[tip:ras/core] x86/MCE: Report only DRAM ECC as memory errors on AMD systems

[tip-bot for Yazen Ghannam]

Commit-ID:  c6708d50f166bea2d763c96485d31fdbc50204f1
Gitweb:     https://git.kernel.org/tip/c6708d50f166bea2d763c96485d31fdbc50204f1
Author:     Yazen Ghannam <yazen.ghannam@xxxxxxx>
AuthorDate: Mon, 18 Dec 2017 12:37:13 +0100
Committer:  Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitDate: Mon, 18 Dec 2017 12:58:29 +0100

x86/MCE: Report only DRAM ECC as memory errors on AMD systems

The MCA_STATUS[ErrorCodeExt] field is very bank type specific.
We currently check if the ErrorCodeExt value is 0x0 or 0x8 in
mce_is_memory_error(), but we don't check the bank number. This means
that we could flag non-memory errors as memory errors.

We know that we want to flag DRAM ECC errors as memory errors, so let's do
those cases first. We can add more cases later when needed.

Define a wrapper function in mce_amd.c so we can use SMCA enums.

[ bp: Remove brackets around return statements. ]

Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20171207203955.118171-2-Yazen.Ghannam@xxxxxxx

---
 arch/x86/include/asm/mce.h           |  2 ++
 arch/x86/kernel/cpu/mcheck/mce.c     |  4 +---
 arch/x86/kernel/cpu/mcheck/mce_amd.c | 11 +++++++++++
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b1e8d8d..96ea4b5 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.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b1d616d..321c7a80 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
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 661c473..0f32ad2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -754,6 +754,17 @@ out_err:
 }
 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;