[PATCH 2/4] x86/mce, EDAC/mce_amd: Add support for new MCA_SYND{1,2} registers
From: Avadhut Naik
Date: Thu May 30 2024 - 17:17:22 EST
From: Avadhut Naik <Avadhut.Naik@xxxxxxx>
AMD's Scalable MCA systems viz. Genoa will include two new registers:
MCA_SYND1 and MCA_SYND2.
These registers will include supplemental error information in addition
to the existing MCA_SYND register. The data within the registers is
considered valid if MCA_STATUS[SyndV] is set.
Add fields for these registers as vendor-specific error information
in struct mce_hw_err. Save and print these registers wherever
MCA_STATUS[SyndV]/MCA_SYND is currently used.
Also, modify the mce_record tracepoint to export these new registers
through __dynamic_array. While the sizeof() operator has been used to
determine the size of this __dynamic_array, the same, if needed in the
future can be substituted by caching the size of vendor-specific error
information as part of struct mce_hw_err.
Note: Checkpatch warnings/errors are ignored to maintain coding style.
[Yazen: Drop Yazen's Co-developed-by tag and moved SoB tag.]
Signed-off-by: Avadhut Naik <Avadhut.Naik@xxxxxxx>
Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
---
arch/x86/include/asm/mce.h | 12 ++++++++++++
arch/x86/kernel/cpu/mce/core.c | 24 +++++++++++++++++-------
drivers/edac/mce_amd.c | 10 +++++++---
include/trace/events/mce.h | 9 +++++++--
4 files changed, 43 insertions(+), 12 deletions(-)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 83923d8a43b0..290d32c84ffd 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -122,6 +122,9 @@
#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008
#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009
#define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a
+/* Registers MISC2 to MISC4 are at offsets B to D. */
+#define MSR_AMD64_SMCA_MC0_SYND1 0xc000200e
+#define MSR_AMD64_SMCA_MC0_SYND2 0xc000200f
#define MSR_AMD64_SMCA_MCx_CTL(x) (MSR_AMD64_SMCA_MC0_CTL + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_STATUS(x) (MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_ADDR(x) (MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x))
@@ -132,6 +135,8 @@
#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
+#define MSR_AMD64_SMCA_MCx_SYND1(x) (MSR_AMD64_SMCA_MC0_SYND1 + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_SYND2(x) (MSR_AMD64_SMCA_MC0_SYND2 + 0x10*(x))
#define XEC(x, mask) (((x) >> 16) & mask)
@@ -189,6 +194,13 @@ enum mce_notifier_prios {
struct mce_hw_err {
struct mce m;
+
+ union vendor_info {
+ struct {
+ u64 synd1;
+ u64 synd2;
+ } amd;
+ } vi;
};
struct notifier_block;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2f93c825e0fc..253d7d0d3331 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -201,6 +201,10 @@ static void __print_mce(struct mce_hw_err *err)
if (mce_flags.smca) {
if (m->synd)
pr_cont("SYND %llx ", m->synd);
+ if (err->vi.amd.synd1)
+ pr_cont("SYND1 %llx ", err->vi.amd.synd1);
+ if (err->vi.amd.synd2)
+ pr_cont("SYND2 %llx ", err->vi.amd.synd2);
if (m->ipid)
pr_cont("IPID %llx ", m->ipid);
}
@@ -651,8 +655,10 @@ static struct notifier_block mce_default_nb = {
/*
* Read ADDR and MISC registers.
*/
-static noinstr void mce_read_aux(struct mce *m, int i)
+static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
{
+ struct mce *m = &err->m;
+
if (m->status & MCI_STATUS_MISCV)
m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC));
@@ -675,8 +681,11 @@ static noinstr void mce_read_aux(struct mce *m, int i)
if (mce_flags.smca) {
m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
- if (m->status & MCI_STATUS_SYNDV)
+ if (m->status & MCI_STATUS_SYNDV) {
m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
+ err->vi.amd.synd1 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(i));
+ err->vi.amd.synd2 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(i));
+ }
}
}
@@ -815,7 +824,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (flags & MCP_DONTLOG)
goto clear_it;
- mce_read_aux(m, i);
+ mce_read_aux(&err, i);
m->severity = mce_severity(m, NULL, NULL, false);
/*
* Don't get the IP here because it's unlikely to
@@ -954,9 +963,10 @@ static __always_inline void quirk_zen_ifu(int bank, struct mce *m, struct pt_reg
* Do a quick check if any of the events requires a panic.
