summaryrefslogtreecommitdiff
path: root/drivers/edac/edac_mc.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/edac/edac_mc.c')
-rw-r--r--drivers/edac/edac_mc.c716
1 files changed, 470 insertions, 246 deletions
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index feef7733fae7..10f375032e96 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -43,9 +43,26 @@ static void edac_mc_dump_channel(struct rank_info *chan)
{
debugf4("\tchannel = %p\n", chan);
debugf4("\tchannel->chan_idx = %d\n", chan->chan_idx);
- debugf4("\tchannel->ce_count = %d\n", chan->ce_count);
- debugf4("\tchannel->label = '%s'\n", chan->label);
debugf4("\tchannel->csrow = %p\n\n", chan->csrow);
+ debugf4("\tchannel->dimm = %p\n", chan->dimm);
+}
+
+static void edac_mc_dump_dimm(struct dimm_info *dimm)
+{
+ int i;
+
+ debugf4("\tdimm = %p\n", dimm);
+ debugf4("\tdimm->label = '%s'\n", dimm->label);
+ debugf4("\tdimm->nr_pages = 0x%x\n", dimm->nr_pages);
+ debugf4("\tdimm location ");
+ for (i = 0; i < dimm->mci->n_layers; i++) {
+ printk(KERN_CONT "%d", dimm->location[i]);
+ if (i < dimm->mci->n_layers - 1)
+ printk(KERN_CONT ".");
+ }
+ printk(KERN_CONT "\n");
+ debugf4("\tdimm->grain = %d\n", dimm->grain);
+ debugf4("\tdimm->nr_pages = 0x%x\n", dimm->nr_pages);
}
static void edac_mc_dump_csrow(struct csrow_info *csrow)
@@ -55,7 +72,6 @@ static void edac_mc_dump_csrow(struct csrow_info *csrow)
debugf4("\tcsrow->first_page = 0x%lx\n", csrow->first_page);
debugf4("\tcsrow->last_page = 0x%lx\n", csrow->last_page);
debugf4("\tcsrow->page_mask = 0x%lx\n", csrow->page_mask);
- debugf4("\tcsrow->nr_pages = 0x%x\n", csrow->nr_pages);
debugf4("\tcsrow->nr_channels = %d\n", csrow->nr_channels);
debugf4("\tcsrow->channels = %p\n", csrow->channels);
debugf4("\tcsrow->mci = %p\n\n", csrow->mci);
@@ -70,6 +86,8 @@ static void edac_mc_dump_mci(struct mem_ctl_info *mci)
debugf4("\tmci->edac_check = %p\n", mci->edac_check);
debugf3("\tmci->nr_csrows = %d, csrows = %p\n",
mci->nr_csrows, mci->csrows);
+ debugf3("\tmci->nr_dimms = %d, dimms = %p\n",
+ mci->tot_dimms, mci->dimms);
debugf3("\tdev = %p\n", mci->dev);
debugf3("\tmod_name:ctl_name = %s:%s\n", mci->mod_name, mci->ctl_name);
debugf3("\tpvt_info = %p\n\n", mci->pvt_info);
@@ -101,18 +119,37 @@ const char *edac_mem_types[] = {
};
EXPORT_SYMBOL_GPL(edac_mem_types);
-/* 'ptr' points to a possibly unaligned item X such that sizeof(X) is 'size'.
- * Adjust 'ptr' so that its alignment is at least as stringent as what the
- * compiler would provide for X and return the aligned result.
+/**
+ * edac_align_ptr - Prepares the pointer offsets for a single-shot allocation
+ * @p: pointer to a pointer with the memory offset to be used. At
+ * return, this will be incremented to point to the next offset
+ * @size: Size of the data structure to be reserved
+ * @n_elems: Number of elements that should be reserved
*
* If 'size' is a constant, the compiler will optimize this whole function
- * down to either a no-op or the addition of a constant to the value of 'ptr'.
+ * down to either a no-op or the addition of a constant to the value of '*p'.
+ *
+ * The 'p' pointer is absolutely needed to keep the proper advancing
+ * further in memory to the proper offsets when allocating the struct along
+ * with its embedded structs, as edac_device_alloc_ctl_info() does it
+ * above, for example.
+ *
+ * At return, the pointer 'p' will be incremented to be used on a next call
+ * to this function.
