x86/mce: Add support for new MCA_SYND register

Syndrome information is no longer contained in MCA_STATUS for SMCA
systems but in a new register - MCA_SYND.

Add a synd field to struct mce to hold MCA_SYND register value. Add it
to the end of struct mce to maintain compatibility with old versions of
mcelog. Also, add it to the respective tracepoint.

Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1467633035-32080-1-git-send-email-Yazen.Ghannam@amd.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/include/asm/mce.h

@@ -40,9 +40,10 @@
 #define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
 
 /* AMD-specific bits */
+#define MCI_STATUS_TCC		(1ULL<<55)  /* Task context corrupt */
+#define MCI_STATUS_SYNDV	(1ULL<<53)  /* synd reg. valid */
 #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 */
 
 /*
  * McaX field if set indicates a given bank supports MCA extensions:
@@ -110,6 +111,7 @@
 #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_SYND		0xc0002006
 #define MSR_AMD64_SMCA_MC0_DESTAT	0xc0002008
 #define MSR_AMD64_SMCA_MC0_DEADDR	0xc0002009
 #define MSR_AMD64_SMCA_MC0_MISC1	0xc000200a
@@ -119,6 +121,7 @@
 #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_SYND(x)	(MSR_AMD64_SMCA_MC0_SYND + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_DESTAT(x)	(MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_DEADDR(x)	(MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
 #define MSR_AMD64_SMCA_MCx_MISCy(x, y)	((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))

arch/x86/include/uapi/asm/mce.h

@@ -26,6 +26,7 @@ struct mce {
 	__u32 socketid;	/* CPU socket ID */
 	__u32 apicid;	/* CPU initial apic ID */
 	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
+	__u64 synd;	/* MCA_SYND MSR: only valid on SMCA systems */
 };
 
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)

arch/x86/kernel/cpu/mcheck/mce.c

@@ -569,6 +569,7 @@ static void mce_read_aux(struct mce *m, int i)
 {
 	if (m->status & MCI_STATUS_MISCV)
 		m->misc = mce_rdmsrl(msr_ops.misc(i));
+
 	if (m->status & MCI_STATUS_ADDRV) {
 		m->addr = mce_rdmsrl(msr_ops.addr(i));
 
@@ -581,6 +582,9 @@ static void mce_read_aux(struct mce *m, int i)
 			m->addr <<= shift;
 		}
 	}
+
+	if (mce_flags.smca && (m->status & MCI_STATUS_SYNDV))
+		m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
 }
 
 static bool memory_error(struct mce *m)

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -479,6 +479,9 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
 	if (m.status & MCI_STATUS_ADDRV)
 		rdmsrl(msr_addr, m.addr);
 
+	if (mce_flags.smca && (m.status & MCI_STATUS_SYNDV))
+		rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd);
+
 	mce_log(&m);
 
 	wrmsrl(msr_status, 0);

include/trace/events/mce.h

@@ -20,6 +20,7 @@ TRACE_EVENT(mce_record,
 		__field(	u64,		status		)
 		__field(	u64,		addr		)
 		__field(	u64,		misc		)
+		__field(	u64,		synd		)
 		__field(	u64,		ip		)
 		__field(	u64,		tsc		)
 		__field(	u64,		walltime	)
@@ -38,6 +39,7 @@ TRACE_EVENT(mce_record,
 		__entry->status		= m->status;
 		__entry->addr		= m->addr;
 		__entry->misc		= m->misc;
+		__entry->synd		= m->synd;
 		__entry->ip		= m->ip;
 		__entry->tsc		= m->tsc;
 		__entry->walltime	= m->time;
@@ -50,11 +52,11 @@ TRACE_EVENT(mce_record,
 		__entry->cpuvendor	= m->cpuvendor;
 	),
 
-	TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, ADDR/MISC: %016Lx/%016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PROCESSOR: %u:%x, TIME: %llu, SOCKET: %u, APIC: %x",
+	TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, ADDR/MISC/SYND: %016Lx/%016Lx/%016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PROCESSOR: %u:%x, TIME: %llu, SOCKET: %u, APIC: %x",
 		__entry->cpu,
 		__entry->mcgcap, __entry->mcgstatus,
 		__entry->bank, __entry->status,
-		__entry->addr, __entry->misc,
+		__entry->addr, __entry->misc, __entry->synd,
 		__entry->cs, __entry->ip,
 		__entry->tsc,
 		__entry->cpuvendor, __entry->cpuid,