Merge tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "This is a bit late, partly due to me travelling, and partly due to a
  power outage knocking out some of my test systems *while* I was
  travelling.

   - Initial support for running on a system with an Ultravisor, which
     is software that runs below the hypervisor and protects guests
     against some attacks by the hypervisor.

   - Support for building the kernel to run as a "Secure Virtual
     Machine", ie. as a guest capable of running on a system with an
     Ultravisor.

   - Some changes to our DMA code on bare metal, to allow devices with
     medium sized DMA masks (> 32 && < 59 bits) to use more than 2GB of
     DMA space.

   - Support for firmware assisted crash dumps on bare metal (powernv).

   - Two series fixing bugs in and refactoring our PCI EEH code.

   - A large series refactoring our exception entry code to use gas
     macros, both to make it more readable and also enable some future
     optimisations.

  As well as many cleanups and other minor features & fixups.

  Thanks to: Adam Zerella, Alexey Kardashevskiy, Alistair Popple, Andrew
  Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Anshuman Khandual,
  Balbir Singh, Benjamin Herrenschmidt, Cédric Le Goater, Christophe
  JAILLET, Christophe Leroy, Christopher M. Riedl, Christoph Hellwig,
  Claudio Carvalho, Daniel Axtens, David Gibson, David Hildenbrand,
  Desnes A. Nunes do Rosario, Ganesh Goudar, Gautham R. Shenoy, Greg
  Kurz, Guerney Hunt, Gustavo Romero, Halil Pasic, Hari Bathini, Joakim
  Tjernlund, Jonathan Neuschafer, Jordan Niethe, Leonardo Bras, Lianbo
  Jiang, Madhavan Srinivasan, Mahesh Salgaonkar, Mahesh Salgaonkar,
  Masahiro Yamada, Maxiwell S. Garcia, Michael Anderson, Nathan
  Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Oliver
  O'Halloran, Qian Cai, Ram Pai, Ravi Bangoria, Reza Arbab, Ryan Grimm,
  Sam Bobroff, Santosh Sivaraj, Segher Boessenkool, Sukadev Bhattiprolu,
  Thiago Bauermann, Thiago Jung Bauermann, Thomas Gleixner, Tom
  Lendacky, Vasant Hegde"

* tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (264 commits)
  powerpc/mm/mce: Keep irqs disabled during lockless page table walk
  powerpc: Use ftrace_graph_ret_addr() when unwinding
  powerpc/ftrace: Enable HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
  ftrace: Look up the address of return_to_handler() using helpers
  powerpc: dump kernel log before carrying out fadump or kdump
  docs: powerpc: Add missing documentation reference
  powerpc/xmon: Fix output of XIVE IPI
  powerpc/xmon: Improve output of XIVE interrupts
  powerpc/mm/radix: remove useless kernel messages
  powerpc/fadump: support holes in kernel boot memory area
  powerpc/fadump: remove RMA_START and RMA_END macros
  powerpc/fadump: update documentation about option to release opalcore
  powerpc/fadump: consider f/w load area
  powerpc/opalcore: provide an option to invalidate /sys/firmware/opal/core file
  powerpc/opalcore: export /sys/firmware/opal/core for analysing opal crashes
  powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP
  powerpc/fadump: add support to preserve crash data on FADUMP disabled kernel
  powerpc/fadump: improve how crashed kernel's memory is reserved
  powerpc/fadump: consider reserved ranges while releasing memory
  powerpc/fadump: make crash memory ranges array allocation generic
  ...

15 files changed, 1078 insertions, 334 deletions

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index f7b484f55553..9e35cddddf73 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -145,3 +145,17 @@ config PAPR_SCM
 	tristate "Support for the PAPR Storage Class Memory interface"
 	help
 	  Enable access to hypervisor provided storage class memory.
+
+config PPC_SVM
+	bool "Secure virtual machine (SVM) support for POWER"
+	depends on PPC_PSERIES
+	select SWIOTLB
+	select ARCH_HAS_MEM_ENCRYPT
+	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
+	help
+	 There are certain POWER platforms which support secure guests using
+	 the Protected Execution Facility, with the help of an Ultravisor
+	 executing below the hypervisor layer. This enables support for
+	 those guests.
+
+	 If unsure, say "N".
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index ab3d59aeacca..a3c74a5cf20d 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -26,6 +26,8 @@ obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)		+= ibmebus.o
 obj-$(CONFIG_PAPR_SCM)		+= papr_scm.o
 obj-$(CONFIG_PPC_SPLPAR)	+= vphn.o
+obj-$(CONFIG_PPC_SVM)		+= svm.o
+obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 
 ifdef CONFIG_PPC_PSERIES
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 9edae1863e2f..893ba3f562c4 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -42,42 +42,44 @@ static int ibm_get_config_addr_info;
 static int ibm_get_config_addr_info2;
 static int ibm_configure_pe;
 
