aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--MAINTAINERS7
-rw-r--r--drivers/acpi/apei/ghes.c71
-rw-r--r--drivers/edac/Kconfig23
-rw-r--r--drivers/edac/Makefile1
-rw-r--r--drivers/edac/edac_core.h5
-rw-r--r--drivers/edac/edac_mc.c152
-rw-r--r--drivers/edac/edac_mc_sysfs.c36
-rw-r--r--drivers/edac/edac_module.c2
-rw-r--r--drivers/edac/edac_pci_sysfs.c2
-rw-r--r--drivers/edac/ghes_edac.c537
-rw-r--r--drivers/edac/i3200_edac.c37
-rw-r--r--drivers/edac/i5100_edac.c178
-rw-r--r--drivers/edac/i7core_edac.c8
-rw-r--r--drivers/edac/sb_edac.c2
-rw-r--r--include/acpi/ghes.h72
-rw-r--r--include/linux/edac.h79
-rw-r--r--include/linux/pci_ids.h1
-rw-r--r--include/ras/ras_event.h4
18 files changed, 1077 insertions, 140 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index c7b9b2bf8a0a..6db1c6bdf015 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2904,6 +2904,13 @@ W: bluesmoke.sourceforge.net
S: Maintained
F: drivers/edac/e7xxx_edac.c
+EDAC-GHES
+M: Mauro Carvalho Chehab <mchehab@redhat.com>
+L: linux-edac@vger.kernel.org
+W: bluesmoke.sourceforge.net
+S: Maintained
+F: drivers/edac/ghes-edac.c
+
EDAC-I82443BXGX
M: Tim Small <tim@buttersideup.com>
L: linux-edac@vger.kernel.org
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 7ae2750bb457..d668a8ae602b 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -48,8 +48,8 @@
#include <linux/genalloc.h>
#include <linux/pci.h>
#include <linux/aer.h>
-#include <acpi/apei.h>
-#include <acpi/hed.h>
+
+#include <acpi/ghes.h>
#include <asm/mce.h>
#include <asm/tlbflush.h>
#include <asm/nmi.h>
@@ -84,42 +84,6 @@
((struct acpi_hest_generic_status *) \
((struct ghes_estatus_node *)(estatus_node) + 1))
-/*
- * One struct ghes is created for each generic hardware error source.
- * It provides the context for APEI hardware error timer/IRQ/SCI/NMI
- * handler.
- *
- * estatus: memory buffer for error status block, allocated during
- * HEST parsing.
- */
-#define GHES_TO_CLEAR 0x0001
-#define GHES_EXITING 0x0002
-
-struct ghes {
- struct acpi_hest_generic *generic;
- struct acpi_hest_generic_status *estatus;
- u64 buffer_paddr;
- unsigned long flags;
- union {
- struct list_head list;
- struct timer_list timer;
- unsigned int irq;
- };
-};
-
-struct ghes_estatus_node {
- struct llist_node llnode;
- struct acpi_hest_generic *generic;
-};
-
-struct ghes_estatus_cache {
- u32 estatus_len;
- atomic_t count;
- struct acpi_hest_generic *generic;
- unsigned long long time_in;
- struct rcu_head rcu;
-};
-
bool ghes_disable;
module_param_named(disable, ghes_disable, bool, 0);
@@ -333,13 +297,6 @@ static void ghes_fini(struct ghes *ghes)
apei_unmap_generic_address(&ghes->generic->error_status_address);
}
-enum {
- GHES_SEV_NO = 0x0,
- GHES_SEV_CORRECTED = 0x1,
- GHES_SEV_RECOVERABLE = 0x2,
- GHES_SEV_PANIC = 0x3,
-};
-
static inline int ghes_severity(int severity)
{
switch (severity) {
@@ -452,7 +409,8 @@ static void ghes_clear_estatus(struct ghes *ghes)
ghes->flags &= ~GHES_TO_CLEAR;
}
-static void ghes_do_proc(const struct acpi_hest_generic_status *estatus)
+static void ghes_do_proc(struct ghes *ghes,
+ const struct acpi_hest_generic_status *estatus)
{
int sev, sec_sev;
struct acpi_hest_generic_data *gdata;
@@ -464,6 +422,8 @@ static void ghes_do_proc(const struct acpi_hest_generic_status *estatus)
CPER_SEC_PLATFORM_MEM)) {
struct cper_sec_mem_err *mem_err;
mem_err = (struct cper_sec_mem_err *)(gdata+1);
+ ghes_edac_report_mem_error(ghes, sev, mem_err);
+
#ifdef CONFIG_X86_MCE
apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED,
mem_err);
@@ -682,7 +642,7 @@ static int ghes_proc(struct ghes *ghes)
if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
ghes_estatus_cache_add(ghes->generic, ghes->estatus);
}
- ghes_do_proc(ghes->estatus);
+ ghes_do_proc(ghes, ghes->estatus);
out:
ghes_clear_estatus(ghes);
return 0;
@@ -775,7 +735,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
len = apei_estatus_len(estatus);
node_len = GHES_ESTATUS_NODE_LEN(len);
- ghes_do_proc(estatus);
+ ghes_do_proc(estatus_node->ghes, estatus);
if (!ghes_estatus_cached(estatus)) {
generic = estatus_node->generic;
if (ghes_print_estatus(NULL, generic, estatus))
@@ -864,6 +824,7 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool,
node_len);
if (estatus_node) {
+ estatus_node->ghes = ghes;
estatus_node->generic = ghes->generic;
estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
memcpy(estatus, ghes->estatus, len);
@@ -942,6 +903,11 @@ static int ghes_probe(struct platform_device *ghes_dev)
ghes = NULL;
goto err;
}
+
+ rc = ghes_edac_register(ghes, &ghes_dev->dev);
+ if (rc < 0)
+ goto err;
+
switch (generic->notify.type) {
case ACPI_HEST_NOTIFY_POLLED:
ghes->timer.function = ghes_poll_func;
@@ -954,13 +920,13 @@ static int ghes_probe(struct platform_device *ghes_dev)
if (acpi_gsi_to_irq(generic->notify.vector, &ghes->irq)) {
pr_err(GHES_PFX "Failed to map GSI to IRQ for generic hardware error source: %d\n",
generic->header.source_id);
- goto err;
+ goto err_edac_unreg;
}
if (request_irq(ghes->irq, ghes_irq_func,
0, "GHES IRQ", ghes)) {
pr_err(GHES_PFX "Failed to register IRQ for generic hardware error source: %d\n",
generic->header.source_id);
- goto err;
+ goto err_edac_unreg;
}
break;
case ACPI_HEST_NOTIFY_SCI:
@@ -986,6 +952,8 @@ static int ghes_probe(struct platform_device *ghes_dev)
platform_set_drvdata(ghes_dev, ghes);
return 0;
+err_edac_unreg:
+ ghes_edac_unregister(ghes);
err:
if (ghes) {
ghes_fini(ghes);
@@ -1038,6 +1006,9 @@ static int ghes_remove(struct platform_device *ghes_dev)
}
ghes_fini(ghes);
+
+ ghes_edac_unregister(ghes);
+
kfree(ghes);
platform_set_drvdata(ghes_dev, NULL);
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index acb709bfac0f..e443f2c1dfd1 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -80,6 +80,29 @@ config EDAC_MM_EDAC
occurred so that a particular failing memory module can be
replaced. If unsure, select 'Y'.
+config EDAC_GHES
+ bool "Output ACPI APEI/GHES BIOS detected errors via EDAC"
+ depends on ACPI_APEI_GHES && (EDAC_MM_EDAC=y)
+ default y
+ help
+ Not all machines support hardware-driven error report. Some of those
+ provide a BIOS-driven error report mechanism via ACPI, using the
+ APEI/GHES driver. By enabling this option, the error reports provided
+ by GHES are sent to userspace via the EDAC API.
+
+ When this option is enabled, it will disable the hardware-driven
+ mechanisms, if a GHES BIOS is detected, entering into the
+ "Firmware First" mode.
