eeh.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 750 行 · 第 1/2 页

	if (!eeh_subsystem_enabled)
		return 0;

	if (!dn)
		return 0;

	/* Access to IO BARs might get this far and still not want checking. */
	if (!(dn->eeh_mode & EEH_MODE_SUPPORTED) ||
	    dn->eeh_mode & EEH_MODE_NOCHECK) {
		return 0;
	}

	if (!dn->eeh_config_addr) {
		return 0;
	}

	/*
	 * Now test for an EEH failure.  This is VERY expensive.
	 * Note that the eeh_config_addr may be a parent device
	 * in the case of a device behind a bridge, or it may be
	 * function zero of a multi-function device.
	 * In any case they must share a common PHB.
	 */
	ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets,
			dn->eeh_config_addr, BUID_HI(dn->phb->buid),
			BUID_LO(dn->phb->buid));

	if (ret == 0 && rets[1] == 1 && (rets[0] == 2 || rets[0] == 4)) {
		int log_event;

		spin_lock_irqsave(&slot_errbuf_lock, flags);
		memset(slot_errbuf, 0, eeh_error_buf_size);

		log_event = rtas_call(ibm_slot_error_detail,
		                      8, 1, NULL, dn->eeh_config_addr,
		                      BUID_HI(dn->phb->buid),
		                      BUID_LO(dn->phb->buid), NULL, 0,
		                      virt_to_phys(slot_errbuf),
		                      eeh_error_buf_size,
		                      1 /* Temporary Error */);

		if (log_event == 0)
			log_error(slot_errbuf, ERR_TYPE_RTAS_LOG,
				  1 /* Fatal */);

		spin_unlock_irqrestore(&slot_errbuf_lock, flags);

		printk(KERN_INFO "EEH: MMIO failure (%d) on device: %s %s\n",
		       rets[0], dn->name, dn->full_name);
		WARN_ON(1);

		/*
		 * XXX We should create a separate sysctl for this.
		 *
		 * Since the panic_on_oops sysctl is used to halt
		 * the system in light of potential corruption, we
		 * can use it here.
		 */
		if (panic_on_oops) {
			panic("EEH: MMIO failure (%d) on device: %s %s\n",
			      rets[0], dn->name, dn->full_name);
		} else {
			__get_cpu_var(ignored_failures)++;
		}
	} else {
		__get_cpu_var(false_positives)++;
	}

	return 0;
}

EXPORT_SYMBOL(eeh_dn_check_failure);

/**
 * eeh_check_failure - check if all 1's data is due to EEH slot freeze
 * @token i/o token, should be address in the form 0xA....
 * @val value, should be all 1's (XXX why do we need this arg??)
 *
 * Check for an eeh failure at the given token address.
 * Check for an EEH failure at the given token address.  Call this
 * routine if the result of a read was all 0xff's and you want to
 * find out if this is due to an EEH slot freeze event.  This routine
 * will query firmware for the EEH status.
 *
 * Note this routine is safe to call in an interrupt context.
 */
unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
{
	unsigned long addr;
	struct pci_dev *dev;
	struct device_node *dn;

	/* Finding the phys addr + pci device; this is pretty quick. */
	addr = eeh_token_to_phys((unsigned long __force) token);
	dev = pci_get_device_by_addr(addr);
	if (!dev)
		return val;

	dn = pci_device_to_OF_node(dev);
	eeh_dn_check_failure (dn, dev);

	pci_dev_put(dev);
	return val;
}

EXPORT_SYMBOL(eeh_check_failure);

struct eeh_early_enable_info {
	unsigned int buid_hi;
	unsigned int buid_lo;
};

/* Enable eeh for the given device node. */
static void *early_enable_eeh(struct device_node *dn, void *data)
{
	struct eeh_early_enable_info *info = data;
	int ret;
	char *status = get_property(dn, "status", NULL);
	u32 *class_code = (u32 *)get_property(dn, "class-code", NULL);
	u32 *vendor_id = (u32 *)get_property(dn, "vendor-id", NULL);
	u32 *device_id = (u32 *)get_property(dn, "device-id", NULL);
	u32 *regs;
	int enable;

	dn->eeh_mode = 0;

	if (status && strcmp(status, "ok") != 0)
		return NULL;	/* ignore devices with bad status */

