|
|
9fadc0 |
commit 9acef39f13833f7d53ef96abc5a72e79384260f4
|
|
|
9fadc0 |
Author: Naveen Krishna Chatradhi <nchatrad@amd.com>
|
|
|
9fadc0 |
Date: Tue Jun 1 11:01:17 2021 +0530
|
|
|
9fadc0 |
|
|
|
9fadc0 |
rasdaemon: Add new SMCA bank types with error decoding
|
|
|
9fadc0 |
|
|
|
9fadc0 |
Upcoming systems with Scalable Machine Check Architecture (SMCA) have
|
|
|
9fadc0 |
new MCA banks added.
|
|
|
9fadc0 |
|
|
|
9fadc0 |
This patch adds the (HWID, MCATYPE) tuple, name and error decoding for
|
|
|
9fadc0 |
those new SMCA banks.
|
|
|
9fadc0 |
While at it, optimize the string names in smca_bank_name[].
|
|
|
9fadc0 |
|
|
|
9fadc0 |
Signed-off-by: Muralidhara M K <muralimk@amd.com>
|
|
|
9fadc0 |
Signed-off-by: Naveen Krishna Chatradhi <nchatrad@amd.com>
|
|
|
9fadc0 |
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
|
|
|
9fadc0 |
|
|
|
9fadc0 |
diff --git a/mce-amd-smca.c b/mce-amd-smca.c
|
|
|
9fadc0 |
index 7c619fd..e0cf512 100644
|
|
|
9fadc0 |
--- a/mce-amd-smca.c
|
|
|
9fadc0 |
+++ b/mce-amd-smca.c
|
|
|
9fadc0 |
@@ -47,7 +47,7 @@
|
|
|
9fadc0 |
/* These may be used by multiple smca_hwid_mcatypes */
|
|
|
9fadc0 |
enum smca_bank_types {
|
|
|
9fadc0 |
SMCA_LS = 0, /* Load Store */
|
|
|
9fadc0 |
- SMCA_LS_V2, /* Load Store */
|
|
|
9fadc0 |
+ SMCA_LS_V2,
|
|
|
9fadc0 |
SMCA_IF, /* Instruction Fetch */
|
|
|
9fadc0 |
SMCA_L2_CACHE, /* L2 Cache */
|
|
|
9fadc0 |
SMCA_DE, /* Decoder Unit */
|
|
|
9fadc0 |
@@ -56,17 +56,22 @@ enum smca_bank_types {
|
|
|
9fadc0 |
SMCA_FP, /* Floating Point */
|
|
|
9fadc0 |
SMCA_L3_CACHE, /* L3 Cache */
|
|
|
9fadc0 |
SMCA_CS, /* Coherent Slave */
|
|
|
9fadc0 |
- SMCA_CS_V2, /* Coherent Slave V2 */
|
|
|
9fadc0 |
+ SMCA_CS_V2,
|
|
|
9fadc0 |
SMCA_PIE, /* Power, Interrupts, etc. */
|
|
|
9fadc0 |
SMCA_UMC, /* Unified Memory Controller */
|
|
|
9fadc0 |
+ SMCA_UMC_V2,
|
|
|
9fadc0 |
SMCA_PB, /* Parameter Block */
|
|
|
9fadc0 |
SMCA_PSP, /* Platform Security Processor */
|
|
|
9fadc0 |
- SMCA_PSP_V2, /* Platform Security Processor V2 */
|
|
|
9fadc0 |
+ SMCA_PSP_V2,
|
|
|
9fadc0 |
SMCA_SMU, /* System Management Unit */
|
|
|
9fadc0 |
- SMCA_SMU_V2, /* System Management Unit V2 */
|
|
|
9fadc0 |
+ SMCA_SMU_V2,
|
|
|
9fadc0 |
SMCA_MP5, /* Microprocessor 5 Unit */
|
|
|
9fadc0 |
SMCA_NBIO, /* Northbridge IO Unit */
|
|
|
9fadc0 |
SMCA_PCIE, /* PCI Express Unit */
|
|
|
9fadc0 |
+ SMCA_PCIE_V2,
|
|
|
9fadc0 |
+ SMCA_XGMI_PCS, /* xGMI PCS Unit */
|
|
|
9fadc0 |
+ SMCA_XGMI_PHY, /* xGMI PHY Unit */
|
|
|
9fadc0 |
+ SMCA_WAFL_PHY, /* WAFL PHY Unit */
|
|
|
9fadc0 |
N_SMCA_BANK_TYPES
|
|
|
9fadc0 |
};
|
|
|
9fadc0 |
|
|
|
9fadc0 |
@@ -237,6 +242,22 @@ static const char * const smca_umc_mce_desc[] = {
|
|
|
9fadc0 |
"Command/address parity error",
|
|
|
9fadc0 |
"Write data CRC error",
|
|
|
9fadc0 |
};
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
