[v2 PATCH 0/5] powerpc/pseries: Machien check handler improvements.

@@ -559,7 +559,7 @@ static int __init rtas_event_scan_init(void)
 	rtas_error_log_max = rtas_get_error_log_max();
 	rtas_error_log_buffer_max = rtas_error_log_max + sizeof(int);
 
-	rtas_log_buf = vmalloc(rtas_error_log_buffer_max*LOG_NUMBER);
+	rtas_log_buf = kmalloc(rtas_error_log_buffer_max*LOG_NUMBER, GFP_KERNEL);
 	if (!rtas_log_buf) {
 		printk(KERN_ERR "rtasd: no memory\n");
 		return -ENOMEM;

@@ -275,6 +275,7 @@ inline uint32_t rtas_ext_event_company_id(struct rtas_ext_event_log_v6 *ext_log)
 #define PSERIES_ELOG_SECT_ID_CALL_HOME		(('C' << 8) | 'H')
 #define PSERIES_ELOG_SECT_ID_USER_DEF		(('U' << 8) | 'D')
 #define PSERIES_ELOG_SECT_ID_HOTPLUG		(('H' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_MCE		(('M' << 8) | 'C')
 
 /* Vendor specific Platform Event Log Format, Version 6, section header */
 struct pseries_errorlog {

@@ -326,6 +327,109 @@ struct pseries_hp_errorlog {
 #define PSERIES_HP_ELOG_ID_DRC_COUNT	3
 #define PSERIES_HP_ELOG_ID_DRC_IC	4
 
+/* RTAS pseries MCE errorlog section */
+#pragma pack(push, 1)
+struct pseries_mc_errorlog {
+	__be32	fru_id;
+	__be32	proc_id;
+	uint8_t	error_type;
+	union {
+		struct {
+			uint8_t	ue_err_type;
+			/* XXXXXXXX
+			 * X		1: Permanent or Transient UE.
+			 *  X		1: Effective address provided.
+			 *   X		1: Logical address provided.
+			 *    XX	2: Reserved.
+			 *      XXX	3: Type of UE error.
+			 */
+			uint8_t	reserved_1[6];
+			__be64	effective_address;
+			__be64	logical_address;
+		} ue_error;
+		struct {
+			uint8_t	soft_err_type;
+			/* XXXXXXXX
+			 * X		1: Effective address provided.
+			 *  XXXXX	5: Reserved.
+			 *       XX	2: Type of SLB/ERAT/TLB error.
+			 */
+			uint8_t	reserved_1[6];
+			__be64	effective_address;
+			uint8_t	reserved_2[8];
+		} soft_error;
+	} u;
+};
+#pragma pack(pop)
+
+/* RTAS pseries MCE error types */
+#define PSERIES_MC_ERROR_TYPE_UE		0x00
+#define PSERIES_MC_ERROR_TYPE_SLB		0x01
+#define PSERIES_MC_ERROR_TYPE_ERAT		0x02
+#define PSERIES_MC_ERROR_TYPE_TLB		0x04
+#define PSERIES_MC_ERROR_TYPE_D_CACHE		0x05
+#define PSERIES_MC_ERROR_TYPE_I_CACHE		0x07
+
+/* RTAS pseries MCE error sub types */
+#define PSERIES_MC_ERROR_UE_INDETERMINATE		0
+#define PSERIES_MC_ERROR_UE_IFETCH			1
+#define PSERIES_MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH	2
+#define PSERIES_MC_ERROR_UE_LOAD_STORE			3
+#define PSERIES_MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE	4
+
+#define PSERIES_MC_ERROR_SLB_PARITY		0
+#define PSERIES_MC_ERROR_SLB_MULTIHIT		1
+#define PSERIES_MC_ERROR_SLB_INDETERMINATE	2
+
+#define PSERIES_MC_ERROR_ERAT_PARITY		1
+#define PSERIES_MC_ERROR_ERAT_MULTIHIT		2
+#define PSERIES_MC_ERROR_ERAT_INDETERMINATE	3
+
+#define PSERIES_MC_ERROR_TLB_PARITY		1
+#define PSERIES_MC_ERROR_TLB_MULTIHIT		2
+#define PSERIES_MC_ERROR_TLB_INDETERMINATE	3
+
+static inline uint8_t rtas_mc_error_type(const struct pseries_mc_errorlog *mlog)
+{
+	return mlog->error_type;
+}
+
+static inline uint8_t rtas_mc_error_sub_type(
+					const struct pseries_mc_errorlog *mlog)
+{
+	switch (mlog->error_type) {
+	case	PSERIES_MC_ERROR_TYPE_UE:
+		return (mlog->u.ue_error.ue_err_type & 0x07);
+	case	PSERIES_MC_ERROR_TYPE_SLB:
+	case	PSERIES_MC_ERROR_TYPE_ERAT:
+	case	PSERIES_MC_ERROR_TYPE_TLB:
+		return (mlog->u.soft_error.soft_err_type & 0x03);
+	default:
+		return 0;
+	}
+}
+
+static inline uint64_t rtas_mc_get_effective_addr(
+					const struct pseries_mc_errorlog *mlog)
+{
+	uint64_t addr = 0;
+
+	switch (mlog->error_type) {
+	case	PSERIES_MC_ERROR_TYPE_UE:
+		if (mlog->u.ue_error.ue_err_type & 0x40)
+			addr = mlog->u.ue_error.effective_address;
+		break;
+	case	PSERIES_MC_ERROR_TYPE_SLB:
+	case	PSERIES_MC_ERROR_TYPE_ERAT:
+	case	PSERIES_MC_ERROR_TYPE_TLB:
+		if (mlog->u.soft_error.soft_err_type & 0x80)
+			addr = mlog->u.soft_error.effective_address;
+	default:
+		break;
+	}
+	return be64_to_cpu(addr);
+}
+
 struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
 					      uint16_t section_id);
 