+
+ It should be noticed that keeping both GHES and a hardware-driven
+ error mechanism won't work well, as BIOS will race with OS, while
+ reading the error registers. So, if you want to not use "Firmware
+ first" GHES error mechanism, you should disable GHES either at
+ compilation time or by passing "ghes.disable=1" Kernel parameter
+ at boot time.
+
+ In doubt, say 'Y'.
+
config EDAC_AMD64
tristate "AMD64 (Opteron, Athlon64) K8, F10h"
depends on EDAC_MM_EDAC && AMD_NB && X86_64 && EDAC_DECODE_MCE
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 5608a9ba61b7..4154ed6a02c6 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -16,6 +16,7 @@ ifdef CONFIG_PCI
edac_core-y += edac_pci.o edac_pci_sysfs.o
endif
+obj-$(CONFIG_EDAC_GHES) += ghes_edac.o
obj-$(CONFIG_EDAC_MCE_INJ) += mce_amd_inj.o
edac_mce_amd-y := mce_amd.o
diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h
index 23bb99fa44f1..3c2625e7980d 100644
--- a/drivers/edac/edac_core.h
+++ b/drivers/edac/edac_core.h
@@ -453,6 +453,11 @@ extern struct mem_ctl_info *find_mci_by_dev(struct device *dev);
extern struct mem_ctl_info *edac_mc_del_mc(struct device *dev);
extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
unsigned long page);
+
+void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type,
+ struct mem_ctl_info *mci,
+ struct edac_raw_error_desc *e);
+
void edac_mc_handle_error(const enum hw_event_mc_err_type type,
struct mem_ctl_info *mci,
const u16 error_count,
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index d1e9eb191f2b..cdb81aa73ab7 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -42,6 +42,12 @@
static DEFINE_MUTEX(mem_ctls_mutex);
static LIST_HEAD(mc_devices);
+/*
+ * Used to lock EDAC MC to just one module, avoiding two drivers e. g.
+ * apei/ghes and i7core_edac to be used at the same time.
+ */
+static void const *edac_mc_owner;
+
unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
unsigned len)
{
@@ -441,13 +447,6 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num,
mci->op_state = OP_ALLOC;
- /* at this point, the root kobj is valid, and in order to
- * 'free' the object, then the function:
- * edac_mc_unregister_sysfs_main_kobj() must be called
- * which will perform kobj unregistration and the actual free
- * will occur during the kobject callback operation
- */
-
return mci;
error:
@@ -666,9 +665,9 @@ fail1:
return 1;
}
-static void del_mc_from_global_list(struct mem_ctl_info *mci)
+static int del_mc_from_global_list(struct mem_ctl_info *mci)
{
- atomic_dec(&edac_handlers);
+ int handlers = atomic_dec_return(&edac_handlers);
list_del_rcu(&mci->link);
/* these are for safe removal of devices from global list while
@@ -676,6 +675,8 @@ static void del_mc_from_global_list(struct mem_ctl_info *mci)
*/
synchronize_rcu();
INIT_LIST_HEAD(&mci->link);
+
+ return handlers;
}
/**
@@ -719,6 +720,7 @@ EXPORT_SYMBOL(edac_mc_find);
/* FIXME - should a warning be printed if no error detection? correction? */
int edac_mc_add_mc(struct mem_ctl_info *mci)
{
+ int ret = -EINVAL;
edac_dbg(0, "\n");
#ifdef CONFIG_EDAC_DEBUG
@@ -749,6 +751,11 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
#endif
mutex_lock(&mem_ctls_mutex);
+ if (edac_mc_owner && edac_mc_owner != mci->mod_name) {
+ ret = -EPERM;
+ goto fail0;
+ }
+
if (add_mc_to_global_list(mci))
goto fail0;
@@ -775,6 +782,8 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
edac_mc_printk(mci, KERN_INFO, "Giving out device to '%s' '%s':"
" DEV %s\n", mci->mod_name, mci->ctl_name, edac_dev_name(mci));
+ edac_mc_owner = mci->mod_name;
+
mutex_unlock(&mem_ctls_mutex);
return 0;
@@ -783,7 +792,7 @@ fail1:
fail0:
mutex_unlock(&mem_ctls_mutex);
- return 1;
+ return ret;
}
EXPORT_SYMBOL_GPL(edac_mc_add_mc);
@@ -809,7 +818,8 @@ struct mem_ctl_info *edac_mc_del_mc(struct device *dev)
return NULL;
}
- del_mc_from_global_list(mci);
+ if (!del_mc_from_global_list(mci))
+ edac_mc_owner = NULL;
mutex_unlock(&mem_ctls_mutex);
/* flush workq processes */
@@ -907,6 +917,7 @@ const char *edac_layer_name[] = {
[EDAC_MC_LAYER_CHANNEL] = "channel",
[EDAC_MC_LAYER_SLOT] = "slot",
[EDAC_MC_LAYER_CHIP_SELECT] = "csrow",
+ [EDAC_MC_LAYER_ALL_MEM] = "memory",
};
EXPORT_SYMBOL_GPL(edac_layer_name);
@@ -1054,7 +1065,46 @@ static void edac_ue_error(struct mem_ctl_info *mci,
edac_inc_ue_error(mci, enable_per_layer_report, pos, error_count);
}
-#define OTHER_LABEL " or "
+/**
+ * edac_raw_mc_handle_error - reports a memory event to userspace without doing
+ * anything to discover the error location
+ *
+ * @type: severity of the error (CE/UE/Fatal)
+ * @mci: a struct mem_ctl_info pointer
+ * @e: error description
+ *
+ * This raw function is used internally by edac_mc_handle_error(). It should
+ * only be called directly when the hardware error come directly from BIOS,
+ * like in the case of APEI GHES driver.
+ */
+void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type,
+ struct mem_ctl_info *mci,
+ struct edac_raw_error_desc *e)
+{
+ char detail[80];
+ int pos[EDAC_MAX_LAYERS] = { e->top_layer, e->mid_layer, e->low_layer };
+
+ /* Memory type dependent details about the error */
+ if (type == HW_EVENT_ERR_CORRECTED) {
+ snprintf(detail, sizeof(detail),
+ "page:0x%lx offset:0x%lx grain:%ld syndrome:0x%lx",
+ e->page_frame_number, e->offset_in_page,
+ e->grain, e->syndrome);
+ edac_ce_error(mci, e->error_count, pos, e->msg, e->location, e->label,
+ detail, e->other_detail, e->enable_per_layer_report,
+ e->page_frame_number, e->offset_in_page, e->grain);
+ } else {
+ snprintf(detail, sizeof(detail),
+ "page:0x%lx offset:0x%lx grain:%ld",
+ e->page_frame_number, e->offset_in_page, e->grain);
+
+ edac_ue_error(mci, e->error_count, pos, e->msg, e->location, e->label,
+ detail, e->other_detail, e->enable_per_layer_report);
+ }
+
+
+}
+EXPORT_SYMBOL_GPL(edac_raw_mc_handle_error);
/**
* edac_mc_handle_error - reports a memory event to userspace
@@ -1086,19 +1136,27 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
const char *msg,
const char *other_detail)
{
- /* 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] = { top_layer, mid_layer, low_layer };
- int i;
- long grain;
- bool enable_per_layer_report = false;
+ int i, n_labels = 0;
u8 grain_bits;
+ struct edac_raw_error_desc *e = &mci->error_desc;
edac_dbg(3, "MC%d\n", mci->mc_idx);
+ /* Fills the error report buffer */
+ memset(e, 0, sizeof (*e));
+ e->error_count = error_count;
+ e->top_layer = top_layer;
+ e->mid_layer = mid_layer;
+ e->low_layer = low_layer;
+ e->page_frame_number = page_frame_number;
+ e->offset_in_page = offset_in_page;
+ e->syndrome = syndrome;
+ e->msg = msg;
+ e->other_detail = other_detail;
+
/*
* Check if the event report is consistent and if the memory
* location is known. If it is known, enable_per_layer_report will be
@@ -1121,7 +1179,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
pos[i] = -1;
}
if (pos[i] >= 0)
- enable_per_layer_report = true;
+ e->enable_per_layer_report = true;
}
/*
@@ -1135,8 +1193,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
* where each memory belongs to a separate channel within the same
* branch.
*/
- grain = 0;
- p = label;
+ p = e->label;
*p = '\0';
for (i = 0; i < mci->tot_dimms; i++) {
@@ -1150,8 +1207,8 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
continue;
/* get the max grain, over the error match range */
- if (dimm->grain > grain)
- grain = dimm->grain;
+ if (dimm->grain > e->grain)
+ e->grain = dimm->grain;
/*
* If the error is memory-controller wide, there's no need to
@@ -1159,8 +1216,13 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
* 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) {
+ if (e->enable_per_layer_report && dimm->nr_pages) {
+ if (n_labels >= EDAC_MAX_LABELS) {
+ e->enable_per_layer_report = false;
+ break;
+ }
+ n_labels++;
+ if (p != e->label) {
strcpy(p, OTHER_LABEL);
p += strlen(OTHER_LABEL);
}
@@ -1187,12 +1249,12 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
}
}
- if (!enable_per_layer_report) {
- strcpy(label, "any memory");
+ if (!e->enable_per_layer_report) {
+ strcpy(e->label, "any memory");
} else {
edac_dbg(4, "csrow/channel to increment: (%d,%d)\n", row, chan);
- if (p == label)
- strcpy(label, "unknown memory");
+ if (p == e->label)
+ strcpy(e->label, "unknown memory");
if (type == HW_EVENT_ERR_CORRECTED) {
if (row >= 0) {
mci->csrows[row]->ce_count += error_count;
@@ -1205,7 +1267,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
}
/* Fill the RAM location data */
- p = location;
+ p = e->location;
for (i = 0; i < mci->n_layers; i++) {
if (pos[i] < 0)
@@ -1215,32 +1277,16 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
edac_layer_name[mci->layers[i].type],
pos[i]);
}
- if (p > location)
+ if (p > e->location)
*(p - 1) = '\0';
/* Report the error via the trace interface */
- grain_bits = fls_long(grain) + 1;
- trace_mc_event(type, msg, label, error_count,
- mci->mc_idx, top_layer, mid_layer, low_layer,
- PAGES_TO_MiB(page_frame_number) | offset_in_page,
- grain_bits, syndrome, other_detail);
+ grain_bits = fls_long(e->grain) + 1;
+ trace_mc_event(type, e->msg, e->label, e->error_count,
+ mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer,
+ PAGES_TO_MiB(e->page_frame_number) | e->offset_in_page,
+ grain_bits, e->syndrome, e->other_detail);
- /* Memory type dependent details about the error */
- if (type == HW_EVENT_ERR_CORRECTED) {
- snprintf(detail, sizeof(detail),
- "page:0x%lx offset:0x%lx grain:%ld syndrome:0x%lx",
- page_frame_number, offset_in_page,
- grain, syndrome);
- edac_ce_error(mci, error_count, 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:%ld",
- page_frame_number, offset_in_page, grain);
-
- edac_ue_error(mci, error_count, pos, msg, location, label,
- detail, other_detail, enable_per_layer_report);
- }
+ edac_raw_mc_handle_error(type, mci, e);
}
EXPORT_SYMBOL_GPL(edac_mc_handle_error);
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 0ca1ca71157f..4f4b6137d74e 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -7,7 +7,7 @@
*
* Written Doug Thompson <norsk5@xmission.com> www.softwarebitmaker.com
*
- * (c) 2012 - Mauro Carvalho Chehab <mchehab@redhat.com>
+ * (c) 2012-2013 - Mauro Carvalho Chehab <mchehab@redhat.com>
* The entire API were re-written, and ported to use struct device
*
*/
@@ -429,8 +429,12 @@ static int edac_create_csrow_objects(struct mem_ctl_info *mci)
if (!nr_pages_per_csrow(csrow))
continue;
err = edac_create_csrow_object(mci, mci->csrows[i], i);
- if (err < 0)
+ if (err < 0) {
+ edac_dbg(1,
+ "failure: create csrow objects for csrow %d\n",
+ i);
goto error;
+ }
}
return 0;
@@ -677,9 +681,6 @@ static ssize_t mci_sdram_scrub_rate_store(struct device *dev,
unsigned long bandwidth = 0;
int new_bw = 0;
- if (!mci->set_sdram_scrub_rate)
- return -ENODEV;
-
if (strict_strtoul(data, 10, &bandwidth) < 0)
return -EINVAL;
@@ -703,9 +704,6 @@ static ssize_t mci_sdram_scrub_rate_show(struct device *dev,
struct mem_ctl_info *mci = to_mci(dev);
int bandwidth = 0;
- if (!mci->get_sdram_scrub_rate)
- return -ENODEV;
-
bandwidth = mci->get_sdram_scrub_rate(mci);
if (bandwidth < 0) {
edac_printk(KERN_DEBUG, EDAC_MC, "Error reading scrub rate\n");
@@ -866,8 +864,7 @@ DEVICE_ATTR(ce_count, S_IRUGO, mci_ce_count_show, NULL);
DEVICE_ATTR(max_location, S_IRUGO, mci_max_location_show, NULL);
/* memory scrubber attribute file */
-DEVICE_ATTR(sdram_scrub_rate, S_IRUGO | S_IWUSR, mci_sdram_scrub_rate_show,
- mci_sdram_scrub_rate_store);
+DEVICE_ATTR(sdram_scrub_rate, 0, NULL, NULL);
static struct attribute *mci_attrs[] = {
&dev_attr_reset_counters.attr,
@@ -878,7 +875,6 @@ static struct attribute *mci_attrs[] = {
&dev_attr_ce_noinfo_count.attr,
&dev_attr_ue_count.attr,
&dev_attr_ce_count.attr,
- &dev_attr_sdram_scrub_rate.attr,
&dev_attr_max_location.attr,
NULL
};
@@ -1007,11 +1003,28 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci)
edac_dbg(0, "creating device %s\n", dev_name(&mci->dev));
err = device_add(&mci->dev);
if (err < 0) {
+ edac_dbg(1, "failure: create device %s\n", dev_name(&mci->dev));
bus_unregister(&mci->bus);
kfree(mci->bus.name);
return err;
}
+ if (mci->set_sdram_scrub_rate || mci->get_sdram_scrub_rate) {
+ if (mci->get_sdram_scrub_rate) {
+ dev_attr_sdram_scrub_rate.attr.mode |= S_IRUGO;
+ dev_attr_sdram_scrub_rate.show = &mci_sdram_scrub_rate_show;
+ }
+ if (mci->set_sdram_scrub_rate) {
+ dev_attr_sdram_scrub_rate.attr.mode |= S_IWUSR;
+ dev_attr_sdram_scrub_rate.store = &mci_sdram_scrub_rate_store;
+ }
+ err = device_create_file(&mci->dev,
+ &dev_attr_sdram_scrub_rate);
+ if (err) {
+ edac_dbg(1, "failure: create sdram_scrub_rate\n");
+ goto fail2;
+ }
+ }
/*
* Create the dimm/rank devices
*/
@@ -1056,6 +1069,7 @@ fail:
continue;
device_unregister(&dimm->dev);
}
+fail2:
device_unregister(&mci->dev);
bus_unregister(&mci->bus);
kfree(mci->bus.name);
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 12c951a2c33d..a66941fea5a4 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -146,7 +146,7 @@ static void __exit edac_exit(void)
/*
* Inform the kernel of our entry and exit points
*/
-module_init(edac_init);
+subsys_initcall(edac_init);
module_exit(edac_exit);
MODULE_LICENSE("GPL");
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 0056c4dae9d5..e8658e451762 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -429,8 +429,8 @@ static void edac_pci_main_kobj_teardown(void)
if (atomic_dec_return(&edac_pci_sysfs_refcount) == 0) {
edac_dbg(0, "called kobject_put on main kobj\n");
kobject_put(edac_pci_top_main_kobj);
+ edac_put_sysfs_subsys();
}
- edac_put_sysfs_subsys();
}
/*
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
new file mode 100644
index 000000000000..bb534670ec02
--- /dev/null
+++ b/drivers/edac/ghes_edac.c
@@ -0,0 +1,537 @@
+/*
+ * GHES/EDAC Linux driver
+ *
+ * This file may be distributed under the terms of the GNU General Public
+ * License version 2.
