#include <linux/sysdev.h>
#include <linux/ctype.h>
#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <asm/uaccess.h>
#include <asm/page.h>
#include <asm/edac.h>
*/
static int edac_sysfs_memctrl_setup(void)
{
- int err=0;
+ int err = 0;
debugf1("%s()\n", __func__);
/* create the /sys/devices/system/edac directory */
err = sysdev_class_register(&edac_class);
- if (!err) {
- /* Init the MC's kobject */
- memset(&edac_memctrl_kobj, 0, sizeof (edac_memctrl_kobj));
- edac_memctrl_kobj.parent = &edac_class.kset.kobj;
- edac_memctrl_kobj.ktype = &ktype_memctrl;
+ if (err) {
+ debugf1("%s() error=%d\n", __func__, err);
+ return err;
+ }
- /* generate sysfs "..../edac/mc" */
- err = kobject_set_name(&edac_memctrl_kobj,"mc");
+ /* Init the MC's kobject */
+ memset(&edac_memctrl_kobj, 0, sizeof (edac_memctrl_kobj));
+ edac_memctrl_kobj.parent = &edac_class.kset.kobj;
+ edac_memctrl_kobj.ktype = &ktype_memctrl;
- if (!err) {
- /* FIXME: maybe new sysdev_create_subdir() */
- err = kobject_register(&edac_memctrl_kobj);
+ /* generate sysfs "..../edac/mc" */
+ err = kobject_set_name(&edac_memctrl_kobj,"mc");
- if (err)
- debugf1("Failed to register '.../edac/mc'\n");
- else
- debugf1("Registered '.../edac/mc' kobject\n");
- }
- } else
- debugf1("%s() error=%d\n", __func__, err);
+ if (err)
+ goto fail;
+
+ /* FIXME: maybe new sysdev_create_subdir() */
+ err = kobject_register(&edac_memctrl_kobj);
+
+ if (err) {
+ debugf1("Failed to register '.../edac/mc'\n");
+ goto fail;
+ }
+ debugf1("Registered '.../edac/mc' kobject\n");
+
+ return 0;
+
+fail:
+ sysdev_class_unregister(&edac_class);
return err;
}
return count;
}
+/* memory scrubbing */
+static ssize_t mci_sdram_scrub_rate_store(struct mem_ctl_info *mci,
+ const char *data, size_t count)
+{
+ u32 bandwidth = -1;
+
+ if (mci->set_sdram_scrub_rate) {
+
+ memctrl_int_store(&bandwidth, data, count);
+
+ if (!(*mci->set_sdram_scrub_rate)(mci, &bandwidth)) {
+ edac_printk(KERN_DEBUG, EDAC_MC,
+ "Scrub rate set successfully, applied: %d\n",
+ bandwidth);
+ } else {
+ /* FIXME: error codes maybe? */
+ edac_printk(KERN_DEBUG, EDAC_MC,
+ "Scrub rate set FAILED, could not apply: %d\n",
+ bandwidth);
+ }
+ } else {
+ /* FIXME: produce "not implemented" ERROR for user-side. */
+ edac_printk(KERN_WARNING, EDAC_MC,
+ "Memory scrubbing 'set'control is not implemented!\n");
+ }
+ return count;
+}
+
+static ssize_t mci_sdram_scrub_rate_show(struct mem_ctl_info *mci, char *data)
+{
+ u32 bandwidth = -1;
+
+ if (mci->get_sdram_scrub_rate) {
+ if (!(*mci->get_sdram_scrub_rate)(mci, &bandwidth)) {
+ edac_printk(KERN_DEBUG, EDAC_MC,
+ "Scrub rate successfully, fetched: %d\n",
+ bandwidth);
+ } else {
+ /* FIXME: error codes maybe? */
+ edac_printk(KERN_DEBUG, EDAC_MC,
+ "Scrub rate fetch FAILED, got: %d\n",
+ bandwidth);
+ }
+ } else {
+ /* FIXME: produce "not implemented" ERROR for user-side. */
+ edac_printk(KERN_WARNING, EDAC_MC,
+ "Memory scrubbing 'get' control is not implemented!\n");
+ }
+ return sprintf(data, "%d\n", bandwidth);
+}
+
/* default attribute files for the MCI object */
static ssize_t mci_ue_count_show(struct mem_ctl_info *mci, char *data)
{
MCIDEV_ATTR(ue_count,S_IRUGO,mci_ue_count_show,NULL);
MCIDEV_ATTR(ce_count,S_IRUGO,mci_ce_count_show,NULL);
+/* memory scrubber attribute file */
+MCIDEV_ATTR(sdram_scrub_rate,S_IRUGO|S_IWUSR,mci_sdram_scrub_rate_show,mci_sdram_scrub_rate_store);
+
static struct mcidev_attribute *mci_attr[] = {
&mci_attr_reset_counters,
&mci_attr_mc_name,
&mci_attr_ce_noinfo_count,
&mci_attr_ue_count,
&mci_attr_ce_count,
+ &mci_attr_sdram_scrub_rate,
NULL
};
/* 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,
+ if (edac_create_sysfs_mci_device(mci)) {
+ edac_mc_printk(mci, KERN_WARNING,
"failed to create sysfs device\n");
- goto fail1;
- }
+ goto fail1;
+ }
/* Report action taken */
edac_mc_printk(mci, KERN_INFO, "Giving out device to %s %s: DEV %s\n",
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 (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 (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 (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
*/
debugf0("%s()\n", __func__);
kthread_stop(edac_thread);
- /* tear down the sysfs device */
+ /* tear down the sysfs device */
edac_sysfs_memctrl_teardown();
edac_sysfs_pci_teardown();
}