[GIT PULL] RAS updates for v4.16

From: Ingo Molnar
Date: Mon Jan 29 2018 - 06:01:10 EST

Linus,

Please pull the latest ras-core-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git ras-core-for-linus

# HEAD: 179eb850ac57c06edaed67fc744ba9d902172f96 x86/MCE: Make correctable error detection look at the Deferred bit

The main changes:

- Various AMD SMCA error parsing/reporting improvements (Yazen Ghannam)

- Extend Intel CMCI error reporting to more cases (Xie XiuQi)

Thanks,

Ingo

------------------>
Xie XiuQi (1):
x86/MCE: Extend table to report action optional errors through CMCI too

Yazen Ghannam (4):
x86/mce/AMD: Don't set DEF_INT_TYPE in MSR_CU_DEF_ERR on SMCA systems
x86/MCE/AMD: Define a function to get SMCA bank type
x86/MCE: Report only DRAM ECC as memory errors on AMD systems
x86/MCE: Make correctable error detection look at the Deferred bit


arch/x86/include/asm/mce.h | 2 ++
arch/x86/kernel/cpu/mcheck/mce-severity.c | 26 +++++++++++++++++---------
arch/x86/kernel/cpu/mcheck/mce.c | 17 +++++++++++++----
arch/x86/kernel/cpu/mcheck/mce_amd.c | 29 ++++++++++++++++++++++++++++-
4 files changed, 60 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b1e8d8db921f..96ea4b5ba658 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -376,6 +376,7 @@ struct smca_bank {
extern struct smca_bank smca_banks[MAX_NR_BANKS];

extern const char *smca_get_long_name(enum smca_bank_types t);
+extern bool amd_mce_is_memory_error(struct mce *m);

extern int mce_threshold_create_device(unsigned int cpu);
extern int mce_threshold_remove_device(unsigned int cpu);
@@ -384,6 +385,7 @@ extern int mce_threshold_remove_device(unsigned int cpu);

static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
+static inline bool amd_mce_is_memory_error(struct mce *m) { return false; };

#endif

diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 4ca632a06e0b..5bbd06f38ff6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -59,6 +59,7 @@ static struct severity {
#define MCGMASK(x, y) .mcgmask = x, .mcgres = y
#define MASK(x, y) .mask = x, .result = y
#define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S)
+#define MCI_UC_AR (MCI_STATUS_UC|MCI_STATUS_AR)
#define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR)
#define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV)

@@ -101,6 +102,22 @@ static struct severity {
NOSER, BITCLR(MCI_STATUS_UC)
),

+ /*
+ * known AO MCACODs reported via MCE or CMC:
+ *
+ * SRAO could be signaled either via a machine check exception or
+ * CMCI with the corresponding bit S 1 or 0. So we don't need to
+ * check bit S for SRAO.
+ */
+ MCESEV(
+ AO, "Action optional: memory scrubbing error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
+ ),
+ MCESEV(
+ AO, "Action optional: last level cache writeback error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
+ ),
+
/* ignore OVER for UCNA */
MCESEV(
UCNA, "Uncorrected no action required",
@@ -149,15 +166,6 @@ static struct severity {
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR)
),

- /* known AO MCACODs: */
- MCESEV(
- AO, "Action optional: memory scrubbing error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_SCRUBMSK, MCI_UC_S|MCACOD_SCRUB)
- ),
- MCESEV(
- AO, "Action optional: last level cache writeback error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|MCACOD_L3WB)
- ),
MCESEV(
SOME, "Action optional: unknown MCACOD",
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b1d616d08eee..1b2c11473376 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -503,10 +503,8 @@ static int mce_usable_address(struct mce *m)
bool mce_is_memory_error(struct mce *m)
{
if (m->cpuvendor == X86_VENDOR_AMD) {
- /* ErrCodeExt[20:16] */
- u8 xec = (m->status >> 16) & 0x1f;
+ return amd_mce_is_memory_error(m);

- return (xec == 0x0 || xec == 0x8);
} else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -530,6 +528,17 @@ bool mce_is_memory_error(struct mce *m)
}
EXPORT_SYMBOL_GPL(mce_is_memory_error);

+static bool mce_is_correctable(struct mce *m)
+{
+ if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
+ return false;
+
+ if (m->status & MCI_STATUS_UC)
+ return false;
+
+ return true;
+}
+
static bool cec_add_mce(struct mce *m)
{
if (!m)
@@ -537,7 +546,7 @@ static bool cec_add_mce(struct mce *m)

/* We eat only correctable DRAM errors with usable addresses. */
if (mce_is_memory_error(m) &&
- !(m->status & MCI_STATUS_UC) &&
+ mce_is_correctable(m) &&
mce_usable_address(m))
if (!cec_add_elem(m->addr >> PAGE_SHIFT))
return true;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 486f640b02ef..0f32ad242324 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -110,6 +110,20 @@ const char *smca_get_long_name(enum smca_bank_types t)
}
EXPORT_SYMBOL_GPL(smca_get_long_name);

+static enum smca_bank_types smca_get_bank_type(struct mce *m)
+{
+ struct smca_bank *b;
+
+ if (m->bank >= N_SMCA_BANK_TYPES)
+ return N_SMCA_BANK_TYPES;
+
+ b = &smca_banks[m->bank];
+ if (!b->hwid)
+ return N_SMCA_BANK_TYPES;
+
+ return b->hwid->bank_type;
+}
+
static struct smca_hwid smca_hwid_mcatypes[] = {
/* { bank_type, hwid_mcatype, xec_bitmap } */

@@ -407,7 +421,9 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
(deferred_error_int_vector != amd_deferred_error_interrupt))
deferred_error_int_vector = amd_deferred_error_interrupt;

- low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+ if (!mce_flags.smca)
+ low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+
wrmsr(MSR_CU_DEF_ERR, low, high);
}

@@ -738,6 +754,17 @@ int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
}
EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr);

+bool amd_mce_is_memory_error(struct mce *m)
+{
+ /* ErrCodeExt[20:16] */
+ u8 xec = (m->status >> 16) & 0x1f;
+
+ if (mce_flags.smca)
+ return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0;
+
+ return m->bank == 4 && xec == 0x8;
+}
+
static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
{
struct mce m;