-#ifdef CONFIG_PCI_IOV
 void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
-	struct pci_dn *physfn_pdn;
-	struct eeh_dev *edev;
 
-	if (!pdev->is_virtfn)
+	if (eeh_has_flag(EEH_FORCE_DISABLED))
 		return;
 
-	pdn->device_id  =  pdev->device;
-	pdn->vendor_id  =  pdev->vendor;
-	pdn->class_code =  pdev->class;
-	/*
-	 * Last allow unfreeze return code used for retrieval
-	 * by user space in eeh-sysfs to show the last command
-	 * completion from platform.
-	 */
-	pdn->last_allow_rc =  0;
-	physfn_pdn      =  pci_get_pdn(pdev->physfn);
-	pdn->pe_number  =  physfn_pdn->pe_num_map[pdn->vf_index];
-	edev = pdn_to_eeh_dev(pdn);
+	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
+#ifdef CONFIG_PCI_IOV
+	if (pdev->is_virtfn) {
+		struct pci_dn *physfn_pdn;
 
-	/*
-	 * The following operations will fail if VF's sysfs files
-	 * aren't created or its resources aren't finalized.
-	 */
+		pdn->device_id  =  pdev->device;
+		pdn->vendor_id  =  pdev->vendor;
+		pdn->class_code =  pdev->class;
+		/*
+		 * Last allow unfreeze return code used for retrieval
+		 * by user space in eeh-sysfs to show the last command
+		 * completion from platform.
+		 */
+		pdn->last_allow_rc =  0;
+		physfn_pdn      =  pci_get_pdn(pdev->physfn);
+		pdn->pe_number  =  physfn_pdn->pe_num_map[pdn->vf_index];
+	}
+#endif
 	eeh_add_device_early(pdn);
 	eeh_add_device_late(pdev);
-	edev->pe_config_addr =  (pdn->busno << 16) | (pdn->devfn << 8);
-	eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */
-	eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
-	eeh_sysfs_add_device(pdev);
+#ifdef CONFIG_PCI_IOV
+	if (pdev->is_virtfn) {
+		struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
-}
+		edev->pe_config_addr =  (pdn->busno << 16) | (pdn->devfn << 8);
+		eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */
+		eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
+	}
 #endif
+	eeh_sysfs_add_device(pdev);
+}
 
 /*
  * Buffer for reporting slot-error-detail rtas calls. Its here
@@ -144,10 +146,8 @@ static int pseries_eeh_init(void)
 	/* Set EEH probe mode */
 	eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG);
 
-#ifdef CONFIG_PCI_IOV
 	/* Set EEH machine dependent code */
 	ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device;
-#endif
 
 	return 0;
 }
@@ -251,6 +251,8 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
         if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
 		return NULL;
 
+	eeh_edev_dbg(edev, "Probing device\n");
+
 	/*
 	 * Update class code and mode of eeh device. We need
 	 * correctly reflects that current device is root port
@@ -280,8 +282,11 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
 	pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8);
 
 	/* Enable EEH on the device */
+	eeh_edev_dbg(edev, "Enabling EEH on device\n");
 	ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE);
-	if (!ret) {
+	if (ret) {
+		eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret);
+	} else {
 		/* Retrieve PE address */
 		edev->pe_config_addr = eeh_ops->get_pe_addr(&pe);
 		pe.addr = edev->pe_config_addr;
@@ -297,11 +302,6 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
 		if (enable) {
 			eeh_add_flag(EEH_ENABLED);
 			eeh_add_to_parent_pe(edev);
-
-			pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%x-PE#%x\n",
-				__func__, pdn->busno, PCI_SLOT(pdn->devfn),
-				PCI_FUNC(pdn->devfn), pe.phb->global_number,
-				pe.addr);
 		} else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) &&
 			   (pdn_to_eeh_dev(pdn->parent))->pe) {
 			/* This device doesn't support EEH, but it may have an
@@ -310,6 +310,8 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
 			edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr;
 			eeh_add_to_parent_pe(edev);
 		}
+		eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n",
+			     (enable ? "enabled" : "unsupported"), ret);
 	}
 
 	/* Save memory bars */
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 46d0d35b9ca4..8e700390f3d6 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -880,34 +880,44 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 
 	switch (hp_elog->action) {
 	case PSERIES_HP_ELOG_ACTION_ADD:
-		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) {
+		switch (hp_elog->id_type) {
+		case PSERIES_HP_ELOG_ID_DRC_COUNT:
 			count = hp_elog->_drc_u.drc_count;
 			rc = dlpar_memory_add_by_count(count);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_INDEX:
 			drc_index = hp_elog->_drc_u.drc_index;
 			rc = dlpar_memory_add_by_index(drc_index);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_IC:
 			count = hp_elog->_drc_u.ic.count;
 			drc_index = hp_elog->_drc_u.ic.index;
 			rc = dlpar_memory_add_by_ic(count, drc_index);
-		} else {
+			break;
+		default:
 			rc = -EINVAL;
+			break;
 		}
 
 		break;
 	case PSERIES_HP_ELOG_ACTION_REMOVE:
-		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) {
+		switch (hp_elog->id_type) {
+		case PSERIES_HP_ELOG_ID_DRC_COUNT:
 			count = hp_elog->_drc_u.drc_count;
 			rc = dlpar_memory_remove_by_count(count);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_INDEX:
 			drc_index = hp_elog->_drc_u.drc_index;
 			rc = dlpar_memory_remove_by_index(drc_index);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_IC:
 			count = hp_elog->_drc_u.ic.count;
 			drc_index = hp_elog->_drc_u.ic.index;
 			rc = dlpar_memory_remove_by_ic(count, drc_index);
-		} else {
+			break;
+		default:
 			rc = -EINVAL;
+			break;
 		}
 
 		break;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 889dc2e44b89..6ba081dd61c9 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -36,6 +36,7 @@
 #include <asm/udbg.h>
 #include <asm/mmzone.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/svm.h>
 
 #include "pseries.h"
 
@@ -609,7 +610,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	tbl->it_ops = &iommu_table_pseries_ops;
-	iommu_init_table(tbl, pci->phb->node);
+	iommu_init_table(tbl, pci->phb->node, 0, 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -621,7 +622,8 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 #ifdef CONFIG_IOMMU_API
 static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
-				long *tce, enum dma_data_direction *direction)
+				long *tce, enum dma_data_direction *direction,
+				bool realmode)
 {
 	long rc;
 	unsigned long ioba = (unsigned long) index << tbl->it_page_shift;
@@ -649,7 +651,7 @@ static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
 struct iommu_table_ops iommu_table_lpar_multi_ops = {
 	.set = tce_buildmulti_pSeriesLP,
 #ifdef CONFIG_IOMMU_API
-	.exchange = tce_exchange_pseries,
+	.xchg_no_kill = tce_exchange_pseries,
 #endif
 	.clear = tce_freemulti_pSeriesLP,
 	.get = tce_get_pSeriesLP
@@ -690,7 +692,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
 				ppci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, ppci->phb->node);
+		iommu_init_table(tbl, ppci->phb->node, 0, 0);
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -719,7 +721,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
 		tbl->it_ops = &iommu_table_pseries_ops;
-		iommu_init_table(tbl, phb->node);
+		iommu_init_table(tbl, phb->node, 0, 0);
 		set_iommu_table_base(&dev->dev, tbl);
 		return;
 	}
@@ -1169,7 +1171,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
 				pci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, pci->phb->node);
+		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
 				pci_domain_nr(pci->phb->bus), 0);
 		pr_debug("  created table: %p\n", pci->table_group);
@@ -1318,7 +1320,15 @@ void iommu_init_early_pSeries(void)
 	of_reconfig_notifier_register(&iommu_reconfig_nb);
 	register_memory_notifier(&iommu_mem_nb);
 
-	set_pci_dma_ops(&dma_iommu_ops);
+	/*
+	 * Secure guest memory is inacessible to devices so regular DMA isn't
+	 * possible.
+	 *
+	 * In that case keep devices' dma_map_ops as NULL so that the generic
+	 * DMA code path will use SWIOTLB to bounce buffers for DMA.
+	 */
+	if (!is_secure_guest())
+		set_pci_dma_ops(&dma_iommu_ops);
 }
 
 static int __init disable_multitce(char *str)
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 09bb878c21e0..36b846f6e74e 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -1413,7 +1413,10 @@ static int pseries_lpar_resize_hpt_commit(void *data)
 	return 0;
 }
 
