x86/mce/AMD: Save MCA_IPID in MCE struct on SMCA systems

The MCA_IPID register uniquely identifies a bank's type and instance
on Scalable MCA systems. We should save the value of this register
in struct mce along with the other relevant error information. This
ensures that we can decode errors without relying on system software to
correlate the bank to the type.
Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1472680624-34221-1-git-send-email-Yazen.Ghannam@amd.comSigned-off-by: Thomas Gleixner <tglx@linutronix.de>

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

@@ -27,6 +27,7 @@ struct mce {
 	__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 */
+	__u64 ipid;	/* MCA_IPID MSR: only valid on SMCA systems */
 };
 
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)

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

@@ -583,8 +583,12 @@ static void mce_read_aux(struct mce *m, int i)
 		}
 	}
 
-	if (mce_flags.smca && (m->status & MCI_STATUS_SYNDV))
+	if (mce_flags.smca) {
+		m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+
+		if (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

@@ -564,8 +564,12 @@ __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))
+	if (mce_flags.smca) {
+		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid);
+
+		if (m.status & MCI_STATUS_SYNDV)
 			rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd);
+	}
 
 	mce_log(&m);
 

include/trace/events/mce.h

@@ -21,6 +21,7 @@ TRACE_EVENT(mce_record,
 		__field(	u64,		addr		)
 		__field(	u64,		misc		)
 		__field(	u64,		synd		)
+		__field(	u64,		ipid		)
 		__field(	u64,		ip		)
 		__field(	u64,		tsc		)
 		__field(	u64,		walltime	)
@@ -40,6 +41,7 @@ TRACE_EVENT(mce_record,
 		__entry->addr		= m->addr;
 		__entry->misc		= m->misc;
 		__entry->synd		= m->synd;
+		__entry->ipid		= m->ipid;
 		__entry->ip		= m->ip;
 		__entry->tsc		= m->tsc;
 		__entry->walltime	= m->time;
@@ -52,10 +54,11 @@ TRACE_EVENT(mce_record,
 		__entry->cpuvendor	= m->cpuvendor;
 	),
 
-	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",
+	TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, IPID: %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->ipid,
 		__entry->addr, __entry->misc, __entry->synd,
 		__entry->cs, __entry->ip,
 		__entry->tsc,