Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "So here's my next branch for powerpc.  A bit late as I was on vacation
  last week.  It's mostly the same stuff that was in next already, I
  just added two patches today which are the wiring up of lockref for
  powerpc, which for some reason fell through the cracks last time and
  is trivial.

  The highlights are, in addition to a bunch of bug fixes:

   - Reworked Machine Check handling on kernels running without a
     hypervisor (or acting as a hypervisor).  Provides hooks to handle
     some errors in real mode such as TLB errors, handle SLB errors,
     etc...

   - Support for retrieving memory error information from the service
     processor on IBM servers running without a hypervisor and routing
     them to the memory poison infrastructure.

   - _PAGE_NUMA support on server processors

   - 32-bit BookE relocatable kernel support

   - FSL e6500 hardware tablewalk support

   - A bunch of new/revived board support

   - FSL e6500 deeper idle states and altivec powerdown support

  You'll notice a generic mm change here, it has been acked by the
  relevant authorities and is a pre-req for our _PAGE_NUMA support"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (121 commits)
  powerpc: Implement arch_spin_is_locked() using arch_spin_value_unlocked()
  powerpc: Add support for the optimised lockref implementation
  powerpc/powernv: Call OPAL sync before kexec'ing
  powerpc/eeh: Escalate error on non-existing PE
  powerpc/eeh: Handle multiple EEH errors
  powerpc: Fix transactional FP/VMX/VSX unavailable handlers
  powerpc: Don't corrupt transactional state when using FP/VMX in kernel
  powerpc: Reclaim two unused thread_info flag bits
  powerpc: Fix races with irq_work
  Move precessing of MCE queued event out from syscall exit path.
  pseries/cpuidle: Remove redundant call to ppc64_runlatch_off() in cpu idle routines
  powerpc: Make add_system_ram_resources() __init
  powerpc: add SATA_MV to ppc64_defconfig
  powerpc/powernv: Increase candidate fw image size
  powerpc: Add debug checks to catch invalid cpu-to-node mappings
  powerpc: Fix the setup of CPU-to-Node mappings during CPU online
  powerpc/iommu: Don't detach device without IOMMU group
  powerpc/eeh: Hotplug improvement
  powerpc/eeh: Call opal_pci_reinit() on powernv for restoring config space
  powerpc/eeh: Add restore_config operation
  ...

14 files changed, 573 insertions, 389 deletions

diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 9fced3f6d2dc..895e8a20a3fc 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -13,11 +13,6 @@ config PPC_POWERNV
 	select ARCH_RANDOM
 	default y
 
-config POWERNV_MSI
-	bool "Support PCI MSI on PowerNV platform"
-	depends on PCI_MSI
-	default y
-
 config PPC_POWERNV_RTAS
 	depends on PPC_POWERNV
 	bool "Support for RTAS based PowerNV platforms such as BML"
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 873fa1370dc4..8d767fde5a6a 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
 obj-$(CONFIG_EEH)	+= eeh-ioda.o eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
+obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index d7ddcee7feb8..e1e71618b70c 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -14,7 +14,6 @@
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
@@ -578,11 +577,8 @@ static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
 		return -EIO;
 	}
 
-	/*
-	 * FIXME: We probably need log the error in somewhere.
-	 * Lets make it up in future.
-	 */
-	/* pr_info("%s", phb->diag.blob); */
+	/* The PHB diag-data is always indicative */
+	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
 
 	spin_unlock_irqrestore(&phb->lock, flags);
 
@@ -670,143 +666,9 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose)
 	}
 }
 
-static void ioda_eeh_p7ioc_phb_diag(struct pci_controller *hose,
-				    struct OpalIoPhbErrorCommon *common)
-{
-	struct OpalIoP7IOCPhbErrorData *data;
-	int i;
-
-	data = (struct OpalIoP7IOCPhbErrorData *)common;
-
-	pr_info("P7IOC PHB#%x Diag-data (Version: %d)\n\n",
-		hose->global_number, common->version);
-
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
-	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
-
-	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
-		if ((data->pestA[i] >> 63) == 0 &&
-		    (data->pestB[i] >> 63) == 0)
-			continue;
-
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
-	}
-}
-
-static void ioda_eeh_phb3_phb_diag(struct pci_controller *hose,
-				    struct OpalIoPhbErrorCommon *common)
-{
-	struct OpalIoPhb3ErrorData *data;
-	int i;
-
-	data = (struct OpalIoPhb3ErrorData*)common;
-	pr_info("PHB3 PHB#%x Diag-data (Version: %d)\n\n",
-		hose->global_number, common->version);
-
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-	pr_info("  nFir:                 %016llx\n", data->nFir);
-	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
-	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
-	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
-	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
-
-	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
-		if ((data->pestA[i] >> 63) == 0 &&
-		    (data->pestB[i] >> 63) == 0)
-			continue;
-
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
-	}
-}
-
 static void ioda_eeh_phb_diag(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
-	struct OpalIoPhbErrorCommon *common;
 	long rc;
 