-/* Must be called in user context */
+/*
+ * Must be called in process context. The caller must hold the
+ * cpus_lock.
+ */
 static int pseries_lpar_resize_hpt(unsigned long shift)
 {
 	struct hpt_resize_state state = {
@@ -1467,7 +1470,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift)
 
 	t1 = ktime_get();
 
-	rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL);
+	rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit,
+				     &state, NULL);
 
 	t2 = ktime_get();
 
@@ -1527,16 +1531,24 @@ void __init hpte_init_pseries(void)
 	mmu_hash_ops.flush_hash_range	 = pSeries_lpar_flush_hash_range;
 	mmu_hash_ops.hpte_clear_all      = pseries_hpte_clear_all;
 	mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
-	register_process_table		 = pseries_lpar_register_process_table;
 
 	if (firmware_has_feature(FW_FEATURE_HPT_RESIZE))
 		mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
+
+	/*
+	 * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall
+	 * to inform the hypervisor that we wish to use the HPT.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		pseries_lpar_register_process_table(0, 0, 0);
 }
 
 void radix_init_pseries(void)
 {
 	pr_info("Using radix MMU under hypervisor\n");
-	register_process_table = pseries_lpar_register_process_table;
+
+	pseries_lpar_register_process_table(__pa(process_tb),
+						0, PRTB_SIZE_SHIFT - 12);
 }
 
 #ifdef CONFIG_PPC_SMLPAR
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index fe812bebdf5e..b571285f6c14 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -9,6 +9,7 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/kobject.h>
+#include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/stat.h>
 #include <linux/completion.h>
@@ -207,7 +208,11 @@ static int update_dt_node(__be32 phandle, s32 scope)
 
 				prop_data += vd;
 			}
+
+			cond_resched();
 		}
+
+		cond_resched();
 	} while (rtas_rc == 1);
 
 	of_node_put(dn);
@@ -310,8 +315,12 @@ int pseries_devicetree_update(s32 scope)
 					add_dt_node(phandle, drc_index);
 					break;
 				}
+
+				cond_resched();
 			}
 		}
+
+		cond_resched();
 	} while (rc == 1);
 
 	kfree(rtas_buf);
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 1eae1d09980c..722830978639 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -229,8 +229,7 @@ void __init pSeries_final_fixup(void)
 
 	pSeries_request_regions();
 
-	eeh_probe_devices();
-	eeh_addr_cache_build();
+	eeh_show_enabled();
 
 #ifdef CONFIG_PCI_IOV
 	ppc_md.pcibios_sriov_enable = pseries_pcibios_sriov_enable;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index f16fdd0f71f7..3acdcc3bb908 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -76,6 +76,7 @@ struct pseries_mc_errorlog {
 #define MC_ERROR_TYPE_UE		0x00
 #define MC_ERROR_TYPE_SLB		0x01
 #define MC_ERROR_TYPE_ERAT		0x02
+#define MC_ERROR_TYPE_UNKNOWN		0x03
 #define MC_ERROR_TYPE_TLB		0x04
 #define MC_ERROR_TYPE_D_CACHE		0x05
 #define MC_ERROR_TYPE_I_CACHE		0x07
@@ -87,6 +88,9 @@ struct pseries_mc_errorlog {
 #define MC_ERROR_UE_LOAD_STORE			3
 #define MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE	4
 
+#define UE_EFFECTIVE_ADDR_PROVIDED		0x40
+#define UE_LOGICAL_ADDR_PROVIDED		0x20
+
 #define MC_ERROR_SLB_PARITY		0
 #define MC_ERROR_SLB_MULTIHIT		1
 #define MC_ERROR_SLB_INDETERMINATE	2
@@ -113,27 +117,6 @@ static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog)
 	}
 }
 
-static
-inline u64 rtas_mc_get_effective_addr(const struct pseries_mc_errorlog *mlog)
-{
-	__be64 addr = 0;
-
-	switch (mlog->error_type) {
-	case	MC_ERROR_TYPE_UE:
-		if (mlog->sub_err_type & 0x40)
-			addr = mlog->effective_address;
-		break;
-	case	MC_ERROR_TYPE_SLB:
-	case	MC_ERROR_TYPE_ERAT:
-	case	MC_ERROR_TYPE_TLB:
-		if (mlog->sub_err_type & 0x80)
-			addr = mlog->effective_address;
-	default:
-		break;
-	}
-	return be64_to_cpu(addr);
-}
-
 /*
  * Enable the hotplug interrupt late because processing them may touch other
  * devices or systems (e.g. hugepages) that have not been initialized at the
@@ -511,160 +494,165 @@ 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)
+static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp)
 {
-	const char *level, *sevstr;
+	struct mce_error_info mce_err = { 0 };
+	unsigned long eaddr = 0, paddr = 0;
 	struct pseries_errorlog *pseries_log;
 	struct pseries_mc_errorlog *mce_log;
-	u8 error_type, err_sub_type;
-	u64 addr;
-	u8 initiator = rtas_error_initiator(errp);
 	int disposition = rtas_error_disposition(errp);
+	int initiator = rtas_error_initiator(errp);
+	int severity = rtas_error_severity(errp);
+	u8 error_type, err_sub_type;
 
-	static const char * const initiators[] = {
-		[0] = "Unknown",
-		[1] = "CPU",
-		[2] = "PCI",
-		[3] = "ISA",
-		[4] = "Memory",
-		[5] = "Power Mgmt",
-	};
-	static const char * const mc_err_types[] = {
-		[0] = "UE",
-		[1] = "SLB",
-		[2] = "ERAT",
-		[3] = "Unknown",
-		[4] = "TLB",
-		[5] = "D-Cache",
-		[6] = "Unknown",
-		[7] = "I-Cache",
-	};
-	static const char * const mc_ue_types[] = {
-		[0] = "Indeterminate",
-		[1] = "Instruction fetch",
-		[2] = "Page table walk ifetch",
-		[3] = "Load/Store",
-		[4] = "Page table walk Load/Store",
-	};
-
-	/* SLB sub errors valid values are 0x0, 0x1, 0x2 */
-	static const char * const mc_slb_types[] = {
-		[0] = "Parity",
-		[1] = "Multihit",
-		[2] = "Indeterminate",
-	};
-
-	/* TLB and ERAT sub errors valid values are 0x1, 0x2, 0x3 */
-	static const char * const mc_soft_types[] = {
-		[0] = "Unknown",
-		[1] = "Parity",
-		[2] = "Multihit",
-		[3] = "Indeterminate",
-	};
-
-	if (!rtas_error_extended(errp)) {
-		pr_err("Machine check interrupt: Missing extended error log\n");
-		return;
-	}
+	if (initiator == RTAS_INITIATOR_UNKNOWN)
+		mce_err.initiator = MCE_INITIATOR_UNKNOWN;
+	else if (initiator == RTAS_INITIATOR_CPU)
+		mce_err.initiator = MCE_INITIATOR_CPU;
+	else if (initiator == RTAS_INITIATOR_PCI)
+		mce_err.initiator = MCE_INITIATOR_PCI;
+	else if (initiator == RTAS_INITIATOR_ISA)
+		mce_err.initiator = MCE_INITIATOR_ISA;
+	else if (initiator == RTAS_INITIATOR_MEMORY)
+		mce_err.initiator = MCE_INITIATOR_MEMORY;
+	else if (initiator == RTAS_INITIATOR_POWERMGM)
+		mce_err.initiator = MCE_INITIATOR_POWERMGM;
+	else
+		mce_err.initiator = MCE_INITIATOR_UNKNOWN;
+
+	if (severity == RTAS_SEVERITY_NO_ERROR)
+		mce_err.severity = MCE_SEV_NO_ERROR;
+	else if (severity == RTAS_SEVERITY_EVENT)
+		mce_err.severity = MCE_SEV_WARNING;
+	else if (severity == RTAS_SEVERITY_WARNING)
+		mce_err.severity = MCE_SEV_WARNING;
+	else if (severity == RTAS_SEVERITY_ERROR_SYNC)
+		mce_err.severity = MCE_SEV_SEVERE;
+	else if (severity == RTAS_SEVERITY_ERROR)
+		mce_err.severity = MCE_SEV_SEVERE;
+	else if (severity == RTAS_SEVERITY_FATAL)
+		mce_err.severity = MCE_SEV_FATAL;
+	else
+		mce_err.severity = MCE_SEV_FATAL;
+
+	if (severity <= RTAS_SEVERITY_ERROR_SYNC)
+		mce_err.sync_error = true;
+	else
+		mce_err.sync_error = false;
+
+	mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN;
+	mce_err.error_class = MCE_ECLASS_UNKNOWN;
+
+	if (!rtas_error_extended(errp))
+		goto out;
 
 	pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
 	if (pseries_log == NULL)
-		return;
+		goto out;
 
 	mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
-
 	error_type = mce_log->error_type;
 	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;
-	}
+	switch (mce_log->error_type) {
+	case MC_ERROR_TYPE_UE:
+		mce_err.error_type = MCE_ERROR_TYPE_UE;
+		switch (err_sub_type) {
+		case MC_ERROR_UE_IFETCH:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_IFETCH;
+			break;
+		case MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+			break;
+		case MC_ERROR_UE_LOAD_STORE:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+			break;
+		case MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+			break;
+		case MC_ERROR_UE_INDETERMINATE:
+		default:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED)
+			eaddr = be64_to_cpu(mce_log->effective_address);
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	/* Display faulty slb contents for SLB errors. */
-	if (error_type == MC_ERROR_TYPE_SLB)
-		slb_dump_contents(local_paca->mce_faulty_slbs);
-#endif
+		if (mce_log->sub_err_type & UE_LOGICAL_ADDR_PROVIDED) {
+			paddr = be64_to_cpu(mce_log->logical_address);
+		} else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) {
+			unsigned long pfn;
 
-	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));
+			pfn = addr_to_pfn(regs, eaddr);
+			if (pfn != ULONG_MAX)
+				paddr = pfn << PAGE_SHIFT;
+		}
 
-	switch (error_type) {
-	case 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 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));
+		mce_err.error_type = MCE_ERROR_TYPE_SLB;
+		switch (err_sub_type) {
+		case MC_ERROR_SLB_PARITY:
+			mce_err.u.slb_error_type = MCE_SLB_ERROR_PARITY;
+			break;
+		case MC_ERROR_SLB_MULTIHIT:
+			mce_err.u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+			break;
+		case MC_ERROR_SLB_INDETERMINATE:
+		default:
+			mce_err.u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & 0x80)
+			eaddr = be64_to_cpu(mce_log->effective_address);
 		break;
 	case MC_ERROR_TYPE_ERAT:
+		mce_err.error_type = MCE_ERROR_TYPE_ERAT;
+		switch (err_sub_type) {
+		case MC_ERROR_ERAT_PARITY:
+			mce_err.u.erat_error_type = MCE_ERAT_ERROR_PARITY;
+			break;
+		case MC_ERROR_ERAT_MULTIHIT:
+			mce_err.u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+			break;
+		case MC_ERROR_ERAT_INDETERMINATE:
+		default:
+			mce_err.u.erat_error_type = MCE_ERAT_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & 0x80)
+			eaddr = be64_to_cpu(mce_log->effective_address);
+		break;
 	case 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));
+		mce_err.error_type = MCE_ERROR_TYPE_TLB;
+		switch (err_sub_type) {
+		case MC_ERROR_TLB_PARITY:
+			mce_err.u.tlb_error_type = MCE_TLB_ERROR_PARITY;
+			break;
+		case MC_ERROR_TLB_MULTIHIT:
+			mce_err.u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+			break;
+		case MC_ERROR_TLB_INDETERMINATE:
+		default:
+			mce_err.u.tlb_error_type = MCE_TLB_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & 0x80)
+			eaddr = be64_to_cpu(mce_log->effective_address);
+		break;
+	case MC_ERROR_TYPE_D_CACHE:
+		mce_err.error_type = MCE_ERROR_TYPE_DCACHE;
 		break;
+	case MC_ERROR_TYPE_I_CACHE:
+		mce_err.error_type = MCE_ERROR_TYPE_DCACHE;
+		break;
+	case MC_ERROR_TYPE_UNKNOWN:
 	default:
-		printk("%s  Error type: %s\n", level,
-		       VAL_TO_STRING(mc_err_types, error_type));
+		mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN;
 		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;
-	struct pseries_mc_errorlog *mce_log;
-	int disposition = rtas_error_disposition(errp);
-	u8 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 = mce_log->error_type;
-
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (disposition == RTAS_DISP_NOT_RECOVERED) {
 		switch (error_type) {
@@ -682,98 +670,24 @@ static int mce_handle_error(struct rtas_error_log *errp)
 				slb_save_contents(local_paca->mce_faulty_slbs);
 			flush_and_reload_slb();
 			disposition = RTAS_DISP_FULLY_RECOVERED;
-			rtas_set_disposition_recovered(errp);
 			break;
 		default:
 			break;
 		}
+	} else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
+		/* Platform corrected itself but could be degraded */
+		printk(KERN_ERR "MCE: limited recovery, system may "
+		       "be degraded\n");
+		disposition = RTAS_DISP_FULLY_RECOVERED;
 	}
 #endif
 