@@ -487,6 +487,7 @@ extern void hpte_init_native(void);
 
 extern void slb_initialize(void);
 extern void slb_flush_and_rebolt(void);
+extern void slb_dump_contents(void);
 
 extern void slb_vmalloc_update(void);
 extern void slb_set_size(u16 size);

@@ -145,6 +145,41 @@ void slb_flush_and_rebolt(void)
 	get_paca()->slb_cache_ptr = 0;
 }
 
+void slb_dump_contents(void)
+{
+	int i;
+	unsigned long e, v;
+	unsigned long llp;
+
+	pr_err("slb contents:\n");
+	for (i = 0; i < mmu_slb_size; i++) {
+		asm volatile("slbmfee  %0,%1" : "=r" (e) : "r" (i));
+		asm volatile("slbmfev  %0,%1" : "=r" (v) : "r" (i));
+
+		if (!e && !v)
+			continue;
+
+		pr_err("%02d %016lx %016lx", i, e, v);
+
+		if (!(e & SLB_ESID_V)) {
+			pr_err("\n");
+			continue;
+		}
+		llp = v & SLB_VSID_LLP;
+		if (v & SLB_VSID_B_1T) {
+			pr_err("  1T  ESID=%9lx  VSID=%13lx LLP:%3lx\n",
+				GET_ESID_1T(e),
+				(v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T,
+				llp);
+		} else {
+			pr_err(" 256M ESID=%9lx  VSID=%13lx LLP:%3lx\n",
+				GET_ESID(e),
+				(v & ~SLB_VSID_B) >> SLB_VSID_SHIFT,
+				llp);
+		}
+	}
+}
+
 void slb_vmalloc_update(void)
 {
 	unsigned long vflags;

@@ -422,6 +422,31 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 	return 0; /* need to perform reset */
 }
 
+static int mce_handle_error(struct rtas_error_log *errp)
+{
+	struct pseries_errorlog *pseries_log;
+	struct pseries_mc_errorlog *mce_log;
+	int disposition = rtas_error_disposition(errp);
+	uint8_t error_type;
+
+	pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
+	if (pseries_log == NULL)
+		goto out;
+
+	mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
+	error_type = rtas_mc_error_type(mce_log);
+
+	if ((disposition == RTAS_DISP_NOT_RECOVERED) &&
+			(error_type == PSERIES_MC_ERROR_TYPE_SLB)) {
+		slb_dump_contents();
+		slb_flush_and_rebolt();
+		disposition = RTAS_DISP_FULLY_RECOVERED;
+	}
+
+out:
+	return disposition;
+}
+
 /*
  * See if we can recover from a machine check exception.
  * This is only called on power4 (or above) and only via

@@ -434,7 +459,9 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
 {
 	int recovered = 0;
-	int disposition = rtas_error_disposition(err);
+	int disposition;
+
+	disposition = mce_handle_error(err);
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */

@@ -190,6 +190,11 @@ static inline uint8_t rtas_error_extended(const struct rtas_error_log *elog)
 	return (elog->byte1 & 0x04) >> 2;
 }
 
+static inline uint8_t rtas_error_initiator(const struct rtas_error_log *elog)
+{
+	return (elog->byte2 & 0xf0) >> 4;
+}
+
 #define rtas_error_type(x)	((x)->byte3)
 
 static inline

@@ -422,7 +422,130 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 	return 0; /* need to perform reset */
 }
 
