c0ce7d0886
With this patch, kdump uses the firmware soft-reset NMI for two purposes: 1) Initiate the kdump (take a crash dump) by issuing a soft-reset. 2) Break a CPU out of a deadlock condition that is detected during kdump processing. When a soft-reset is initiated each CPU will enter system_reset_exception() and set its corresponding bit in the global bit-array cpus_in_sr then call die(). When die() finds the CPU's bit set in cpu_in_sr crash_kexec() is called to initiate a crash dump. The first CPU to enter crash_kexec() is called the "crashing CPU". All other CPUs are "secondary CPUs". The secondary CPU's pass through to crash_kexec_secondary() and sleep. The crashing CPU waits for all CPUs to enter via soft-reset then boots the kdump kernel (see crash_soft_reset_check()) When the system crashes due to a panic or exception, crash_kexec() is called by panic() or die(). The crashing CPU sends an IPI to all other CPUs to notify them of the pending shutdown. If a CPU is in a deadlock or hung state with interrupts disabled, the IPI will not be delivered. The result being, that the kdump kernel is not booted. This problem is solved with the use of a firmware generated soft-reset. After the crashing_cpu has issued the IPI, it waits for 10 sec for all CPUs to enter crash_ipi_callback(). A CPU signifies its entry to crash_ipi_callback() by setting its corresponding bit in the cpus_in_crash bit array. After 10 sec, if one or more CPUs have not set their bit in cpus_in_crash we assume that the CPU(s) is deadlocked. The operator is then prompted to generate a soft-reset to break the deadlock. Each CPU enters the soft reset handler as described above. Two conditions must be handled at this point: 1) The system crashed because the operator generated a soft-reset. See 2) The system had crashed before the soft-reset was generated ( in the case of a Panic or oops). The first CPU to enter crash_kexec() uses the state of the kexec_lock to determine this state. If kexec_lock is already held then condition 2 is true and crash_kexec_secondary() is called, else; this CPU is flagged as the crashing CPU, the kexec_lock is acquired and crash_kexec() proceeds as described above. Each additional CPUs responding to the soft-reset will pass through crash_kexec() to kexec_secondary(). All secondary CPUs call crash_ipi_callback() readying them self's for the shutdown. When ready they clear their bit in cpus_in_sr. The crashing CPU waits in kexec_secondary() until all other CPUs have cleared their bits in cpus_in_sr. The kexec kernel boot is then started. Signed-off-by: Haren Myneni <haren@us.ibm.com> Signed-off-by: David Wilder <dwilder@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
149 lines
3.8 KiB
C
149 lines
3.8 KiB
C
#ifndef _ASM_POWERPC_KEXEC_H
|
|
#define _ASM_POWERPC_KEXEC_H
|
|
#ifdef __KERNEL__
|
|
|
|
/*
|
|
* Maximum page that is mapped directly into kernel memory.
|
|
* XXX: Since we copy virt we can use any page we allocate
|
|
*/
|
|
#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
|
|
|
|
/*
|
|
* Maximum address we can reach in physical address mode.
|
|
* XXX: I want to allow initrd in highmem. Otherwise set to rmo on LPAR.
|
|
*/
|
|
#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
|
|
|
|
/* Maximum address we can use for the control code buffer */
|
|
#ifdef __powerpc64__
|
|
#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
|
|
#else
|
|
/* TASK_SIZE, probably left over from use_mm ?? */
|
|
#define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
|
|
#endif
|
|
|
|
#define KEXEC_CONTROL_CODE_SIZE 4096
|
|
|
|
/* The native architecture */
|
|
#ifdef __powerpc64__
|
|
#define KEXEC_ARCH KEXEC_ARCH_PPC64
|
|
#else
|
|
#define KEXEC_ARCH KEXEC_ARCH_PPC
|
|
#endif
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#ifdef CONFIG_KEXEC
|
|
|
|
#ifdef __powerpc64__
|
|
/*
|
|
* This function is responsible for capturing register states if coming
|
|
* via panic or invoking dump using sysrq-trigger.
