[PATCH v4 1/4] x86/mce: Add Zhaoxin MCE support

From: Tony W Wang-oc
Date: Wed Sep 18 2019 - 02:19:58 EST


All Zhaoxin newer CPUs support MCE that compatible with Intel's
"Machine-Check Architecture", so add support for Zhaoxin MCE in
mce/core.c.

Signed-off-by: Tony W Wang-oc <TonyWWang-oc@xxxxxxxxxxx>
---
arch/x86/kernel/cpu/mce/core.c | 38 ++++++++++++++++++++++++++++----------
1 file changed, 28 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 743370e..7bcd8c1 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
if (!(m->status & MCI_STATUS_ADDRV))
return 0;

- /* Checks after this one are Intel-specific: */
- if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ /* Checks after this one are Intel/Zhaoxin-specific: */
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
return 1;

if (!(m->status & MCI_STATUS_MISCV))
@@ -507,10 +508,13 @@ EXPORT_SYMBOL_GPL(mce_usable_address);

bool mce_is_memory_error(struct mce *m)
{
- if (m->cpuvendor == X86_VENDOR_AMD ||
- m->cpuvendor == X86_VENDOR_HYGON) {
+ switch (m->cpuvendor) {
+ case X86_VENDOR_AMD:
+ case X86_VENDOR_HYGON:
return amd_mce_is_memory_error(m);
- } else if (m->cpuvendor == X86_VENDOR_INTEL) {
+
+ case X86_VENDOR_INTEL:
+ case X86_VENDOR_ZHAOXIN:
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
*
@@ -527,9 +531,10 @@ bool mce_is_memory_error(struct mce *m)
return (m->status & 0xef80) == BIT(7) ||
(m->status & 0xef00) == BIT(8) ||
(m->status & 0xeffc) == 0xc;
- }

- return false;
+ default:
+ return false;
+ }
}
EXPORT_SYMBOL_GPL(mce_is_memory_error);

@@ -1697,6 +1702,18 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
if (c->x86 == 6 && c->x86_model == 45)
quirk_no_way_out = quirk_sandybridge_ifu;
}
+
+ if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+ /*
+ * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+ * synchronization with a one second timeout.
+ */
+ if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+ if (cfg->monarch_timeout < 0)
+ cfg->monarch_timeout = USEC_PER_SEC;
+ }
+ }
+
if (cfg->monarch_timeout < 0)
cfg->monarch_timeout = 0;
if (cfg->bootlog != 0)
@@ -2014,15 +2031,16 @@ static void mce_disable_error_reporting(void)
static void vendor_disable_error_reporting(void)
{
/*
- * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
- * are socket-wide.
+ * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these
+ * MSRs are socket-wide.
* Disabling them for just a single offlined CPU is bad, since it will
* inhibit reporting for all shared resources on the socket like the
* last level cache (LLC), the integrated memory controller (iMC), etc.
*/
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
- boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN)
return;

mce_disable_error_reporting();
--
2.7.4