+static const char * const smca_umc2_mce_desc[] = {
|
|
|
9fadc0 |
+ "DRAM ECC error",
|
|
|
9fadc0 |
+ "Data poison error",
|
|
|
9fadc0 |
+ "SDP parity error",
|
|
|
9fadc0 |
+ "Reserved",
|
|
|
9fadc0 |
+ "Address/Command parity error",
|
|
|
9fadc0 |
+ "Write data parity error",
|
|
|
9fadc0 |
+ "DCQ SRAM ECC error",
|
|
|
9fadc0 |
+ "Reserved",
|
|
|
9fadc0 |
+ "Read data parity error",
|
|
|
9fadc0 |
+ "Rdb SRAM ECC error",
|
|
|
9fadc0 |
+ "RdRsp SRAM ECC error",
|
|
|
9fadc0 |
+ "LM32 MP errors",
|
|
|
9fadc0 |
+};
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
/* Parameter Block */
|
|
|
9fadc0 |
static const char * const smca_pb_mce_desc[] = {
|
|
|
9fadc0 |
"Parameter Block RAM ECC error",
|
|
|
9fadc0 |
@@ -314,6 +335,55 @@ static const char * const smca_pcie_mce_desc[] = {
|
|
|
9fadc0 |
"CCIX Non-okay write response with data error",
|
|
|
9fadc0 |
};
|
|
|
9fadc0 |
|
|
|
9fadc0 |
+static const char * const smca_pcie2_mce_desc[] = {
|
|
|
9fadc0 |
+ "SDP Parity Error logging",
|
|
|
9fadc0 |
+};
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
+static const char * const smca_xgmipcs_mce_desc[] = {
|
|
|
9fadc0 |
+ "Data Loss Error",
|
|
|
9fadc0 |
+ "Training Error",
|
|
|
9fadc0 |
+ "Flow Control Acknowledge Error",
|
|
|
9fadc0 |
+ "Rx Fifo Underflow Error",
|
|
|
9fadc0 |
+ "Rx Fifo Overflow Error",
|
|
|
9fadc0 |
+ "CRC Error",
|
|
|
9fadc0 |
+ "BER Exceeded Error",
|
|
|
9fadc0 |
+ "Tx Vcid Data Error",
|
|
|
9fadc0 |
+ "Replay Buffer Parity Error",
|
|
|
9fadc0 |
+ "Data Parity Error",
|
|
|
9fadc0 |
+ "Replay Fifo Overflow Error",
|
|
|
9fadc0 |
+ "Replay Fifo Underflow Error",
|
|
|
9fadc0 |
+ "Elastic Fifo Overflow Error",
|
|
|
9fadc0 |
+ "Deskew Error",
|
|
|
9fadc0 |
+ "Flow Control CRC Error",
|
|
|
9fadc0 |
+ "Data Startup Limit Error",
|
|
|
9fadc0 |
+ "FC Init Timeout Error",
|
|
|
9fadc0 |
+ "Recovery Timeout Error",
|
|
|
9fadc0 |
+ "Ready Serial Timeout Error",
|
|
|
9fadc0 |
+ "Ready Serial Attempt Error",
|
|
|
9fadc0 |
+ "Recovery Attempt Error",
|
|
|
9fadc0 |
+ "Recovery Relock Attempt Error",
|
|
|
9fadc0 |
+ "Replay Attempt Error",
|
|
|
9fadc0 |
+ "Sync Header Error",
|
|
|
9fadc0 |
+ "Tx Replay Timeout Error",
|
|
|
9fadc0 |
+ "Rx Replay Timeout Error",
|
|
|
9fadc0 |
+ "LinkSub Tx Timeout Error",
|
|
|
9fadc0 |
+ "LinkSub Rx Timeout Error",
|
|
|
9fadc0 |
+ "Rx CMD Pocket Error",
|
|
|
9fadc0 |
+};
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
+static const char * const smca_xgmiphy_mce_desc[] = {
|
|
|
9fadc0 |
+ "RAM ECC Error",
|
|
|
9fadc0 |
+ "ARC instruction buffer parity error",
|
|
|
9fadc0 |
+ "ARC data buffer parity error",
|
|
|
9fadc0 |
+ "PHY APB error",
|
|
|
9fadc0 |
+};
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
+static const char * const smca_waflphy_mce_desc[] = {
|
|
|
9fadc0 |