|
|
*/
|
|
static inline void crash_setup_regs(struct pt_regs *newregs,
|
|
struct pt_regs *oldregs)
|
|
{
|
|
if (oldregs)
|
|
memcpy(newregs, oldregs, sizeof(*newregs));
|
|
else {
|
|
/* FIXME Merge this with xmon_save_regs ?? */
|
|
unsigned long tmp1, tmp2;
|
|
__asm__ __volatile__ (
|
|
"std 0,0(%2)\n"
|
|
"std 1,8(%2)\n"
|
|
"std 2,16(%2)\n"
|
|
"std 3,24(%2)\n"
|
|
"std 4,32(%2)\n"
|
|
"std 5,40(%2)\n"
|
|
"std 6,48(%2)\n"
|
|
"std 7,56(%2)\n"
|
|
"std 8,64(%2)\n"
|
|
"std 9,72(%2)\n"
|
|
"std 10,80(%2)\n"
|
|
"std 11,88(%2)\n"
|
|
"std 12,96(%2)\n"
|
|
"std 13,104(%2)\n"
|
|
"std 14,112(%2)\n"
|
|
"std 15,120(%2)\n"
|
|
"std 16,128(%2)\n"
|
|
"std 17,136(%2)\n"
|
|
"std 18,144(%2)\n"
|
|
"std 19,152(%2)\n"
|
|
"std 20,160(%2)\n"
|
|
"std 21,168(%2)\n"
|
|
"std 22,176(%2)\n"
|
|
"std 23,184(%2)\n"
|
|
"std 24,192(%2)\n"
|
|
"std 25,200(%2)\n"
|
|
"std 26,208(%2)\n"
|
|
"std 27,216(%2)\n"
|
|
"std 28,224(%2)\n"
|
|
"std 29,232(%2)\n"
|
|
"std 30,240(%2)\n"
|
|
"std 31,248(%2)\n"
|
|
"mfmsr %0\n"
|
|
"std %0, 264(%2)\n"
|
|
"mfctr %0\n"
|
|
"std %0, 280(%2)\n"
|
|
"mflr %0\n"
|
|
"std %0, 288(%2)\n"
|
|
"bl 1f\n"
|
|
"1: mflr %1\n"
|
|
"std %1, 256(%2)\n"
|
|
"mtlr %0\n"
|
|
"mfxer %0\n"
|
|
"std %0, 296(%2)\n"
|
|
: "=&r" (tmp1), "=&r" (tmp2)
|
|
: "b" (newregs)
|
|
: "memory");
|
|
}
|
|
}
|
|
#else
|
|
/*
|
|
* Provide a dummy definition to avoid build failures. Will remain
|
|
* empty till crash dump support is enabled.
|
|
*/
|
|
static inline void crash_setup_regs(struct pt_regs *newregs,
|
|
struct pt_regs *oldregs) { }
|
|
#endif /* !__powerpc64 __ */
|
|
|
|
#define MAX_NOTE_BYTES 1024
|
|
|
|
#ifdef __powerpc64__
|
|
extern void kexec_smp_wait(void); /* get and clear naca physid, wait for
|
|
master to copy new code to 0 */
|
|
extern int crashing_cpu;
|
|
extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
|
|
extern cpumask_t cpus_in_sr;
|
|
static inline int kexec_sr_activated(int cpu)
|
|
{
|
|
return cpu_isset(cpu,cpus_in_sr);
|
|
}
|
|
#endif /* __powerpc64 __ */
|
|
|
|
struct kimage;
|
|
struct pt_regs;
|
|
extern void default_machine_kexec(struct kimage *image);
|
|
extern int default_machine_kexec_prepare(struct kimage *image);
|
|
extern void default_machine_crash_shutdown(struct pt_regs *regs);
|
|
|
|
extern void machine_kexec_simple(struct kimage *image);
|
|
extern void crash_kexec_secondary(struct pt_regs *regs);
|
|
extern int overlaps_crashkernel(unsigned long start, unsigned long size);
|
|
extern void reserve_crashkernel(void);
|
|
|
|
#else /* !CONFIG_KEXEC */
|
|
static inline int kexec_sr_activated(int cpu) { return 0; }
|
|
static inline void crash_kexec_secondary(struct pt_regs *regs) { }
|
|
|
|
static inline int overlaps_crashkernel(unsigned long start, unsigned long size)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void reserve_crashkernel(void) { ; }
|
|
|
|
#endif /* CONFIG_KEXEC */
|
|
#endif /* ! __ASSEMBLY__ */
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_POWERPC_KEXEC_H */
|