 out:
-	return disposition;
-}
-
-#ifdef CONFIG_MEMORY_FAILURE
-
-static DEFINE_PER_CPU(int, rtas_ue_count);
-static DEFINE_PER_CPU(unsigned long, rtas_ue_paddr[MAX_MC_EVT]);
+	save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED,
+			&mce_err, regs->nip, eaddr, paddr);
 
-#define UE_EFFECTIVE_ADDR_PROVIDED	0x40
-#define UE_LOGICAL_ADDR_PROVIDED	0x20
-
-
-static void pseries_hwpoison_work_fn(struct work_struct *work)
-{
-	unsigned long paddr;
-	int index;
-
-	while (__this_cpu_read(rtas_ue_count) > 0) {
-		index = __this_cpu_read(rtas_ue_count) - 1;
-		paddr = __this_cpu_read(rtas_ue_paddr[index]);
-		memory_failure(paddr >> PAGE_SHIFT, 0);
-		__this_cpu_dec(rtas_ue_count);
-	}
-}
-
-static DECLARE_WORK(hwpoison_work, pseries_hwpoison_work_fn);
-
-static void queue_ue_paddr(unsigned long paddr)
-{
-	int index;
-
-	index = __this_cpu_inc_return(rtas_ue_count) - 1;
-	if (index >= MAX_MC_EVT) {
-		__this_cpu_dec(rtas_ue_count);
-		return;
-	}
-	this_cpu_write(rtas_ue_paddr[index], paddr);
-	schedule_work(&hwpoison_work);
-}
-
-static void pseries_do_memory_failure(struct pt_regs *regs,
-				      struct pseries_mc_errorlog *mce_log)
-{
-	unsigned long paddr;
-
-	if (mce_log->sub_err_type & UE_LOGICAL_ADDR_PROVIDED) {
-		paddr = be64_to_cpu(mce_log->logical_address);
-	} else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) {
-		unsigned long pfn;
-
-		pfn = addr_to_pfn(regs,
-				  be64_to_cpu(mce_log->effective_address));
-		if (pfn == ULONG_MAX)
-			return;
-		paddr = pfn << PAGE_SHIFT;
-	} else {
-		return;
-	}
-	queue_ue_paddr(paddr);
-}
-
-static void pseries_process_ue(struct pt_regs *regs,
-			       struct rtas_error_log *errp)
-{
-	struct pseries_errorlog *pseries_log;
-	struct pseries_mc_errorlog *mce_log;
-
-	if (!rtas_error_extended(errp))
-		return;
-
-	pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
-	if (!pseries_log)
-		return;
-
-	mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
-
-	if (mce_log->error_type == MC_ERROR_TYPE_UE)
-		pseries_do_memory_failure(regs, mce_log);
+	return disposition;
 }
-#else
-static inline void pseries_process_ue(struct pt_regs *regs,
-				      struct rtas_error_log *errp) { }
-#endif /*CONFIG_MEMORY_FAILURE */
 
 /*
  * Process MCE rtas errlog event.
@@ -795,49 +709,51 @@ static void mce_process_errlog_event(struct irq_work *work)
  * Return 1 if corrected (or delivered a signal).
  * Return 0 if there is nothing we can do.
  */
-static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
+static int recover_mce(struct pt_regs *regs, struct machine_check_event *evt)
 {
 	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 */
 		pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
 		recovered = 0;
-
-	} else if (disposition == RTAS_DISP_FULLY_RECOVERED) {
+	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
 		/* Platform corrected itself */
 		recovered = 1;
+	} else if (evt->severity == MCE_SEV_FATAL) {
+		/* Fatal machine check */
+		pr_err("Machine check interrupt is fatal\n");
+		recovered = 0;
+	}
 
