[tip:x86/cpu] x86/mce: Add Hygon Dhyana support to the MCA infrastructure

From: tip-bot for Pu Wen
Date: Thu Sep 27 2018 - 13:06:51 EST


Commit-ID: ac78bd72355d0da64c073c12927264d4ff19b886
Gitweb: https://git.kernel.org/tip/ac78bd72355d0da64c073c12927264d4ff19b886
Author: Pu Wen <puwen@xxxxxxxx>
AuthorDate: Sun, 23 Sep 2018 17:36:04 +0800
Committer: Borislav Petkov <bp@xxxxxxx>
CommitDate: Thu, 27 Sep 2018 18:28:59 +0200

x86/mce: Add Hygon Dhyana support to the MCA infrastructure

The machine check architecture for Hygon Dhyana CPU is similar to the
AMD family 17h one. Add vendor checking for Hygon Dhyana to share the
code path of AMD family 17h.

Signed-off-by: Pu Wen <puwen@xxxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Reviewed-by: Borislav Petkov <bp@xxxxxxx>
Cc: tglx@xxxxxxxxxxxxx
Cc: mingo@xxxxxxxxxx
Cc: hpa@xxxxxxxxx
Cc: tony.luck@xxxxxxxxx
Cc: thomas.lendacky@xxxxxxx
Cc: linux-edac@xxxxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/87d8a4f16bdea0bfe0c0cf2e4a8d2c2a99b1055c.1537533369.git.puwen@xxxxxxxx
---
arch/x86/include/asm/mce.h | 2 ++
arch/x86/kernel/cpu/mcheck/mce-severity.c | 3 ++-
arch/x86/kernel/cpu/mcheck/mce.c | 20 +++++++++++++++-----
3 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 3a17107594c8..550f2c95dc1e 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -214,6 +214,8 @@ static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
#endif

+static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); }
+
int mce_available(struct cpuinfo_x86 *c);
bool mce_is_memory_error(struct mce *m);

diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index f34d89c01edc..44396d521987 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -336,7 +336,8 @@ int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) =

void __init mcheck_vendor_init_severity(void)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
mce_severity = mce_severity_amd;
}

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 953b3ce92dcc..909f1d75165c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -270,7 +270,7 @@ static void print_mce(struct mce *m)
{
__print_mce(m);

- if (m->cpuvendor != X86_VENDOR_AMD)
+ if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON)
pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}

@@ -508,9 +508,9 @@ static int mce_usable_address(struct mce *m)

bool mce_is_memory_error(struct mce *m)
{
- if (m->cpuvendor == X86_VENDOR_AMD) {
+ if (m->cpuvendor == X86_VENDOR_AMD ||
+ m->cpuvendor == X86_VENDOR_HYGON) {
return amd_mce_is_memory_error(m);
-
} else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -539,6 +539,9 @@ static bool mce_is_correctable(struct mce *m)
if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
return false;

+ if (m->cpuvendor == X86_VENDOR_HYGON && m->status & MCI_STATUS_DEFERRED)
+ return false;
+
if (m->status & MCI_STATUS_UC)
return false;

@@ -1705,7 +1708,7 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
*/
static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
{
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) {
mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR);
mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA);
@@ -1746,6 +1749,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
mce_amd_feature_init(c);
break;
}
+
+ case X86_VENDOR_HYGON:
+ mce_hygon_feature_init(c);
+ break;
+
case X86_VENDOR_CENTAUR:
mce_centaur_feature_init(c);
break;
@@ -1971,12 +1979,14 @@ static void mce_disable_error_reporting(void)
static void vendor_disable_error_reporting(void)
{
/*
- * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide.
+ * Don't clear on Intel or AMD or Hygon 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)
return;