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

From: tip-bot2 for Alex Kluver
Date: Wed Sep 30 2020 - 01:22:36 EST


The following commit has been merged into the efi/core branch of tip:

Commit-ID: 612b5d506d066cdf0a739963e7cd28642d500ec1
Gitweb: https://git.kernel.org/tip/612b5d506d066cdf0a739963e7cd28642d500ec1
Author: Alex Kluver <alex.kluver@xxxxxxx>
AuthorDate: Wed, 19 Aug 2020 09:35:44 -05:00
Committer: Ard Biesheuvel <ardb@xxxxxxxxxx>
CommitterDate: Thu, 17 Sep 2020 10:19:52 +03:00

cper,edac,efi: Memory Error Record: bank group/address and chip id

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.

Signed-off-by: Alex Kluver <alex.kluver@xxxxxxx>
Reviewed-by: Russ Anderson <russ.anderson@xxxxxxx>
Reviewed-by: Kyle Meyer <kyle.meyer@xxxxxxx>
Reviewed-by: Steve Wahl <steve.wahl@xxxxxxx>
Acked-by: Borislav Petkov <bp@xxxxxxx>
Link: https://lore.kernel.org/r/20200819143544.155096-3-alex.kluver@xxxxxxx
Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx>
---
drivers/edac/ghes_edac.c | 9 +++++++++
drivers/firmware/efi/cper.c | 9 +++++++++
include/linux/cper.h | 8 ++++++++
3 files changed, 26 insertions(+)

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 741e760..8a44f32 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -372,6 +372,12 @@ 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;

@@ -399,6 +405,9 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
strcpy(e->label, dimm->label);
}
}
+ 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 a60acd1..e15d484 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 bd2d8a7..6a511a1 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