* This decides if we keep the events around or clear them.
*/
-static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
+static __always_inline int mce_no_way_out(struct mce_hw_err *err, char **msg, unsigned long *validp,
struct pt_regs *regs)
{
+ struct mce *m = &err->m;
char *tmp = *msg;
int i;
@@ -974,7 +984,7 @@ static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned lo
m->bank = i;
if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) {
- mce_read_aux(m, i);
+ mce_read_aux(err, i);
*msg = tmp;
return 1;
}
@@ -1372,7 +1382,7 @@ __mc_scan_banks(struct mce_hw_err *err, struct pt_regs *regs, struct mce *final,
if (severity == MCE_NO_SEVERITY)
continue;
- mce_read_aux(m, i);
+ mce_read_aux(err, i);
/* assuming valid severity level != 0 */
m->severity = severity;
@@ -1573,7 +1583,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
final = this_cpu_ptr(&hw_errs_seen);
final->m = *m;
- no_way_out = mce_no_way_out(m, &msg, valid_banks, regs);
+ no_way_out = mce_no_way_out(&err, &msg, valid_banks, regs);
barrier();
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index c5fae99de781..69e12cb2f0de 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -792,7 +792,8 @@ static const char *decode_error_status(struct mce *m)
static int
amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
{
- struct mce *m = &((struct mce_hw_err *)data)->m;
+ struct mce_hw_err *err = (struct mce_hw_err *)data;
+ struct mce *m = &err->m;
unsigned int fam = x86_family(m->cpuid);
int ecc;
@@ -850,8 +851,11 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
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);
+ pr_emerg(HW_ERR "Syndrome1: 0x%016llx, Syndrome2: 0x%016llx",
+ err->vi.amd.synd1, err->vi.amd.synd2);
+ }
pr_cont("\n");
diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 65aba1afcd07..9e7211eddbca 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -43,6 +43,8 @@ TRACE_EVENT(mce_record,
__field( u8, bank )
__field( u8, cpuvendor )
__field( u32, microcode )
+ __field( u8, len )
+ __dynamic_array(u8, v_data, sizeof(err->vi))
),
TP_fast_assign(
@@ -65,9 +67,11 @@ TRACE_EVENT(mce_record,
__entry->bank = err->m.bank;
__entry->cpuvendor = err->m.cpuvendor;
__entry->microcode = err->m.microcode;
+ __entry->len = sizeof(err->vi);
+ memcpy(__get_dynamic_array(v_data), &err->vi, sizeof(err->vi));
),
- TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, IPID: %016Lx, ADDR: %016Lx, MISC: %016Lx, SYND: %016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PPIN: %llx, vendor: %u, CPUID: %x, time: %llu, socket: %u, APIC: %x, microcode: %x",
+ TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016llx, IPID: %016llx, ADDR: %016llx, MISC: %016llx, SYND: %016llx, RIP: %02x:<%016llx>, TSC: %llx, PPIN: %llx, vendor: %u, CPUID: %x, time: %llu, socket: %u, APIC: %x, microcode: %x, vendor data: %s",
__entry->cpu,
__entry->mcgcap, __entry->mcgstatus,
__entry->bank, __entry->status,
@@ -83,7 +87,8 @@ TRACE_EVENT(mce_record,
__entry->walltime,
__entry->socketid,
__entry->apicid,
- __entry->microcode)
+ __entry->microcode,
+ __print_array(__get_dynamic_array(v_data), __entry->len / 8, 8))
);
#endif /* _TRACE_MCE_H */
--
2.34.1