+ *
+ * Copyright (c) 2013 by Mauro Carvalho Chehab <mchehab@redhat.com>
+ *
+ * Red Hat Inc. http://www.redhat.com
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <acpi/ghes.h>
+#include <linux/edac.h>
+#include <linux/dmi.h>
+#include "edac_core.h"
+#include <ras/ras_event.h>
+
+#define GHES_EDAC_REVISION " Ver: 1.0.0"
+
+struct ghes_edac_pvt {
+ struct list_head list;
+ struct ghes *ghes;
+ struct mem_ctl_info *mci;
+
+ /* Buffers for the error handling routine */
+ char detail_location[240];
+ char other_detail[160];
+ char msg[80];
+};
+
+static LIST_HEAD(ghes_reglist);
+static DEFINE_MUTEX(ghes_edac_lock);
+static int ghes_edac_mc_num;
+
+
+/* Memory Device - Type 17 of SMBIOS spec */
+struct memdev_dmi_entry {
+ u8 type;
+ u8 length;
+ u16 handle;
+ u16 phys_mem_array_handle;
+ u16 mem_err_info_handle;
+ u16 total_width;
+ u16 data_width;
+ u16 size;
+ u8 form_factor;
+ u8 device_set;
+ u8 device_locator;
+ u8 bank_locator;
+ u8 memory_type;
+ u16 type_detail;
+ u16 speed;
+ u8 manufacturer;
+ u8 serial_number;
+ u8 asset_tag;
+ u8 part_number;
+ u8 attributes;
+ u32 extended_size;
+ u16 conf_mem_clk_speed;
+} __attribute__((__packed__));
+
+struct ghes_edac_dimm_fill {
+ struct mem_ctl_info *mci;
+ unsigned count;
+};
+
+char *memory_type[] = {
+ [MEM_EMPTY] = "EMPTY",
+ [MEM_RESERVED] = "RESERVED",
+ [MEM_UNKNOWN] = "UNKNOWN",
+ [MEM_FPM] = "FPM",
+ [MEM_EDO] = "EDO",
+ [MEM_BEDO] = "BEDO",
+ [MEM_SDR] = "SDR",
+ [MEM_RDR] = "RDR",
+ [MEM_DDR] = "DDR",
+ [MEM_RDDR] = "RDDR",
+ [MEM_RMBS] = "RMBS",
+ [MEM_DDR2] = "DDR2",
+ [MEM_FB_DDR2] = "FB_DDR2",
+ [MEM_RDDR2] = "RDDR2",
+ [MEM_XDR] = "XDR",
+ [MEM_DDR3] = "DDR3",
+ [MEM_RDDR3] = "RDDR3",
+};
+
+static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg)
+{
+ int *num_dimm = arg;
+
+ if (dh->type == DMI_ENTRY_MEM_DEVICE)
+ (*num_dimm)++;
+}
+
+static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
+{
+ struct ghes_edac_dimm_fill *dimm_fill = arg;
+ struct mem_ctl_info *mci = dimm_fill->mci;
+
+ if (dh->type == DMI_ENTRY_MEM_DEVICE) {
+ struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh;
+ struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
+ mci->n_layers,
+ dimm_fill->count, 0, 0);
+
+ if (entry->size == 0xffff) {
+ pr_info("Can't get DIMM%i size\n",
+ dimm_fill->count);
+ dimm->nr_pages = MiB_TO_PAGES(32);/* Unknown */
+ } else if (entry->size == 0x7fff) {
+ dimm->nr_pages = MiB_TO_PAGES(entry->extended_size);
+ } else {
+ if (entry->size & 1 << 15)
+ dimm->nr_pages = MiB_TO_PAGES((entry->size &
+ 0x7fff) << 10);
+ else
+ dimm->nr_pages = MiB_TO_PAGES(entry->size);
+ }
+
+ switch (entry->memory_type) {
+ case 0x12:
+ if (entry->type_detail & 1 << 13)
+ dimm->mtype = MEM_RDDR;
+ else
+ dimm->mtype = MEM_DDR;
+ break;
+ case 0x13:
+ if (entry->type_detail & 1 << 13)
+ dimm->mtype = MEM_RDDR2;
+ else
+ dimm->mtype = MEM_DDR2;
+ break;
+ case 0x14:
+ dimm->mtype = MEM_FB_DDR2;
+ break;
+ case 0x18:
+ if (entry->type_detail & 1 << 13)
+ dimm->mtype = MEM_RDDR3;
+ else
+ dimm->mtype = MEM_DDR3;
+ break;
+ default:
+ if (entry->type_detail & 1 << 6)
+ dimm->mtype = MEM_RMBS;
+ else if ((entry->type_detail & ((1 << 7) | (1 << 13)))
+ == ((1 << 7) | (1 << 13)))
+ dimm->mtype = MEM_RDR;
+ else if (entry->type_detail & 1 << 7)
+ dimm->mtype = MEM_SDR;
+ else if (entry->type_detail & 1 << 9)
+ dimm->mtype = MEM_EDO;
+ else
+ dimm->mtype = MEM_UNKNOWN;
+ }
+
+ /*
+ * Actually, we can only detect if the memory has bits for
+ * checksum or not
+ */
+ if (entry->total_width == entry->data_width)
+ dimm->edac_mode = EDAC_NONE;
+ else
+ dimm->edac_mode = EDAC_SECDED;
+
+ dimm->dtype = DEV_UNKNOWN;
+ dimm->grain = 128; /* Likely, worse case */
+
+ /*
+ * FIXME: It shouldn't be hard to also fill the DIMM labels
+ */
+
+ if (dimm->nr_pages) {
+ edac_dbg(1, "DIMM%i: %s size = %d MB%s\n",
+ dimm_fill->count, memory_type[dimm->mtype],
+ PAGES_TO_MiB(dimm->nr_pages),
+ (dimm->edac_mode != EDAC_NONE) ? "(ECC)" : "");
+ edac_dbg(2, "\ttype %d, detail 0x%02x, width %d(total %d)\n",
+ entry->memory_type, entry->type_detail,
+ entry->total_width, entry->data_width);
+ }
+
+ dimm_fill->count++;
+ }
+}
+
+void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
+ struct cper_sec_mem_err *mem_err)
+{
+ enum hw_event_mc_err_type type;
+ struct edac_raw_error_desc *e;
+ struct mem_ctl_info *mci;
+ struct ghes_edac_pvt *pvt = NULL;
+ char *p;
+ u8 grain_bits;
+
+ list_for_each_entry(pvt, &ghes_reglist, list) {
+ if (ghes == pvt->ghes)
+ break;
+ }
+ if (!pvt) {
+ pr_err("Internal error: Can't find EDAC structure\n");
+ return;
+ }
+ mci = pvt->mci;
+ e = &mci->error_desc;
+
+ /* Cleans the error report buffer */
+ memset(e, 0, sizeof (*e));
+ e->error_count = 1;
+ strcpy(e->label, "unknown label");
+ e->msg = pvt->msg;
+ e->other_detail = pvt->other_detail;
+ e->top_layer = -1;
+ e->mid_layer = -1;
+ e->low_layer = -1;
+ *pvt->other_detail = '\0';
+ *pvt->msg = '\0';
+
+ switch (sev) {
+ case GHES_SEV_CORRECTED:
+ type = HW_EVENT_ERR_CORRECTED;
+ break;
+ case GHES_SEV_RECOVERABLE:
+ type = HW_EVENT_ERR_UNCORRECTED;
+ break;
+ case GHES_SEV_PANIC:
+ type = HW_EVENT_ERR_FATAL;
+ break;
+ default:
+ case GHES_SEV_NO:
+ type = HW_EVENT_ERR_INFO;
+ }
+
+ edac_dbg(1, "error validation_bits: 0x%08llx\n",
+ (long long)mem_err->validation_bits);
+
+ /* Error type, mapped on e->msg */
+ if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
+ p = pvt->msg;
+ switch (mem_err->error_type) {
+ case 0:
+ p += sprintf(p, "Unknown");
+ break;
+ case 1:
+ p += sprintf(p, "No error");
+ break;
+ case 2:
+ p += sprintf(p, "Single-bit ECC");
+ break;
+ case 3:
+ p += sprintf(p, "Multi-bit ECC");
+ break;
+ case 4:
+ p += sprintf(p, "Single-symbol ChipKill ECC");
+ break;
+ case 5:
+ p += sprintf(p, "Multi-symbol ChipKill ECC");
+ break;
+ case 6:
+ p += sprintf(p, "Master abort");
+ break;
+ case 7:
+ p += sprintf(p, "Target abort");
+ break;
+ case 8:
+ p += sprintf(p, "Parity Error");
+ break;
+ case 9:
+ p += sprintf(p, "Watchdog timeout");
+ break;
+ case 10:
+ p += sprintf(p, "Invalid address");
+ break;
+ case 11:
+ p += sprintf(p, "Mirror Broken");
+ break;
+ case 12:
+ p += sprintf(p, "Memory Sparing");
+ break;
+ case 13:
+ p += sprintf(p, "Scrub corrected error");
+ break;
+ case 14:
+ p += sprintf(p, "Scrub uncorrected error");
+ break;
+ case 15:
+ p += sprintf(p, "Physical Memory Map-out event");
+ break;
+ default:
+ p += sprintf(p, "reserved error (%d)",
+ mem_err->error_type);
+ }
+ } else {
+ strcpy(pvt->msg, "unknown error");
+ }
+
+ /* Error address */
+ if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+ e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;
+ e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;
+ }
+
+ /* Error grain */
+ if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) {
+ e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
+ }
+
+ /* Memory error location, mapped on e->location */
+ p = e->location;
+ if (mem_err->validation_bits & CPER_MEM_VALID_NODE)
+ p += sprintf(p, "node:%d ", mem_err->node);
+ if (mem_err->validation_bits & CPER_MEM_VALID_CARD)
+ p += sprintf(p, "card:%d ", mem_err->card);
+ if (mem_err->validation_bits & CPER_MEM_VALID_MODULE)
+ p += sprintf(p, "module:%d ", mem_err->module);
+ if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
+ p += sprintf(p, "bank:%d ", mem_err->bank);
+ if (mem_err->validation_bits & CPER_MEM_VALID_ROW)
+ p += sprintf(p, "row:%d ", mem_err->row);
+ if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN)
+ p += sprintf(p, "col:%d ", mem_err->column);
+ if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION)
+ p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos);
+ if (p > e->location)
+ *(p - 1) = '\0';
+
+ /* All other fields are mapped on e->other_detail */
+ p = pvt->other_detail;
+ if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) {
+ u64 status = mem_err->error_status;
+
+ p += sprintf(p, "status(0x%016llx): ", (long long)status);
+ switch ((status >> 8) & 0xff) {
+ case 1:
+ p += sprintf(p, "Error detected internal to the component ");
+ break;
+ case 16:
+ p += sprintf(p, "Error detected in the bus ");
+ break;
+ case 4:
+ p += sprintf(p, "Storage error in DRAM memory ");
+ break;
+ case 5:
+ p += sprintf(p, "Storage error in TLB ");
+ break;
+ case 6:
+ p += sprintf(p, "Storage error in cache ");
+ break;
+ case 7:
+ p += sprintf(p, "Error in one or more functional units ");
+ break;
+ case 8:
+ p += sprintf(p, "component failed self test ");
+ break;
+ case 9:
+ p += sprintf(p, "Overflow or undervalue of internal queue ");
+ break;
+ case 17:
+ p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR ");
+ break;
+ case 18:
+ p += sprintf(p, "Improper access error ");
+ break;
+ case 19:
+ p += sprintf(p, "Access to a memory address which is not mapped to any component ");
+ break;
+ case 20:
+ p += sprintf(p, "Loss of Lockstep ");
+ break;
+ case 21:
+ p += sprintf(p, "Response not associated with a request ");
+ break;
+ case 22:
+ p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits ");
+ break;
+ case 23:
+ p += sprintf(p, "Detection of a PATH_ERROR ");
+ break;
+ case 25:
+ p += sprintf(p, "Bus operation timeout ");
+ break;
+ case 26:
+ p += sprintf(p, "A read was issued to data that has been poisoned ");
+ break;
+ default:
+ p += sprintf(p, "reserved ");
+ break;
+ }
+ }
+ if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)
+ p += sprintf(p, "requestorID: 0x%016llx ",
+ (long long)mem_err->requestor_id);
+ if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID)
+ p += sprintf(p, "responderID: 0x%016llx ",
+ (long long)mem_err->responder_id);
+ if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID)
+ p += sprintf(p, "targetID: 0x%016llx ",
+ (long long)mem_err->responder_id);
+ if (p > pvt->other_detail)
+ *(p - 1) = '\0';
+
+ /* Generate the trace event */
+ grain_bits = fls_long(e->grain);
+ sprintf(pvt->detail_location, "APEI location: %s %s",
+ e->location, e->other_detail);
+ trace_mc_event(type, e->msg, e->label, e->error_count,
+ mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer,
+ PAGES_TO_MiB(e->page_frame_number) | e->offset_in_page,
+ grain_bits, e->syndrome, pvt->detail_location);
+
+ /* Report the error via EDAC API */
+ edac_raw_mc_handle_error(type, mci, e);
+}
+EXPORT_SYMBOL_GPL(ghes_edac_report_mem_error);
+
+int ghes_edac_register(struct ghes *ghes, struct device *dev)
+{
+ bool fake = false;
+ int rc, num_dimm = 0;
+ struct mem_ctl_info *mci;
+ struct edac_mc_layer layers[1];
+ struct ghes_edac_pvt *pvt;
+ struct ghes_edac_dimm_fill dimm_fill;
+
+ /* Get the number of DIMMs */
+ dmi_walk(ghes_edac_count_dimms, &num_dimm);
+
+ /* Check if we've got a bogus BIOS */
+ if (num_dimm == 0) {
+ fake = true;
+ num_dimm = 1;
+ }
+
+ layers[0].type = EDAC_MC_LAYER_ALL_MEM;
+ layers[0].size = num_dimm;
+ layers[0].is_virt_csrow = true;
+
+ /*
+ * We need to serialize edac_mc_alloc() and edac_mc_add_mc(),
+ * to avoid duplicated memory controller numbers
+ */
+ mutex_lock(&ghes_edac_lock);
+ mci = edac_mc_alloc(ghes_edac_mc_num, ARRAY_SIZE(layers), layers,
+ sizeof(*pvt));
+ if (!mci) {
+ pr_info("Can't allocate memory for EDAC data\n");
+ mutex_unlock(&ghes_edac_lock);
+ return -ENOMEM;
+ }
+
+ pvt = mci->pvt_info;
+ memset(pvt, 0, sizeof(*pvt));
+ list_add_tail(&pvt->list, &ghes_reglist);
+ pvt->ghes = ghes;
+ pvt->mci = mci;
+ mci->pdev = dev;
+
+ mci->mtype_cap = MEM_FLAG_EMPTY;
+ mci->edac_ctl_cap = EDAC_FLAG_NONE;
+ mci->edac_cap = EDAC_FLAG_NONE;
+ mci->mod_name = "ghes_edac.c";
+ mci->mod_ver = GHES_EDAC_REVISION;
+ mci->ctl_name = "ghes_edac";
+ mci->dev_name = "ghes";
+
+ if (!ghes_edac_mc_num) {
+ if (!fake) {
+ pr_info("This EDAC driver relies on BIOS to enumerate memory and get error reports.\n");
+ pr_info("Unfortunately, not all BIOSes reflect the memory layout correctly.\n");
+ pr_info("So, the end result of using this driver varies from vendor to vendor.\n");
+ pr_info("If you find incorrect reports, please contact your hardware vendor\n");
+ pr_info("to correct its BIOS.\n");
+ pr_info("This system has %d DIMM sockets.\n",
+ num_dimm);
+ } else {
+ pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS.\n");
+ pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would\n");
+ pr_info("work on such system. Use this driver with caution\n");
+ }
+ }
+
+ if (!fake) {
+ /*
+ * Fill DIMM info from DMI for the memory controller #0
+ *
+ * Keep it in blank for the other memory controllers, as
+ * there's no reliable way to properly credit each DIMM to
+ * the memory controller, as different BIOSes fill the
+ * DMI bank location fields on different ways
+ */
+ if (!ghes_edac_mc_num) {
+ dimm_fill.count = 0;
+ dimm_fill.mci = mci;
+ dmi_walk(ghes_edac_dmidecode, &dimm_fill);
+ }
+ } else {
+ struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
+ mci->n_layers, 0, 0, 0);
+
+ dimm->nr_pages = 1;
+ dimm->grain = 128;
+ dimm->mtype = MEM_UNKNOWN;
+ dimm->dtype = DEV_UNKNOWN;
+ dimm->edac_mode = EDAC_SECDED;
+ }
+
+ rc = edac_mc_add_mc(mci);
+ if (rc < 0) {
+ pr_info("Can't register at EDAC core\n");
+ edac_mc_free(mci);
+ mutex_unlock(&ghes_edac_lock);
+ return -ENODEV;
+ }
+
+ ghes_edac_mc_num++;
+ mutex_unlock(&ghes_edac_lock);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ghes_edac_register);
+
+void ghes_edac_unregister(struct ghes *ghes)
+{
+ struct mem_ctl_info *mci;
+ struct ghes_edac_pvt *pvt, *tmp;
+
+ list_for_each_entry_safe(pvt, tmp, &ghes_reglist, list) {
+ if (ghes == pvt->ghes) {
+ mci = pvt->mci;
+ edac_mc_del_mc(mci->pdev);
+ edac_mc_free(mci);
+ list_del(&pvt->list);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(ghes_edac_unregister);
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index 4e8337602e78..aa44c1718f50 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -106,16 +106,26 @@ static int nr_channels;
static int how_many_channels(struct pci_dev *pdev)
{
+ int n_channels;
+
unsigned char capid0_8b; /* 8th byte of CAPID0 */
pci_read_config_byte(pdev, I3200_CAPID0 + 8, &capid0_8b);
+
if (capid0_8b & 0x20) { /* check DCD: Dual Channel Disable */
edac_dbg(0, "In single channel mode\n");
- return 1;
+ n_channels = 1;
} else {
edac_dbg(0, "In dual channel mode\n");
- return 2;
+ n_channels = 2;
}
+
+ if (capid0_8b & 0x10) /* check if both channels are filled */
+ edac_dbg(0, "2 DIMMS per channel disabled\n");
+ else
+ edac_dbg(0, "2 DIMMS per channel enabled\n");
+
+ return n_channels;
}
static unsigned long eccerrlog_syndrome(u64 log)
@@ -290,6 +300,8 @@ static void i3200_get_drbs(void __iomem *window,
for (i = 0; i < I3200_RANKS_PER_CHANNEL; i++) {
drbs[0][i] = readw(window + I3200_C0DRB + 2*i) & I3200_DRB_MASK;
drbs[1][i] = readw(window + I3200_C1DRB + 2*i) & I3200_DRB_MASK;
+
+ edac_dbg(0, "drb[0][%d] = %d, drb[1][%d] = %d\n", i, drbs[0][i], i, drbs[1][i]);
}
}
@@ -311,6 +323,9 @@ static unsigned long drb_to_nr_pages(
int n;
n = drbs[channel][rank];
+ if (!n)
+ return 0;
+
if (rank > 0)
n -= drbs[channel][rank - 1];
if (stacked && (channel == 1) &&
@@ -377,19 +392,19 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx)
* cumulative; the last one will contain the total memory
* contained in all ranks.
*/
- for (i = 0; i < mci->nr_csrows; i++) {
+ for (i = 0; i < I3200_DIMMS; i++) {
unsigned long nr_pages;
- struct csrow_info *csrow = mci->csrows[i];
- nr_pages = drb_to_nr_pages(drbs, stacked,
- i / I3200_RANKS_PER_CHANNEL,
- i % I3200_RANKS_PER_CHANNEL);
+ for (j = 0; j < nr_channels; j++) {
+ struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
+ mci->n_layers, i, j, 0);
- if (nr_pages == 0)
- continue;
+ nr_pages = drb_to_nr_pages(drbs, stacked, j, i);
+ if (nr_pages == 0)
+ continue;
- for (j = 0; j < nr_channels; j++) {
- struct dimm_info *dimm = csrow->channels[j]->dimm;
+ edac_dbg(0, "csrow %d, channel %d%s, size = %ld Mb\n", i, j,
+ stacked ? " (stacked)" : "", PAGES_TO_MiB(nr_pages));
dimm->nr_pages = nr_pages;
dimm->grain = nr_pages << PAGE_SHIFT;
diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c
index d6955b2cc99f..1b635178cc44 100644
--- a/drivers/edac/i5100_edac.c
+++ b/drivers/edac/i5100_edac.c
@@ -27,6 +27,7 @@
#include <linux/edac.h>
#include <linux/delay.h>
#include <linux/mmzone.h>
+#include <linux/debugfs.h>
#include "edac_core.h"
@@ -68,6 +69,14 @@
I5100_FERR_NF_MEM_M1ERR_MASK)
#define I5100_NERR_NF_MEM 0xa4 /* MC Next Non-Fatal Errors */
#define I5100_EMASK_MEM 0xa8 /* MC Error Mask Register */
+#define I5100_MEM0EINJMSK0 0x200 /* Injection Mask0 Register Channel 0 */
+#define I5100_MEM1EINJMSK0 0x208 /* Injection Mask0 Register Channel 1 */
+#define I5100_MEMXEINJMSK0_EINJEN (1 << 27)
+#define I5100_MEM0EINJMSK1 0x204 /* Injection Mask1 Register Channel 0 */
+#define I5100_MEM1EINJMSK1 0x206 /* Injection Mask1 Register Channel 1 */
+
+/* Device 19, Function 0 */
+#define I5100_DINJ0 0x9a
/* device 21 and 22, func 0 */
#define I5100_MTR_0 0x154 /* Memory Technology Registers 0-3 */
@@ -338,13 +347,26 @@ struct i5100_priv {
unsigned ranksperchan; /* number of ranks per channel */
struct pci_dev *mc; /* device 16 func 1 */
+ struct pci_dev *einj; /* device 19 func 0 */
struct pci_dev *ch0mm; /* device 21 func 0 */
struct pci_dev *ch1mm; /* device 22 func 0 */
struct delayed_work i5100_scrubbing;
int scrub_enable;
+
+ /* Error injection */
+ u8 inject_channel;
+ u8 inject_hlinesel;
+ u8 inject_deviceptr1;
+ u8 inject_deviceptr2;
+ u16 inject_eccmask1;
+ u16 inject_eccmask2;
+
+ struct dentry *debugfs;
};
+static struct dentry *i5100_debugfs;
+
/* map a rank/chan to a slot number on the mainboard */
static int i5100_rank_to_slot(const struct mem_ctl_info *mci,
int chan, int rank)
@@ -863,13 +885,126 @@ static void i5100_init_csrows(struct mem_ctl_info *mci)
}
}
+/****************************************************************************
+ * Error injection routines
+ ****************************************************************************/
+
+static void i5100_do_inject(struct mem_ctl_info *mci)
+{
+ struct i5100_priv *priv = mci->pvt_info;
+ u32 mask0;
+ u16 mask1;
+
+ /* MEM[1:0]EINJMSK0
+ * 31 - ADDRMATCHEN
+ * 29:28 - HLINESEL
+ * 00 Reserved
+ * 01 Lower half of cache line
+ * 10 Upper half of cache line
+ * 11 Both upper and lower parts of cache line
+ * 27 - EINJEN
+ * 25:19 - XORMASK1 for deviceptr1
+ * 9:5 - SEC2RAM for deviceptr2
+ * 4:0 - FIR2RAM for deviceptr1
+ */
+ mask0 = ((priv->inject_hlinesel & 0x3) << 28) |
+ I5100_MEMXEINJMSK0_EINJEN |
+ ((priv->inject_eccmask1 & 0xffff) << 10) |
+ ((priv->inject_deviceptr2 & 0x1f) << 5) |
+ (priv->inject_deviceptr1 & 0x1f);
+
+ /* MEM[1:0]EINJMSK1
+ * 15:0 - XORMASK2 for deviceptr2
+ */
+ mask1 = priv->inject_eccmask2;
+
+ if (priv->inject_channel == 0) {
+ pci_write_config_dword(priv->mc, I5100_MEM0EINJMSK0, mask0);
+ pci_write_config_word(priv->mc, I5100_MEM0EINJMSK1, mask1);
+ } else {
+ pci_write_config_dword(priv->mc, I5100_MEM1EINJMSK0, mask0);
+ pci_write_config_word(priv->mc, I5100_MEM1EINJMSK1, mask1);
+ }
+
+ /* Error Injection Response Function
+ * Intel 5100 Memory Controller Hub Chipset (318378) datasheet
+ * hints about this register but carry no data about them. All
+ * data regarding device 19 is based on experimentation and the
+ * Intel 7300 Chipset Memory Controller Hub (318082) datasheet
+ * which appears to be accurate for the i5100 in this area.