*/
-void *edac_align_ptr(void *ptr, unsigned size)
+void *edac_align_ptr(void **p, unsigned size, int n_elems)
{
unsigned align, r;
+ void *ptr = *p;
+
+ *p += size * n_elems;
- /* Here we assume that the alignment of a "long long" is the most
+ /*
+ * 'p' can possibly be an unaligned item X such that sizeof(X) is
+ * 'size'. Adjust 'p' so that its alignment is at least as
+ * stringent as what the compiler would provide for X and return
+ * the aligned result.
+ * Here we assume that the alignment of a "long long" is the most
* stringent alignment that the compiler will ever provide by default.
* As far as I know, this is a reasonable assumption.
*/
@@ -132,14 +169,18 @@ void *edac_align_ptr(void *ptr, unsigned size)
if (r == 0)
return (char *)ptr;
+ *p += align - r;
+
return (void *)(((unsigned long)ptr) + align - r);
}
/**
- * edac_mc_alloc: Allocate a struct mem_ctl_info structure
- * @size_pvt: size of private storage needed
- * @nr_csrows: Number of CWROWS needed for this MC
- * @nr_chans: Number of channels for the MC
+ * edac_mc_alloc: Allocate and partially fill a struct mem_ctl_info structure
+ * @mc_num: Memory controller number
+ * @n_layers: Number of MC hierarchy layers
+ * layers: Describes each layer as seen by the Memory Controller
+ * @size_pvt: size of private storage needed
+ *
*
* Everything is kmalloc'ed as one big chunk - more efficient.
* Only can be used if all structures have the same lifetime - otherwise
@@ -147,32 +188,77 @@ void *edac_align_ptr(void *ptr, unsigned size)
*
* Use edac_mc_free() to free mc structures allocated by this function.
*
+ * NOTE: drivers handle multi-rank memories in different ways: in some
+ * drivers, one multi-rank memory stick is mapped as one entry, while, in
+ * others, a single multi-rank memory stick would be mapped into several
+ * entries. Currently, this function will allocate multiple struct dimm_info
+ * on such scenarios, as grouping the multiple ranks require drivers change.
+ *
* Returns:
- * NULL allocation failed
- * struct mem_ctl_info pointer
+ * On failure: NULL
+ * On success: struct mem_ctl_info pointer
*/
-struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
- unsigned nr_chans, int edac_index)
+struct mem_ctl_info *edac_mc_alloc(unsigned mc_num,
+ unsigned n_layers,
+ struct edac_mc_layer *layers,
+ unsigned sz_pvt)
{
struct mem_ctl_info *mci;
- struct csrow_info *csi, *csrow;
+ struct edac_mc_layer *layer;
+ struct csrow_info *csi, *csr;
struct rank_info *chi, *chp, *chan;
- void *pvt;
- unsigned size;
- int row, chn;
- int err;
+ struct dimm_info *dimm;
+ u32 *ce_per_layer[EDAC_MAX_LAYERS], *ue_per_layer[EDAC_MAX_LAYERS];
+ unsigned pos[EDAC_MAX_LAYERS];
+ unsigned size, tot_dimms = 1, count = 1;
+ unsigned tot_csrows = 1, tot_channels = 1, tot_errcount = 0;
+ void *pvt, *p, *ptr = NULL;
+ int i, j, err, row, chn, n, len;
+ bool per_rank = false;
+
+ BUG_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0);
+ /*
+ * Calculate the total amount of dimms and csrows/cschannels while
+ * in the old API emulation mode
+ */
+ for (i = 0; i < n_layers; i++) {
+ tot_dimms *= layers[i].size;
+ if (layers[i].is_virt_csrow)
+ tot_csrows *= layers[i].size;
+ else
+ tot_channels *= layers[i].size;
+
+ if (layers[i].type == EDAC_MC_LAYER_CHIP_SELECT)
+ per_rank = true;
+ }
/* Figure out the offsets of the various items from the start of an mc
* structure. We want the alignment of each item to be at least as
* stringent as what the compiler would provide if we could simply
* hardcode everything into a single struct.