 	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
@@ -817,18 +679,7 @@ static void ioda_eeh_phb_diag(struct pci_controller *hose)
 		return;
 	}
 
-	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
-	switch (common->ioType) {
-	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
-		ioda_eeh_p7ioc_phb_diag(hose, common);
-		break;
-	case OPAL_PHB_ERROR_DATA_TYPE_PHB3:
-		ioda_eeh_phb3_phb_diag(hose, common);
-		break;
-	default:
-		pr_warning("%s: Unrecognized I/O chip %d\n",
-			   __func__, common->ioType);
-	}
+	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
 }
 
 static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
@@ -862,11 +713,7 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	dev.phb = hose;
 	dev.pe_config_addr = pe_no;
 	dev_pe = eeh_pe_get(&dev);
-	if (!dev_pe) {
-		pr_warning("%s: Can't find PE for PHB#%x - PE#%x\n",
-			   __func__, hose->global_number, pe_no);
-		return -EEXIST;
-	}
+	if (!dev_pe) return -EEXIST;
 
 	*pe = dev_pe;
 	return 0;
@@ -884,12 +731,12 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
  */
 static int ioda_eeh_next_error(struct eeh_pe **pe)
 {
-	struct pci_controller *hose, *tmp;
+	struct pci_controller *hose;
 	struct pnv_phb *phb;
 	u64 frozen_pe_no;
 	u16 err_type, severity;
 	long rc;
-	int ret = 1;
+	int ret = EEH_NEXT_ERR_NONE;
 
 	/*
 	 * While running here, it's safe to purge the event queue.
@@ -899,7 +746,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 	eeh_remove_event(NULL);
 	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
 
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+	list_for_each_entry(hose, &hose_list, list_node) {
 		/*
 		 * If the subordinate PCI buses of the PHB has been
 		 * removed, we needn't take care of it any more.
@@ -938,19 +785,19 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		switch (err_type) {
 		case OPAL_EEH_IOC_ERROR:
 			if (severity == OPAL_EEH_SEV_IOC_DEAD) {
-				list_for_each_entry_safe(hose, tmp,
-						&hose_list, list_node) {
+				list_for_each_entry(hose, &hose_list,
+						    list_node) {
 					phb = hose->private_data;
 					phb->eeh_state |= PNV_EEH_STATE_REMOVED;
 				}
 
 				pr_err("EEH: dead IOC detected\n");
-				ret = 4;
-				goto out;
+				ret = EEH_NEXT_ERR_DEAD_IOC;
 			} else if (severity == OPAL_EEH_SEV_INF) {
 				pr_info("EEH: IOC informative error "
 					"detected\n");
 				ioda_eeh_hub_diag(hose);
+				ret = EEH_NEXT_ERR_NONE;
 			}
 
 			break;
@@ -962,37 +809,61 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 				pr_err("EEH: dead PHB#%x detected\n",
 					hose->global_number);
 				phb->eeh_state |= PNV_EEH_STATE_REMOVED;
-				ret = 3;
-				goto out;
+				ret = EEH_NEXT_ERR_DEAD_PHB;
 			} else if (severity == OPAL_EEH_SEV_PHB_FENCED) {
 				if (ioda_eeh_get_phb_pe(hose, pe))
 					break;
 
 				pr_err("EEH: fenced PHB#%x detected\n",
 					hose->global_number);
-				ret = 2;
-				goto out;
+				ret = EEH_NEXT_ERR_FENCED_PHB;
 			} else if (severity == OPAL_EEH_SEV_INF) {
 				pr_info("EEH: PHB#%x informative error "
 					"detected\n",
 					hose->global_number);
 				ioda_eeh_phb_diag(hose);
+				ret = EEH_NEXT_ERR_NONE;
 			}
 
 			break;
 		case OPAL_EEH_PE_ERROR:
-			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe))
-				break;
+			/*
+			 * If we can't find the corresponding PE, the
+			 * PEEV / PEST would be messy. So we force an
+			 * fenced PHB so that it can be recovered.
+			 */
+			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe)) {
+				if (!ioda_eeh_get_phb_pe(hose, pe)) {
+					pr_err("EEH: Escalated fenced PHB#%x "
+					       "detected for PE#%llx\n",
+						hose->global_number,
+						frozen_pe_no);
+					ret = EEH_NEXT_ERR_FENCED_PHB;
+				} else {
+					ret = EEH_NEXT_ERR_NONE;
+				}
+			} else {
+				pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
+					(*pe)->addr, (*pe)->phb->global_number);
+				ret = EEH_NEXT_ERR_FROZEN_PE;
+			}
 
