diff mbox series

[v2,2/2] cper,edac,efi: Memory Error Record: bank group/address and chip id

Message ID 20200819143544.155096-3-alex.kluver@hpe.com (mailing list archive)
State New, archived
Headers show
Series UEFI v2.8 Memory Error Record Updates | expand

Commit Message

Alex Kluver Aug. 19, 2020, 2:35 p.m. UTC 
Updates to the UEFI 2.8 Memory Error Record allow splitting the bank field
into bank address and bank group, and using the last 3 bits of the extended
field as a chip identifier.

When needed, print correct version of bank field, bank group, and chip
identification

Based on UEFI 2.8 Table 299. Memory Error Record

Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Reviewed-by: Kyle Meyer <kyle.meyer@hpe.com>
Reviewed-by: Russ Anderson <russ.anderson@hpe.com>
Signed-off-by: Alex Kluver <alex.kluver@hpe.com>
---

v1 -> v2:
   * Add static inline cper_get_mem_extension() to make it
    more readable, as suggested by Borislav Petkov.

   * Add second patch for bank field, bank group, and chip id.

---
 drivers/edac/ghes_edac.c    | 9 +++++++++
 drivers/firmware/efi/cper.c | 9 +++++++++
 include/linux/cper.h        | 8 ++++++++
 3 files changed, 26 insertions(+)

Comments

Borislav Petkov Sept. 15, 2020, 4:36 p.m. UTC | #1 
On Wed, Aug 19, 2020 at 09:35:44AM -0500, Alex Kluver wrote:
> Updates to the UEFI 2.8 Memory Error Record allow splitting the bank field
> into bank address and bank group, and using the last 3 bits of the extended
> field as a chip identifier.
> 
> When needed, print correct version of bank field, bank group, and chip
> identification
> 
> Based on UEFI 2.8 Table 299. Memory Error Record

Whoever commits this - those last two sentences need fullstops.

> Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
> Reviewed-by: Kyle Meyer <kyle.meyer@hpe.com>
> Reviewed-by: Russ Anderson <russ.anderson@hpe.com>
> Signed-off-by: Alex Kluver <alex.kluver@hpe.com>
> ---
> 
> v1 -> v2:
>    * Add static inline cper_get_mem_extension() to make it
>     more readable, as suggested by Borislav Petkov.
> 
>    * Add second patch for bank field, bank group, and chip id.
> 
> ---
>  drivers/edac/ghes_edac.c    | 9 +++++++++
>  drivers/firmware/efi/cper.c | 9 +++++++++
>  include/linux/cper.h        | 8 ++++++++
>  3 files changed, 26 insertions(+)

For the EDAC bits:

Acked-by: Borislav Petkov <bp@suse.de>

Thx.
diff mbox series

Patch

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 98fcdaf72a09..31eb72b67265 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -337,6 +337,12 @@  void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 		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_BANK_GROUP)
+		p += sprintf(p, "bank_group:%d ",
+			     mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT);
+	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
+		p += sprintf(p, "bank_address:%d ",
+			     mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK);
 	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
 		u32 row = mem_err->row;
 
@@ -362,6 +368,9 @@  void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 		if (index >= 0)
 			e->top_layer = index;
 	}
+	if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID)
+		p += sprintf(p, "chipID: %d ",
+			     mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT);
 	if (p > e->location)
 		*(p - 1) = '\0';
 
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index a60acd17bcaa..e15d484b6a5a 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -232,6 +232,12 @@  static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 		n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank);
 	if (mem->validation_bits & CPER_MEM_VALID_BANK)
 		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
+	if (mem->validation_bits & CPER_MEM_VALID_BANK_GROUP)
+		n += scnprintf(msg + n, len - n, "bank_group: %d ",
+			       mem->bank >> CPER_MEM_BANK_GROUP_SHIFT);
+	if (mem->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
+		n += scnprintf(msg + n, len - n, "bank_address: %d ",
+			       mem->bank & CPER_MEM_BANK_ADDRESS_MASK);
 	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 | CPER_MEM_VALID_ROW_EXT)) {
@@ -254,6 +260,9 @@  static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 	if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID)
 		scnprintf(msg + n, len - n, "target_id: 0x%016llx ",
 			  mem->target_id);
+	if (mem->validation_bits & CPER_MEM_VALID_CHIP_ID)
+		scnprintf(msg + n, len - n, "chip_id: %d ",
+			  mem->extended >> CPER_MEM_CHIP_ID_SHIFT);
 
 	msg[n] = '\0';
 	return n;
diff --git a/include/linux/cper.h b/include/linux/cper.h
index bd2d8a77a784..6a511a1078ca 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -231,10 +231,18 @@  enum {
 #define CPER_MEM_VALID_CARD_HANDLE		0x10000
 #define CPER_MEM_VALID_MODULE_HANDLE		0x20000
 #define CPER_MEM_VALID_ROW_EXT			0x40000
+#define CPER_MEM_VALID_BANK_GROUP		0x80000
+#define CPER_MEM_VALID_BANK_ADDRESS		0x100000
+#define CPER_MEM_VALID_CHIP_ID			0x200000
 
 #define CPER_MEM_EXT_ROW_MASK			0x3
 #define CPER_MEM_EXT_ROW_SHIFT			16
 
+#define CPER_MEM_BANK_ADDRESS_MASK		0xff
+#define CPER_MEM_BANK_GROUP_SHIFT		8
+
+#define CPER_MEM_CHIP_ID_SHIFT			5
+
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002
 #define CPER_PCIE_VALID_COMMAND_STATUS		0x0004