Until now, the mce_severity mechanism can only identify the severity
of UCNA error as MCE_KEEP_SEVERITY. Meanwhile, it is not able to filter
out DEFERRED error for ADM platform.
This patch aims to extend the mce_severity mechanism for handling
UCNA/DEFERRED error. In order to do this, the patch introduces a new
severity level - MCE_UCNA/DEFERRED_SEVERITY.
In addition, mce_severity is specific to machine check exception,
and it will check MCIP/EIPV/RIPV bits. In order to use mce_severity
mechanism in non-exception context, the patch also introduces a new
argument (is_excp) for mce_severity. `is_excp' is used to explicitly
specify the calling context of mce_severity.
Signed-off-by: Chen Yucong <[email protected]>
---
arch/x86/include/asm/mce.h | 4 ++++
arch/x86/kernel/cpu/mcheck/mce-internal.h | 4 +++-
arch/x86/kernel/cpu/mcheck/mce-severity.c | 21 ++++++++++++++++-----
arch/x86/kernel/cpu/mcheck/mce.c | 14 ++++++++------
drivers/edac/mce_amd.h | 3 ---
5 files changed, 31 insertions(+), 15 deletions(-)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 276392f..51b26e89 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -34,6 +34,10 @@
#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
+/* AMD-specific bits */
+#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */
+#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */
+
/*
* Note that the full MCACOD field of IA32_MCi_STATUS MSR is
* bits 15:0. But bit 12 is the 'F' bit, defined for corrected
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h
b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 09edd0b..10b4690 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -3,6 +3,8 @@
enum severity_level {
MCE_NO_SEVERITY,
+ MCE_DEFERRED_SEVERITY,
+ MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY,
MCE_KEEP_SEVERITY,
MCE_SOME_SEVERITY,
MCE_AO_SEVERITY,
@@ -21,7 +23,7 @@ struct mce_bank {
char attrname[ATTR_LEN]; /* attribute name */
};
-int mce_severity(struct mce *a, int tolerant, char **msg);
+int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp);
struct dentry *mce_get_debugfs_dir(void);
extern struct mce_bank *mce_banks;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c
b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index c370e1c..c61feb3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -31,6 +31,7 @@
enum context { IN_KERNEL = 1, IN_USER = 2 };
enum ser { SER_REQUIRED = 1, NO_SER = 2 };
+enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 };
static struct severity {
u64 mask;
@@ -40,6 +41,7 @@ static struct severity {
unsigned char mcgres;
unsigned char ser;
unsigned char context;
+ unsigned char excp;
unsigned char covered;
char *msg;
} severities[] = {
@@ -48,6 +50,8 @@ static struct severity {
#define USER .context = IN_USER
#define SER .ser = SER_REQUIRED
#define NOSER .ser = NO_SER
+#define EXCP .excp = EXCP_CONTEXT
+#define NOEXCP .excp = NO_EXCP
#define BITCLR(x) .mask = x, .result = 0
#define BITSET(x) .mask = x, .result = x
#define MCGMASK(x, y) .mcgmask = x, .mcgres = y
@@ -71,16 +75,20 @@ static struct severity {
/* When MCIP is not set something is very confused */
MCESEV(
PANIC, "MCIP not set in MCA handler",
- MCGMASK(MCG_STATUS_MCIP, 0)
+ EXCP, MCGMASK(MCG_STATUS_MCIP, 0)
),
/* Neither return not error IP -- no chance to recover -> PANIC */
MCESEV(
PANIC, "Neither restart nor error IP",
- MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0)
+ EXCP, MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0)
),
MCESEV(
PANIC, "In kernel and no restart IP",
- KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
+ EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
+ ),
+ MCESEV(
+ DEFERRED, "Deferred error",
+ NOSER,
MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED)
),