-static int mce_handle_error(struct rtas_error_log *errp)
+#define VAL_TO_STRING(ar, val)	((val < ARRAY_SIZE(ar)) ? ar[val] : "Unknown")
+
+static void pseries_print_mce_info(struct pt_regs *regs,
+				struct rtas_error_log *errp, int disposition)
+{
+	const char *level, *sevstr;
+	struct pseries_errorlog *pseries_log;
+	struct pseries_mc_errorlog *mce_log;
+	uint8_t error_type, err_sub_type;
+	uint8_t initiator = rtas_error_initiator(errp);
+	uint64_t addr;
+
+	static const char * const initiators[] = {
+		"Unknown",
+		"CPU",
+		"PCI",
+		"ISA",
+		"Memory",
+		"Power Mgmt",
+	};
+	static const char * const mc_err_types[] = {
+		"UE",
+		"SLB",
+		"ERAT",
+		"TLB",
+		"D-Cache",
+		"Unknown",
+		"I-Cache",
+	};
+	static const char * const mc_ue_types[] = {
+		"Indeterminate",
+		"Instruction fetch",
+		"Page table walk ifetch",
+		"Load/Store",
+		"Page table walk Load/Store",
+	};
+
+	/* SLB sub errors valid values are 0x0, 0x1, 0x2 */
+	static const char * const mc_slb_types[] = {
+		"Parity",
+		"Multihit",
+		"Indeterminate",
+	};
+
+	/* TLB and ERAT sub errors valid values are 0x1, 0x2, 0x3 */
+	static const char * const mc_soft_types[] = {
+		"Unknown",
+		"Parity",
+		"Multihit",
+		"Indeterminate",
+	};
+
+	pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
+	if (pseries_log == NULL)
+		return;
+
+	mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
+
+	error_type = rtas_mc_error_type(mce_log);
+	err_sub_type = rtas_mc_error_sub_type(mce_log);
+
+	switch (rtas_error_severity(errp)) {
+	case RTAS_SEVERITY_NO_ERROR:
+		level = KERN_INFO;
+		sevstr = "Harmless";
+		break;
+	case RTAS_SEVERITY_WARNING:
+		level = KERN_WARNING;
+		sevstr = "";
+		break;
+	case RTAS_SEVERITY_ERROR:
+	case RTAS_SEVERITY_ERROR_SYNC:
+		level = KERN_ERR;
+		sevstr = "Severe";
+		break;
+	case RTAS_SEVERITY_FATAL:
+	default:
+		level = KERN_ERR;
+		sevstr = "Fatal";
+		break;
+	}
+
+	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+		disposition == RTAS_DISP_FULLY_RECOVERED ?
+		"Recovered" : "Not recovered");
+	if (user_mode(regs)) {
+		printk("%s  NIP: [%016lx] PID: %d Comm: %s\n", level,
+			regs->nip, current->pid, current->comm);
+	} else {
+		printk("%s  NIP [%016lx]: %pS\n", level, regs->nip,
+			(void *)regs->nip);
+	}
+	printk("%s  Initiator: %s\n", level,
+				VAL_TO_STRING(initiators, initiator));
+
+	switch (error_type) {
+	case PSERIES_MC_ERROR_TYPE_UE:
+		printk("%s  Error type: %s [%s]\n", level,
+			VAL_TO_STRING(mc_err_types, error_type),
+			VAL_TO_STRING(mc_ue_types, err_sub_type));
+		break;
+	case PSERIES_MC_ERROR_TYPE_SLB:
+		printk("%s  Error type: %s [%s]\n", level,
+			VAL_TO_STRING(mc_err_types, error_type),
+			VAL_TO_STRING(mc_slb_types, err_sub_type));
+		break;
+	case PSERIES_MC_ERROR_TYPE_ERAT:
+	case PSERIES_MC_ERROR_TYPE_TLB:
+		printk("%s  Error type: %s [%s]\n", level,
+			VAL_TO_STRING(mc_err_types, error_type),
+			VAL_TO_STRING(mc_soft_types, err_sub_type));
+		break;
+	default:
+		printk("%s  Error type: %s\n", level,
+			VAL_TO_STRING(mc_err_types, error_type));
+		break;
+	}
+
+	addr = rtas_mc_get_effective_addr(mce_log);
+	if (addr)
+		printk("%s    Effective address: %016llx\n", level, addr);
+}
+
+static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp)
 {
 	struct pseries_errorlog *pseries_log;
 	struct pseries_mc_errorlog *mce_log;

@@ -442,6 +565,7 @@ static int mce_handle_error(struct rtas_error_log *errp)
 		slb_flush_and_rebolt();
 		disposition = RTAS_DISP_FULLY_RECOVERED;
 	}
+	pseries_print_mce_info(regs, errp, disposition);
 
 out:
 	return disposition;

@@ -461,7 +585,7 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
 	int recovered = 0;
 	int disposition;
 
-	disposition = mce_handle_error(err);
+	disposition = mce_handle_error(regs, err);
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */

@@ -360,7 +360,7 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 	}
 
 	savep = __va(regs->gpr[3]);
-	regs->gpr[3] = savep[0];	/* restore original r3 */
+	regs->gpr[3] = be64_to_cpu(savep[0]);	/* restore original r3 */
 
 	/* If it isn't an extended log we can use the per cpu 64bit buffer */
 	h = (struct rtas_error_log *)&savep[1];