edac_mce: Add an interface driver to report mce errors via edac

edac_mce module is an interface module that gets mcelog data and
forwards to any registered edac module that expects to receive data via
mce.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>

5 files changed, 107 insertions, 1 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8a6f0afa767e..6585ff07ddf5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -36,6 +36,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/debugfs.h>
+#include <linux/edac_mce.h>
 
 #include <asm/processor.h>
 #include <asm/hw_irq.h>
@@ -169,6 +170,15 @@ void mce_log(struct mce *mce)
                 entry = rcu_dereference_check_mce(mcelog.next);
                 for (;;) {
                         /*
+                         * If edac_mce is enabled, it will check the error type
+                         * and will process it, if it is a known error.
+                         * Otherwise, the error will be sent through mcelog
+                         * interface
+                         */
+                        if (edac_mce_parse(mce))
+                                return;
+
+                        /*
                          * When the buffer fills up discard new entries.
                          * Assume that the earlier errors are the more
                          * interesting ones:
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 391ddbfb2a34..5b7fbc5aec87 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -69,6 +69,9 @@ config EDAC_MM_EDAC
           occurred so that a particular failing memory module can be
           replaced.  If unsure, select 'Y'.
 
+config EDAC_MCE
+        tristate
+
 config EDAC_AMD64
         tristate "AMD64 (Opteron, Athlon64) K8, F10h, F11h"
         depends on EDAC_MM_EDAC && K8_NB && X86_64 && PCI && EDAC_DECODE_MCE
@@ -169,9 +172,12 @@ config EDAC_I5400
 config EDAC_I7CORE
         tristate "Intel i7 Core (Nehalem) processors"
         depends on EDAC_MM_EDAC && PCI && X86
+        select EDAC_MCE
         help
           Support for error detection and correction the Intel
-          i7 Core (Nehalem) Integrated Memory Controller
+          i7 Core (Nehalem) Integrated Memory Controller that exists on
+          newer processors like i7 Core, i7 Core Extreme, Xeon 35xx
+          and Xeon 55xx processors.
 
 config EDAC_I82860
         tristate "Intel 82860"
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index b9996195b233..ca6b1bb24ccc 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -8,6 +8,7 @@
 
 obj-$(CONFIG_EDAC)                      := edac_stub.o
 obj-$(CONFIG_EDAC_MM_EDAC)              += edac_core.o
+obj-$(CONFIG_EDAC_MCE)                  += edac_mce.o
 
 edac_core-objs  := edac_mc.o edac_device.o edac_mc_sysfs.o edac_pci_sysfs.o
 edac_core-objs  += edac_module.o edac_device_sysfs.o
diff --git a/drivers/edac/edac_mce.c b/drivers/edac/edac_mce.c
new file mode 100644
index 000000000000..b1efa8e51921
--- /dev/null
+++ b/drivers/edac/edac_mce.c
@@ -0,0 +1,58 @@
+/* Provides edac interface to mcelog events
+ *
+ * This file may be distributed under the terms of the
+ * GNU General Public License version 2.
+ *
+ * Copyright (c) 2009 by:
+ *       Mauro Carvalho Chehab <mchehab@redhat.com>
+ *
+ * Red Hat Inc. http://www.redhat.com
+ */
+
+#include <linux/module.h>
+#include <linux/edac_mce.h>
+#include <asm/mce.h>
+
+int edac_mce_enabled;
+EXPORT_SYMBOL_GPL(edac_mce_enabled);
+
+
+/*
+ * Extension interface
+ */
+
+static LIST_HEAD(edac_mce_list);
+static DEFINE_MUTEX(edac_mce_lock);
+
+int edac_mce_register(struct edac_mce *edac_mce)
+{
+        mutex_lock(&edac_mce_lock);
+        list_add_tail(&edac_mce->list, &edac_mce_list);
+        mutex_unlock(&edac_mce_lock);
+        return 0;
+}
+EXPORT_SYMBOL(edac_mce_register);
+
+void edac_mce_unregister(struct edac_mce *edac_mce)
+{
+        mutex_lock(&edac_mce_lock);
+        list_del(&edac_mce->list);
+        mutex_unlock(&edac_mce_lock);
+}
+EXPORT_SYMBOL(edac_mce_unregister);
+
+
+
+int edac_mce_queue(struct mce *mce)
+{
+        struct edac_mce *edac_mce;
+
+        list_for_each_entry(edac_mce, &edac_mce_list, list) {
+                if (edac_mce->check_error(edac_mce->priv, mce))
+                        return 1;
+        }
+
+        /* Nobody queued the error */
+        return 0;
+}
+EXPORT_SYMBOL_GPL(edac_mce_queue);
diff --git a/include/linux/edac_mce.h b/include/linux/edac_mce.h
new file mode 100644
index 000000000000..f974fc035363
--- /dev/null
+++ b/include/linux/edac_mce.h
@@ -0,0 +1,31 @@
+/* Provides edac interface to mcelog events
+ *
+ * This file may be distributed under the terms of the
+ * GNU General Public License version 2.
+ *
+ * Copyright (c) 2009 by:
+ *       Mauro Carvalho Chehab <mchehab@redhat.com>
+ *
+ * Red Hat Inc. http://www.redhat.com
+ */
+
+#if defined(CONFIG_EDAC_MCE) || \
+                        (defined(CONFIG_EDAC_MCE_MODULE) && defined(MODULE))
+
+#include <asm/mce.h>
+#include <linux/list.h>
+
+struct edac_mce {
+        struct list_head list;
+
+        void *priv;
+        int (*check_error)(void *priv, struct mce *mce);
+};
+
+int edac_mce_register(struct edac_mce *edac_mce);
+void edac_mce_unregister(struct edac_mce *edac_mce);
+int edac_mce_parse(struct mce *mce);
+
+#else
+#define edac_mce_parse(mce) (0)
+#endif