*/
- mci = (struct mem_ctl_info *)0;
- csi = edac_align_ptr(&mci[1], sizeof(*csi));
- chi = edac_align_ptr(&csi[nr_csrows], sizeof(*chi));
- pvt = edac_align_ptr(&chi[nr_chans * nr_csrows], sz_pvt);
+ mci = edac_align_ptr(&ptr, sizeof(*mci), 1);
+ layer = edac_align_ptr(&ptr, sizeof(*layer), n_layers);
+ csi = edac_align_ptr(&ptr, sizeof(*csi), tot_csrows);
+ chi = edac_align_ptr(&ptr, sizeof(*chi), tot_csrows * tot_channels);
+ dimm = edac_align_ptr(&ptr, sizeof(*dimm), tot_dimms);
+ for (i = 0; i < n_layers; i++) {
+ count *= layers[i].size;
+ debugf4("%s: errcount layer %d size %d\n", __func__, i, count);
+ ce_per_layer[i] = edac_align_ptr(&ptr, sizeof(u32), count);
+ ue_per_layer[i] = edac_align_ptr(&ptr, sizeof(u32), count);
+ tot_errcount += 2 * count;
+ }
+
+ debugf4("%s: allocating %d error counters\n", __func__, tot_errcount);
+ pvt = edac_align_ptr(&ptr, sz_pvt, 1);
size = ((unsigned long)pvt) + sz_pvt;
+ debugf1("%s(): allocating %u bytes for mci data (%d %s, %d csrows/channels)\n",
+ __func__, size,
+ tot_dimms,
+ per_rank ? "ranks" : "dimms",
+ tot_csrows * tot_channels);
mci = kzalloc(size, GFP_KERNEL);
if (mci == NULL)
return NULL;
@@ -180,28 +266,103 @@ struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
/* Adjust pointers so they point within the memory we just allocated
* rather than an imaginary chunk of memory located at address 0.
*/
+ layer = (struct edac_mc_layer *)(((char *)mci) + ((unsigned long)layer));
csi = (struct csrow_info *)(((char *)mci) + ((unsigned long)csi));
chi = (struct rank_info *)(((char *)mci) + ((unsigned long)chi));
+ dimm = (struct dimm_info *)(((char *)mci) + ((unsigned long)dimm));
+ for (i = 0; i < n_layers; i++) {
+ mci->ce_per_layer[i] = (u32 *)((char *)mci + ((unsigned long)ce_per_layer[i]));
+ mci->ue_per_layer[i] = (u32 *)((char *)mci + ((unsigned long)ue_per_layer[i]));
+ }
pvt = sz_pvt ? (((char *)mci) + ((unsigned long)pvt)) : NULL;
/* setup index and various internal pointers */
- mci->mc_idx = edac_index;
+ mci->mc_idx = mc_num;
mci->csrows = csi;
+ mci->dimms = dimm;
+ mci->tot_dimms = tot_dimms;
mci->pvt_info = pvt;
- mci->nr_csrows = nr_csrows;
-
- for (row = 0; row < nr_csrows; row++) {
- csrow = &csi[row];
- csrow->csrow_idx = row;
- csrow->mci = mci;
- csrow->nr_channels = nr_chans;
- chp = &chi[row * nr_chans];
- csrow->channels = chp;
+ mci->n_layers = n_layers;
+ mci->layers = layer;
+ memcpy(mci->layers, layers, sizeof(*layer) * n_layers);
+ mci->nr_csrows = tot_csrows;
+ mci->num_cschannel = tot_channels;
+ mci->mem_is_per_rank = per_rank;
- for (chn = 0; chn < nr_chans; chn++) {
+ /*
+ * Fill the csrow struct
+ */
+ for (row = 0; row < tot_csrows; row++) {
+ csr = &csi[row];
+ csr->csrow_idx = row;
+ csr->mci = mci;
+ csr->nr_channels = tot_channels;
+ chp = &chi[row * tot_channels];
+ csr->channels = chp;
+
+ for (chn = 0; chn < tot_channels; chn++) {
chan = &chp[chn];
chan->chan_idx = chn;
- chan->csrow = csrow;
+ chan->csrow = csr;
+ }
+ }
+
+ /*
+ * Fill the dimm struct
+ */
+ memset(&pos, 0, sizeof(pos));
+ row = 0;
+ chn = 0;
+ debugf4("%s: initializing %d %s\n", __func__, tot_dimms,
+ per_rank ? "ranks" : "dimms");
+ for (i = 0; i < tot_dimms; i++) {
+ chan = &csi[row].channels[chn];
+ dimm = EDAC_DIMM_PTR(layer, mci->dimms, n_layers,
+ pos[0], pos[1], pos[2]);
+ dimm->mci = mci;
+
+ debugf2("%s: %d: %s%zd (%d:%d:%d): row %d, chan %d\n", __func__,
+ i, per_rank ? "rank" : "dimm", (dimm - mci->dimms),
+ pos[0], pos[1], pos[2], row, chn);
+
+ /*
+ * Copy DIMM location and initialize it.
