3f22c5789e
After a crash we should wait for NMI IPI event and not for external NMI or NMI watchdog tick. Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org>
203 lines
4.4 KiB
C
203 lines
4.4 KiB
C
/*
|
|
* 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>
|
|
#include <linux/irq.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/mach_apic.h>
|
|
#include <asm/kdebug.h>
|
|
|
|
/* This keeps a track of which one is crashing cpu. */
|
|
static int crashing_cpu;
|
|
|
|
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, ¬e, 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, ¬e, 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
|
|
* all of that that no need to invent something new.
|
|
*/
|
|
|
|
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);
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
static atomic_t waiting_for_crash_ipi;
|
|
|
|
static int crash_nmi_callback(struct notifier_block *self,
|
|
unsigned long val, void *data)
|
|
{
|
|
struct pt_regs *regs;
|
|
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();
|
|
|
|
crash_save_this_cpu(regs, cpu);
|
|
disable_local_APIC();
|
|
atomic_dec(&waiting_for_crash_ipi);
|
|
/* Assume hlt works */
|
|
for(;;)
|
|
halt();
|
|
|
|
return 1;
|
|
}
|
|
|
|
static void smp_send_nmi_allbutself(void)
|
|
{
|
|
send_IPI_allbutself(NMI_VECTOR);
|
|
}
|
|
|
|
/*
|
|
* This code is a best effort heuristic to get the
|
|
* other cpus to stop executing. So races with
|
|
* cpu hotplug shouldn't matter.
|
|
*/
|
|
|
|
static struct notifier_block crash_nmi_nb = {
|
|
.notifier_call = crash_nmi_callback,
|
|
};
|
|
|
|
static void nmi_shootdown_cpus(void)
|
|
{
|
|
unsigned long msecs;
|
|
|
|
atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
|
|
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 */
|
|
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
|
|
* 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();
|
|
|
|
/* 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
|
|
|
|
crash_save_self(regs);
|
|
}
|