summaryrefslogtreecommitdiff
path: root/drivers/edac
diff options
context:
space:
mode:
authorYazen Ghannam <yazen.ghannam@amd.com>2024-10-22 19:36:31 +0000
committerBorislav Petkov (AMD) <bp@alien8.de>2024-10-31 10:53:04 +0100
commit612c2addff367ee461dc99ffca2bc786f105d2ec (patch)
treeadbf197b0274f78074b8eae4bae52ee3eedb962a /drivers/edac
parente9876dafa28ebbeead11b6376b1402832d895c85 (diff)
EDAC/mce_amd: Add support for FRU text in MCA
A new "FRU Text in MCA" feature is defined where the Field Replaceable Unit (FRU) Text for a device is represented by a string in the new MCA_SYND1 and MCA_SYND2 registers. This feature is supported per MCA bank, and it is advertised by the McaFruTextInMca bit (MCA_CONFIG[9]). The FRU Text is populated dynamically for each individual error state (MCA_STATUS, MCA_ADDR, et al.). Handle the case where an MCA bank covers multiple devices, for example, a Unified Memory Controller (UMC) bank that manages two DIMMs. [ Yazen: Add Avadhut as co-developer for wrapper changes. ] [ bp: Do not expose MCA_CONFIG to userspace yet. ] Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com> Co-developed-by: Avadhut Naik <avadhut.naik@amd.com> Signed-off-by: Avadhut Naik <avadhut.naik@amd.com> Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de> Link: https://lore.kernel.org/r/20241022194158.110073-6-avadhut.naik@amd.com
Diffstat (limited to 'drivers/edac')
-rw-r--r--drivers/edac/mce_amd.c18
1 files changed, 12 insertions, 6 deletions
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 194d9fd47d20..50d74d3bf0f5 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -795,6 +795,7 @@ 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)
@@ -814,11 +815,9 @@ 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" : "-"));
@@ -853,8 +852,15 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
if (m->status & MCI_STATUS_SYNDV) {
pr_cont(", Syndrome: 0x%016llx\n", m->synd);
- pr_emerg(HW_ERR "Syndrome1: 0x%016llx, Syndrome2: 0x%016llx",
- err->vendor.amd.synd1, err->vendor.amd.synd2);
+ 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");