edac_mc.c

来自「linux 内核源代码」· C语言 代码 · 共 910 行 · 第 1/2 页

	return NULL;
}
EXPORT_SYMBOL(edac_mc_find);

/**
 * edac_mc_add_mc: Insert the 'mci' structure into the mci global list and
 *                 create sysfs entries associated with mci structure
 * @mci: pointer to the mci structure to be added to the list
 * @mc_idx: A unique numeric identifier to be assigned to the 'mci' structure.
 *
 * Return:
 *	0	Success
 *	!0	Failure
 */

/* FIXME - should a warning be printed if no error detection? correction? */
int edac_mc_add_mc(struct mem_ctl_info *mci)
{
	debugf0("%s()\n", __func__);

#ifdef CONFIG_EDAC_DEBUG
	if (edac_debug_level >= 3)
		edac_mc_dump_mci(mci);

	if (edac_debug_level >= 4) {
		int i;

		for (i = 0; i < mci->nr_csrows; i++) {
			int j;

			edac_mc_dump_csrow(&mci->csrows[i]);
			for (j = 0; j < mci->csrows[i].nr_channels; j++)
				edac_mc_dump_channel(&mci->csrows[i].
						channels[j]);
		}
	}
#endif
	mutex_lock(&mem_ctls_mutex);

	if (add_mc_to_global_list(mci))
		goto fail0;

	/* set load time so that error rate can be tracked */
	mci->start_time = jiffies;

	if (edac_create_sysfs_mci_device(mci)) {
		edac_mc_printk(mci, KERN_WARNING,
			"failed to create sysfs device\n");
		goto fail1;
	}

	/* If there IS a check routine, then we are running POLLED */
	if (mci->edac_check != NULL) {
		/* This instance is NOW RUNNING */
		mci->op_state = OP_RUNNING_POLL;

		edac_mc_workq_setup(mci, edac_mc_get_poll_msec());
	} else {
		mci->op_state = OP_RUNNING_INTERRUPT;
	}

	/* Report action taken */
	edac_mc_printk(mci, KERN_INFO, "Giving out device to '%s' '%s':"
		" DEV %s\n", mci->mod_name, mci->ctl_name, dev_name(mci));

	mutex_unlock(&mem_ctls_mutex);
	return 0;

fail1:
	del_mc_from_global_list(mci);

fail0:
	mutex_unlock(&mem_ctls_mutex);
	return 1;
}
EXPORT_SYMBOL_GPL(edac_mc_add_mc);

/**
 * edac_mc_del_mc: Remove sysfs entries for specified mci structure and
 *                 remove mci structure from global list
 * @pdev: Pointer to 'struct device' representing mci structure to remove.
 *
 * Return pointer to removed mci structure, or NULL if device not found.
 */
struct mem_ctl_info *edac_mc_del_mc(struct device *dev)
{
	struct mem_ctl_info *mci;

	debugf0("%s()\n", __func__);

	mutex_lock(&mem_ctls_mutex);

	/* find the requested mci struct in the global list */
	mci = find_mci_by_dev(dev);
	if (mci == NULL) {
		mutex_unlock(&mem_ctls_mutex);
		return NULL;
	}

	/* marking MCI offline */
	mci->op_state = OP_OFFLINE;

	del_mc_from_global_list(mci);
	mutex_unlock(&mem_ctls_mutex);

	/* flush workq processes and remove sysfs */
	edac_mc_workq_teardown(mci);
	edac_remove_sysfs_mci_device(mci);

	edac_printk(KERN_INFO, EDAC_MC,
		"Removed device %d for %s %s: DEV %s\n", mci->mc_idx,
		mci->mod_name, mci->ctl_name, dev_name(mci));

	return mci;
}
EXPORT_SYMBOL_GPL(edac_mc_del_mc);

static void edac_mc_scrub_block(unsigned long page, unsigned long offset,
				u32 size)
{
	struct page *pg;
	void *virt_addr;
	unsigned long flags = 0;

	debugf3("%s()\n", __func__);

	/* ECC error page was not in our memory. Ignore it. */
	if (!pfn_valid(page))
		return;

	/* Find the actual page structure then map it and fix */
	pg = pfn_to_page(page);

	if (PageHighMem(pg))
		local_irq_save(flags);

	virt_addr = kmap_atomic(pg, KM_BOUNCE_READ);

	/* Perform architecture specific atomic scrub operation */
	atomic_scrub(virt_addr + offset, size);