+ "RAM ECC Error",
|
|
|
9fadc0 |
+ "ARC instruction buffer parity error",
|
|
|
9fadc0 |
+ "ARC data buffer parity error",
|
|
|
9fadc0 |
+ "PHY APB error",
|
|
|
9fadc0 |
+};
|
|
|
9fadc0 |
|
|
|
9fadc0 |
struct smca_mce_desc {
|
|
|
9fadc0 |
const char * const *descs;
|
|
|
9fadc0 |
@@ -333,6 +403,7 @@ static struct smca_mce_desc smca_mce_descs[] = {
|
|
|
9fadc0 |
[SMCA_CS_V2] = { smca_cs2_mce_desc, ARRAY_SIZE(smca_cs2_mce_desc) },
|
|
|
9fadc0 |
[SMCA_PIE] = { smca_pie_mce_desc, ARRAY_SIZE(smca_pie_mce_desc) },
|
|
|
9fadc0 |
[SMCA_UMC] = { smca_umc_mce_desc, ARRAY_SIZE(smca_umc_mce_desc) },
|
|
|
9fadc0 |
+ [SMCA_UMC_V2] = { smca_umc2_mce_desc, ARRAY_SIZE(smca_umc2_mce_desc) },
|
|
|
9fadc0 |
[SMCA_PB] = { smca_pb_mce_desc, ARRAY_SIZE(smca_pb_mce_desc) },
|
|
|
9fadc0 |
[SMCA_PSP] = { smca_psp_mce_desc, ARRAY_SIZE(smca_psp_mce_desc) },
|
|
|
9fadc0 |
[SMCA_PSP_V2] = { smca_psp2_mce_desc, ARRAY_SIZE(smca_psp2_mce_desc)},
|
|
|
9fadc0 |
@@ -341,6 +412,10 @@ static struct smca_mce_desc smca_mce_descs[] = {
|
|
|
9fadc0 |
[SMCA_MP5] = { smca_mp5_mce_desc, ARRAY_SIZE(smca_mp5_mce_desc) },
|
|
|
9fadc0 |
[SMCA_NBIO] = { smca_nbio_mce_desc, ARRAY_SIZE(smca_nbio_mce_desc)},
|
|
|
9fadc0 |
[SMCA_PCIE] = { smca_pcie_mce_desc, ARRAY_SIZE(smca_pcie_mce_desc)},
|
|
|
9fadc0 |
+ [SMCA_PCIE_V2] = { smca_pcie2_mce_desc, ARRAY_SIZE(smca_pcie2_mce_desc) },
|
|
|
9fadc0 |
+ [SMCA_XGMI_PCS] = { smca_xgmipcs_mce_desc, ARRAY_SIZE(smca_xgmipcs_mce_desc) },
|
|
|
9fadc0 |
+ [SMCA_XGMI_PHY] = { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc) },
|
|
|
9fadc0 |
+ [SMCA_WAFL_PHY] = { smca_waflphy_mce_desc, ARRAY_SIZE(smca_waflphy_mce_desc) },
|
|
|
9fadc0 |
};
|
|
|
9fadc0 |
|
|
|
9fadc0 |
struct smca_hwid {
|
|
|
9fadc0 |
@@ -369,6 +444,8 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
|
|
|
9fadc0 |
|
|
|
9fadc0 |
/* Unified Memory Controller MCA type */
|
|
|
9fadc0 |
{ SMCA_UMC, 0x00000096 },
|
|
|
9fadc0 |
+ /* Heterogeneous systems may have both UMC and UMC_v2 types on the same node. */
|
|
|
9fadc0 |
+ { SMCA_UMC_V2, 0x00010096 },
|
|
|
9fadc0 |
|
|
|
9fadc0 |
/* Parameter Block MCA type */
|
|
|
9fadc0 |
{ SMCA_PB, 0x00000005 },
|
|
|
9fadc0 |
@@ -389,6 +466,16 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
|
|
|
9fadc0 |
|
|
|
9fadc0 |
/* PCI Express Unit MCA type */
|
|
|
9fadc0 |
{ SMCA_PCIE, 0x00000046 },
|
|
|
9fadc0 |
+ { SMCA_PCIE_V2, 0x00010046 },
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
+ /* Ext Global Memory Interconnect PCS MCA type */
|
|
|
9fadc0 |
+ { SMCA_XGMI_PCS, 0x00000050 },
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
+ /* Ext Global Memory Interconnect PHY MCA type */
|
|
|
9fadc0 |
+ { SMCA_XGMI_PHY, 0x00000259 },
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
+ /* WAFL PHY MCA type */
|
|
|
9fadc0 |
+ { SMCA_WAFL_PHY, 0x00000267 },
|
|
