Merge tag 'ras_core_for_6.7_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS updates from Borislav Petkov:

 - Specify what error addresses reported on AMD are actually usable
   memory error addresses for further decoding

* tag 'ras_core_for_6.7_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Cleanup mce_usable_address()
  x86/mce: Define amd_mce_usable_address()
  x86/MCE/AMD: Split amd_mce_is_memory_error()

5 files changed, 99 insertions, 27 deletions

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 180b1cbfcc4e..6de6e1d95952 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -245,7 +245,7 @@ static inline void cmci_recheck(void) {}
 int mce_available(struct cpuinfo_x86 *c);
 bool mce_is_memory_error(struct mce *m);
 bool mce_is_correctable(struct mce *m);
-int mce_usable_address(struct mce *m);
+bool mce_usable_address(struct mce *m);
 
 DECLARE_PER_CPU(unsigned, mce_exception_count);
 DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index c267f43de39e..f3517b8a8e91 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -713,17 +713,75 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 		deferred_error_interrupt_enable(c);
 }
 
-bool amd_mce_is_memory_error(struct mce *m)
+/*
+ * DRAM ECC errors are reported in the Northbridge (bank 4) with
+ * Extended Error Code 8.
+ */
+static bool legacy_mce_is_memory_error(struct mce *m)
+{
+	return m->bank == 4 && XEC(m->status, 0x1f) == 8;
+}
+
+/*
+ * DRAM ECC errors are reported in Unified Memory Controllers with
+ * Extended Error Code 0.
+ */
+static bool smca_mce_is_memory_error(struct mce *m)
 {
 	enum smca_bank_types bank_type;
-	/* ErrCodeExt[20:16] */
-	u8 xec = (m->status >> 16) & 0x1f;
+
+	if (XEC(m->status, 0x3f))
+		return false;
 
 	bank_type = smca_get_bank_type(m->extcpu, m->bank);
+
+	return bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2;
+}
+
+bool amd_mce_is_memory_error(struct mce *m)
+{
 	if (mce_flags.smca)
-		return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0;
+		return smca_mce_is_memory_error(m);
+	else
+		return legacy_mce_is_memory_error(m);
+}
+
+/*
+ * AMD systems do not have an explicit indicator that the value in MCA_ADDR is
+ * a system physical address. Therefore, individual cases need to be detected.
+ * Future cases and checks will be added as needed.
+ *
+ * 1) General case
+ *	a) Assume address is not usable.
+ * 2) Poison errors
+ *	a) Indicated by MCA_STATUS[43]: poison. Defined for all banks except legacy
+ *	   northbridge (bank 4).
+ *	b) Refers to poison consumption in the core. Does not include "no action",
+ *	   "action optional", or "deferred" error severities.
+ *	c) Will include a usable address so that immediate action can be taken.
+ * 3) Northbridge DRAM ECC errors
+ *	a) Reported in legacy bank 4 with extended error code (XEC) 8.
+ *	b) MCA_STATUS[43] is *not* defined as poison in legacy bank 4. Therefore,
+ *	   this bit should not be checked.
+ *
+ * NOTE: SMCA UMC memory errors fall into case #1.
+ */
+bool amd_mce_usable_address(struct mce *m)
+{
+	/* Check special northbridge case 3) first. */
+	if (!mce_flags.smca) {
+		if (legacy_mce_is_memory_error(m))
+			return true;
+		else if (m->bank == 4)
+			return false;
+	}
 
-	return m->bank == 4 && xec == 0x8;
+	/* Check poison bit for all other bank types. */
+	if (m->status & MCI_STATUS_POISON)
+		return true;
+
+	/* Assume address is not usable for all others. */
+	return false;
 }
 
 static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 6f35f724cc14..0214d4232346 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -453,32 +453,22 @@ static void mce_irq_work_cb(struct irq_work *entry)
 	mce_schedule_work();
 }
 
-/*
- * Check if the address reported by the CPU is in a format we can parse.
- * It would be possible to add code for most other cases, but all would
- * be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses up to page granularity for now.
- */
-int mce_usable_address(struct mce *m)
+bool mce_usable_address(struct mce *m)
 {
 	if (!(m->status & MCI_STATUS_ADDRV))
-		return 0;
-
-	/* 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))
-		return 0;
+		return false;
 
-	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
-		return 0;
+	switch (m->cpuvendor) {
+	case X86_VENDOR_AMD:
+		return amd_mce_usable_address(m);
 
-	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
-		return 0;
+	case X86_VENDOR_INTEL:
+	case X86_VENDOR_ZHAOXIN:
+		return intel_mce_usable_address(m);
 
-	return 1;
+	default:
+		return true;
+	}
 }
 EXPORT_SYMBOL_GPL(mce_usable_address);
 
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index f5323551c1a9..52bce533ddcc 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -536,3 +536,23 @@ bool intel_filter_mce(struct mce *m)
 
 	return false;
 }
+
+/*
+ * Check if the address reported by the CPU is in a format we can parse.
+ * It would be possible to add code for most other cases, but all would
+ * be somewhat complicated (e.g. segment offset would require an instruction
+ * parser). So only support physical addresses up to page granularity for now.
+ */
+bool intel_mce_usable_address(struct mce *m)
+{
+	if (!(m->status & MCI_STATUS_MISCV))
+		return false;
+
+	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
+		return false;
+
+	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
+		return false;
+
+	return true;
+}
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index bcf1b3c66c9c..e13a26c9c0ac 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -49,6 +49,7 @@ void intel_init_cmci(void);
 void intel_init_lmce(void);
 void intel_clear_lmce(void);
 bool intel_filter_mce(struct mce *m);
+bool intel_mce_usable_address(struct mce *m);
 #else
 # define cmci_intel_adjust_timer mce_adjust_timer_default
 static inline bool mce_intel_cmci_poll(void) { return false; }
@@ -58,6 +59,7 @@ static inline void intel_init_cmci(void) { }
 static inline void intel_init_lmce(void) { }
 static inline void intel_clear_lmce(void) { }
 static inline bool intel_filter_mce(struct mce *m) { return false; }
+static inline bool intel_mce_usable_address(struct mce *m) { return false; }
 #endif
 
 void mce_timer_kick(unsigned long interval);
@@ -210,6 +212,7 @@ extern bool filter_mce(struct mce *m);
 
 #ifdef CONFIG_X86_MCE_AMD
 extern bool amd_filter_mce(struct mce *m);
+bool amd_mce_usable_address(struct mce *m);
 
 /*
  * If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits
@@ -237,6 +240,7 @@ static __always_inline void smca_extract_err_addr(struct mce *m)
 
 #else
 static inline bool amd_filter_mce(struct mce *m) { return false; }
+static inline bool amd_mce_usable_address(struct mce *m) { return false; }
 static inline void smca_extract_err_addr(struct mce *m) { }
 #endif