mca.c

xen虚拟机源代码安装包

/*
 * File:	mca.c
 * Purpose:	Generic MCA handling layer
 *
 * Updated for latest kernel
 * Copyright (C) 2003 Hewlett-Packard Co
 *	David Mosberger-Tang <[e-mail]>
 *
 * Copyright (C) 2002 Dell Inc.
 * Copyright (C) Matt Domsch ([e-mail])
 *
 * Copyright (C) 2002 Intel
 * Copyright (C) Jenna Hall ([e-mail])
 *
 * Copyright (C) 2001 Intel
 * Copyright (C) Fred Lewis ([e-mail])
 *
 * Copyright (C) 2000 Intel
 * Copyright (C) Chuck Fleckenstein ([e-mail])
 *
 * Copyright (C) 1999, 2004 Silicon Graphics, Inc.
 * Copyright (C) Vijay Chander([e-mail])
 *
 * 03/04/15 D. Mosberger Added INIT backtrace support.
 * 02/03/25 M. Domsch	GUID cleanups
 *
 * 02/01/04 J. Hall	Aligned MCA stack to 16 bytes, added platform vs. CPU
 *			error flag, set SAL default return values, changed
 *			error record structure to linked list, added init call
 *			to sal_get_state_info_size().
 *
 * 01/01/03 F. Lewis    Added setup of CMCI and CPEI IRQs, logging of corrected
 *                      platform errors, completed code for logging of
 *                      corrected & uncorrected machine check errors, and
 *                      updated for conformance with Nov. 2000 revision of the
 *                      SAL 3.0 spec.
 * 00/03/29 C. Fleckenstein  Fixed PAL/SAL update issues, began MCA bug fixes, logging issues,
 *                           added min save state dump, added INIT handler.
 *
 * 2003-12-08 Keith Owens <[e-mail]>
 *            smp_call_function() must not be called from interrupt context (can
 *            deadlock on tasklist_lock).  Use keventd to call smp_call_function().
 *
 * 2004-02-01 Keith Owens <[e-mail]>
 *            Avoid deadlock when using printk() for MCA and INIT records.
 *            Delete all record printing code, moved to salinfo_decode in user space.
 *            Mark variables and functions static where possible.
 *            Delete dead variables and functions.
 *            Reorder to remove the need for forward declarations and to consolidate
 *            related code.
 */
#include <linux/config.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kallsyms.h>
#include <linux/smp_lock.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/timer.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/smp.h>
#include <linux/workqueue.h>

#include <asm/delay.h>
#include <asm/machvec.h>
#include <asm/meminit.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/system.h>
#include <asm/sal.h>
#include <asm/mca.h>

#include <asm/irq.h>
#include <asm/hw_irq.h>

#ifdef XEN
#include <xen/symbols.h>
#include <xen/mm.h>
#include <xen/console.h>
#include <xen/event.h>
#include <xen/softirq.h>
#include <asm/xenmca.h>
#include <linux/shutdown.h>
#endif

#if defined(IA64_MCA_DEBUG_INFO)
# define IA64_MCA_DEBUG(fmt...)	printk(fmt)
#else
# define IA64_MCA_DEBUG(fmt...)
#endif

/* Used by mca_asm.S */
#ifndef XEN
ia64_mca_sal_to_os_state_t	ia64_sal_to_os_handoff_state;
#else
ia64_mca_sal_to_os_state_t	ia64_sal_to_os_handoff_state[NR_CPUS];
DEFINE_PER_CPU(u64, ia64_sal_to_os_handoff_state_addr); 
#endif
ia64_mca_os_to_sal_state_t	ia64_os_to_sal_handoff_state;
u64				ia64_mca_serialize;
DEFINE_PER_CPU(u64, ia64_mca_data); /* == __per_cpu_mca[smp_processor_id()] */
DEFINE_PER_CPU(u64, ia64_mca_per_cpu_pte); /* PTE to map per-CPU area */
DEFINE_PER_CPU(u64, ia64_mca_pal_pte);	    /* PTE to map PAL code */
DEFINE_PER_CPU(u64, ia64_mca_pal_base);    /* vaddr PAL code granule */

unsigned long __per_cpu_mca[NR_CPUS];

/* In mca_asm.S */
extern void			ia64_monarch_init_handler (void);
extern void			ia64_slave_init_handler (void);
#ifdef XEN
extern void setup_vector (unsigned int vec, struct irqaction *action);
#define setup_irq(irq, action)	setup_vector(irq, action)
#endif

static ia64_mc_info_t		ia64_mc_info;