-			pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
-				(*pe)->addr, (*pe)->phb->global_number);
-			ret = 1;
-			goto out;
+			break;
+		default:
+			pr_warn("%s: Unexpected error type %d\n",
+				__func__, err_type);
 		}
+
+		/*
+		 * If we have no errors on the specific PHB or only
+		 * informative error there, we continue poking it.
+		 * Otherwise, we need actions to be taken by upper
+		 * layer.
+		 */
+		if (ret > EEH_NEXT_ERR_INF)
+			break;
 	}
 
-	ret = 0;
-out:
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 73b981438cc5..a79fddc5e74e 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -344,6 +344,27 @@ static int powernv_eeh_next_error(struct eeh_pe **pe)
 	return -EEXIST;
 }
 
+static int powernv_eeh_restore_config(struct device_node *dn)
+{
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct pnv_phb *phb;
+	s64 ret;
+
+	if (!edev)
+		return -EEXIST;
+
+	phb = edev->phb->private_data;
+	ret = opal_pci_reinit(phb->opal_id,
+			      OPAL_REINIT_PCI_DEV, edev->config_addr);
+	if (ret) {
+		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
+			__func__, edev->config_addr, ret);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static struct eeh_ops powernv_eeh_ops = {
 	.name                   = "powernv",
 	.init                   = powernv_eeh_init,
@@ -359,7 +380,8 @@ static struct eeh_ops powernv_eeh_ops = {
 	.configure_bridge       = powernv_eeh_configure_bridge,
 	.read_config            = pnv_pci_cfg_read,
 	.write_config           = pnv_pci_cfg_write,
-	.next_error		= powernv_eeh_next_error
+	.next_error		= powernv_eeh_next_error,
+	.restore_config		= powernv_eeh_restore_config
 };
 
 /**
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index d8773079ce19..714ef972406b 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -76,8 +76,8 @@
 /* Validate buffer size */
 #define VALIDATE_BUF_SIZE	4096
 
-/* XXX: Assume candidate image size is <= 256MB */
-#define MAX_IMAGE_SIZE	0x10000000
+/* XXX: Assume candidate image size is <= 1GB */
+#define MAX_IMAGE_SIZE	0x40000000
 
 /* Flash sg list version */
 #define SG_LIST_VERSION (1UL)
@@ -103,27 +103,6 @@ struct image_header_t {
 	uint32_t	size;
 };
 
-/* Scatter/gather entry */
-struct opal_sg_entry {
-	void	*data;
-	long	length;
-};
-
-/* We calculate number of entries based on PAGE_SIZE */
-#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry))
-
-/*
- * This struct is very similar but not identical to that
- * needed by the opal flash update. All we need to do for
- * opal is rewrite num_entries into a version/length and
- * translate the pointers to absolute.
- */
-struct opal_sg_list {
-	unsigned long num_entries;
-	struct opal_sg_list *next;
-	struct opal_sg_entry entry[SG_ENTRIES_PER_NODE];
-};
-
 struct validate_flash_t {
 	int		status;		/* Return status */
 	void		*buf;		/* Candidate image buffer */
@@ -333,7 +312,7 @@ static struct opal_sg_list *image_data_to_sglist(void)
 	addr = image_data.data;
 	size = image_data.size;
 
-	sg1 = kzalloc((sizeof(struct opal_sg_list)), GFP_KERNEL);
+	sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!sg1)
 		return NULL;
 
@@ -351,8 +330,7 @@ static struct opal_sg_list *image_data_to_sglist(void)
 
 		sg1->num_entries++;
 		if (sg1->num_entries >= SG_ENTRIES_PER_NODE) {
-			sg1->next = kzalloc((sizeof(struct opal_sg_list)),
-					    GFP_KERNEL);
+			sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL);
 			if (!sg1->next) {
 				pr_err("%s : Failed to allocate memory\n",
 				       __func__);
@@ -402,7 +380,10 @@ static int opal_flash_update(int op)
 		else
 			sg->next = NULL;
 
-		/* Make num_entries into the version/length field */
+		/*
+		 * Convert num_entries to version/length format
+		 * to satisfy OPAL.
+		 */
 		sg->num_entries = (SG_LIST_VERSION << 56) |
 			(sg->num_entries * sizeof(struct opal_sg_entry) + 16);
 	}
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
new file mode 100644
index 000000000000..ec4132239cdf
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -0,0 +1,146 @@
+/*
+ * OPAL asynchronus Memory error handling support in PowreNV.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include <asm/opal.h>
+#include <asm/cputable.h>
+
+static int opal_mem_err_nb_init;
+static LIST_HEAD(opal_memory_err_list);
+static DEFINE_SPINLOCK(opal_mem_err_lock);
+
+struct OpalMsgNode {
+	struct list_head list;
+	struct opal_msg msg;
+};
+
+static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt)
+{
+	uint64_t paddr_start, paddr_end;
+
+	pr_debug("%s: Retrived memory error event, type: 0x%x\n",
+		  __func__, merr_evt->type);
+	switch (merr_evt->type) {
+	case OPAL_MEM_ERR_TYPE_RESILIENCE:
+		paddr_start = merr_evt->u.resilience.physical_address_start;
+		paddr_end = merr_evt->u.resilience.physical_address_end;
+		break;
+	case OPAL_MEM_ERR_TYPE_DYN_DALLOC:
+		paddr_start = merr_evt->u.dyn_dealloc.physical_address_start;
+		paddr_end = merr_evt->u.dyn_dealloc.physical_address_end;
+		break;
+	default:
+		return;
+	}
+
+	for (; paddr_start < paddr_end; paddr_start += PAGE_SIZE) {
+		memory_failure(paddr_start >> PAGE_SHIFT, 0, 0);
+	}
+}
+
+static void handle_memory_error(void)
+{
+	unsigned long flags;
+	struct OpalMemoryErrorData *merr_evt;
+	struct OpalMsgNode *msg_node;
+
+	spin_lock_irqsave(&opal_mem_err_lock, flags);
+	while (!list_empty(&opal_memory_err_list)) {
+		 msg_node = list_entry(opal_memory_err_list.next,
+					   struct OpalMsgNode, list);
+		list_del(&msg_node->list);
+		spin_unlock_irqrestore(&opal_mem_err_lock, flags);
+
+		merr_evt = (struct OpalMemoryErrorData *)
+					&msg_node->msg.params[0];
+		handle_memory_error_event(merr_evt);
+		kfree(msg_node);
+		spin_lock_irqsave(&opal_mem_err_lock, flags);
+	}
+	spin_unlock_irqrestore(&opal_mem_err_lock, flags);
+}
+
+static void mem_error_handler(struct work_struct *work)
+{
+	handle_memory_error();
+}
+
+static DECLARE_WORK(mem_error_work, mem_error_handler);
+
+/*
+ * opal_memory_err_event - notifier handler that queues up the opal message
+ * to be preocessed later.
+ */
+static int opal_memory_err_event(struct notifier_block *nb,
+			  unsigned long msg_type, void *msg)
+{
+	unsigned long flags;
+	struct OpalMsgNode *msg_node;
+
+	if (msg_type != OPAL_MSG_MEM_ERR)
+		return 0;
+
+	msg_node = kzalloc(sizeof(*msg_node), GFP_ATOMIC);
+	if (!msg_node) {
+		pr_err("MEMORY_ERROR: out of memory, Opal message event not"
+		       "handled\n");
+		return -ENOMEM;
+	}
+	memcpy(&msg_node->msg, msg, sizeof(struct opal_msg));
+
+	spin_lock_irqsave(&opal_mem_err_lock, flags);
+	list_add(&msg_node->list, &opal_memory_err_list);
+	spin_unlock_irqrestore(&opal_mem_err_lock, flags);
+
+	schedule_work(&mem_error_work);
+	return 0;
+}
+
+static struct notifier_block opal_mem_err_nb = {
+	.notifier_call	= opal_memory_err_event,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+static int __init opal_mem_err_init(void)
+{
+	int ret;
+
+	if (!opal_mem_err_nb_init) {
+		ret = opal_message_notifier_register(
+					OPAL_MSG_MEM_ERR, &opal_mem_err_nb);
+		if (ret) {
+			pr_err("%s: Can't register OPAL event notifier (%d)\n",
+			       __func__, ret);
+			return ret;
+		}
+		opal_mem_err_nb_init = 1;
+	}
+	return 0;
+}
+subsys_initcall(opal_mem_err_init);
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index 7d07c7e80ec0..b1885db8fdf3 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -18,6 +18,7 @@
 
 #include <asm/opal.h>
 #include <asm/firmware.h>
+#include <asm/machdep.h>
 
 static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
 {
@@ -48,8 +49,11 @@ unsigned long __init opal_get_boot_time(void)
 		else
 			mdelay(10);
 	}
-	if (rc != OPAL_SUCCESS)
+	if (rc != OPAL_SUCCESS) {
+		ppc_md.get_rtc_time = NULL;
+		ppc_md.set_rtc_time = NULL;
 		return 0;
+	}
 	y_m_d = be32_to_cpu(__y_m_d);
 	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, &tm);
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index e7806504e976..3e8829c40fbb 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -126,3 +126,6 @@ OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
 OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
 OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
 OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
+OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
+OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 1c798cd55372..65499adaecff 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -18,9 +18,12 @@
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 #include <linux/kobject.h>
+#include <linux/delay.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
+#include <asm/mce.h>
 
 #include "powernv.h"
 
@@ -38,6 +41,7 @@ extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
 static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
+static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX];
 static DEFINE_SPINLOCK(opal_notifier_lock);
 static uint64_t last_notified_mask = 0x0ul;
 static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
@@ -88,14 +92,10 @@ static int __init opal_register_exception_handlers(void)
 	if (!(powerpc_firmware_features & FW_FEATURE_OPAL))
 		return -ENODEV;
 
-	/* Hookup some exception handlers. We use the fwnmi area at 0x7000
-	 * to provide the glue space to OPAL
+	/* Hookup some exception handlers except machine check. We use the
+	 * fwnmi area at 0x7000 to provide the glue space to OPAL
 	 */
 	glue = 0x7000;
-	opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER,
-					__pa(opal_mc_secondary_handler[0]),
-					glue);
-	glue += 128;
 	opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
 					0, glue);
 	glue += 128;
@@ -169,6 +169,95 @@ void opal_notifier_disable(void)
 	atomic_set(&opal_notifier_hold, 1);
 }
 
+/*
+ * Opal message notifier based on message type. Allow subscribers to get
+ * notified for specific messgae type.
+ */
+int opal_message_notifier_register(enum OpalMessageType msg_type,
+					struct notifier_block *nb)
+{
+	if (!nb) {
+		pr_warning("%s: Invalid argument (%p)\n",
+			   __func__, nb);
+		return -EINVAL;
+	}
+	if (msg_type > OPAL_MSG_TYPE_MAX) {
+		pr_warning("%s: Invalid message type argument (%d)\n",
+			   __func__, msg_type);
+		return -EINVAL;
+	}
+	return atomic_notifier_chain_register(
+				&opal_msg_notifier_head[msg_type], nb);
+}
+
+static void opal_message_do_notify(uint32_t msg_type, void *msg)
+{
+	/* notify subscribers */
+	atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type],
+					msg_type, msg);
+}
+
+static void opal_handle_message(void)
+{
+	s64 ret;
+	/*
+	 * TODO: pre-allocate a message buffer depending on opal-msg-size
+	 * value in /proc/device-tree.
+	 */
+	static struct opal_msg msg;
+
+	ret = opal_get_msg(__pa(&msg), sizeof(msg));
+	/* No opal message pending. */
+	if (ret == OPAL_RESOURCE)
+		return;
+
+	/* check for errors. */
+	if (ret) {
+		pr_warning("%s: Failed to retrive opal message, err=%lld\n",
+				__func__, ret);
+		return;
+	}
+
+	/* Sanity check */
+	if (msg.msg_type > OPAL_MSG_TYPE_MAX) {
+		pr_warning("%s: Unknown message type: %u\n",
+				__func__, msg.msg_type);
+		return;
+	}
+	opal_message_do_notify(msg.msg_type, (void *)&msg);
+}
+
+static int opal_message_notify(struct notifier_block *nb,
+			  unsigned long events, void *change)
+{
+	if (events & OPAL_EVENT_MSG_PENDING)
+		opal_handle_message();
+	return 0;
+}
+
+static struct notifier_block opal_message_nb = {
+	.notifier_call	= opal_message_notify,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+static int __init opal_message_init(void)
+{
+	int ret, i;
+
+	for (i = 0; i < OPAL_MSG_TYPE_MAX; i++)
+		ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]);
+
+	ret = opal_notifier_register(&opal_message_nb);
+	if (ret) {
+		pr_err("%s: Can't register OPAL event notifier (%d)\n",
+		       __func__, ret);
+		return ret;
+	}
+	return 0;
+}
+early_initcall(opal_message_init);
+
 int opal_get_chars(uint32_t vtermno, char *buf, int count)
 {
 	s64 rc;
@@ -254,119 +343,62 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	return written;
 }
 
+static int opal_recover_mce(struct pt_regs *regs,
+					struct machine_check_event *evt)
+{
+	int recovered = 0;
+	uint64_t ea = get_mce_fault_addr(evt);
+
+	if (!(regs->msr & MSR_RI)) {
+		/* If MSR_RI isn't set, we cannot recover */
+		recovered = 0;
+	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
+		/* Platform corrected itself */
+		recovered = 1;
+	} else if (ea && !is_kernel_addr(ea)) {
+		/*
+		 * Faulting address is not in kernel text. We should be fine.
+		 * We need to find which process uses this address.
+		 * For now, kill the task if we have received exception when
+		 * in userspace.
+		 *
+		 * TODO: Queue up this address for hwpoisioning later.
+		 */
+		if (user_mode(regs) && !is_global_init(current)) {
+			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+			recovered = 1;
+		} else
+			recovered = 0;
+	} else if (user_mode(regs) && !is_global_init(current) &&
+		evt->severity == MCE_SEV_ERROR_SYNC) {
+		/*
+		 * If we have received a synchronous error when in userspace
+		 * kill the task.
+		 */
+		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+		recovered = 1;
+	}
+	return recovered;
+}
+
 int opal_machine_check(struct pt_regs *regs)
 {
-	struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt;
-	struct opal_machine_check_event evt;
-	const char *level, *sevstr, *subtype;
-	static const char *opal_mc_ue_types[] = {
-		"Indeterminate",
-		"Instruction fetch",
-		"Page table walk ifetch",
-		"Load/Store",
-		"Page table walk Load/Store",
-	};
-	static const char *opal_mc_slb_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-	static const char *opal_mc_erat_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-	static const char *opal_mc_tlb_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-
-	/* Copy the event structure and release the original */
-	evt = *opal_evt;
-	opal_evt->in_use = 0;
+	struct machine_check_event evt;
+
+	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+		return 0;
 
 	/* Print things out */
-	if (evt.version != OpalMCE_V1) {
+	if (evt.version != MCE_V1) {
 		pr_err("Machine Check Exception, Unknown event version %d !\n",
 		       evt.version);
 		return 0;
 	}
-	switch(evt.severity) {
-	case OpalMCE_SEV_NO_ERROR:
-		level = KERN_INFO;
-		sevstr = "Harmless";
-		break;
-	case OpalMCE_SEV_WARNING:
-		level = KERN_WARNING;
-		sevstr = "";
-		break;
-	case OpalMCE_SEV_ERROR_SYNC:
-		level = KERN_ERR;
-		sevstr = "Severe";
-		break;
-	case OpalMCE_SEV_FATAL:
-	default:
-		level = KERN_ERR;
-		sevstr = "Fatal";
-		break;
-	}
+	machine_check_print_event_info(&evt);
 
-	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
-	       evt.disposition == OpalMCE_DISPOSITION_RECOVERED ?
-	       "Recovered" : "[Not recovered");
-	printk("%s  Initiator: %s\n", level,
-	       evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown");
-	switch(evt.error_type) {
-	case OpalMCE_ERROR_TYPE_UE:
-		subtype = evt.u.ue_error.ue_error_type <
-			ARRAY_SIZE(opal_mc_ue_types) ?
-			opal_mc_ue_types[evt.u.ue_error.ue_error_type]
-			: "Unknown";
-		printk("%s  Error type: UE [%s]\n", level, subtype);
-		if (evt.u.ue_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.ue_error.effective_address);
-		if (evt.u.ue_error.physical_address_provided)
-			printk("%s      Physial address: %016llx\n",
-			       level, evt.u.ue_error.physical_address);
-		break;
-	case OpalMCE_ERROR_TYPE_SLB:
-		subtype = evt.u.slb_error.slb_error_type <
-			ARRAY_SIZE(opal_mc_slb_types) ?
-			opal_mc_slb_types[evt.u.slb_error.slb_error_type]
-			: "Unknown";
-		printk("%s  Error type: SLB [%s]\n", level, subtype);
-		if (evt.u.slb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.slb_error.effective_address);
-		break;
-	case OpalMCE_ERROR_TYPE_ERAT:
-		subtype = evt.u.erat_error.erat_error_type <
-			ARRAY_SIZE(opal_mc_erat_types) ?
-			opal_mc_erat_types[evt.u.erat_error.erat_error_type]
-			: "Unknown";
-		printk("%s  Error type: ERAT [%s]\n", level, subtype);
-		if (evt.u.erat_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.erat_error.effective_address);
-		break;
-	case OpalMCE_ERROR_TYPE_TLB:
-		subtype = evt.u.tlb_error.tlb_error_type <
-			ARRAY_SIZE(opal_mc_tlb_types) ?
-			opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
-			: "Unknown";
-		printk("%s  Error type: TLB [%s]\n", level, subtype);
-		if (evt.u.tlb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.tlb_error.effective_address);
-		break;
-	default:
-	case OpalMCE_ERROR_TYPE_UNKNOWN:
-		printk("%s  Error type: Unknown\n", level);
-		break;
-	}
-	return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1;
+	if (opal_recover_mce(regs, &evt))
+		return 1;
+	return 0;
 }
 
 static irqreturn_t opal_interrupt(int irq, void *data)
@@ -451,10 +483,25 @@ subsys_initcall(opal_init);
 void opal_shutdown(void)
 {
 	unsigned int i;
+	long rc = OPAL_BUSY;
 
+	/* First free interrupts, which will also mask them */
 	for (i = 0; i < opal_irq_count; i++) {
 		if (opal_irqs[i])
 			free_irq(opal_irqs[i], NULL);
 		opal_irqs[i] = 0;
 	}
+
+	/*
+	 * Then sync with OPAL which ensure anything that can
+	 * potentially write to our memory has completed such
+	 * as an ongoing dump retrieval
+	 */
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_sync_host_reboot();
+		if (rc == OPAL_BUSY)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 2c6d173842b2..7d6dcc6d5fa9 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -460,7 +460,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 		return;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
-	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
@@ -468,7 +468,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		set_iommu_table_base(&dev->dev, &pe->tce32_table);
+		set_iommu_table_base_and_group(&dev->dev, &pe->tce32_table);
 		if (dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
 	}
@@ -644,7 +644,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
 
 	if (pe->pdev)
-		set_iommu_table_base(&pe->pdev->dev, tbl);
+		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
@@ -723,7 +723,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
 
 	if (pe->pdev)
-		set_iommu_table_base(&pe->pdev->dev, tbl);
+		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
@@ -1144,7 +1144,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
-	unsigned long size, m32map_off, iomap_off, pemap_off;
+	unsigned long size, m32map_off, pemap_off, iomap_off = 0;
 	const __be64 *prop64;
 	const __be32 *prop32;
 	int len;
@@ -1231,7 +1231,6 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
 	m32map_off = size;
 	size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
-	iomap_off = size;
 	if (phb->type == PNV_PHB_IODA1) {
 		iomap_off = size;
 		size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index f8b4bd8afb2e..e3807d69393e 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -92,7 +92,7 @@ static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
 				pci_domain_nr(phb->hose->bus), phb->opal_id);
 	}
 
-	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
+	set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table);
 }
 
 static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 4eb33a9ed532..b555ebc57ef5 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -124,77 +124,157 @@ static void pnv_teardown_msi_irqs(struct pci_dev *pdev)
 }
 #endif /* CONFIG_PCI_MSI */
 
-static void pnv_pci_dump_p7ioc_diag_data(struct pnv_phb *phb)
+static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
+					 struct OpalIoPhbErrorCommon *common)
 {
-	struct OpalIoP7IOCPhbErrorData *data = &phb->diag.p7ioc;
+	struct OpalIoP7IOCPhbErrorData *data;
 	int i;
 
-	pr_info("PHB %d diagnostic data:\n", phb->hose->global_number);
-
-	pr_info("  brdgCtl              = 0x%08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg        = 0x%08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus      = 0x%08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus       = 0x%08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus         = 0x%08x\n", data->deviceStatus);
-	pr_info("  slotStatus           = 0x%08x\n", data->slotStatus);
-	pr_info("  linkStatus           = 0x%08x\n", data->linkStatus);
-	pr_info("  devCmdStatus         = 0x%08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus         = 0x%08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus      = 0x%08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus    = 0x%08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus      = 0x%08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1              = 0x%08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2              = 0x%08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3              = 0x%08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4              = 0x%08x\n", data->tlpHdr4);
-	pr_info("  sourceId             = 0x%08x\n", data->sourceId);
-
-	pr_info("  errorClass           = 0x%016llx\n", data->errorClass);
-	pr_info("  correlator           = 0x%016llx\n", data->correlator);
-
-	pr_info("  p7iocPlssr           = 0x%016llx\n", data->p7iocPlssr);
-	pr_info("  p7iocCsr             = 0x%016llx\n", data->p7iocCsr);
-	pr_info("  lemFir               = 0x%016llx\n", data->lemFir);
-	pr_info("  lemErrorMask         = 0x%016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF               = 0x%016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus       = 0x%016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus  = 0x%016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0         = 0x%016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1         = 0x%016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus      = 0x%016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus = 0x%016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0        = 0x%016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1        = 0x%016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus      = 0x%016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus = 0x%016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0        = 0x%016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1        = 0x%016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus      = 0x%016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus = 0x%016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0        = 0x%016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1        = 0x%016llx\n", data->dma1ErrorLog1);
+	data = (struct OpalIoP7IOCPhbErrorData *)common;
+	pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
+		hose->global_number, common->version);
+
+	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
+	pr_info("  slotStatus:           %08x\n", data->slotStatus);
+	pr_info("  linkStatus:           %08x\n", data->linkStatus);
+	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
+	pr_info("  sourceId:             %08x\n", data->sourceId);
+	pr_info("  errorClass:           %016llx\n", data->errorClass);
+	pr_info("  correlator:           %016llx\n", data->correlator);
+	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
+	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
+	pr_info("  lemFir:               %016llx\n", data->lemFir);
+	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
-		pr_info("  PE[%3d] PESTA        = 0x%016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB        = 0x%016llx\n", data->pestB[i]);
+
+		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+	}
+}
+
+static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose,
+					struct OpalIoPhbErrorCommon *common)
+{
+	struct OpalIoPhb3ErrorData *data;
+	int i;
+
+	data = (struct OpalIoPhb3ErrorData*)common;
+	pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
+		hose->global_number, common->version);
+
+	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
+	pr_info("  slotStatus:           %08x\n", data->slotStatus);
+	pr_info("  linkStatus:           %08x\n", data->linkStatus);
+	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
+	pr_info("  sourceId:             %08x\n", data->sourceId);
+	pr_info("  errorClass:           %016llx\n", data->errorClass);
+	pr_info("  correlator:           %016llx\n", data->correlator);
+
+	pr_info("  nFir:                 %016llx\n", data->nFir);
+	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
+	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
+	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
+	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
+	pr_info("  lemFir:               %016llx\n", data->lemFir);
+	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+
+	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
+		if ((data->pestA[i] >> 63) == 0 &&
+		    (data->pestB[i] >> 63) == 0)
+			continue;
+
+		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
 	}
 }
 