+ */
+ len = sizeof(dimm->label);
+ p = dimm->label;
+ n = snprintf(p, len, "mc#%u", mc_num);
+ p += n;
+ len -= n;
+ for (j = 0; j < n_layers; j++) {
+ n = snprintf(p, len, "%s#%u",
+ edac_layer_name[layers[j].type],
+ pos[j]);
+ p += n;
+ len -= n;
+ dimm->location[j] = pos[j];
+
+ if (len <= 0)
+ break;
+ }
+
+ /* Link it to the csrows old API data */
+ chan->dimm = dimm;
+ dimm->csrow = row;
+ dimm->cschannel = chn;
+
+ /* Increment csrow location */
+ row++;
+ if (row == tot_csrows) {
+ row = 0;
+ chn++;
+ }
+
+ /* Increment dimm location */
+ for (j = n_layers - 1; j >= 0; j--) {
+ pos[j]++;
+ if (pos[j] < layers[j].size)
+ break;
+ pos[j] = 0;
}
}
@@ -490,7 +651,6 @@ 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
@@ -517,6 +677,8 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
edac_mc_dump_channel(&mci->csrows[i].
channels[j]);
}
+ for (i = 0; i < mci->tot_dimms; i++)
+ edac_mc_dump_dimm(&mci->dimms[i]);
}
#endif
mutex_lock(&mem_ctls_mutex);
@@ -636,15 +798,19 @@ static void edac_mc_scrub_block(unsigned long page, unsigned long offset,
int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, unsigned long page)
{
struct csrow_info *csrows = mci->csrows;
- int row, i;
+ int row, i, j, n;
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)
+ n = 0;
+ for (j = 0; j < csrow->nr_channels; j++) {
+ struct dimm_info *dimm = csrow->channels[j].dimm;
+ n += dimm->nr_pages;
+ }
+ if (n == 0)
continue;
debugf3("MC%d: %s(): first(0x%lx) page(0x%lx) last(0x%lx) "
@@ -670,249 +836,307 @@ int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, unsigned long page)
}
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;
+const char *edac_layer_name[] = {
+ [EDAC_MC_LAYER_BRANCH] = "branch",
+ [EDAC_MC_LAYER_CHANNEL] = "channel",
+ [EDAC_MC_LAYER_SLOT] = "slot",
+ [EDAC_MC_LAYER_CHIP_SELECT] = "csrow",
+};
+EXPORT_SYMBOL_GPL(edac_layer_name);
- debugf3("MC%d: %s()\n", mci->mc_idx, __func__);
+static void edac_inc_ce_error(struct mem_ctl_info *mci,
+ bool enable_per_layer_report,
+ const int pos[EDAC_MAX_LAYERS])
+{
+ int i, index = 0;
- /* 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;
- }
+ mci->ce_mc++;
- 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");
+ if (!enable_per_layer_report) {
+ mci->ce_noinfo_count++;
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 dependent 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;
+ for (i = 0; i < mci->n_layers; i++) {
+ if (pos[i] < 0)
+ break;
+ index += pos[i];
+ mci->ce_per_layer[i][index]++;
- edac_mc_scrub_block(remapped_page, offset_in_page,
- mci->csrows[row].grain);
+ if (i < mci->n_layers - 1)
+ index *= mci->layers[i + 1].size;
}
}
-EXPORT_SYMBOL_GPL(edac_mc_handle_ce);
-void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci, const char *msg)
+static void edac_inc_ue_error(struct mem_ctl_info *mci,
+ bool enable_per_layer_report,
+ const int pos[EDAC_MAX_LAYERS])
{
- if (edac_mc_get_log_ce())
- edac_mc_printk(mci, KERN_WARNING,
- "CE - no information available: %s\n", msg);
+ int i, index = 0;
- mci->ce_noinfo_count++;
- mci->ce_count++;
-}
-EXPORT_SYMBOL_GPL(edac_mc_handle_ce_no_info);
+ mci->ue_mc++;
-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");
+ if (!enable_per_layer_report) {
+ mci->ce_noinfo_count++;
return;
}
- chars = snprintf(pos, len + 1, "%s",
- mci->csrows[row].channels[0].label);
- len -= chars;
- pos += chars;
+ for (i = 0; i < mci->n_layers; i++) {
+ if (pos[i] < 0)
+ break;
+ index += pos[i];
+ mci->ue_per_layer[i][index]++;
- 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 (i < mci->n_layers - 1)
+ index *= mci->layers[i + 1].size;
}
+}
- 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);
+static void edac_ce_error(struct mem_ctl_info *mci,
+ const int pos[EDAC_MAX_LAYERS],
+ const char *msg,
