[PATCH v5 0/7] powerpc/pseries: Machien check handler improvements.

@@ -371,7 +371,7 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 		int len, error_log_length;
 
 		error_log_length = 8 + rtas_error_extended_log_length(h);
-		len = max_t(int, error_log_length, RTAS_ERROR_LOG_MAX);
+		len = min_t(int, error_log_length, RTAS_ERROR_LOG_MAX);
 		memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX);
 		memcpy(global_mce_data_buf, h, len);
 		errhdr = (struct rtas_error_log *)global_mce_data_buf;

@@ -251,6 +251,9 @@ struct paca_struct {
 	void *rfi_flush_fallback_area;
 	u64 l1d_flush_size;
 #endif
+#ifdef CONFIG_PPC_PSERIES
+	u8 *mce_data_buf;		/* buffer to hold per cpu rtas errlog */
+#endif /* CONFIG_PPC_PSERIES */
 } ____cacheline_aligned;
 
 extern void copy_mm_to_paca(struct mm_struct *mm);

@@ -22,6 +22,7 @@
 #include <linux/of.h>
 #include <linux/fs.h>
 #include <linux/reboot.h>
+#include <linux/irq_work.h>
 
 #include <asm/machdep.h>
 #include <asm/rtas.h>

@@ -32,11 +33,13 @@
 static unsigned char ras_log_buf[RTAS_ERROR_LOG_MAX];
 static DEFINE_SPINLOCK(ras_log_buf_lock);
 
-static char global_mce_data_buf[RTAS_ERROR_LOG_MAX];
-static DEFINE_PER_CPU(__u64, mce_data_buf);
-
 static int ras_check_exception_token;
 
+static void mce_process_errlog_event(struct irq_work *work);
+static struct irq_work mce_errlog_process_work = {
+	.func = mce_process_errlog_event,
+};
+
 #define EPOW_SENSOR_TOKEN	9
 #define EPOW_SENSOR_INDEX	0
 

@@ -330,16 +333,20 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 	((((A) >= 0x7000) && ((A) < 0x7ff0)) || \
 	(((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16))))
 
+static inline struct rtas_error_log *fwnmi_get_errlog(void)
+{
+	return (struct rtas_error_log *)local_paca->mce_data_buf;
+}
+
 /*
  * Get the error information for errors coming through the
  * FWNMI vectors.  The pt_regs' r3 will be updated to reflect
  * the actual r3 if possible, and a ptr to the error log entry
  * will be returned if found.
  *
- * If the RTAS error is not of the extended type, then we put it in a per
- * cpu 64bit buffer. If it is the extended type we use global_mce_data_buf.
+ * Use one buffer mce_data_buf per cpu to store RTAS error.
  *
- * The global_mce_data_buf does not have any locks or protection around it,
+ * The mce_data_buf does not have any locks or protection around it,
  * if a second machine check comes in, or a system reset is done
  * before we have logged the error, then we will get corruption in the
  * error log.  This is preferable over holding off on calling

@@ -349,7 +356,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 {
 	unsigned long *savep;
-	struct rtas_error_log *h, *errhdr = NULL;
+	struct rtas_error_log *h;
 
 	/* Mask top two bits */
 	regs->gpr[3] &= ~(0x3UL << 62);

@@ -362,22 +369,20 @@ 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 */
 
-	/* If it isn't an extended log we can use the per cpu 64bit buffer */
 	h = (struct rtas_error_log *)&savep[1];
+	/* Use the per cpu buffer from paca to store rtas error log */
+	memset(local_paca->mce_data_buf, 0, RTAS_ERROR_LOG_MAX);
 	if (!rtas_error_extended(h)) {
-		memcpy(this_cpu_ptr(&mce_data_buf), h, sizeof(__u64));
-		errhdr = (struct rtas_error_log *)this_cpu_ptr(&mce_data_buf);
+		memcpy(local_paca->mce_data_buf, h, sizeof(__u64));
 	} else {
 		int len, error_log_length;
 
 		error_log_length = 8 + rtas_error_extended_log_length(h);
 		len = min_t(int, error_log_length, RTAS_ERROR_LOG_MAX);
-		memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX);
-		memcpy(global_mce_data_buf, h, len);
-		errhdr = (struct rtas_error_log *)global_mce_data_buf;
+		memcpy(local_paca->mce_data_buf, h, len);
 	}
 
-	return errhdr;
+	return (struct rtas_error_log *)local_paca->mce_data_buf;
 }
 
 /* Call this when done with the data returned by FWNMI_get_errinfo.