#ifdef XEN
#define jiffies			NOW()
#undef HZ
#define HZ			1000000000UL
#endif

#define MAX_CPE_POLL_INTERVAL (15*60*HZ) /* 15 minutes */
#define MIN_CPE_POLL_INTERVAL (2*60*HZ)  /* 2 minutes */
#define CMC_POLL_INTERVAL     (1*60*HZ)  /* 1 minute */
#define CPE_HISTORY_LENGTH    5
#define CMC_HISTORY_LENGTH    5

#ifndef XEN 
static struct timer_list cpe_poll_timer;
static struct timer_list cmc_poll_timer;
#else
#define mod_timer(timer, expires)	set_timer(timer, expires)
static struct timer cpe_poll_timer;
static struct timer cmc_poll_timer;
#endif
/*
 * This variable tells whether we are currently in polling mode.
 * Start with this in the wrong state so we won't play w/ timers
 * before the system is ready.
 */
static int cmc_polling_enabled = 1;

/*
 * Clearing this variable prevents CPE polling from getting activated
 * in mca_late_init.  Use it if your system doesn't provide a CPEI,
 * but encounters problems retrieving CPE logs.  This should only be
 * necessary for debugging.
 */
static int cpe_poll_enabled = 1;

extern void salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe);

static int mca_init;

/*
 * IA64_MCA log support
 */
#define IA64_MAX_LOGS		2	/* Double-buffering for nested MCAs */
#define IA64_MAX_LOG_TYPES      4   /* MCA, INIT, CMC, CPE */

typedef struct ia64_state_log_s
{
	spinlock_t	isl_lock;
	int		isl_index;
	unsigned long	isl_count;
	ia64_err_rec_t  *isl_log[IA64_MAX_LOGS]; /* need space to store header + error log */
} ia64_state_log_t;

static ia64_state_log_t ia64_state_log[IA64_MAX_LOG_TYPES];

#ifndef XEN
#define IA64_LOG_ALLOCATE(it, size) \
	{ia64_state_log[it].isl_log[IA64_LOG_CURR_INDEX(it)] = \
		(ia64_err_rec_t *)alloc_bootmem(size); \
	ia64_state_log[it].isl_log[IA64_LOG_NEXT_INDEX(it)] = \
		(ia64_err_rec_t *)alloc_bootmem(size);}
#else
#define IA64_LOG_ALLOCATE(it, size) \
	do { \
		unsigned int pageorder; \
		struct page_info *page;	\
		pageorder = get_order_from_bytes(size); \
		page = alloc_domheap_pages(NULL, pageorder, 0); \
		ia64_state_log[it].isl_log[IA64_LOG_CURR_INDEX(it)] = \
			page? (ia64_err_rec_t *)page_to_virt(page): NULL;  \
		page = alloc_domheap_pages(NULL, pageorder, 0); \
		ia64_state_log[it].isl_log[IA64_LOG_NEXT_INDEX(it)] = \
			page? (ia64_err_rec_t *)page_to_virt(page): NULL; \
	} while(0)
#endif

#define IA64_LOG_LOCK_INIT(it) spin_lock_init(&ia64_state_log[it].isl_lock)
#define IA64_LOG_LOCK(it)      spin_lock_irqsave(&ia64_state_log[it].isl_lock, s)
#define IA64_LOG_UNLOCK(it)    spin_unlock_irqrestore(&ia64_state_log[it].isl_lock,s)
#define IA64_LOG_NEXT_INDEX(it)    ia64_state_log[it].isl_index
#define IA64_LOG_CURR_INDEX(it)    1 - ia64_state_log[it].isl_index
#define IA64_LOG_INDEX_INC(it) \
    {ia64_state_log[it].isl_index = 1 - ia64_state_log[it].isl_index; \
    ia64_state_log[it].isl_count++;}
#define IA64_LOG_INDEX_DEC(it) \
    ia64_state_log[it].isl_index = 1 - ia64_state_log[it].isl_index
#define IA64_LOG_NEXT_BUFFER(it)   (void *)((ia64_state_log[it].isl_log[IA64_LOG_NEXT_INDEX(it)]))
#define IA64_LOG_CURR_BUFFER(it)   (void *)((ia64_state_log[it].isl_log[IA64_LOG_CURR_INDEX(it)]))
#define IA64_LOG_COUNT(it)         ia64_state_log[it].isl_count

#ifdef XEN
struct list_head *sal_queue, sal_log_queues[IA64_MAX_LOG_TYPES];
sal_log_record_header_t *sal_record;
DEFINE_SPINLOCK(sal_queue_lock);
#endif