	/* Ignore bad nodes. */
	if (!class_code || !vendor_id || !device_id)
		return NULL;

	/* There is nothing to check on PCI to ISA bridges */
	if (dn->type && !strcmp(dn->type, "isa")) {
		dn->eeh_mode |= EEH_MODE_NOCHECK;
		return NULL;
	}

	/*
	 * Now decide if we are going to "Disable" EEH checking
	 * for this device.  We still run with the EEH hardware active,
	 * but we won't be checking for ff's.  This means a driver
	 * could return bad data (very bad!), an interrupt handler could
	 * hang waiting on status bits that won't change, etc.
	 * But there are a few cases like display devices that make sense.
	 */
	enable = 1;	/* i.e. we will do checking */
	if ((*class_code >> 16) == PCI_BASE_CLASS_DISPLAY)
		enable = 0;

	if (!enable)
		dn->eeh_mode |= EEH_MODE_NOCHECK;

	/* Ok... see if this device supports EEH.  Some do, some don't,
	 * and the only way to find out is to check each and every one. */
	regs = (u32 *)get_property(dn, "reg", NULL);
	if (regs) {
		/* First register entry is addr (00BBSS00)  */
		/* Try to enable eeh */
		ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL,
				regs[0], info->buid_hi, info->buid_lo,
				EEH_ENABLE);
		if (ret == 0) {
			eeh_subsystem_enabled = 1;
			dn->eeh_mode |= EEH_MODE_SUPPORTED;
			dn->eeh_config_addr = regs[0];
#ifdef DEBUG
			printk(KERN_DEBUG "EEH: %s: eeh enabled\n", dn->full_name);
#endif
		} else {

			/* This device doesn't support EEH, but it may have an
			 * EEH parent, in which case we mark it as supported. */
			if (dn->parent && (dn->parent->eeh_mode & EEH_MODE_SUPPORTED)) {
				/* Parent supports EEH. */
				dn->eeh_mode |= EEH_MODE_SUPPORTED;
				dn->eeh_config_addr = dn->parent->eeh_config_addr;
				return NULL;
			}
		}
	} else {
		printk(KERN_WARNING "EEH: %s: unable to get reg property.\n",
		       dn->full_name);
	}

	return NULL; 
}

/*
 * Initialize EEH by trying to enable it for all of the adapters in the system.
 * As a side effect we can determine here if eeh is supported at all.
 * Note that we leave EEH on so failed config cycles won't cause a machine
 * check.  If a user turns off EEH for a particular adapter they are really
 * telling Linux to ignore errors.  Some hardware (e.g. POWER5) won't
 * grant access to a slot if EEH isn't enabled, and so we always enable
 * EEH for all slots/all devices.
 *
 * The eeh-force-off option disables EEH checking globally, for all slots.
 * Even if force-off is set, the EEH hardware is still enabled, so that
 * newer systems can boot.
 */
void __init eeh_init(void)
{
	struct device_node *phb, *np;
	struct eeh_early_enable_info info;

	init_pci_config_tokens();

	np = of_find_node_by_path("/rtas");
	if (np == NULL)
		return;

	ibm_set_eeh_option = rtas_token("ibm,set-eeh-option");
	ibm_set_slot_reset = rtas_token("ibm,set-slot-reset");
	ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state");
	ibm_slot_error_detail = rtas_token("ibm,slot-error-detail");

	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE)
		return;

	eeh_error_buf_size = rtas_token("rtas-error-log-max");
	if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) {
		eeh_error_buf_size = 1024;
	}
	if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) {
		printk(KERN_WARNING "EEH: rtas-error-log-max is bigger than allocated "
		      "buffer ! (%d vs %d)", eeh_error_buf_size, RTAS_ERROR_LOG_MAX);
		eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
	}

	/* Enable EEH for all adapters.  Note that eeh requires buid's */
	for (phb = of_find_node_by_name(NULL, "pci"); phb;
	     phb = of_find_node_by_name(phb, "pci")) {
		unsigned long buid;

		buid = get_phb_buid(phb);
		if (buid == 0)
			continue;

		info.buid_lo = BUID_LO(buid);
		info.buid_hi = BUID_HI(buid);
		traverse_pci_devices(phb, early_enable_eeh, &info);
	}

	if (eeh_subsystem_enabled)
		printk(KERN_INFO "EEH: PCI Enhanced I/O Error Handling Enabled\n");
	else
		printk(KERN_WARNING "EEH: No capable adapters found\n");
}

