Blob Blame History Raw
From: Alex Kluver <alex.kluver@hpe.com>
Date: Wed, 19 Aug 2020 09:35:43 -0500
Subject: edac,ghes,cper: Add Row Extension to Memory Error Record
Patch-mainline: v5.10-rc1
Git-commit: 9baf68cc4544056f33797b78ec09388f54ecc8f0
References: jsc#SLE-16407

Memory errors could be printed with incorrect row values since the DIMM
size has outgrown the 16 bit row field in the CPER structure. UEFI
Specification Version 2.8 has increased the size of row by allowing it to
use the first 2 bits from a previously reserved space within the structure.

When needed, add the extension bits to the row value printed.

Based on UEFI 2.8 Table 299. Memory Error Record

Signed-off-by: Alex Kluver <alex.kluver@hpe.com>
Tested-by: Russ Anderson <russ.anderson@hpe.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Reviewed-by: Kyle Meyer <kyle.meyer@hpe.com>
Acked-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20200819143544.155096-2-alex.kluver@hpe.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Lee, Chun-Yi <jlee@suse.com>
---
 drivers/edac/ghes_edac.c    |    8 ++++++--
 drivers/firmware/efi/cper.c |    9 +++++++--
 include/linux/cper.h        |   16 ++++++++++++++--
 3 files changed, 27 insertions(+), 6 deletions(-)

--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -345,8 +345,12 @@ void ghes_edac_report_mem_error(int sev,
 		p += sprintf(p, "rank:%d ", mem_err->rank);
 	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_ROW | CPER_MEM_VALID_ROW_EXT)) {
+		u32 row = mem_err->row;
+
+		row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended);
+		p += sprintf(p, "row:%d ", 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)
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -234,8 +234,12 @@ static int cper_mem_err_location(struct
 		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
 		n += scnprintf(msg + n, len - n, "device: %d ", mem->device);
-	if (mem->validation_bits & CPER_MEM_VALID_ROW)
-		n += scnprintf(msg + n, len - n, "row: %d ", mem->row);
+	if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
+		u32 row = mem->row;
+
+		row |= cper_get_mem_extension(mem->validation_bits, mem->extended);
+		n += scnprintf(msg + n, len - n, "row: %d ", row);
+	}
 	if (mem->validation_bits & CPER_MEM_VALID_COLUMN)
 		n += scnprintf(msg + n, len - n, "column: %d ", mem->column);
 	if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION)
@@ -292,6 +296,7 @@ void cper_mem_err_pack(const struct cper
 	cmem->requestor_id = mem->requestor_id;
 	cmem->responder_id = mem->responder_id;
 	cmem->target_id = mem->target_id;
+	cmem->extended = mem->extended;
 	cmem->rank = mem->rank;
 	cmem->mem_array_handle = mem->mem_array_handle;
 	cmem->mem_dev_handle = mem->mem_dev_handle;
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -230,6 +230,10 @@ enum {
 #define CPER_MEM_VALID_RANK_NUMBER		0x8000
 #define CPER_MEM_VALID_CARD_HANDLE		0x10000
 #define CPER_MEM_VALID_MODULE_HANDLE		0x20000
+#define CPER_MEM_VALID_ROW_EXT			0x40000
+
+#define CPER_MEM_EXT_ROW_MASK			0x3
+#define CPER_MEM_EXT_ROW_SHIFT			16
 
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002
@@ -443,7 +447,7 @@ struct cper_sec_mem_err_old {
 	u8	error_type;
 };
 
-/* Memory Error Section (UEFI >= v2.3), UEFI v2.7 sec N.2.5 */
+/* Memory Error Section (UEFI >= v2.3), UEFI v2.8 sec N.2.5 */
 struct cper_sec_mem_err {
 	u64	validation_bits;
 	u64	error_status;
@@ -461,7 +465,7 @@ struct cper_sec_mem_err {
 	u64	responder_id;
 	u64	target_id;
 	u8	error_type;
-	u8	reserved;
+	u8	extended;
 	u16	rank;
 	u16	mem_array_handle;	/* "card handle" in UEFI 2.4 */
 	u16	mem_dev_handle;		/* "module handle" in UEFI 2.4 */
@@ -483,8 +487,16 @@ struct cper_mem_err_compact {
 	u16	rank;
 	u16	mem_array_handle;
 	u16	mem_dev_handle;
+	u8      extended;
 };
 
+static inline u32 cper_get_mem_extension(u64 mem_valid, u8 mem_extended)
+{
+	if (!(mem_valid & CPER_MEM_VALID_ROW_EXT))
+		return 0;
+	return (mem_extended & CPER_MEM_EXT_ROW_MASK) << CPER_MEM_EXT_ROW_SHIFT;
+}
+
 /* PCI Express Error Section, UEFI v2.7 sec N.2.7 */
 struct cper_sec_pcie {
 	u64		validation_bits;