|
9fadc0 |
};
|
|
|
9fadc0 |
|
|
|
9fadc0 |
struct smca_bank_name {
|
|
|
9fadc0 |
@@ -396,27 +483,28 @@ struct smca_bank_name {
|
|
|
9fadc0 |
};
|
|
|
9fadc0 |
|
|
|
9fadc0 |
static struct smca_bank_name smca_names[] = {
|
|
|
9fadc0 |
- [SMCA_LS] = { "Load Store Unit" },
|
|
|
9fadc0 |
- [SMCA_LS_V2] = { "Load Store Unit" },
|
|
|
9fadc0 |
- [SMCA_IF] = { "Instruction Fetch Unit" },
|
|
|
9fadc0 |
- [SMCA_L2_CACHE] = { "L2 Cache" },
|
|
|
9fadc0 |
- [SMCA_DE] = { "Decode Unit" },
|
|
|
9fadc0 |
- [SMCA_RESERVED] = { "Reserved" },
|
|
|
9fadc0 |
- [SMCA_EX] = { "Execution Unit" },
|
|
|
9fadc0 |
- [SMCA_FP] = { "Floating Point Unit" },
|
|
|
9fadc0 |
- [SMCA_L3_CACHE] = { "L3 Cache" },
|
|
|
9fadc0 |
- [SMCA_CS] = { "Coherent Slave" },
|
|
|
9fadc0 |
- [SMCA_CS_V2] = { "Coherent Slave" },
|
|
|
9fadc0 |
- [SMCA_PIE] = { "Power, Interrupts, etc." },
|
|
|
9fadc0 |
- [SMCA_UMC] = { "Unified Memory Controller" },
|
|
|
9fadc0 |
- [SMCA_PB] = { "Parameter Block" },
|
|
|
9fadc0 |
- [SMCA_PSP] = { "Platform Security Processor" },
|
|
|
9fadc0 |
- [SMCA_PSP_V2] = { "Platform Security Processor" },
|
|
|
9fadc0 |
- [SMCA_SMU] = { "System Management Unit" },
|
|
|
9fadc0 |
- [SMCA_SMU_V2] = { "System Management Unit" },
|
|
|
9fadc0 |
- [SMCA_MP5] = { "Microprocessor 5 Unit" },
|
|
|
9fadc0 |
- [SMCA_NBIO] = { "Northbridge IO Unit" },
|
|
|
9fadc0 |
- [SMCA_PCIE] = { "PCI Express Unit" },
|
|
|
9fadc0 |
+ [SMCA_LS ... SMCA_LS_V2] = { "Load Store Unit" },
|
|
|
9fadc0 |
+ [SMCA_IF] = { "Instruction Fetch Unit" },
|
|
|
9fadc0 |
+ [SMCA_L2_CACHE] = { "L2 Cache" },
|
|
|
9fadc0 |
+ [SMCA_DE] = { "Decode Unit" },
|
|
|
9fadc0 |
+ [SMCA_RESERVED] = { "Reserved" },
|
|
|
9fadc0 |
+ [SMCA_EX] = { "Execution Unit" },
|
|
|
9fadc0 |
+ [SMCA_FP] = { "Floating Point Unit" },
|
|
|
9fadc0 |
+ [SMCA_L3_CACHE] = { "L3 Cache" },
|
|
|
9fadc0 |
+ [SMCA_CS ... SMCA_CS_V2] = { "Coherent Slave" },
|
|
|
9fadc0 |
+ [SMCA_PIE] = { "Power, Interrupts, etc." },
|
|
|
9fadc0 |
+ [SMCA_UMC] = { "Unified Memory Controller" },
|
|
|
9fadc0 |
+ [SMCA_UMC_V2] = { "Unified Memory Controller V2" },
|
|
|
9fadc0 |
+ [SMCA_PB] = { "Parameter Block" },
|
|
|
9fadc0 |
+ [SMCA_PSP ... SMCA_PSP_V2] = { "Platform Security Processor" },
|
|
|
9fadc0 |
+ [SMCA_SMU ... SMCA_SMU_V2] = { "System Management Unit" },
|
|
|
9fadc0 |
+ [SMCA_MP5] = { "Microprocessor 5 Unit" },
|
|
|
9fadc0 |
+ [SMCA_NBIO] = { "Northbridge IO Unit" },
|
|
|
9fadc0 |
+ [SMCA_PCIE ... SMCA_PCIE_V2] = { "PCI Express Unit" },
|
|
|
9fadc0 |
+ [SMCA_XGMI_PCS] = { "Ext Global Memory Interconnect PCS Unit" },
|
|
|
9fadc0 |
+ [SMCA_XGMI_PHY] = { "Ext Global Memory Interconnect PHY Unit" },
|
|
|
9fadc0 |
+ [SMCA_WAFL_PHY] = { "WAFL PHY Unit" },
|
|
|
9fadc0 |
+
|
|
|
9fadc0 |
};
|
|
|
9fadc0 |
|
|
|
9fadc0 |
static void amd_decode_errcode(struct mce_event *e)
|