	/* Unmap and complete */
	kunmap_atomic(virt_addr, KM_BOUNCE_READ);

	if (PageHighMem(pg))
		local_irq_restore(flags);
}

/* FIXME - should return -1 */
int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, unsigned long page)
{
	struct csrow_info *csrows = mci->csrows;
	int row, i;

	debugf1("MC%d: %s(): 0x%lx\n", mci->mc_idx, __func__, page);
	row = -1;

	for (i = 0; i < mci->nr_csrows; i++) {
		struct csrow_info *csrow = &csrows[i];

		if (csrow->nr_pages == 0)
			continue;

		debugf3("MC%d: %s(): first(0x%lx) page(0x%lx) last(0x%lx) "
			"mask(0x%lx)\n", mci->mc_idx, __func__,
			csrow->first_page, page, csrow->last_page,
			csrow->page_mask);

		if ((page >= csrow->first_page) &&
		    (page <= csrow->last_page) &&
		    ((page & csrow->page_mask) ==
		     (csrow->first_page & csrow->page_mask))) {
			row = i;
			break;
		}
	}

	if (row == -1)
		edac_mc_printk(mci, KERN_ERR,
			"could not look up page error address %lx\n",
			(unsigned long)page);

	return row;
}
EXPORT_SYMBOL_GPL(edac_mc_find_csrow_by_page);

/* FIXME - setable log (warning/emerg) levels */
/* FIXME - integrate with evlog: http://evlog.sourceforge.net/ */
void edac_mc_handle_ce(struct mem_ctl_info *mci,
		unsigned long page_frame_number,
		unsigned long offset_in_page, unsigned long syndrome,
		int row, int channel, const char *msg)
{
	unsigned long remapped_page;

	debugf3("MC%d: %s()\n", mci->mc_idx, __func__);

	/* FIXME - maybe make panic on INTERNAL ERROR an option */
	if (row >= mci->nr_csrows || row < 0) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: row out of range "
			"(%d >= %d)\n", row, mci->nr_csrows);
		edac_mc_handle_ce_no_info(mci, "INTERNAL ERROR");
		return;
	}

	if (channel >= mci->csrows[row].nr_channels || channel < 0) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: channel out of range "
			"(%d >= %d)\n", channel,
			mci->csrows[row].nr_channels);
		edac_mc_handle_ce_no_info(mci, "INTERNAL ERROR");
		return;
	}

	if (edac_mc_get_log_ce())
		/* FIXME - put in DIMM location */
		edac_mc_printk(mci, KERN_WARNING,
			"CE page 0x%lx, offset 0x%lx, grain %d, syndrome "
			"0x%lx, row %d, channel %d, label \"%s\": %s\n",
			page_frame_number, offset_in_page,
			mci->csrows[row].grain, syndrome, row, channel,
			mci->csrows[row].channels[channel].label, msg);

	mci->ce_count++;
	mci->csrows[row].ce_count++;
	mci->csrows[row].channels[channel].ce_count++;

	if (mci->scrub_mode & SCRUB_SW_SRC) {
		/*
		 * Some MC's can remap memory so that it is still available
		 * at a different address when PCI devices map into memory.
		 * MC's that can't do this lose the memory where PCI devices
		 * are mapped.  This mapping is MC dependant and so we call
		 * back into the MC driver for it to map the MC page to
		 * a physical (CPU) page which can then be mapped to a virtual
		 * page - which can then be scrubbed.
		 */
		remapped_page = mci->ctl_page_to_phys ?
			mci->ctl_page_to_phys(mci, page_frame_number) :
			page_frame_number;

		edac_mc_scrub_block(remapped_page, offset_in_page,
				mci->csrows[row].grain);
	}
}
EXPORT_SYMBOL_GPL(edac_mc_handle_ce);

void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci, const char *msg)
{
	if (edac_mc_get_log_ce())
		edac_mc_printk(mci, KERN_WARNING,
			"CE - no information available: %s\n", msg);

	mci->ce_noinfo_count++;
	mci->ce_count++;
}
EXPORT_SYMBOL_GPL(edac_mc_handle_ce_no_info);

void edac_mc_handle_ue(struct mem_ctl_info *mci,
		unsigned long page_frame_number,
		unsigned long offset_in_page, int row, const char *msg)
{
	int len = EDAC_MC_LABEL_LEN * 4;
	char labels[len + 1];
	char *pos = labels;
	int chan;
	int chars;

	debugf3("MC%d: %s()\n", mci->mc_idx, __func__);

	/* FIXME - maybe make panic on INTERNAL ERROR an option */
	if (row >= mci->nr_csrows || row < 0) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: row out of range "
			"(%d >= %d)\n", row, mci->nr_csrows);
		edac_mc_handle_ue_no_info(mci, "INTERNAL ERROR");
		return;
	}

	chars = snprintf(pos, len + 1, "%s",
			 mci->csrows[row].channels[0].label);
	len -= chars;
	pos += chars;

	for (chan = 1; (chan < mci->csrows[row].nr_channels) && (len > 0);
		chan++) {
		chars = snprintf(pos, len + 1, ":%s",
				 mci->csrows[row].channels[chan].label);
		len -= chars;
		pos += chars;
	}

	if (edac_mc_get_log_ue())
		edac_mc_printk(mci, KERN_EMERG,
			"UE page 0x%lx, offset 0x%lx, grain %d, row %d, "
			"labels \"%s\": %s\n", page_frame_number,
			offset_in_page, mci->csrows[row].grain, row,
			labels, msg);

