[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <654292c78376dfe2b65cd9027787ab54705eeaa6.1351705248.git.mchehab@redhat.com>
Date: Wed, 31 Oct 2012 15:44:55 -0200
From: Mauro Carvalho Chehab <mchehab@...hat.com>
To: unlisted-recipients:; (no To-header on input)
Cc: Mauro Carvalho Chehab <mchehab@...hat.com>,
Linux Edac Mailing List <linux-edac@...r.kernel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: [RFC EDAC/GHES 3/3] ghes: add support for reporting errors via EDAC
Signed-off-by: Mauro Carvalho Chehab <mchehab@...hat.com>
---
drivers/acpi/apei/ghes.c | 52 +++++++++++++++++++++++++++++++++++++++++++++---
include/linux/edac.h | 1 +
2 files changed, 50 insertions(+), 3 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 9466d36..54c2d97 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -115,6 +115,7 @@ struct ghes {
struct ghes_estatus_node {
struct llist_node llnode;
struct acpi_hest_generic *generic;
+ struct ghes *ghes;
};
struct ghes_estatus_cache {
@@ -457,7 +458,49 @@ 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_edac_report_mem_error(struct ghes *ghes, int sev,
+ struct cper_sec_mem_err *mem_err)
+{
+#ifdef CONFIG_EDAC_MM_EDAC
+ enum hw_event_mc_err_type type;
+ unsigned long page = 0, offset = 0, grain = 0;
+ char location[80];
+ char *label = "unknown";
+
+ if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+ page = mem_err->physical_addr >> PAGE_SHIFT;
+ offset = mem_err->physical_addr & ~PAGE_MASK;
+ grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
+ }
+
+ 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;
+ }
+
+ sprintf(location,"node:%d card:%d module:%d bank:%d device:%d row: %d column:%d bit_pos:%d",
+ mem_err->node, mem_err->card, mem_err->module,
+ mem_err->bank, mem_err->device, mem_err->row, mem_err->column,
+ mem_err->bit_pos);
+
+ edac_raw_mc_handle_error(type, ghes->mci, grain, 1, 0, 0, 0,
+ page, offset, 0,
+ "APEI", location, label, "", 0);
+#endif
+}
+
+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;
@@ -469,6 +512,8 @@ 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);
@@ -687,7 +732,7 @@ 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;
@@ -780,7 +825,7 @@ 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))
@@ -869,6 +914,7 @@ 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);
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 1e9d19b..f26fe40 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -100,6 +100,7 @@ enum hw_event_mc_err_type {
HW_EVENT_ERR_CORRECTED,
HW_EVENT_ERR_UNCORRECTED,
HW_EVENT_ERR_FATAL,
+ HW_EVENT_ERR_INFO,
};
/**
--
1.7.11.7
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists