[PATCH v2 16/16] EDAC/mce_amd: Add support for FRU Text in MCA

From: Yazen Ghannam
Date: Thu Apr 04 2024 - 11:17:49 EST


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.). This handles the case where an MCA bank
covers multiple devices, for example, a Unified Memory Controller (UMC)
bank that manages two DIMMs.

Print the FRU Text string, if available, when decoding an MCA error.

Also, add field for MCA_CONFIG MSR in struct mce_hw_err as vendor specific
error information and save the value of the MSR. The very value can then be
exported through tracepoint for userspace tools like rasdaemon to print FRU
Text, if available.

Co-developed-by: Avadhut Naik <Avadhut.Naik@xxxxxxx>
Signed-off-by: Avadhut Naik <Avadhut.Naik@xxxxxxx>
Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
---

Notes:
Link:
https://lkml.kernel.org/r/20231118193248.1296798-21-yazen.ghannam@xxxxxxx

v1->v2:
* No change.

arch/x86/include/asm/mce.h | 2 ++
arch/x86/kernel/cpu/mce/apei.c | 2 ++
arch/x86/kernel/cpu/mce/core.c | 3 +++
drivers/edac/mce_amd.c | 21 ++++++++++++++-------
4 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index a701290f80a1..2a8997d7ba4d 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -59,6 +59,7 @@
* - TCC bit is present in MCx_STATUS.
*/
#define MCI_CONFIG_MCAX 0x1
+#define MCI_CONFIG_FRUTEXT BIT_ULL(9)

/*
* Note that the full MCACOD field of IA32_MCi_STATUS MSR is
@@ -195,6 +196,7 @@ struct mce_hw_err {
struct {
u64 synd1;
u64 synd2;
+ u64 config;
} amd;
} vi;
};
diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c
index 43622241c379..a9c28614530b 100644
--- a/arch/x86/kernel/cpu/mce/apei.c
+++ b/arch/x86/kernel/cpu/mce/apei.c
@@ -154,6 +154,8 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id)
fallthrough;
/* MCA_CONFIG */
case 4:
+ err.vi.amd.config = *(i_mce + 3);
+ fallthrough;
/* MCA_MISC0 */
case 3:
m->misc = *(i_mce + 2);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index aa27729f7899..a4d09dda5fae 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -207,6 +207,8 @@ static void __print_mce(struct mce_hw_err *err)
pr_cont("SYND2 %llx ", err->vi.amd.synd2);
if (m->ipid)
pr_cont("IPID %llx ", m->ipid);
+ if (err->vi.amd.config)
+ pr_cont("CONFIG %llx ", err->vi.amd.config);
}

pr_cont("\n");
@@ -679,6 +681,7 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)

if (mce_flags.smca) {
m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+ err->vi.amd.config = mce_rdmsrl(MSR_AMD64_SMCA_MCx_CONFIG(i));

if (m->status & MCI_STATUS_SYNDV) {
m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 32bf4cc564a3..f68b3d1b558e 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_hw_err *err = (struct mce_hw_err *)data;
struct mce *m = &err->m;
unsigned int fam = x86_family(m->cpuid);
+ u64 mca_config = err->vi.amd.config;
int ecc;

if (m->kflags & MCE_HANDLED_CEC)
@@ -814,11 +815,7 @@ 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);
-
- if (!rdmsr_safe(addr, &low, &high) &&
- (low & MCI_CONFIG_MCAX))
+ if (mca_config & MCI_CONFIG_MCAX)
pr_cont("|%s", ((m->status & MCI_STATUS_TCC) ? "TCC" : "-"));

pr_cont("|%s", ((m->status & MCI_STATUS_SYNDV) ? "SyndV" : "-"));
@@ -853,8 +850,18 @@ 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->vi.amd.synd1, err->vi.amd.synd2);
+ if (mca_config & MCI_CONFIG_FRUTEXT) {
+ char frutext[17];
+
+ memset(frutext, 0, sizeof(frutext));
+ memcpy(&frutext[0], &err->vi.amd.synd1, 8);
+ memcpy(&frutext[8], &err->vi.amd.synd2, 8);
+
+ pr_emerg(HW_ERR "FRU Text: %s", frutext);
+ } else {
+ pr_emerg(HW_ERR "Syndrome1: 0x%016llx, Syndrome2: 0x%016llx",
+ err->vi.amd.synd1, err->vi.amd.synd2);
+ }
}

pr_cont("\n");
--
2.34.1