arch/x86/kernel/crash.c

/*
 * Architecture specific (i386/x86_64) functions for kexec based crash dumps.
 *
 * Created by: Hariprasad Nellitheertha (hari@in.ibm.com)
 *
 * Copyright (C) IBM Corporation, 2004. All rights reserved.
 *
 */

#include <linux/init.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/smp.h>
#include <linux/reboot.h>
#include <linux/kexec.h>
#include <linux/delay.h>
#include <linux/elf.h>
#include <linux/elfcore.h>

#include <asm/processor.h>
#include <asm/hardirq.h>
#include <asm/nmi.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/hpet.h>
#include <linux/kdebug.h>
#include <asm/smp.h>
#include <asm/reboot.h>

#include <mach_ipi.h>

typedef void (*nmi_shootdown_cb)(int, struct die_args*);

#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)

/* This keeps a track of which one is crashing cpu. */
static int crashing_cpu;
static nmi_shootdown_cb shootdown_callback;

static atomic_t waiting_for_crash_ipi;

static void kdump_nmi_callback(int cpu, struct die_args *args)
{
	struct pt_regs *regs;
#ifdef CONFIG_X86_32
	struct pt_regs fixed_regs;
#endif

	regs = args->regs;

#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();
}

static int crash_nmi_callback(struct notifier_block *self,
			unsigned long val, void *data)
{
	int cpu;

	if (val != DIE_NMI_IPI)
		return NOTIFY_OK;

	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();

	shootdown_callback(cpu, (struct die_args *)data);

	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,
};

static void nmi_shootdown_cpus(nmi_shootdown_cb callback)
{
	unsigned long msecs;

	/* Make a note of crashing cpu. Will be used in NMI callback.*/
	crashing_cpu = safe_smp_processor_id();

	shootdown_callback = callback;

	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
	 */
	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 */
}

static void kdump_nmi_shootdown_cpus(void)
{
	nmi_shootdown_cpus(kdump_nmi_callback);

	disable_local_APIC();
}

#else
static void kdump_nmi_shootdown_cpus(void)
{
	/* There are no cpus to shootdown */
}
#endif

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.
	 * The minimum amount of code to allow a kexec'd kernel
	 * to run successfully needs to happen here.
	 *
	 * In practice this means shooting down the other cpus in
	 * an SMP system.
	 */
	/* The kernel is broken so disable interrupts */
	local_irq_disable();

	kdump_nmi_shootdown_cpus();
	lapic_shutdown();
#if defined(CONFIG_X86_IO_APIC)
	disable_IO_APIC();
#endif
#ifdef CONFIG_HPET_TIMER
	hpet_disable();
#endif
	crash_save_cpu(regs, safe_smp_processor_id());
}