI_VECTOR); -} - -static struct notifier_block crash_nmi_nb = { - .notifier_call = crash_nmi_callback, -}; + /* + * VMCLEAR VMCSs loaded on all cpus if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); -static void nmi_shootdown_cpus(void) -{ - unsigned long msecs; - - atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); - /* Would it be better to replace the trap vector here? */ - if (register_die_notifier(&crash_nmi_nb)) - return; /* return what? */ - /* Ensure the new callback function is set before sending - * out the NMI + /* Disable VMX or SVM if needed. + * + * We need to disable virtualization on all CPUs. + * Having VMX or SVM enabled on any CPU may break rebooting + * after the kdump kernel has finished its task. */ - wmb(); + cpu_emergency_vmxoff(); + cpu_emergency_svm_disable(); - smp_send_nmi_allbutself(); + disable_local_APIC(); +} - 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--; - } +static void kdump_nmi_shootdown_cpus(void) +{ + in_crash_kexec = 1; + nmi_shootdown_cpus(kdump_nmi_callback); - /* Leave the nmi callback set */ disable_local_APIC(); } + #else -static void nmi_shootdown_cpus(void) +static void kdump_nmi_shootdown_cpus(void) { /* There are no cpus to shootdown */ } #endif -void machine_crash_shutdown(struct pt_regs *regs) +void native_machine_crash_shutdown(struct pt_regs *regs) { /* This function is only called after the system * has panicked or is otherwise in a critical state. @@ -134,13 +110,26 @@ void machine_crash_shutdown(struct pt_regs *regs) /* The kernel is broken so disable interrupts */ local_irq_disable(); - /* Make a note of crashing cpu. Will be used in NMI callback.*/ - crashing_cpu = safe_smp_processor_id(); - nmi_shootdown_cpus(); - lapic_shutdown(); -#if defined(CONFIG_X86_IO_APIC) + kdump_nmi_shootdown_cpus(); + + /* + * VMCLEAR VMCSs loaded on this cpu if needed. + */ + cpu_crash_vmclear_loaded_vmcss(); + + /* Booting kdump kernel with VMX or SVM enabled won't work, + * because (among other limitations) we can't disable paging + * with the virt flags. + */ + cpu_emergency_vmxoff(); + cpu_emergency_svm_disable(); + +#ifdef CONFIG_X86_IO_APIC + /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ + ioapic_zap_locks(); disable_IO_APIC(); #endif + lapic_shutdown(); #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif |