summaryrefslogtreecommitdiff
path: root/drivers/edac/mce_amd.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/edac/mce_amd.c')
-rw-r--r--drivers/edac/mce_amd.c375
1 files changed, 71 insertions, 304 deletions
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 2b5401db56ad..af3c12284a1e 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -3,6 +3,7 @@
#include <linux/slab.h>
#include <asm/cpu.h>
+#include <asm/msr.h>
#include "mce_amd.h"
@@ -143,282 +144,6 @@ static const char * const mc6_mce_desc[] = {
"Status Register File",
};
-/* Scalable MCA error strings */
-static const char * const smca_ls_mce_desc[] = {
- "Load queue parity error",
- "Store queue parity error",
- "Miss address buffer payload parity error",
- "Level 1 TLB parity error",
- "DC Tag error type 5",
- "DC Tag error type 6",
- "DC Tag error type 1",
- "Internal error type 1",
- "Internal error type 2",
- "System Read Data Error Thread 0",
- "System Read Data Error Thread 1",
- "DC Tag error type 2",
- "DC Data error type 1 and poison consumption",
- "DC Data error type 2",
- "DC Data error type 3",
- "DC Tag error type 4",
- "Level 2 TLB parity error",
- "PDC parity error",
- "DC Tag error type 3",
- "DC Tag error type 5",
- "L2 Fill Data error",
-};
-
-static const char * const smca_ls2_mce_desc[] = {
- "An ECC error was detected on a data cache read by a probe or victimization",
- "An ECC error or L2 poison was detected on a data cache read by a load",
- "An ECC error was detected on a data cache read-modify-write by a store",
- "An ECC error or poison bit mismatch was detected on a tag read by a probe or victimization",
- "An ECC error or poison bit mismatch was detected on a tag read by a load",
- "An ECC error or poison bit mismatch was detected on a tag read by a store",
- "An ECC error was detected on an EMEM read by a load",
- "An ECC error was detected on an EMEM read-modify-write by a store",
- "A parity error was detected in an L1 TLB entry by any access",
- "A parity error was detected in an L2 TLB entry by any access",
- "A parity error was detected in a PWC entry by any access",
- "A parity error was detected in an STQ entry by any access",
- "A parity error was detected in an LDQ entry by any access",
- "A parity error was detected in a MAB entry by any access",
- "A parity error was detected in an SCB entry state field by any access",
- "A parity error was detected in an SCB entry address field by any access",
- "A parity error was detected in an SCB entry data field by any access",
- "A parity error was detected in a WCB entry by any access",
- "A poisoned line was detected in an SCB entry by any access",
- "A SystemReadDataError error was reported on read data returned from L2 for a load",
- "A SystemReadDataError error was reported on read data returned from L2 for an SCB store",
- "A SystemReadDataError error was reported on read data returned from L2 for a WCB store",
- "A hardware assertion error was reported",
- "A parity error was detected in an STLF, SCB EMEM entry or SRB store data by any access",
-};
-
-static const char * const smca_if_mce_desc[] = {
- "Op Cache Microtag Probe Port Parity Error",
- "IC Microtag or Full Tag Multi-hit Error",
- "IC Full Tag Parity Error",
- "IC Data Array Parity Error",
- "Decoupling Queue PhysAddr Parity Error",
- "L0 ITLB Parity Error",
- "L1 ITLB Parity Error",
- "L2 ITLB Parity Error",
- "BPQ Thread 0 Snoop Parity Error",
- "BPQ Thread 1 Snoop Parity Error",
- "L1 BTB Multi-Match Error",
- "L2 BTB Multi-Match Error",
- "L2 Cache Response Poison Error",
- "System Read Data Error",
-};
-
-static const char * const smca_l2_mce_desc[] = {
- "L2M Tag Multiple-Way-Hit error",
- "L2M Tag or State Array ECC Error",
- "L2M Data Array ECC Error",
- "Hardware Assert Error",
-};
-
-static const char * const smca_de_mce_desc[] = {
- "Micro-op cache tag parity error",
- "Micro-op cache data parity error",
- "Instruction buffer parity error",
- "Micro-op queue parity error",
- "Instruction dispatch queue parity error",
- "Fetch address FIFO parity error",
- "Patch RAM data parity error",
- "Patch RAM sequencer parity error",
- "Micro-op buffer parity error"
-};
-
-static const char * const smca_ex_mce_desc[] = {
- "Watchdog Timeout error",
- "Physical register file parity error",
- "Flag register file parity error",
- "Immediate displacement register file parity error",
- "Address generator payload parity error",
- "EX payload parity error",
- "Checkpoint queue parity error",
- "Retire dispatch queue parity error",
- "Retire status queue parity error",
- "Scheduling queue parity error",
- "Branch buffer queue parity error",
- "Hardware Assertion error",
-};
-
-static const char * const smca_fp_mce_desc[] = {
- "Physical register file (PRF) parity error",
- "Freelist (FL) parity error",
- "Schedule queue parity error",
- "NSQ parity error",
- "Retire queue (RQ) parity error",
- "Status register file (SRF) parity error",
- "Hardware assertion",
-};
-
-static const char * const smca_l3_mce_desc[] = {
- "Shadow Tag Macro ECC Error",
- "Shadow Tag Macro Multi-way-hit Error",
- "L3M Tag ECC Error",
- "L3M Tag Multi-way-hit Error",
- "L3M Data ECC Error",
- "SDP Parity Error or SystemReadDataError from XI",
- "L3 Victim Queue Parity Error",
- "L3 Hardware Assertion",
-};
-
-static const char * const smca_cs_mce_desc[] = {
- "Illegal Request",
- "Address Violation",
- "Security Violation",
- "Illegal Response",
- "Unexpected Response",
- "Request or Probe Parity Error",
- "Read Response Parity Error",
- "Atomic Request Parity Error",
- "Probe Filter ECC Error",
-};
-
-static const char * const smca_cs2_mce_desc[] = {
- "Illegal Request",
- "Address Violation",
- "Security Violation",
- "Illegal Response",
- "Unexpected Response",
- "Request or Probe Parity Error",
- "Read Response Parity Error",
- "Atomic Request Parity Error",
- "SDP read response had no match in the CS queue",
- "Probe Filter Protocol Error",
- "Probe Filter ECC Error",
- "SDP read response had an unexpected RETRY error",
- "Counter overflow error",
- "Counter underflow error",
-};
-
-static const char * const smca_pie_mce_desc[] = {
- "Hardware Assert",
- "Register security violation",
- "Link Error",
- "Poison data consumption",
- "A deferred error was detected in the DF"
-};
-
-static const char * const smca_umc_mce_desc[] = {
- "DRAM ECC error",
- "Data poison error",
- "SDP parity error",
- "Advanced peripheral bus error",
- "Address/Command parity error",
- "Write data CRC error",
- "DCQ SRAM ECC error",
- "AES SRAM ECC error",
-};
-
-static const char * const smca_pb_mce_desc[] = {
- "An ECC error in the Parameter Block RAM array",
-};
-
-static const char * const smca_psp_mce_desc[] = {
- "An ECC or parity error in a PSP RAM instance",
-};
-
-static const char * const smca_psp2_mce_desc[] = {
- "High SRAM ECC or parity error",
- "Low SRAM ECC or parity error",
- "Instruction Cache Bank 0 ECC or parity error",
- "Instruction Cache Bank 1 ECC or parity error",
- "Instruction Tag Ram 0 parity error",
- "Instruction Tag Ram 1 parity error",
- "Data Cache Bank 0 ECC or parity error",
- "Data Cache Bank 1 ECC or parity error",
- "Data Cache Bank 2 ECC or parity error",
- "Data Cache Bank 3 ECC or parity error",
- "Data Tag Bank 0 parity error",
- "Data Tag Bank 1 parity error",
- "Data Tag Bank 2 parity error",
- "Data Tag Bank 3 parity error",
- "Dirty Data Ram parity error",
- "TLB Bank 0 parity error",
- "TLB Bank 1 parity error",
- "System Hub Read Buffer ECC or parity error",
-};
-
-static const char * const smca_smu_mce_desc[] = {
- "An ECC or parity error in an SMU RAM instance",
-};
-
-static const char * const smca_smu2_mce_desc[] = {
- "High SRAM ECC or parity error",
- "Low SRAM ECC or parity error",
- "Data Cache Bank A ECC or parity error",
- "Data Cache Bank B ECC or parity error",
- "Data Tag Cache Bank A ECC or parity error",
- "Data Tag Cache Bank B ECC or parity error",
- "Instruction Cache Bank A ECC or parity error",
- "Instruction Cache Bank B ECC or parity error",
- "Instruction Tag Cache Bank A ECC or parity error",
- "Instruction Tag Cache Bank B ECC or parity error",
- "System Hub Read Buffer ECC or parity error",
-};
-
-static const char * const smca_mp5_mce_desc[] = {
- "High SRAM ECC or parity error",
- "Low SRAM ECC or parity error",
- "Data Cache Bank A ECC or parity error",
- "Data Cache Bank B ECC or parity error",
- "Data Tag Cache Bank A ECC or parity error",
- "Data Tag Cache Bank B ECC or parity error",
- "Instruction Cache Bank A ECC or parity error",
- "Instruction Cache Bank B ECC or parity error",
- "Instruction Tag Cache Bank A ECC or parity error",
- "Instruction Tag Cache Bank B ECC or parity error",
-};
-
-static const char * const smca_nbio_mce_desc[] = {
- "ECC or Parity error",
- "PCIE error",
- "SDP ErrEvent error",
- "SDP Egress Poison Error",
- "IOHC Internal Poison Error",
-};
-
-static const char * const smca_pcie_mce_desc[] = {
- "CCIX PER Message logging",
- "CCIX Read Response with Status: Non-Data Error",
- "CCIX Write Response with Status: Non-Data Error",
- "CCIX Read Response with Status: Data Error",
- "CCIX Non-okay write response with data error",
-};
-
-struct smca_mce_desc {
- const char * const *descs;
- unsigned int num_descs;
-};
-
-static struct smca_mce_desc smca_mce_descs[] = {
- [SMCA_LS] = { smca_ls_mce_desc, ARRAY_SIZE(smca_ls_mce_desc) },
- [SMCA_LS_V2] = { smca_ls2_mce_desc, ARRAY_SIZE(smca_ls2_mce_desc) },
- [SMCA_IF] = { smca_if_mce_desc, ARRAY_SIZE(smca_if_mce_desc) },
- [SMCA_L2_CACHE] = { smca_l2_mce_desc, ARRAY_SIZE(smca_l2_mce_desc) },
- [SMCA_DE] = { smca_de_mce_desc, ARRAY_SIZE(smca_de_mce_desc) },
- [SMCA_EX] = { smca_ex_mce_desc, ARRAY_SIZE(smca_ex_mce_desc) },
- [SMCA_FP] = { smca_fp_mce_desc, ARRAY_SIZE(smca_fp_mce_desc) },
- [SMCA_L3_CACHE] = { smca_l3_mce_desc, ARRAY_SIZE(smca_l3_mce_desc) },
- [SMCA_CS] = { smca_cs_mce_desc, ARRAY_SIZE(smca_cs_mce_desc) },
- [SMCA_CS_V2] = { smca_cs2_mce_desc, ARRAY_SIZE(smca_cs2_mce_desc) },
- [SMCA_PIE] = { smca_pie_mce_desc, ARRAY_SIZE(smca_pie_mce_desc) },
- [SMCA_UMC] = { smca_umc_mce_desc, ARRAY_SIZE(smca_umc_mce_desc) },
- [SMCA_PB] = { smca_pb_mce_desc, ARRAY_SIZE(smca_pb_mce_desc) },
- [SMCA_PSP] = { smca_psp_mce_desc, ARRAY_SIZE(smca_psp_mce_desc) },
- [SMCA_PSP_V2] = { smca_psp2_mce_desc, ARRAY_SIZE(smca_psp2_mce_desc) },
- [SMCA_SMU] = { smca_smu_mce_desc, ARRAY_SIZE(smca_smu_mce_desc) },
- [SMCA_SMU_V2] = { smca_smu2_mce_desc, ARRAY_SIZE(smca_smu2_mce_desc) },
- [SMCA_MP5] = { smca_mp5_mce_desc, ARRAY_SIZE(smca_mp5_mce_desc) },
- [SMCA_NBIO] = { smca_nbio_mce_desc, ARRAY_SIZE(smca_nbio_mce_desc) },
- [SMCA_PCIE] = { smca_pcie_mce_desc, ARRAY_SIZE(smca_pcie_mce_desc) },
-};
-
static bool f12h_mc0_mce(u16 ec, u8 xec)
{
bool ret = false;
@@ -860,7 +585,7 @@ static void decode_mc3_mce(struct mce *m)
static void decode_mc4_mce(struct mce *m)
{
unsigned int fam = x86_family(m->cpuid);
- int node_id = amd_get_nb_id(m->extcpu);
+ int node_id = topology_amd_node_id(m->extcpu);
u16 ec = EC(m->status);
u8 xec = XEC(m->status, 0x1f);
u8 offset = 0;
@@ -963,40 +688,66 @@ static void decode_mc6_mce(struct mce *m)
pr_emerg(HW_ERR "Corrupted MC6 MCE info?\n");
}
+static const char * const smca_long_names[] = {
+ [SMCA_LS ... SMCA_LS_V2] = "Load Store Unit",
+ [SMCA_IF] = "Instruction Fetch Unit",
+ [SMCA_L2_CACHE] = "L2 Cache",
+ [SMCA_DE] = "Decode Unit",
+ [SMCA_RESERVED] = "Reserved",
+ [SMCA_EX] = "Execution Unit",
+ [SMCA_FP] = "Floating Point Unit",
+ [SMCA_L3_CACHE] = "L3 Cache",
+ [SMCA_CS ... SMCA_CS_V2] = "Coherent Slave",
+ [SMCA_PIE] = "Power, Interrupts, etc.",
+
+ /* UMC v2 is separate because both of them can exist in a single system. */
+ [SMCA_UMC] = "Unified Memory Controller",
+ [SMCA_UMC_V2] = "Unified Memory Controller v2",
+ [SMCA_PB] = "Parameter Block",
+ [SMCA_PSP ... SMCA_PSP_V2] = "Platform Security Processor",
+ [SMCA_SMU ... SMCA_SMU_V2] = "System Management Unit",
+ [SMCA_MP5] = "Microprocessor 5 Unit",
+ [SMCA_MPDMA] = "MPDMA Unit",
+ [SMCA_NBIO] = "Northbridge IO Unit",
+ [SMCA_PCIE ... SMCA_PCIE_V2] = "PCI Express Unit",
+ [SMCA_XGMI_PCS] = "Ext Global Memory Interconnect PCS Unit",
+ [SMCA_NBIF] = "NBIF Unit",
+ [SMCA_SHUB] = "System Hub Unit",
+ [SMCA_SATA] = "SATA Unit",
+ [SMCA_USB] = "USB Unit",
+ [SMCA_GMI_PCS] = "Global Memory Interconnect PCS Unit",
+ [SMCA_XGMI_PHY] = "Ext Global Memory Interconnect PHY Unit",
+ [SMCA_WAFL_PHY] = "WAFL PHY Unit",
+ [SMCA_GMI_PHY] = "Global Memory Interconnect PHY Unit",
+};
+
+static const char *smca_get_long_name(enum smca_bank_types t)
+{
+ if (t >= N_SMCA_BANK_TYPES)
+ return NULL;
+
+ return smca_long_names[t];