+ const char *location,
+ const char *label,
+ const char *detail,
+ const char *other_detail,
+ const bool enable_per_layer_report,
+ const unsigned long page_frame_number,
+ const unsigned long offset_in_page,
+ u32 grain)
+{
+ unsigned long remapped_page;
- 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);
+ if (edac_mc_get_log_ce()) {
+ if (other_detail && *other_detail)
+ edac_mc_printk(mci, KERN_WARNING,
+ "CE %s on %s (%s%s - %s)\n",
+ msg, label, location,
+ detail, other_detail);
+ else
+ edac_mc_printk(mci, KERN_WARNING,
+ "CE %s on %s (%s%s)\n",
+ msg, label, location,
+ detail);
+ }
+ edac_inc_ce_error(mci, enable_per_layer_report, pos);
- mci->ue_count++;
- mci->csrows[row].ue_count++;
+ if (mci->scrub_mode & SCRUB_SW_SRC) {
+ /*
+ * Some memory controllers (called MCs below) 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-dependent
+ * 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, grain);
+ }
}
-EXPORT_SYMBOL_GPL(edac_mc_handle_ue);
-void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg)
+static void edac_ue_error(struct mem_ctl_info *mci,
+ const int pos[EDAC_MAX_LAYERS],
+ const char *msg,
+ const char *location,
+ const char *label,
+ const char *detail,
+ const char *other_detail,
+ const bool enable_per_layer_report)
{
- if (edac_mc_get_panic_on_ue())
- panic("EDAC MC%d: Uncorrected Error", mci->mc_idx);
+ if (edac_mc_get_log_ue()) {
+ if (other_detail && *other_detail)
+ edac_mc_printk(mci, KERN_WARNING,
+ "UE %s on %s (%s%s - %s)\n",
+ msg, label, location, detail,
+ other_detail);
+ else
+ edac_mc_printk(mci, KERN_WARNING,
+ "UE %s on %s (%s%s)\n",
+ msg, label, location, detail);
+ }
- 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++;
+ if (edac_mc_get_panic_on_ue()) {
+ if (other_detail && *other_detail)
+ panic("UE %s on %s (%s%s - %s)\n",
+ msg, label, location, detail, other_detail);
+ else
+ panic("UE %s on %s (%s%s)\n",
+ msg, label, location, detail);
+ }
+
+ edac_inc_ue_error(mci, enable_per_layer_report, pos);
}
-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)
+#define OTHER_LABEL " or "
+void edac_mc_handle_error(const enum hw_event_mc_err_type type,
+ struct mem_ctl_info *mci,
+ const unsigned long page_frame_number,
+ const unsigned long offset_in_page,
+ const unsigned long syndrome,
+ const int layer0,
+ const int layer1,
+ const int layer2,
+ const char *msg,
+ const char *other_detail,
+ const void *mcelog)
{
- int len = EDAC_MC_LABEL_LEN * 4;
- char labels[len + 1];
- char *pos = labels;
- int chars;
+ /* FIXME: too much for stack: move it to some pre-alocated area */
+ char detail[80], location[80];
+ char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * mci->tot_dimms];
+ char *p;
+ int row = -1, chan = -1;
+ int pos[EDAC_MAX_LAYERS] = { layer0, layer1, layer2 };
+ int i;
+ u32 grain;
+ bool enable_per_layer_report = false;
- 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;
- }
+ debugf3("MC%d: %s()\n", mci->mc_idx, __func__);
- 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;
+ /*
+ * Check if the event report is consistent and if the memory
+ * location is known. If it is known, enable_per_layer_report will be
+ * true, the DIMM(s) label info will be filled and the per-layer
+ * error counters will be incremented.
+ */
+ for (i = 0; i < mci->n_layers; i++) {
+ if (pos[i] >= (int)mci->layers[i].size) {
+ if (type == HW_EVENT_ERR_CORRECTED)
+ p = "CE";
+ else
+ p = "UE";
+
+ edac_mc_printk(mci, KERN_ERR,
+ "INTERNAL ERROR: %s value is out of range (%d >= %d)\n",
+ edac_layer_name[mci->layers[i].type],
+ pos[i], mci->layers[i].size);
+ /*
+ * Instead of just returning it, let's use what's
+ * known about the error. The increment routines and
+ * the DIMM filter logic will do the right thing by
+ * pointing the likely damaged DIMMs.
