dect/linux-2.6
Archived
14
0
Fork 0
Code Releases Activity
This repository has been archived on 2022-02-17. You can view files and clone it, but cannot push or open issues or pull requests.
linux-2.6/arch/ia64/include/asm/mca.h
Hidetoshi Seto 07a6a4ae82 [IA64] kexec: Make INIT safe while transition to 
kdump/kexec kernel

Summary:

  Asserting INIT on the beginning of kdump/kexec kernel will result
  in unexpected behavior because INIT handler for previous kernel is
  invoked on new kernel.

Description:

  In panic situation, we can receive INIT while kernel transition,
  i.e. from beginning of panic to bootstrap of kdump kernel.
  Since we initialize registers on leave from current kernel, no
  longer monarch/slave handlers of current kernel in virtual mode are
  called safely.  (In fact system goes hang as far as I confirmed)

How to Reproduce:

  Start kdump
    # echo c > /proc/sysrq-trigger
  Then assert INIT while kdump kernel is booting, before new INIT
  handler for kdump kernel is registered.

Expected(Desirable) result:

  kdump kernel boots without any problem, crashdump retrieved

Actual result:

  INIT handler for previous kernel is invoked on kdump kernel
  => panic, hang etc. (unexpected)

Proposed fix:

  We can unregister these init handlers from SAL before jumping into
  new kernel, however then the INIT will fallback to default behavior,
  result in warmboot by SAL (according to the SAL specification) and
  we cannot retrieve the crashdump.

  Therefore this patch introduces a NOP init handler and register it
  to SAL before leave from current kernel, to start kdump safely by
  preventing INITs from entering virtual mode and resulting in warmboot.

  On the other hand, in case of kexec that not for kdump, it also
  has same problem with INIT while kernel transition.
  This patch handles this case differently, because for kexec
  unregistering handlers will be preferred than registering NOP
  handler, since the situation "no handlers registered" is usual
  state for kernel's entry.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Haren Myneni <hbabu@us.ibm.com>
Cc: kexec@lists.infradead.org
Acked-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
2009-09-14 16:18:02 -07:00