/*
 * ia64_log_init
 *	Reset the OS ia64 log buffer
 * Inputs   :   info_type   (SAL_INFO_TYPE_{MCA,INIT,CMC,CPE})
 * Outputs	:	None
 */
static void
ia64_log_init(int sal_info_type)
{
	u64	max_size = 0;

	IA64_LOG_NEXT_INDEX(sal_info_type) = 0;
	IA64_LOG_LOCK_INIT(sal_info_type);

	// SAL will tell us the maximum size of any error record of this type
	max_size = ia64_sal_get_state_info_size(sal_info_type);
	if (!max_size)
		/* alloc_bootmem() doesn't like zero-sized allocations! */
		return;

	// set up OS data structures to hold error info
	IA64_LOG_ALLOCATE(sal_info_type, max_size);
	memset(IA64_LOG_CURR_BUFFER(sal_info_type), 0, max_size);
	memset(IA64_LOG_NEXT_BUFFER(sal_info_type), 0, max_size);

#ifdef XEN
	if (sal_record == NULL) {
		unsigned int pageorder;
		struct page_info *page;
		pageorder  = get_order_from_bytes(max_size);
		page = alloc_domheap_pages(NULL, pageorder, 0);
		BUG_ON(page == NULL);
		sal_record = (sal_log_record_header_t *)page_to_virt(page);
		BUG_ON(sal_record == NULL);
	}
#endif
}

#ifndef XEN
/*
 * ia64_log_get
 *
 *	Get the current MCA log from SAL and copy it into the OS log buffer.
 *
 *  Inputs  :   info_type   (SAL_INFO_TYPE_{MCA,INIT,CMC,CPE})
 *              irq_safe    whether you can use printk at this point
 *  Outputs :   size        (total record length)
 *              *buffer     (ptr to error record)
 *
 */
static u64
ia64_log_get(int sal_info_type, u8 **buffer, int irq_safe)
{
	sal_log_record_header_t     *log_buffer;
	u64                         total_len = 0;
	int                         s;

	IA64_LOG_LOCK(sal_info_type);

	/* Get the process state information */
	log_buffer = IA64_LOG_NEXT_BUFFER(sal_info_type);

	total_len = ia64_sal_get_state_info(sal_info_type, (u64 *)log_buffer);

	if (total_len) {
		IA64_LOG_INDEX_INC(sal_info_type);
		IA64_LOG_UNLOCK(sal_info_type);
		if (irq_safe) {
			IA64_MCA_DEBUG("%s: SAL error record type %d retrieved. "
				       "Record length = %ld\n", __FUNCTION__, sal_info_type, total_len);
		}
		*buffer = (u8 *) log_buffer;
		return total_len;
	} else {
		IA64_LOG_UNLOCK(sal_info_type);
		return 0;
	}
}

/*
 *  ia64_mca_log_sal_error_record
 *
 *  This function retrieves a specified error record type from SAL
 *  and wakes up any processes waiting for error records.
 *
 *  Inputs  :   sal_info_type   (Type of error record MCA/CMC/CPE/INIT)
 */
static void
ia64_mca_log_sal_error_record(int sal_info_type)
{
	u8 *buffer;
	sal_log_record_header_t *rh;
	u64 size;
	int irq_safe = sal_info_type != SAL_INFO_TYPE_MCA && sal_info_type != SAL_INFO_TYPE_INIT;
#ifdef IA64_MCA_DEBUG_INFO
	static const char * const rec_name[] = { "MCA", "INIT", "CMC", "CPE" };
#endif

	size = ia64_log_get(sal_info_type, &buffer, irq_safe);
	if (!size)
		return;

	salinfo_log_wakeup(sal_info_type, buffer, size, irq_safe);

	if (irq_safe)
		IA64_MCA_DEBUG("CPU %d: SAL log contains %s error record\n",
			smp_processor_id(),
			sal_info_type < ARRAY_SIZE(rec_name) ? rec_name[sal_info_type] : "UNKNOWN");

	/* Clear logs from corrected errors in case there's no user-level logger */
	rh = (sal_log_record_header_t *)buffer;
	if (rh->severity == sal_log_severity_corrected)
		ia64_sal_clear_state_info(sal_info_type);
}
#else /* !XEN */
/*
 * ia64_log_queue
 *
 *	Get the current MCA log from SAL and copy it into the OS log buffer.
 *
 *  Inputs  :   info_type   (SAL_INFO_TYPE_{MCA,INIT,CMC,CPE})
 *  Outputs :   size        (total record length)
 *              *buffer     (ptr to error record)
 *
 */
static u64
ia64_log_queue(int sal_info_type, int virq)
{
	sal_log_record_header_t     *log_buffer;
	u64                         total_len = 0;
	int                         s;
	sal_queue_entry_t	    *e;
	unsigned long		    flags;

