summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-02-28 20:42:33 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-02-28 20:42:33 -0800
commitad6c2c2eb34f234d6253292b9b3c047614fbfe7e (patch)
tree8ceb00db9874c09f3002b5ca579f1f9146b30a28 /include
parent19cc90f58d4f2538b4cf5371681a057d2e5209f2 (diff)
parentb0769891ba7baa53f270dc70d71934748beb4c5b (diff)
Merge branch 'linux_next' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac
Pull EDAC fixes and ghes-edac from Mauro Carvalho Chehab: "For: - Some fixes at edac drivers (i7core_edac, sb_edac, i3200_edac); - error injection support for i5100, when EDAC debug is enabled; - fix edac when it is loaded builtin (early init for the subsystem); - a "Firmware First" EDAC driver, allowing ghes to report errors via EDAC (ghes-edac). With regards to ghes-edac, this fixes a longstanding BZ at Red Hat that happens with Nehalem and Sandy Bridge CPUs: when both GHES and i7core_edac or sb_edac are running, the error reports are unpredictable, as both BIOS and OS race to access the registers. With ghes-edac, the EDAC core will refuse to register any other concurrent memory error driver. This patchset moves the ghes struct definitions to a separate header file (include/acpi/ghes.h) and adds 3 hooks at apei/ghes.c to register/unregister and to report errors via ghes-edac. Those changes were acked by ghes driver maintainer (Huang)." * 'linux_next' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac: (30 commits) i5100_edac: convert to use simple_open() ghes_edac: fix to use list_for_each_entry_safe() when delete list items ghes_edac: Fix RAS tracing ghes_edac: Make it compliant with UEFI spec 2.3.1 ghes_edac: Improve driver's printk messages ghes_edac: Don't credit the same memory dimm twice ghes_edac: do a better job of filling EDAC DIMM info ghes_edac: add support for reporting errors via EDAC ghes_edac: Register at EDAC core the BIOS report ghes: add the needed hooks for EDAC error report ghes: move structures/enum to a header file edac: add support for error type "Info" edac: add support for raw error reports edac: reduce stack pressure by using a pre-allocated buffer edac: lock module owner to avoid error report conflicts edac: remove proc_name from mci structure edac: add a new memory layer type edac: initialize the core earlier edac: better report error conditions in debug mode i5100_edac: Remove two checkpatch warnings ...
Diffstat (limited to 'include')
-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
4 files changed, 150 insertions, 6 deletions
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),