+ */
+ pos[i] = -1;
+ }
+ if (pos[i] >= 0)
+ enable_per_layer_report = true;
}
- 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;
- }
+ /*
+ * Get the dimm label/grain that applies to the match criteria.
+ * As the error algorithm may not be able to point to just one memory
+ * stick, the logic here will get all possible labels that could
+ * pottentially be affected by the error.
+ * On FB-DIMM memory controllers, for uncorrected errors, it is common
+ * to have only the MC channel and the MC dimm (also called "branch")
+ * but the channel is not known, as the memory is arranged in pairs,
+ * where each memory belongs to a separate channel within the same
+ * branch.
+ */
+ grain = 0;
+ p = label;
+ *p = '\0';
+ for (i = 0; i < mci->tot_dimms; i++) {
+ struct dimm_info *dimm = &mci->dimms[i];
- mci->ue_count++;
- mci->csrows[csrow].ue_count++;
+ if (layer0 >= 0 && layer0 != dimm->location[0])
+ continue;
+ if (layer1 >= 0 && layer1 != dimm->location[1])
+ continue;
+ if (layer2 >= 0 && layer2 != dimm->location[2])
+ continue;
- /* 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);
+ /* get the max grain, over the error match range */
+ if (dimm->grain > grain)
+ grain = dimm->grain;
- 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 the error is memory-controller wide, there's no need to
+ * seek for the affected DIMMs because the whole
+ * channel/memory controller/... may be affected.
+ * Also, don't show errors for empty DIMM slots.
+ */
+ if (enable_per_layer_report && dimm->nr_pages) {
+ if (p != label) {
+ strcpy(p, OTHER_LABEL);
+ p += strlen(OTHER_LABEL);
+ }
+ strcpy(p, dimm->label);
+ p += strlen(p);
+ *p = '\0';
+
+ /*
+ * get csrow/channel of the DIMM, in order to allow
+ * incrementing the compat API counters
+ */
+ debugf4("%s: %s csrows map: (%d,%d)\n",
+ __func__,
+ mci->mem_is_per_rank ? "rank" : "dimm",
+ dimm->csrow, dimm->cschannel);
+
+ if (row == -1)
+ row = dimm->csrow;
+ else if (row >= 0 && row != dimm->csrow)
+ row = -2;
+
+ if (chan == -1)
+ chan = dimm->cschannel;
+ else if (chan >= 0 && chan != dimm->cschannel)
+ chan = -2;
+ }
+ }
- 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);
+ if (!enable_per_layer_report) {
+ strcpy(label, "any memory");
+ } else {
+ debugf4("%s: csrow/channel to increment: (%d,%d)\n",
+ __func__, row, chan);
+ if (p == label)
+ strcpy(label, "unknown memory");
+ if (type == HW_EVENT_ERR_CORRECTED) {
+ if (row >= 0) {
+ mci->csrows[row].ce_count++;
+ if (chan >= 0)
+ mci->csrows[row].channels[chan].ce_count++;
+ }
+ } else
+ if (row >= 0)
+ mci->csrows[row].ue_count++;
+ }
-/*************************************************************
- * 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)
-{
+ /* Fill the RAM location data */
+ p = location;
+ for (i = 0; i < mci->n_layers; i++) {
+ if (pos[i] < 0)
+ continue;
- /* 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;
+ p += sprintf(p, "%s:%d ",
+ edac_layer_name[mci->layers[i].type],
+ pos[i]);
}
- 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);
+ /* Memory type dependent details about the error */
+ if (type == HW_EVENT_ERR_CORRECTED) {
+ snprintf(detail, sizeof(detail),
+ "page:0x%lx offset:0x%lx grain:%d syndrome:0x%lx",
+ page_frame_number, offset_in_page,
+ grain, syndrome);
+ edac_ce_error(mci, pos, msg, location, label, detail,
+ other_detail, enable_per_layer_report,
+ page_frame_number, offset_in_page, grain);
+ } else {
+ snprintf(detail, sizeof(detail),
+ "page:0x%lx offset:0x%lx grain:%d",
+ page_frame_number, offset_in_page, grain);
- mci->ce_count++;
- mci->csrows[csrow].ce_count++;
- mci->csrows[csrow].channels[channel].ce_count++;
+ edac_ue_error(mci, pos, msg, location, label, detail,
+ other_detail, enable_per_layer_report);
+ }
}
-EXPORT_SYMBOL(edac_mc_handle_fbd_ce);
+EXPORT_SYMBOL_GPL(edac_mc_handle_error);