+ *
+ * The injection code don't work without setting this register.
+ * The register needs to be flipped off then on else the hardware
+ * will only preform the first injection.
+ *
+ * Stop condition bits 7:4
+ * 1010 - Stop after one injection
+ * 1011 - Never stop injecting faults
+ *
+ * Start condition bits 3:0
+ * 1010 - Never start
+ * 1011 - Start immediately
+ */
+ pci_write_config_byte(priv->einj, I5100_DINJ0, 0xaa);
+ pci_write_config_byte(priv->einj, I5100_DINJ0, 0xab);
+}
+
+#define to_mci(k) container_of(k, struct mem_ctl_info, dev)
+static ssize_t inject_enable_write(struct file *file, const char __user *data,
+ size_t count, loff_t *ppos)
+{
+ struct device *dev = file->private_data;
+ struct mem_ctl_info *mci = to_mci(dev);
+
+ i5100_do_inject(mci);
+
+ return count;
+}
+
+static const struct file_operations i5100_inject_enable_fops = {
+ .open = simple_open,
+ .write = inject_enable_write,
+ .llseek = generic_file_llseek,
+};
+
+static int i5100_setup_debugfs(struct mem_ctl_info *mci)
+{
+ struct i5100_priv *priv = mci->pvt_info;
+
+ if (!i5100_debugfs)
+ return -ENODEV;
+
+ priv->debugfs = debugfs_create_dir(mci->bus.name, i5100_debugfs);
+
+ if (!priv->debugfs)
+ return -ENOMEM;
+
+ debugfs_create_x8("inject_channel", S_IRUGO | S_IWUSR, priv->debugfs,
+ &priv->inject_channel);
+ debugfs_create_x8("inject_hlinesel", S_IRUGO | S_IWUSR, priv->debugfs,
+ &priv->inject_hlinesel);
+ debugfs_create_x8("inject_deviceptr1", S_IRUGO | S_IWUSR, priv->debugfs,
+ &priv->inject_deviceptr1);
+ debugfs_create_x8("inject_deviceptr2", S_IRUGO | S_IWUSR, priv->debugfs,
+ &priv->inject_deviceptr2);
+ debugfs_create_x16("inject_eccmask1", S_IRUGO | S_IWUSR, priv->debugfs,
+ &priv->inject_eccmask1);
+ debugfs_create_x16("inject_eccmask2", S_IRUGO | S_IWUSR, priv->debugfs,
+ &priv->inject_eccmask2);
+ debugfs_create_file("inject_enable", S_IWUSR, priv->debugfs,
+ &mci->dev, &i5100_inject_enable_fops);
+
+ return 0;
+
+}
+
static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
{
int rc;
struct mem_ctl_info *mci;
struct edac_mc_layer layers[2];
struct i5100_priv *priv;
- struct pci_dev *ch0mm, *ch1mm;
+ struct pci_dev *ch0mm, *ch1mm, *einj;
int ret = 0;
u32 dw;
int ranksperch;
@@ -941,6 +1076,22 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
goto bail_disable_ch1;
}
+
+ /* device 19, func 0, Error injection */
+ einj = pci_get_device_func(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_5100_19, 0);
+ if (!einj) {
+ ret = -ENODEV;
+ goto bail_einj;
+ }
+
+ rc = pci_enable_device(einj);
+ if (rc < 0) {
+ ret = rc;
+ goto bail_disable_einj;
+ }
+
+
mci->pdev = &pdev->dev;
priv = mci->pvt_info;
@@ -948,6 +1099,7 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
priv->mc = pdev;
priv->ch0mm = ch0mm;
priv->ch1mm = ch1mm;
+ priv->einj = einj;
INIT_DELAYED_WORK(&(priv->i5100_scrubbing), i5100_refresh_scrubbing);
@@ -975,6 +1127,13 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
mci->set_sdram_scrub_rate = i5100_set_scrub_rate;
mci->get_sdram_scrub_rate = i5100_get_scrub_rate;
+ priv->inject_channel = 0;
+ priv->inject_hlinesel = 0;
+ priv->inject_deviceptr1 = 0;
+ priv->inject_deviceptr2 = 0;
+ priv->inject_eccmask1 = 0;
+ priv->inject_eccmask2 = 0;
+
i5100_init_csrows(mci);
/* this strange construction seems to be in every driver, dunno why */
@@ -992,6 +1151,8 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
goto bail_scrub;
}
+ i5100_setup_debugfs(mci);
+
return ret;
bail_scrub:
@@ -999,6 +1160,12 @@ bail_scrub:
cancel_delayed_work_sync(&(priv->i5100_scrubbing));
edac_mc_free(mci);
+bail_disable_einj:
+ pci_disable_device(einj);
+
+bail_einj:
+ pci_dev_put(einj);
+
bail_disable_ch1:
pci_disable_device(ch1mm);
@@ -1030,14 +1197,18 @@ static void i5100_remove_one(struct pci_dev *pdev)
priv = mci->pvt_info;
+ debugfs_remove_recursive(priv->debugfs);
+
priv->scrub_enable = 0;
cancel_delayed_work_sync(&(priv->i5100_scrubbing));
pci_disable_device(pdev);
pci_disable_device(priv->ch0mm);
pci_disable_device(priv->ch1mm);
+ pci_disable_device(priv->einj);
pci_dev_put(priv->ch0mm);
pci_dev_put(priv->ch1mm);
+ pci_dev_put(priv->einj);
edac_mc_free(mci);
}
@@ -1060,13 +1231,16 @@ static int __init i5100_init(void)
{
int pci_rc;
- pci_rc = pci_register_driver(&i5100_driver);
+ i5100_debugfs = debugfs_create_dir("i5100_edac", NULL);
+ pci_rc = pci_register_driver(&i5100_driver);
return (pci_rc < 0) ? pci_rc : 0;
}
static void __exit i5100_exit(void)
{
+ debugfs_remove(i5100_debugfs);
+
pci_unregister_driver(&i5100_driver);
}
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index e213d030b0dd..0ec3e95a12cd 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -420,21 +420,21 @@ static inline int numdimms(u32 dimms)
static inline int numrank(u32 rank)
{
- static int ranks[4] = { 1, 2, 4, -EINVAL };
+ static const int ranks[] = { 1, 2, 4, -EINVAL };
return ranks[rank & 0x3];
}
static inline int numbank(u32 bank)
{
- static int banks[4] = { 4, 8, 16, -EINVAL };
+ static const int banks[] = { 4, 8, 16, -EINVAL };
return banks[bank & 0x3];
}
static inline int numrow(u32 row)
{
- static int rows[8] = {
+ static const int rows[] = {
1 << 12, 1 << 13, 1 << 14, 1 << 15,
1 << 16, -EINVAL, -EINVAL, -EINVAL,
};
@@ -444,7 +444,7 @@ static inline int numrow(u32 row)
static inline int numcol(u32 col)
{
- static int cols[8] = {
+ static const int cols[] = {
1 << 10, 1 << 11, 1 << 12, -EINVAL,
};
return cols[col & 0x3];
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index da7e2986e3d5..57244f995614 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -639,7 +639,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
tmp_mb = (1 + pvt->tohm) >> 20;
mb = div_u64_rem(tmp_mb, 1000, &kb);
- edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)", mb, kb, (u64)pvt->tohm);
+ edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tohm);
/*
* Step 2) Get SAD range and SAD Interleave list
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
new file mode 100644
index 000000000000..720446cb243e
--- /dev/null
+++ b/include/acpi/ghes.h
@@ -0,0 +1,72 @@
+#include <acpi/apei.h>
+#include <acpi/hed.h>
+
+/*
+ * One struct ghes is created for each generic hardware error source.
+ * It provides the context for APEI hardware error timer/IRQ/SCI/NMI
+ * handler.
+ *
+ * estatus: memory buffer for error status block, allocated during
+ * HEST parsing.
+ */
+#define GHES_TO_CLEAR 0x0001
+#define GHES_EXITING 0x0002
+
+struct ghes {
+ struct acpi_hest_generic *generic;
+ struct acpi_hest_generic_status *estatus;
+ u64 buffer_paddr;
+ unsigned long flags;
+ union {
+ struct list_head list;
+ struct timer_list timer;
+ unsigned int irq;
+ };
+};
+
+struct ghes_estatus_node {
+ struct llist_node llnode;
+ struct acpi_hest_generic *generic;
+ struct ghes *ghes;
+};
+
+struct ghes_estatus_cache {
+ u32 estatus_len;
+ atomic_t count;
+ struct acpi_hest_generic *generic;
+ unsigned long long time_in;
+ struct rcu_head rcu;
+};
+
+enum {
+ GHES_SEV_NO = 0x0,
+ GHES_SEV_CORRECTED = 0x1,
+ GHES_SEV_RECOVERABLE = 0x2,
+ GHES_SEV_PANIC = 0x3,
+};
+
+/* From drivers/edac/ghes_edac.c */
+
+#ifdef CONFIG_EDAC_GHES
+void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
+ struct cper_sec_mem_err *mem_err);
+
+int ghes_edac_register(struct ghes *ghes, struct device *dev);
+
+void ghes_edac_unregister(struct ghes *ghes);
+
+#else
+static inline void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
+ struct cper_sec_mem_err *mem_err)
+{
+}
+
+static inline int ghes_edac_register(struct ghes *ghes, struct device *dev)
+{
+ return 0;
+}
+
+static inline void ghes_edac_unregister(struct ghes *ghes)
+{
+}
+#endif
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 1b8c02b36f76..4fd4999ccb5b 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -14,7 +14,6 @@
#include <linux/atomic.h>
#include <linux/device.h>
-#include <linux/kobject.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/debugfs.h>
@@ -48,8 +47,17 @@ static inline void opstate_init(void)
return;
}
+/* Max length of a DIMM label*/
#define EDAC_MC_LABEL_LEN 31
-#define MC_PROC_NAME_MAX_LEN 7
+
+/* Maximum size of the location string */
+#define LOCATION_SIZE 80
+
+/* Defines the maximum number of labels that can be reported */
+#define EDAC_MAX_LABELS 8
+
+/* String used to join two or more labels */
+#define OTHER_LABEL " or "
/**
* enum dev_type - describe the type of memory DRAM chips used at the stick
@@ -101,8 +109,24 @@ enum hw_event_mc_err_type {
HW_EVENT_ERR_CORRECTED,
HW_EVENT_ERR_UNCORRECTED,
HW_EVENT_ERR_FATAL,
+ HW_EVENT_ERR_INFO,
};
+static inline char *mc_event_error_type(const unsigned int err_type)
+{
+ switch (err_type) {
+ case HW_EVENT_ERR_CORRECTED:
+ return "Corrected";
+ case HW_EVENT_ERR_UNCORRECTED:
+ return "Uncorrected";
+ case HW_EVENT_ERR_FATAL:
+ return "Fatal";
+ default:
+ case HW_EVENT_ERR_INFO:
+ return "Info";
+ }
+}
+
/**
* enum mem_type - memory types. For a more detailed reference, please see
* http://en.wikipedia.org/wiki/DRAM
@@ -376,6 +400,9 @@ enum scrub_type {
* @EDAC_MC_LAYER_CHANNEL: memory layer is named "channel"
* @EDAC_MC_LAYER_SLOT: memory layer is named "slot"
* @EDAC_MC_LAYER_CHIP_SELECT: memory layer is named "chip select"
+ * @EDAC_MC_LAYER_ALL_MEM: memory layout is unknown. All memory is mapped
+ * as a single memory area. This is used when
+ * retrieving errors from a firmware driven driver.
*
* This enum is used by the drivers to tell edac_mc_sysfs what name should
* be used when describing a memory stick location.
@@ -385,6 +412,7 @@ enum edac_mc_layer_type {
EDAC_MC_LAYER_CHANNEL,
EDAC_MC_LAYER_SLOT,
EDAC_MC_LAYER_CHIP_SELECT,
+ EDAC_MC_LAYER_ALL_MEM,
};
/**
@@ -551,6 +579,46 @@ struct errcount_attribute_data {
int layer0, layer1, layer2;
};
+/**
+ * edac_raw_error_desc - Raw error report structure
+ * @grain: minimum granularity for an error report, in bytes
+ * @error_count: number of errors of the same type
+ * @top_layer: top layer of the error (layer[0])
+ * @mid_layer: middle layer of the error (layer[1])
+ * @low_layer: low layer of the error (layer[2])
+ * @page_frame_number: page where the error happened
+ * @offset_in_page: page offset
+ * @syndrome: syndrome of the error (or 0 if unknown or if
+ * the syndrome is not applicable)
+ * @msg: error message
+ * @location: location of the error
+ * @label: label of the affected DIMM(s)
+ * @other_detail: other driver-specific detail about the error
+ * @enable_per_layer_report: if false, the error affects all layers
+ * (typically, a memory controller error)
+ */
+struct edac_raw_error_desc {
+ /*
+ * NOTE: everything before grain won't be cleaned by
+ * edac_raw_error_desc_clean()
+ */
+ char location[LOCATION_SIZE];
+ char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * EDAC_MAX_LABELS];
+ long grain;
+
+ /* the vars below and grain will be cleaned on every new error report */
+ u16 error_count;
+ int top_layer;
+ int mid_layer;
+ int low_layer;
+ unsigned long page_frame_number;
+ unsigned long offset_in_page;
+ unsigned long syndrome;
+ const char *msg;
+ const char *other_detail;
+ bool enable_per_layer_report;
+};
+
/* MEMORY controller information structure
*/
struct mem_ctl_info {
@@ -630,7 +698,6 @@ struct mem_ctl_info {
const char *mod_ver;
const char *ctl_name;
const char *dev_name;
- char proc_name[MC_PROC_NAME_MAX_LEN + 1];
void *pvt_info;
unsigned long start_time; /* mci load start time (in jiffies) */
@@ -659,6 +726,12 @@ struct mem_ctl_info {
/* work struct for this MC */
struct delayed_work work;
+ /*
+ * Used to report an error - by being at the global struct
+ * makes the memory allocated by the EDAC core
+ */
+ struct edac_raw_error_desc error_desc;
+
/* the internal state of this controller instance */
int op_state;
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 31717bd287fd..f11c1c2609d5 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2802,6 +2802,7 @@
#define PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX 0x3ce0
#define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f
#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0
+#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3
#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5
#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6
#define PCI_DEVICE_ID_INTEL_5400_ERR 0x4030
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 260470e72483..21cdb0b7b0fb 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -78,9 +78,7 @@ TRACE_EVENT(mc_event,
TP_printk("%d %s error%s:%s%s on %s (mc:%d location:%d:%d:%d address:0x%08lx grain:%d syndrome:0x%08lx%s%s)",
__entry->error_count,
- (__entry->error_type == HW_EVENT_ERR_CORRECTED) ? "Corrected" :
- ((__entry->error_type == HW_EVENT_ERR_FATAL) ?
- "Fatal" : "Uncorrected"),
+ mc_event_error_type(__entry->error_type),
__entry->error_count > 1 ? "s" : "",
((char *)__get_str(msg))[0] ? " " : "",
__get_str(msg),