x86/RAS: Enable error decoding of AMD Scalable MCA errors

index 2ea4527e462f..80ba0a8d6d06 100644
@@ -91,6 +91,10 @@
 #define MCE_LOG_LEN 32
 #define MCE_LOG_SIGNATURE	"MACHINECHECK"
 
+/* AMD Scalable MCA */
+#define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
+#define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
+
 /*
  * This structure contains all data related to the MCE log.  Also
  * carries a signature to make it easier to find from external

index 552346598dab..b05402ef3b84 100644
@@ -264,10 +264,6 @@
 #define MSR_IA32_MC0_CTL2		0x00000280
 #define MSR_IA32_MCx_CTL2(x)		(MSR_IA32_MC0_CTL2 + (x))
 
-/* 'SMCA': AMD64 Scalable MCA */
-#define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
-#define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
-
 #define MSR_P6_PERFCTR0			0x000000c1
 #define MSR_P6_PERFCTR1			0x000000c2
 #define MSR_P6_EVNTSEL0			0x00000186

index 80ba0a8d6d06..9c467fe00551 100644
@@ -42,6 +42,18 @@
 /* AMD-specific bits */
 #define MCI_STATUS_DEFERRED	(1ULL<<44)  /* declare an uncorrected error */
 #define MCI_STATUS_POISON	(1ULL<<43)  /* access poisonous data */
+#define MCI_STATUS_TCC		(1ULL<<55)  /* Task context corrupt */
+
+/*
+ * McaX field if set indicates a given bank supports MCA extensions:
+ *  - Deferred error interrupt type is specifiable by bank.
+ *  - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers,
+ *    But should not be used to determine MSR numbers.
+ *  - TCC bit is present in MCx_STATUS.
+ */
+#define MCI_CONFIG_MCAX		0x1
+#define MCI_IPID_MCATYPE	0xFFFF0000
+#define MCI_IPID_HWID		0xFFF
 
 /*
  * Note that the full MCACOD field of IA32_MCi_STATUS MSR is

@@ -93,7 +105,9 @@
 
 /* AMD Scalable MCA */
 #define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
+#define MSR_AMD64_SMCA_MC0_IPID		0xc0002005
 #define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_IPID(x)	(MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
 
 /*
  * This structure contains all data related to the MCE log.  Also

@@ -291,4 +305,49 @@ struct cper_sec_mem_err;
 extern void apei_mce_report_mem_error(int corrected,
 				      struct cper_sec_mem_err *mem_err);
 
+/*
+ * Enumerate new IP types and HWID values in AMD processors which support
+ * Scalable MCA.
+ */
+#ifdef CONFIG_X86_MCE_AMD
+enum amd_ip_types {
+	SMCA_F17H_CORE = 0,	/* Core errors */
+	SMCA_DF,		/* Data Fabric */
+	SMCA_UMC,		/* Unified Memory Controller */
+	SMCA_PB,		/* Parameter Block */
+	SMCA_PSP,		/* Platform Security Processor */
+	SMCA_SMU,		/* System Management Unit */
+	N_AMD_IP_TYPES
+};
+
+struct amd_hwid {
+	const char *name;
+	unsigned int hwid;
+};
+
+extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES];
+
+enum amd_core_mca_blocks {
+	SMCA_LS = 0,	/* Load Store */
+	SMCA_IF,	/* Instruction Fetch */
+	SMCA_L2_CACHE,	/* L2 cache */
+	SMCA_DE,	/* Decoder unit */
+	RES,		/* Reserved */
+	SMCA_EX,	/* Execution unit */
+	SMCA_FP,	/* Floating Point */
+	SMCA_L3_CACHE,	/* L3 cache */
+	N_CORE_MCA_BLOCKS
+};
+
+extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS];
+
+enum amd_df_mca_blocks {
+	SMCA_CS = 0,	/* Coherent Slave */
+	SMCA_PIE,	/* Power management, Interrupts, etc */
+	N_DF_BLOCKS
+};
+
+extern const char * const amd_df_mcablock_names[N_DF_BLOCKS];
+#endif
+
 #endif /* _ASM_X86_MCE_H */

index 88de27bd5797..ee487a93ebe7 100644
@@ -71,6 +71,35 @@ static const char * const th_names[] = {
 	"execution_unit",
 };
 