+}
+
/* Decode errors according to Scalable MCA specification */
static void decode_smca_error(struct mce *m)
{
- struct smca_hwid *hwid;
- enum smca_bank_types bank_type;
- const char *ip_name;
+ enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank);
u8 xec = XEC(m->status, xec_mask);
- if (m->bank >= ARRAY_SIZE(smca_banks))
- return;
-
- hwid = smca_banks[m->bank].hwid;
- if (!hwid)
+ if (bank_type >= N_SMCA_BANK_TYPES)
return;
- bank_type = hwid->bank_type;
-
if (bank_type == SMCA_RESERVED) {
pr_emerg(HW_ERR "Bank %d is reserved.\n", m->bank);
return;
}
- ip_name = smca_get_long_name(bank_type);
+ pr_emerg(HW_ERR "%s Ext. Error Code: %d", smca_get_long_name(bank_type), xec);
- pr_emerg(HW_ERR "%s Ext. Error Code: %d", ip_name, xec);
-
- /* Only print the decode of valid error codes */
- if (xec < smca_mce_descs[bank_type].num_descs &&
- (hwid->xec_bitmap & BIT_ULL(xec))) {
- pr_cont(", %s.\n", smca_mce_descs[bank_type].descs[xec]);
- }
-
- if (bank_type == SMCA_UMC && xec == 0 && decode_dram_ecc)
- decode_dram_ecc(cpu_to_node(m->extcpu), m);
+ if ((bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) &&
+ xec == 0 && decode_dram_ecc)
+ decode_dram_ecc(topology_amd_node_id(m->extcpu), m);
}
static inline void amd_decode_err_code(u16 ec)
@@ -1043,7 +794,9 @@ static int
amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
{
struct mce *m = (struct mce *)data;
+ struct mce_hw_err *err = to_mce_hw_err(m);
unsigned int fam = x86_family(m->cpuid);
+ u32 mca_config_lo = 0, dummy;
int ecc;
if (m->kflags & MCE_HANDLED_CEC)
@@ -1063,11 +816,9 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
((m->status & MCI_STATUS_PCC) ? "PCC" : "-"));
if (boot_cpu_has(X86_FEATURE_SMCA)) {
- u32 low, high;
- u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
+ rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(m->bank), &mca_config_lo, &dummy);
- if (!rdmsr_safe(addr, &low, &high) &&
- (low & MCI_CONFIG_MCAX))
+ if (mca_config_lo & MCI_CONFIG_MCAX)
pr_cont("|%s", ((m->status & MCI_STATUS_TCC) ? "TCC" : "-"));
pr_cont("|%s", ((m->status & MCI_STATUS_SYNDV) ? "SyndV" : "-"));
@@ -1094,11 +845,24 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
if (m->status & MCI_STATUS_ADDRV)
pr_emerg(HW_ERR "Error Addr: 0x%016llx\n", m->addr);
+ if (m->ppin)
+ pr_emerg(HW_ERR "PPIN: 0x%016llx\n", m->ppin);
+
if (boot_cpu_has(X86_FEATURE_SMCA)) {
pr_emerg(HW_ERR "IPID: 0x%016llx", m->ipid);
- if (m->status & MCI_STATUS_SYNDV)
- pr_cont(", Syndrome: 0x%016llx", m->synd);
+ if (m->status & MCI_STATUS_SYNDV) {
+ pr_cont(", Syndrome: 0x%016llx\n", m->synd);
+ if (mca_config_lo & MCI_CONFIG_FRUTEXT) {
+ char frutext[17];
+
+ frutext[16] = '\0';
+ memcpy(&frutext[0], &err->vendor.amd.synd1, 8);
+ memcpy(&frutext[8], &err->vendor.amd.synd2, 8);
+
+ pr_emerg(HW_ERR "FRU Text: %s", frutext);
+ }
+ }
pr_cont("\n");
@@ -1166,6 +930,9 @@ static int __init mce_amd_init(void)
c->x86_vendor != X86_VENDOR_HYGON)
return -ENODEV;
+ if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+ return -ENODEV;
+
if (boot_cpu_has(X86_FEATURE_SMCA)) {
xec_mask = 0x3f;
goto out;
generated by cgit (git 2.34.1) at 2025-12-26 06:10:52 +0000