182 lines
5.8 KiB
C
Raw Blame History

/*
* File: mca.h
* Purpose: Machine check handling specific defines
*
* Copyright (C) 1999, 2004 Silicon Graphics, Inc.
* Copyright (C) Vijay Chander <vijay@engr.sgi.com>
* Copyright (C) Srinivasa Thirumalachar <sprasad@engr.sgi.com>
* Copyright (C) Russ Anderson <rja@sgi.com>
*/
#ifndef _ASM_IA64_MCA_H
#define _ASM_IA64_MCA_H
#if !defined(__ASSEMBLY__)
#include <linux/interrupt.h>
#include <linux/types.h>
#include <asm/param.h>
#include <asm/sal.h>
#include <asm/processor.h>
#include <asm/mca_asm.h>
#define IA64_MCA_RENDEZ_TIMEOUT (20 * 1000) /* value in milliseconds - 20 seconds */
typedef struct ia64_fptr {
unsigned long fp;
unsigned long gp;
} ia64_fptr_t;
typedef union cmcv_reg_u {
u64 cmcv_regval;
struct {
u64 cmcr_vector : 8;
u64 cmcr_reserved1 : 4;
u64 cmcr_ignored1 : 1;
u64 cmcr_reserved2 : 3;
u64 cmcr_mask : 1;
u64 cmcr_ignored2 : 47;
} cmcv_reg_s;
} cmcv_reg_t;
#define cmcv_mask cmcv_reg_s.cmcr_mask
#define cmcv_vector cmcv_reg_s.cmcr_vector
enum {
IA64_MCA_RENDEZ_CHECKIN_NOTDONE = 0x0,
IA64_MCA_RENDEZ_CHECKIN_DONE = 0x1,
IA64_MCA_RENDEZ_CHECKIN_INIT = 0x2,
IA64_MCA_RENDEZ_CHECKIN_CONCURRENT_MCA = 0x3,
};
/* Information maintained by the MC infrastructure */
typedef struct ia64_mc_info_s {
u64 imi_mca_handler;
size_t imi_mca_handler_size;
u64 imi_monarch_init_handler;
size_t imi_monarch_init_handler_size;
u64 imi_slave_init_handler;
size_t imi_slave_init_handler_size;
u8 imi_rendez_checkin[NR_CPUS];
} ia64_mc_info_t;
/* Handover state from SAL to OS and vice versa, for both MCA and INIT events.
* Besides the handover state, it also contains some saved registers from the
* time of the event.
* Note: mca_asm.S depends on the precise layout of this structure.
*/
struct ia64_sal_os_state {
/* SAL to OS */
unsigned long os_gp; /* GP of the os registered with the SAL, physical */
unsigned long pal_proc; /* PAL_PROC entry point, physical */
unsigned long sal_proc; /* SAL_PROC entry point, physical */
unsigned long rv_rc; /* MCA - Rendezvous state, INIT - reason code */
unsigned long proc_state_param; /* from R18 */
unsigned long monarch; /* 1 for a monarch event, 0 for a slave */
/* common */
unsigned long sal_ra; /* Return address in SAL, physical */
unsigned long sal_gp; /* GP of the SAL - physical */
pal_min_state_area_t *pal_min_state; /* from R17. physical in asm, virtual in C */
/* Previous values of IA64_KR(CURRENT) and IA64_KR(CURRENT_STACK).
* Note: if the MCA/INIT recovery code wants to resume to a new context
* then it must change these values to reflect the new kernel stack.
*/
unsigned long prev_IA64_KR_CURRENT; /* previous value of IA64_KR(CURRENT) */
unsigned long prev_IA64_KR_CURRENT_STACK;
struct task_struct *prev_task; /* previous task, NULL if it is not useful */
/* Some interrupt registers are not saved in minstate, pt_regs or
* switch_stack. Because MCA/INIT can occur when interrupts are
* disabled, we need to save the additional interrupt registers over
* MCA/INIT and resume.
*/
unsigned long isr;
unsigned long ifa;
unsigned long itir;
unsigned long iipa;
unsigned long iim;
unsigned long iha;
/* OS to SAL */
unsigned long os_status; /* OS status to SAL, enum below */
unsigned long context; /* 0 if return to same context
1 if return to new context */
};
enum {
IA64_MCA_CORRECTED = 0x0, /* Error has been corrected by OS_MCA */
IA64_MCA_WARM_BOOT = -1, /* Warm boot of the system need from SAL */
IA64_MCA_COLD_BOOT = -2, /* Cold boot of the system need from SAL */
IA64_MCA_HALT = -3 /* System to be halted by SAL */
};
enum {
IA64_INIT_RESUME = 0x0, /* Resume after return from INIT */
IA64_INIT_WARM_BOOT = -1, /* Warm boot of the system need from SAL */
};
enum {
IA64_MCA_SAME_CONTEXT = 0x0, /* SAL to return to same context */
IA64_MCA_NEW_CONTEXT = -1 /* SAL to return to new context */
};
/* Per-CPU MCA state that is too big for normal per-CPU variables. */
struct ia64_mca_cpu {
u64 mca_stack[KERNEL_STACK_SIZE/8];
u64 init_stack[KERNEL_STACK_SIZE/8];
};
/* Array of physical addresses of each CPU's MCA area. */
extern unsigned long __per_cpu_mca[NR_CPUS];
extern int cpe_vector;
extern int ia64_cpe_irq;
extern void ia64_mca_init(void);
extern void ia64_mca_cpu_init(void *);
extern void ia64_os_mca_dispatch(void);
extern void ia64_os_mca_dispatch_end(void);
extern void ia64_mca_ucmc_handler(struct pt_regs *, struct ia64_sal_os_state *);
extern void ia64_init_handler(struct pt_regs *,
struct switch_stack *,
struct ia64_sal_os_state *);
extern void ia64_os_init_on_kdump(void);
extern void ia64_monarch_init_handler(void);
extern void ia64_slave_init_handler(void);
extern void ia64_mca_cmc_vector_setup(void);
extern int ia64_reg_MCA_extension(int (*fn)(void *, struct ia64_sal_os_state *));
extern void ia64_unreg_MCA_extension(void);
extern unsigned long ia64_get_rnat(unsigned long *);
extern void ia64_set_psr_mc(void);
extern void ia64_mca_printk(const char * fmt, ...)
__attribute__ ((format (printf, 1, 2)));
struct ia64_mca_notify_die {
struct ia64_sal_os_state *sos;
int *monarch_cpu;
int *data;
};
DECLARE_PER_CPU(u64, ia64_mca_pal_base);
#else /* __ASSEMBLY__ */
#define IA64_MCA_CORRECTED 0x0 /* Error has been corrected by OS_MCA */
#define IA64_MCA_WARM_BOOT -1 /* Warm boot of the system need from SAL */
#define IA64_MCA_COLD_BOOT -2 /* Cold boot of the system need from SAL */
#define IA64_MCA_HALT -3 /* System to be halted by SAL */
#define IA64_INIT_RESUME 0x0 /* Resume after return from INIT */
#define IA64_INIT_WARM_BOOT -1 /* Warm boot of the system need from SAL */
#define IA64_MCA_SAME_CONTEXT 0x0 /* SAL to return to same context */
#define IA64_MCA_NEW_CONTEXT -1 /* SAL to return to new context */
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_IA64_MCA_H */
View git blame Copy permalink