+/* Define HWID to IP type mappings for Scalable MCA */
+struct amd_hwid amd_hwids[] = {
+	[SMCA_F17H_CORE]	= { "f17h_core",	0xB0 },
+	[SMCA_DF]		= { "data_fabric",	0x2E },
+	[SMCA_UMC]		= { "umc",		0x96 },
+	[SMCA_PB]		= { "param_block",	0x5 },
+	[SMCA_PSP]		= { "psp",		0xFF },
+	[SMCA_SMU]		= { "smu",		0x1 },
+};
+EXPORT_SYMBOL_GPL(amd_hwids);
+
+const char * const amd_core_mcablock_names[] = {
+	[SMCA_LS]		= "load_store",
+	[SMCA_IF]		= "insn_fetch",
+	[SMCA_L2_CACHE]		= "l2_cache",
+	[SMCA_DE]		= "decode_unit",
+	[RES]			= "",
+	[SMCA_EX]		= "execution_unit",
+	[SMCA_FP]		= "floating_point",
+	[SMCA_L3_CACHE]		= "l3_cache",
+};
+EXPORT_SYMBOL_GPL(amd_core_mcablock_names);
+
+const char * const amd_df_mcablock_names[] = {
+	[SMCA_CS]		= "coherent_slave",
+	[SMCA_PIE]		= "pie",
+};
+EXPORT_SYMBOL_GPL(amd_df_mcablock_names);
+
 static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 

389 lines not on this page · raw message

index 9c467fe00551..72f86882d62a 100644
@@ -104,10 +104,14 @@
 #define MCE_LOG_SIGNATURE	"MACHINECHECK"
 
 /* AMD Scalable MCA */
+#define MSR_AMD64_SMCA_MC0_MISC0	0xc0002003
 #define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
 #define MSR_AMD64_SMCA_MC0_IPID		0xc0002005
+#define MSR_AMD64_SMCA_MC0_MISC1	0xc000200a
+#define MSR_AMD64_SMCA_MCx_MISC(x)	(MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_IPID(x)	(MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_MISCy(x, y)	((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
 
 /*
  * This structure contains all data related to the MCE log.  Also

109 lines not on this page · raw message

index 72f86882d62a..cfff34172be0 100644
@@ -40,7 +40,7 @@
 #define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
 
 /* AMD-specific bits */
-#define MCI_STATUS_DEFERRED	(1ULL<<44)  /* declare an uncorrected error */
+#define MCI_STATUS_DEFERRED	(1ULL<<44)  /* uncorrected error, deferred exception */
 #define MCI_STATUS_POISON	(1ULL<<43)  /* access poisonous data */
 #define MCI_STATUS_TCC		(1ULL<<55)  /* Task context corrupt */
 

index 3c56ef1ae068..5e828da2e18f 100644
@@ -27,15 +27,23 @@ struct amd_l3_cache {
 };
 
 struct threshold_block {
-	unsigned int		block;
-	unsigned int		bank;
-	unsigned int		cpu;
-	u32			address;
-	u16			interrupt_enable;
-	bool			interrupt_capable;
-	u16			threshold_limit;
-	struct kobject		kobj;
-	struct list_head	miscj;
+	unsigned int	 block;			/* Number within bank */
+	unsigned int	 bank;			/* MCA bank the block belongs to */
+	unsigned int	 cpu;			/* CPU which controls MCA bank */
+	u32		 address;		/* MSR address for the block */
+	u16		 interrupt_enable;	/* Enable/Disable APIC interrupt */
+	bool		 interrupt_capable;	/* Bank can generate an interrupt. */
+
+	u16		 threshold_limit;	/*
+						 * Value upon which threshold
+						 * interrupt is generated.
+						 */
+
+	struct kobject	 kobj;			/* sysfs object */
+	struct list_head miscj;			/*
+						 * List of threshold blocks
+						 * within a bank.
+						 */
 };
 
 struct threshold_bank {

index a53eb1ba587e..9d656fd436ef 100644
@@ -1,5 +1,5 @@
 /*
- *  (c) 2005-2015 Advanced Micro Devices, Inc.
+ *  (c) 2005-2016 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html

@@ -201,10 +201,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
 	return 1;
 };
 
-/*
- * Called via smp_call_function_single(), must be called with correct
- * cpu affinity.
- */
+/* Reprogram MCx_MISC MSR behind this threshold bank. */
 static void threshold_restart_bank(void *_tr)
 {
 	struct thresh_restart *tr = _tr;