/**
 * eeh_add_device_early - enable EEH for the indicated device_node
 * @dn: device node for which to set up EEH
 *
 * This routine must be used to perform EEH initialization for PCI
 * devices that were added after system boot (e.g. hotplug, dlpar).
 * This routine must be called before any i/o is performed to the
 * adapter (inluding any config-space i/o).
 * Whether this actually enables EEH or not for this device depends
 * on the CEC architecture, type of the device, on earlier boot
 * command-line arguments & etc.
 */
void eeh_add_device_early(struct device_node *dn)
{
	struct pci_controller *phb;
	struct eeh_early_enable_info info;

	if (!dn || !eeh_subsystem_enabled)
		return;
	phb = dn->phb;
	if (NULL == phb || 0 == phb->buid) {
		printk(KERN_WARNING "EEH: Expected buid but found none\n");
		return;
	}

	info.buid_hi = BUID_HI(phb->buid);
	info.buid_lo = BUID_LO(phb->buid);
	early_enable_eeh(dn, &info);
}
EXPORT_SYMBOL(eeh_add_device_early);

/**
 * eeh_add_device_late - perform EEH initialization for the indicated pci device
 * @dev: pci device for which to set up EEH
 *
 * This routine must be used to complete EEH initialization for PCI
 * devices that were added after system boot (e.g. hotplug, dlpar).
 */
void eeh_add_device_late(struct pci_dev *dev)
{
	if (!dev || !eeh_subsystem_enabled)
		return;

#ifdef DEBUG
	printk(KERN_DEBUG "EEH: adding device %s %s\n", pci_name(dev),
	       pci_pretty_name(dev));
#endif

	pci_addr_cache_insert_device (dev);
}
EXPORT_SYMBOL(eeh_add_device_late);

/**
 * eeh_remove_device - undo EEH setup for the indicated pci device
 * @dev: pci device to be removed
 *
 * This routine should be when a device is removed from a running
 * system (e.g. by hotplug or dlpar).
 */
void eeh_remove_device(struct pci_dev *dev)
{
	if (!dev || !eeh_subsystem_enabled)
		return;

	/* Unregister the device with the EEH/PCI address search system */
#ifdef DEBUG
	printk(KERN_DEBUG "EEH: remove device %s %s\n", pci_name(dev),
	       pci_pretty_name(dev));
#endif
	pci_addr_cache_remove_device(dev);
}
EXPORT_SYMBOL(eeh_remove_device);

static int proc_eeh_show(struct seq_file *m, void *v)
{
	unsigned int cpu;
	unsigned long ffs = 0, positives = 0, failures = 0;

	for_each_cpu(cpu) {
		ffs += per_cpu(total_mmio_ffs, cpu);
		positives += per_cpu(false_positives, cpu);
		failures += per_cpu(ignored_failures, cpu);
	}

	if (0 == eeh_subsystem_enabled) {
		seq_printf(m, "EEH Subsystem is globally disabled\n");
		seq_printf(m, "eeh_total_mmio_ffs=%ld\n", ffs);
	} else {
		seq_printf(m, "EEH Subsystem is enabled\n");
		seq_printf(m, "eeh_total_mmio_ffs=%ld\n"
			   "eeh_false_positives=%ld\n"
			   "eeh_ignored_failures=%ld\n",
			   ffs, positives, failures);
	}

	return 0;
}

static int proc_eeh_open(struct inode *inode, struct file *file)
{
	return single_open(file, proc_eeh_show, NULL);
}

static struct file_operations proc_eeh_operations = {
	.open      = proc_eeh_open,
	.read      = seq_read,
	.llseek    = seq_lseek,
	.release   = single_release,
};

static int __init eeh_init_proc(void)
{
	struct proc_dir_entry *e;

	if (systemcfg->platform & PLATFORM_PSERIES) {
		e = create_proc_entry("ppc64/eeh", 0, NULL);
		if (e)
			e->proc_fops = &proc_eeh_operations;
	}

	return 0;
}
__initcall(eeh_init_proc);