	if (edac_mc_get_panic_on_ue())
		panic("EDAC MC%d: UE page 0x%lx, offset 0x%lx, grain %d, "
			"row %d, labels \"%s\": %s\n", mci->mc_idx,
			page_frame_number, offset_in_page,
			mci->csrows[row].grain, row, labels, msg);

	mci->ue_count++;
	mci->csrows[row].ue_count++;
}
EXPORT_SYMBOL_GPL(edac_mc_handle_ue);

void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg)
{
	if (edac_mc_get_panic_on_ue())
		panic("EDAC MC%d: Uncorrected Error", mci->mc_idx);

	if (edac_mc_get_log_ue())
		edac_mc_printk(mci, KERN_WARNING,
			"UE - no information available: %s\n", msg);
	mci->ue_noinfo_count++;
	mci->ue_count++;
}
EXPORT_SYMBOL_GPL(edac_mc_handle_ue_no_info);

/*************************************************************
 * On Fully Buffered DIMM modules, this help function is
 * called to process UE events
 */
void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
			unsigned int csrow,
			unsigned int channela,
			unsigned int channelb, char *msg)
{
	int len = EDAC_MC_LABEL_LEN * 4;
	char labels[len + 1];
	char *pos = labels;
	int chars;

	if (csrow >= mci->nr_csrows) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: row out of range (%d >= %d)\n",
			csrow, mci->nr_csrows);
		edac_mc_handle_ue_no_info(mci, "INTERNAL ERROR");
		return;
	}

	if (channela >= mci->csrows[csrow].nr_channels) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: channel-a out of range "
			"(%d >= %d)\n",
			channela, mci->csrows[csrow].nr_channels);
		edac_mc_handle_ue_no_info(mci, "INTERNAL ERROR");
		return;
	}

	if (channelb >= mci->csrows[csrow].nr_channels) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: channel-b out of range "
			"(%d >= %d)\n",
			channelb, mci->csrows[csrow].nr_channels);
		edac_mc_handle_ue_no_info(mci, "INTERNAL ERROR");
		return;
	}

	mci->ue_count++;
	mci->csrows[csrow].ue_count++;

	/* Generate the DIMM labels from the specified channels */
	chars = snprintf(pos, len + 1, "%s",
			 mci->csrows[csrow].channels[channela].label);
	len -= chars;
	pos += chars;
	chars = snprintf(pos, len + 1, "-%s",
			 mci->csrows[csrow].channels[channelb].label);

	if (edac_mc_get_log_ue())
		edac_mc_printk(mci, KERN_EMERG,
			"UE row %d, channel-a= %d channel-b= %d "
			"labels \"%s\": %s\n", csrow, channela, channelb,
			labels, msg);

	if (edac_mc_get_panic_on_ue())
		panic("UE row %d, channel-a= %d channel-b= %d "
			"labels \"%s\": %s\n", csrow, channela,
			channelb, labels, msg);
}
EXPORT_SYMBOL(edac_mc_handle_fbd_ue);

/*************************************************************
 * On Fully Buffered DIMM modules, this help function is
 * called to process CE events
 */
void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
			unsigned int csrow, unsigned int channel, char *msg)
{

	/* Ensure boundary values */
	if (csrow >= mci->nr_csrows) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: row out of range (%d >= %d)\n",
			csrow, mci->nr_csrows);
		edac_mc_handle_ce_no_info(mci, "INTERNAL ERROR");
		return;
	}
	if (channel >= mci->csrows[csrow].nr_channels) {
		/* something is wrong */
		edac_mc_printk(mci, KERN_ERR,
			"INTERNAL ERROR: channel out of range (%d >= %d)\n",
			channel, mci->csrows[csrow].nr_channels);
		edac_mc_handle_ce_no_info(mci, "INTERNAL ERROR");
		return;
	}

	if (edac_mc_get_log_ce())
		/* FIXME - put in DIMM location */
		edac_mc_printk(mci, KERN_WARNING,
			"CE row %d, channel %d, label \"%s\": %s\n",
			csrow, channel,
			mci->csrows[csrow].channels[channel].label, msg);

	mci->ce_count++;
	mci->csrows[csrow].ce_count++;
	mci->csrows[csrow].channels[channel].ce_count++;
}
EXPORT_SYMBOL(edac_mc_handle_fbd_ce);

/*
 * Iterate over all MC instances and check for ECC, et al, errors
 */
void edac_check_mc_devices(void)
{
	struct list_head *item;
	struct mem_ctl_info *mci;

	debugf3("%s()\n", __func__);
	mutex_lock(&mem_ctls_mutex);

	list_for_each(item, &mc_devices) {
		mci = list_entry(item, struct mem_ctl_info, link);

		if (mci->edac_check != NULL)
			mci->edac_check(mci);
	}

	mutex_unlock(&mem_ctls_mutex);
}