@@ -422,6 +427,17 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 	return 0; /* need to perform reset */
 }
 
+/*
+ * Process MCE rtas errlog event.
+ */
+static void mce_process_errlog_event(struct irq_work *work)
+{
+	struct rtas_error_log *err;
+
+	err = fwnmi_get_errlog();
+	log_error((char *)err, ERR_TYPE_RTAS_LOG, 0);
+}
+
 /*
  * See if we can recover from a machine check exception.
  * This is only called on power4 (or above) and only via

@@ -466,7 +482,8 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
 		recovered = 1;
 	}
 
-	log_error((char *)err, ERR_TYPE_RTAS_LOG, 0);
+	/* Queue irq work to log this rtas event later. */
+	irq_work_queue(&mce_errlog_process_work);
 
 	return recovered;
 }

@@ -41,6 +41,7 @@
 #include <linux/root_dev.h>
 #include <linux/of.h>
 #include <linux/of_pci.h>
+#include <linux/memblock.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>

@@ -101,6 +102,9 @@ static void pSeries_show_cpuinfo(struct seq_file *m)
 static void __init fwnmi_init(void)
 {
 	unsigned long system_reset_addr, machine_check_addr;
+	u8 *mce_data_buf;
+	unsigned int i;
+	int nr_cpus = num_possible_cpus();
 
 	int ibm_nmi_register = rtas_token("ibm,nmi-register");
 	if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE)

@@ -114,6 +118,18 @@ static void __init fwnmi_init(void)
 	if (0 == rtas_call(ibm_nmi_register, 2, 1, NULL, system_reset_addr,
 				machine_check_addr))
 		fwnmi_active = 1;
+
+	/*
+	 * Allocate a chunk for per cpu buffer to hold rtas errorlog.
+	 * It will be used in real mode mce handler, hence it needs to be
+	 * below RMA.
+	 */
+	mce_data_buf = __va(memblock_alloc_base(RTAS_ERROR_LOG_MAX * nr_cpus,
+					RTAS_ERROR_LOG_MAX, ppc64_rma_size));
+	for_each_possible_cpu(i) {
+		paca_ptrs[i]->mce_data_buf = mce_data_buf +
+						(RTAS_ERROR_LOG_MAX * i);
+	}
 }
 
 static void pseries_8259_cascade(struct irq_desc *desc)

@@ -367,7 +367,7 @@ 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 */
 
 	h = (struct rtas_error_log *)&savep[1];
 	/* Use the per cpu buffer from paca to store rtas error log */

@@ -185,6 +185,13 @@ static inline uint8_t rtas_error_disposition(const struct rtas_error_log *elog)
 	return (elog->byte1 & 0x18) >> 3;
 }
 
+static inline
+void rtas_set_disposition_recovered(struct rtas_error_log *elog)
+{
+	elog->byte1 &= ~0x18;
+	elog->byte1 |= (RTAS_DISP_FULLY_RECOVERED << 3);
+}
+
 static inline uint8_t rtas_error_extended(const struct rtas_error_log *elog)
 {
 	return (elog->byte1 & 0x04) >> 2;

@@ -275,6 +282,7 @@ 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 +334,109 @@ 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_flush_and_rebolt_realmode(void);
 
 extern void slb_vmalloc_update(void);
 extern void slb_set_size(u16 size);

@@ -108,6 +108,7 @@ struct machdep_calls {
 
 	/* Early exception handlers called in realmode */
 	int		(*hmi_exception_early)(struct pt_regs *regs);
+	int		(*machine_check_early)(struct pt_regs *regs);
 
 	/* Called during machine check exception to retrive fixup address. */
 	bool		(*mce_check_early_recovery)(struct pt_regs *regs);

@@ -332,6 +332,9 @@ TRAMP_REAL_BEGIN(machine_check_pSeries)
 machine_check_fwnmi:
 	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_0(PACA_EXMC)
+BEGIN_FTR_SECTION
+	b	machine_check_pSeries_early
+END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
 machine_check_pSeries_0:
 	EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200)
 	/*

@@ -343,6 +346,45 @@ machine_check_pSeries_0:
 
 TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
 
+TRAMP_REAL_BEGIN(machine_check_pSeries_early)
+BEGIN_FTR_SECTION
+	EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
+	mr	r10,r1			/* Save r1 */
+	ld	r1,PACAMCEMERGSP(r13)	/* Use MC emergency stack */
+	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
+	mfspr	r11,SPRN_SRR0		/* Save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* Save SRR1 */
+	EXCEPTION_PROLOG_COMMON_1()
+	EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
+	EXCEPTION_PROLOG_COMMON_3(0x200)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	BRANCH_LINK_TO_FAR(machine_check_early) /* Function call ABI */
+
+	/* Move original SRR0 and SRR1 into the respective regs */
+	ld	r9,_MSR(r1)
+	mtspr	SPRN_SRR1,r9
+	ld	r3,_NIP(r1)
+	mtspr	SPRN_SRR0,r3
+	ld	r9,_CTR(r1)
+	mtctr	r9
+	ld	r9,_XER(r1)
+	mtxer	r9
+	ld	r9,_LINK(r1)
+	mtlr	r9
+	REST_GPR(0, r1)
+	REST_8GPRS(2, r1)
+	REST_GPR(10, r1)
+	ld	r11,_CCR(r1)
+	mtcr	r11
+	REST_GPR(11, r1)
+	REST_2GPRS(12, r1)
+	/* restore original r1. */
+	ld	r1,GPR1(r1)
+	SET_SCRATCH0(r13)		/* save r13 */
+	EXCEPTION_PROLOG_0(PACA_EXMC)
+	b	machine_check_pSeries_0
+END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
+
 EXC_COMMON_BEGIN(machine_check_common)
 	/*
 	 * Machine check is different because we use a different

@@ -488,9 +488,21 @@ long machine_check_early(struct pt_regs *regs)
 {
 	long handled = 0;
 
-	__this_cpu_inc(irq_stat.mce_exceptions);
+	/*
+	 * For pSeries we count mce when we go into virtual mode machine
+	 * check handler. Hence skip it. Also, We can't access per cpu
+	 * variables in real mode for LPAR.
+	 */
+	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+		__this_cpu_inc(irq_stat.mce_exceptions);
 
-	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
+	/*
+	 * See if platform is capable of handling machine check.
+	 * Otherwise fallthrough and allow CPU to handle this machine check.
+	 */
+	if (ppc_md.machine_check_early)
+		handled = ppc_md.machine_check_early(regs);
+	else if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
 	return handled;
 }

@@ -145,6 +145,12 @@ void slb_flush_and_rebolt(void)
 	get_paca()->slb_cache_ptr = 0;
 }
 
+void slb_flush_and_rebolt_realmode(void)
+{
+	__slb_flush_and_rebolt();
+	get_paca()->slb_cache_ptr = 0;
+}
+
 void slb_vmalloc_update(void)
 {
 	unsigned long vflags;

@@ -417,7 +417,6 @@ static int opal_recover_mce(struct pt_regs *regs,
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */
-		pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
 		recovered = 0;
 	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
 		/* Platform corrected itself */

@@ -24,6 +24,7 @@ struct pt_regs;
 
 extern int pSeries_system_reset_exception(struct pt_regs *regs);
 extern int pSeries_machine_check_exception(struct pt_regs *regs);
+extern int pSeries_machine_check_realmode(struct pt_regs *regs);
 
 #ifdef CONFIG_SMP
 extern void smp_init_pseries(void);

@@ -427,6 +427,35 @@ 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;
+
+	if (!rtas_error_extended(errp))
+		goto out;
+
+	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)) {
+		/* Store the old slb content someplace. */
+		slb_flush_and_rebolt_realmode();
+		disposition = RTAS_DISP_FULLY_RECOVERED;
+		rtas_set_disposition_recovered(errp);
+	}
+
+out:
+	return disposition;
+}
+
 /*
  * Process MCE rtas errlog event.
  */

@@ -503,11 +532,31 @@ int pSeries_machine_check_exception(struct pt_regs *regs)
 	struct rtas_error_log *errp;
 
 	if (fwnmi_active) {
-		errp = fwnmi_get_errinfo(regs);
 		fwnmi_release_errinfo();
+		errp = fwnmi_get_errlog();
 		if (errp && recover_mce(regs, errp))
 			return 1;
 	}
 
 	return 0;
 }
+
+int pSeries_machine_check_realmode(struct pt_regs *regs)
+{
+	struct rtas_error_log *errp;
+	int disposition;
+
+	if (fwnmi_active) {
+		errp = fwnmi_get_errinfo(regs);
+		/*
+		 * Call to fwnmi_release_errinfo() in real mode causes kernel
+		 * to panic. Hence we will call it as soon as we go into
+		 * virtual mode.
+		 */
+		disposition = mce_handle_error(errp);
+		if (disposition == RTAS_DISP_FULLY_RECOVERED)
+			return 1;
+	}
+
+	return 0;
+}

@@ -999,6 +999,7 @@ define_machine(pseries) {
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= rtas_progress,
 	.system_reset_exception = pSeries_system_reset_exception,
+	.machine_check_early	= pSeries_machine_check_realmode,
 	.machine_check_exception = pSeries_machine_check_exception,
 #ifdef CONFIG_KEXEC_CORE
 	.machine_kexec          = pSeries_machine_kexec,

@@ -197,6 +197,11 @@ 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

@@ -427,6 +427,135 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 	return 0; /* need to perform reset */
 }
 
