crash.c 4.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 * Architecture specific (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>
14
#include <linux/irq.h>
15 16
#include <linux/reboot.h>
#include <linux/kexec.h>
17
#include <linux/delay.h>
18 19
#include <linux/elf.h>
#include <linux/elfcore.h>
20 21 22 23 24

#include <asm/processor.h>
#include <asm/hardirq.h>
#include <asm/nmi.h>
#include <asm/hw_irq.h>
25
#include <asm/mach_apic.h>
26
#include <asm/kdebug.h>
27 28 29 30

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

31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
static u32 *append_elf_note(u32 *buf, char *name, unsigned type,
						void *data, size_t data_len)
{
	struct elf_note note;

	note.n_namesz = strlen(name) + 1;
	note.n_descsz = data_len;
	note.n_type   = type;
	memcpy(buf, &note, sizeof(note));
	buf += (sizeof(note) +3)/4;
	memcpy(buf, name, note.n_namesz);
	buf += (note.n_namesz + 3)/4;
	memcpy(buf, data, note.n_descsz);
	buf += (note.n_descsz + 3)/4;

	return buf;
}

static void final_note(u32 *buf)
{
	struct elf_note note;

	note.n_namesz = 0;
	note.n_descsz = 0;
	note.n_type   = 0;
	memcpy(buf, &note, sizeof(note));
}

static void crash_save_this_cpu(struct pt_regs *regs, int cpu)
{
	struct elf_prstatus prstatus;
	u32 *buf;

	if ((cpu < 0) || (cpu >= NR_CPUS))
		return;

	/* Using ELF notes here is opportunistic.
	 * I need a well defined structure format
	 * for the data I pass, and I need tags
	 * on the data to indicate what information I have
	 * squirrelled away.  ELF notes happen to provide
72
	 * all of that, no need to invent something new.
73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
	 */

	buf = (u32*)per_cpu_ptr(crash_notes, cpu);

	if (!buf)
		return;

	memset(&prstatus, 0, sizeof(prstatus));
	prstatus.pr_pid = current->pid;
	elf_core_copy_regs(&prstatus.pr_reg, regs);
	buf = append_elf_note(buf, "CORE", NT_PRSTATUS, &prstatus,
					sizeof(prstatus));
	final_note(buf);
}

static void crash_save_self(struct pt_regs *regs)
{
	int cpu;

	cpu = smp_processor_id();
	crash_save_this_cpu(regs, cpu);
}

96 97 98
#ifdef CONFIG_SMP
static atomic_t waiting_for_crash_ipi;

99 100
static int crash_nmi_callback(struct notifier_block *self,
				unsigned long val, void *data)
101
{
102 103 104
	struct pt_regs *regs;
	int cpu;

105
	if (val != DIE_NMI_IPI)
106 107 108 109 110
		return NOTIFY_OK;

	regs = ((struct die_args *)data)->regs;
	cpu = raw_smp_processor_id();

111 112 113 114 115 116
	/*
	 * 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)
117
		return NOTIFY_STOP;
118 119
	local_irq_disable();

120
	crash_save_this_cpu(regs, cpu);
121 122 123 124
	disable_local_APIC();
	atomic_dec(&waiting_for_crash_ipi);
	/* Assume hlt works */
	for(;;)
125
		halt();
126 127 128 129 130 131

	return 1;
}

static void smp_send_nmi_allbutself(void)
{
132
	send_IPI_allbutself(NMI_VECTOR);
133 134 135 136 137 138 139 140
}

/*
 * This code is a best effort heuristic to get the
 * other cpus to stop executing. So races with
 * cpu hotplug shouldn't matter.
 */

141 142 143 144
static struct notifier_block crash_nmi_nb = {
	.notifier_call = crash_nmi_callback,
};

145 146 147 148 149
static void nmi_shootdown_cpus(void)
{
	unsigned long msecs;

	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
150 151
	if (register_die_notifier(&crash_nmi_nb))
		return;         /* return what? */
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174

	/*
	 * 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
175

176
void machine_crash_shutdown(struct pt_regs *regs)
177
{
178 179
	/*
	 * This function is only called after the system
L
Lee Revell 已提交
180
	 * has panicked or is otherwise in a critical state.
181 182 183 184 185 186
	 * 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.
	 */
187 188 189 190 191 192 193 194 195 196 197 198
	/* 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();

	disable_IO_APIC();

199
	crash_save_self(regs);
200
}