	IA64_LOG_LOCK(sal_info_type);

	/* Get the process state information */
	log_buffer = IA64_LOG_NEXT_BUFFER(sal_info_type);

	total_len = ia64_sal_get_state_info(sal_info_type, (u64 *)log_buffer);

	if (total_len) {
		int queue_type;

		spin_lock_irqsave(&sal_queue_lock, flags);

		if (sal_info_type == SAL_INFO_TYPE_MCA && virq == VIRQ_MCA_CMC)
			queue_type = SAL_INFO_TYPE_CMC;
		else
			queue_type = sal_info_type;

		e = xmalloc(sal_queue_entry_t);
		BUG_ON(e == NULL);
		e->cpuid = smp_processor_id();
		e->sal_info_type = sal_info_type;
		e->vector = IA64_CMC_VECTOR;
		e->virq = virq;
		e->length = total_len;

		list_add_tail(&e->list, &sal_queue[queue_type]);
		spin_unlock_irqrestore(&sal_queue_lock, flags);

		IA64_LOG_INDEX_INC(sal_info_type);
		IA64_LOG_UNLOCK(sal_info_type);
		if (sal_info_type != SAL_INFO_TYPE_MCA &&
		    sal_info_type != SAL_INFO_TYPE_INIT) {
			IA64_MCA_DEBUG("%s: SAL error record type %d retrieved. "
				       "Record length = %ld\n", __FUNCTION__,
			               sal_info_type, total_len);
		}
		return total_len;
	} else {
		IA64_LOG_UNLOCK(sal_info_type);
		return 0;
	}
}
#endif /* !XEN */

/*
 * platform dependent error handling
 */
#ifndef PLATFORM_MCA_HANDLERS

#ifdef CONFIG_ACPI

#ifdef XEN
/**
 *	Copy from linux/kernel/irq/manage.c
 *
 *	disable_irq_nosync - disable an irq without waiting
 *	@irq: Interrupt to disable
 *
 *	Disable the selected interrupt line.  Disables and Enables are
 *	nested.
 *	Unlike disable_irq(), this function does not ensure existing
 *	instances of the IRQ handler have completed before returning.
 *
 *	This function may be called from IRQ context.
 */
void disable_irq_nosync(unsigned int irq)
{
	irq_desc_t *desc = irq_desc + irq;
	unsigned long flags;

	if (irq >= NR_IRQS)
		return;

	spin_lock_irqsave(&desc->lock, flags);
	if (!desc->depth++) {
		desc->status |= IRQ_DISABLED;
		desc->handler->disable(irq);
	}
	spin_unlock_irqrestore(&desc->lock, flags);
}

/**
 *	Copy from linux/kernel/irq/manage.c
 *
 *	enable_irq - enable handling of an irq
 *	@irq: Interrupt to enable
 *
 *	Undoes the effect of one call to disable_irq().  If this
 *	matches the last disable, processing of interrupts on this
 *	IRQ line is re-enabled.
 *
 *	This function may be called from IRQ context.
 */
void enable_irq(unsigned int irq)
{
	irq_desc_t *desc = irq_desc + irq;
	unsigned long flags;

	if (irq >= NR_IRQS)
		return;

	spin_lock_irqsave(&desc->lock, flags);
	switch (desc->depth) {
	case 0:
		WARN_ON(1);
		break;
	case 1: {
		unsigned int status = desc->status & ~IRQ_DISABLED;

		desc->status = status;
		if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
			desc->status = status | IRQ_REPLAY;
			hw_resend_irq(desc->handler,irq);
		}
		desc->handler->enable(irq);
		/* fall-through */
	}
	default:
		desc->depth--;
	}
	spin_unlock_irqrestore(&desc->lock, flags);
}
#endif	/* XEN */

int cpe_vector = -1;

static irqreturn_t
ia64_mca_cpe_int_handler (int cpe_irq, void *arg, struct pt_regs *ptregs)
{
	static unsigned long	cpe_history[CPE_HISTORY_LENGTH];
	static int		index;
	static DEFINE_SPINLOCK(cpe_history_lock);

	IA64_MCA_DEBUG("%s: received interrupt vector = %#x on CPU %d\n",
		       __FUNCTION__, cpe_irq, smp_processor_id());

	/* SAL spec states this should run w/ interrupts enabled */