+#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)
+{
+	const char *level, *sevstr;
+	struct pseries_errorlog *pseries_log;
+	struct pseries_mc_errorlog *mce_log;
+	uint8_t error_type, err_sub_type;
+	uint64_t addr;
+	uint8_t initiator = rtas_error_initiator(errp);
+	int disposition = rtas_error_disposition(errp);
+
+	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",
+	};
+
+	if (!rtas_error_extended(errp)) {
+		pr_err("Machine check interrupt: Missing extended error log\n");
+		return;
+	}
+
+	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 rtas_error_log *errp)
 {
 	struct pseries_errorlog *pseries_log;

@@ -481,6 +610,8 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
 	int recovered = 0;
 	int disposition = rtas_error_disposition(err);
 
+	pseries_print_mce_info(regs, err);
+
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */
 		recovered = 0;

@@ -485,9 +485,16 @@ static inline void hpte_init_pseries(void) { }
 
 extern void hpte_init_native(void);
 
+struct slb_entry {
+	u64	esid;
+	u64	vsid;
+};
+
 extern void slb_initialize(void);
 extern void slb_flush_and_rebolt(void);
 extern void slb_flush_and_rebolt_realmode(void);
+extern void slb_save_contents(struct slb_entry *slb_ptr);
+extern void slb_dump_contents(struct slb_entry *slb_ptr);
 
 extern void slb_vmalloc_update(void);
 extern void slb_set_size(u16 size);

@@ -253,6 +253,7 @@ struct paca_struct {
 #endif
 #ifdef CONFIG_PPC_PSERIES
 	u8 *mce_data_buf;		/* buffer to hold per cpu rtas errlog */
+	struct slb_entry *mce_faulty_slbs;
 #endif /* CONFIG_PPC_PSERIES */
 } ____cacheline_aligned;
 

@@ -151,6 +151,63 @@ void slb_flush_and_rebolt_realmode(void)
 	get_paca()->slb_cache_ptr = 0;
 }
 
+void slb_save_contents(struct slb_entry *slb_ptr)
+{
+	int i;
+	unsigned long e, v;
+
+	if (!slb_ptr)
+		return;
+
+	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));
+		slb_ptr->esid = e;
+		slb_ptr->vsid = v;
+		slb_ptr++;
+	}
+}
+
+void slb_dump_contents(struct slb_entry *slb_ptr)
+{
+	int i;
+	unsigned long e, v;
+	unsigned long llp;
+
+	if (!slb_ptr)
+		return;
+
+	pr_err("SLB contents of cpu 0x%x\n", smp_processor_id());
+
+	for (i = 0; i < mmu_slb_size; i++) {
+		e = slb_ptr->esid;
+		v = slb_ptr->vsid;
+		slb_ptr++;
+
+		if (!e && !v)
+			continue;
+
+		pr_err("%02d %016lx %016lx\n", 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;

@@ -515,6 +515,10 @@ static void pseries_print_mce_info(struct pt_regs *regs,
 		break;
 	}
 
+	/* Display faulty slb contents for SLB errors. */
+	if (error_type == PSERIES_MC_ERROR_TYPE_SLB)
+		slb_dump_contents(local_paca->mce_faulty_slbs);
+
 	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
 		disposition == RTAS_DISP_FULLY_RECOVERED ?
 		"Recovered" : "Not recovered");

@@ -575,7 +579,11 @@ static int mce_handle_error(struct rtas_error_log *errp)
 
 	if ((disposition == RTAS_DISP_NOT_RECOVERED) &&
 			(error_type == PSERIES_MC_ERROR_TYPE_SLB)) {
-		/* Store the old slb content someplace. */
+		/*
+		 * Store the old slb content in paca before flushing. Print
+		 * this when we go to virtual mode.
+		 */
+		slb_save_contents(local_paca->mce_faulty_slbs);
 		slb_flush_and_rebolt_realmode();
 		disposition = RTAS_DISP_FULLY_RECOVERED;
 		rtas_set_disposition_recovered(errp);

@@ -105,6 +105,9 @@ static void __init fwnmi_init(void)
 	u8 *mce_data_buf;
 	unsigned int i;
 	int nr_cpus = num_possible_cpus();
+	struct slb_entry *slb_ptr;
+	size_t size;
+
 
 	int ibm_nmi_register = rtas_token("ibm,nmi-register");
 	if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE)

@@ -130,6 +133,13 @@ static void __init fwnmi_init(void)
 		paca_ptrs[i]->mce_data_buf = mce_data_buf +
 						(RTAS_ERROR_LOG_MAX * i);
 	}
+
+	/* Allocate per cpu slb area to save old slb contents during MCE */
+	size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
+	slb_ptr = __va(memblock_alloc_base(size, sizeof(struct slb_entry),
+							ppc64_rma_size));
+	for_each_possible_cpu(i)
+		paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
 }
 
 static void pseries_8259_cascade(struct irq_desc *desc)