-static void pnv_pci_dump_phb_diag_data(struct pnv_phb *phb)
+void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
+				unsigned char *log_buff)
 {
-	switch(phb->model) {
-	case PNV_PHB_MODEL_P7IOC:
-		pnv_pci_dump_p7ioc_diag_data(phb);
+	struct OpalIoPhbErrorCommon *common;
+
+	if (!hose || !log_buff)
+		return;
+
+	common = (struct OpalIoPhbErrorCommon *)log_buff;
+	switch (common->ioType) {
+	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
+		pnv_pci_dump_p7ioc_diag_data(hose, common);
+		break;
+	case OPAL_PHB_ERROR_DATA_TYPE_PHB3:
+		pnv_pci_dump_phb3_diag_data(hose, common);
 		break;
 	default:
-		pr_warning("PCI %d: Can't decode this PHB diag data\n",
-			   phb->hose->global_number);
+		pr_warn("%s: Unrecognized ioType %d\n",
+			__func__, common->ioType);
 	}
 }
 
@@ -222,7 +302,7 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
 		 * with the normal errors generated when probing empty slots
 		 */
 		if (has_diag)
-			pnv_pci_dump_phb_diag_data(phb);
+			pnv_pci_dump_phb_diag_data(phb->hose, phb->diag.blob);
 		else
 			pr_warning("PCI %d: No diag data available\n",
 				   phb->hose->global_number);
@@ -484,7 +564,8 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 {
 	tbl->it_blocksize = 16;
 	tbl->it_base = (unsigned long)tce_mem;
-	tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT;
+	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
+	tbl->it_offset = dma_offset >> tbl->it_page_shift;
 	tbl->it_index = 0;
 	tbl->it_size = tce_size >> 3;
 	tbl->it_busno = 0;
@@ -536,7 +617,7 @@ static void pnv_pci_dma_fallback_setup(struct pci_controller *hose,
 		pdn->iommu_table = pnv_pci_setup_bml_iommu(hose);
 	if (!pdn->iommu_table)
 		return;
-	set_iommu_table_base(&pdev->dev, pdn->iommu_table);
+	set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table);
 }
 
 static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
@@ -657,3 +738,32 @@ void __init pnv_pci_init(void)
 	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
 #endif
 }
+
+static int tce_iommu_bus_notifier(struct notifier_block *nb,
+		unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		return iommu_add_device(dev);
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->iommu_group)
+			iommu_del_device(dev);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static struct notifier_block tce_iommu_bus_nb = {
+	.notifier_call = tce_iommu_bus_notifier,
+};
+
+static int __init tce_iommu_bus_notifier_init(void)
+{
+	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+	return 0;
+}
+
+subsys_initcall_sync(tce_iommu_bus_notifier_init);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 1ed8d5f40f5a..13f1942a9a5f 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -176,6 +176,7 @@ struct pnv_phb {
 	union {
 		unsigned char			blob[PNV_PCI_DIAG_BUF_SIZE];
 		struct OpalIoP7IOCPhbErrorData	p7ioc;
+		struct OpalIoPhb3ErrorData	phb3;
 		struct OpalIoP7IOCErrorData 	hub_diag;
 	} diag;
 
@@ -186,6 +187,8 @@ extern struct pci_ops pnv_pci_ops;
 extern struct pnv_eeh_ops ioda_eeh_ops;
 #endif
 
+void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
+				unsigned char *log_buff);
 int pnv_pci_cfg_read(struct device_node *dn,
 		     int where, int size, u32 *val);
 int pnv_pci_cfg_write(struct device_node *dn,
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 19884b2a51b4..a932feb2901c 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -145,8 +145,10 @@ static void pnv_shutdown(void)
 	/* Let the PCI code clear up IODA tables */
 	pnv_pci_shutdown();
 
-	/* And unregister all OPAL interrupts so they don't fire
-	 * up while we kexec
+	/*
+	 * Stop OPAL activity: Unregister all OPAL interrupts so they
+	 * don't fire up while we kexec and make sure all potentially
+	 * DMA'ing ops are complete (such as dump retrieval).
 	 */
 	opal_shutdown();
 }