-	} else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
-		/* Platform corrected itself but could be degraded */
-		printk(KERN_ERR "MCE: limited recovery, system may "
-		       "be degraded\n");
-		recovered = 1;
-
-	} else if (user_mode(regs) && !is_global_init(current) &&
-		   rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) {
-
+	if (!recovered && evt->sync_error) {
 		/*
-		 * If we received a synchronous error when in userspace
-		 * kill the task. Firmware may report details of the fail
-		 * asynchronously, so we can't rely on the target and type
-		 * fields being valid here.
+		 * Try to kill processes if we get a synchronous machine check
+		 * (e.g., one caused by execution of this instruction). This
+		 * will devolve into a panic if we try to kill init or are in
+		 * an interrupt etc.
+		 *
+		 * TODO: Queue up this address for hwpoisioning later.
+		 * TODO: This is not quite right for d-side machine
+		 *       checks ->nip is not necessarily the important
+		 *       address.
 		 */
-		printk(KERN_ERR "MCE: uncorrectable error, killing task "
-		       "%s:%d\n", current->comm, current->pid);
-
-		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
-		recovered = 1;
+		if ((user_mode(regs))) {
+			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+			recovered = 1;
+		} else if (die_will_crash()) {
+			/*
+			 * die() would kill the kernel, so better to go via
+			 * the platform reboot code that will log the
+			 * machine check.
+			 */
+			recovered = 0;
+		} else {
+			die("Machine check", regs, SIGBUS);
+			recovered = 1;
+		}
 	}
 
-	pseries_process_ue(regs, err);
-
-	/* Queue irq work to log this rtas event later. */
-	irq_work_queue(&mce_errlog_process_work);
-
 	return recovered;
 }
 
@@ -853,14 +769,21 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
  */
 int pSeries_machine_check_exception(struct pt_regs *regs)
 {
-	struct rtas_error_log *errp;
+	struct machine_check_event evt;
 
-	if (fwnmi_active) {
-		fwnmi_release_errinfo();
-		errp = fwnmi_get_errlog();
-		if (errp && recover_mce(regs, errp))
-			return 1;
+	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+		return 0;
+
+	/* Print things out */
+	if (evt.version != MCE_V1) {
+		pr_err("Machine Check Exception, Unknown event version %d !\n",
+		       evt.version);
+		return 0;
 	}
+	machine_check_print_event_info(&evt, user_mode(regs), false);
+
+	if (recover_mce(regs, &evt))
+		return 1;
 
 	return 0;
 }
@@ -877,7 +800,12 @@ long pseries_machine_check_realmode(struct pt_regs *regs)
 		 * to panic. Hence we will call it as soon as we go into
 		 * virtual mode.
 		 */
-		disposition = mce_handle_error(errp);
+		disposition = mce_handle_error(regs, errp);
+		fwnmi_release_errinfo();
+
+		/* Queue irq work to log this rtas event later. */
+		irq_work_queue(&mce_errlog_process_work);
+
 		if (disposition == RTAS_DISP_FULLY_RECOVERED)
 			return 1;
 	}
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
new file mode 100644
index 000000000000..70c3013fdd07
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -0,0 +1,550 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2011, Mahesh Salgaonkar, IBM Corporation.
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "rtas fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+#include <asm/fadump-internal.h>
+
+#include "rtas-fadump.h"
+
+static struct rtas_fadump_mem_struct fdm;
+static const struct rtas_fadump_mem_struct *fdm_active;
+
+static void rtas_fadump_update_config(struct fw_dump *fadump_conf,
+				      const struct rtas_fadump_mem_struct *fdm)
+{
+	fadump_conf->boot_mem_dest_addr =
+		be64_to_cpu(fdm->rmr_region.destination_address);
+
+	fadump_conf->fadumphdr_addr = (fadump_conf->boot_mem_dest_addr +
+				       fadump_conf->boot_memory_size);
+}
+
+/*
+ * This function is called in the capture kernel to get configuration details
+ * setup in the first kernel and passed to the f/w.
+ */
+static void rtas_fadump_get_config(struct fw_dump *fadump_conf,
+				   const struct rtas_fadump_mem_struct *fdm)
+{
+	fadump_conf->boot_mem_addr[0] =
+		be64_to_cpu(fdm->rmr_region.source_address);
+	fadump_conf->boot_mem_sz[0] = be64_to_cpu(fdm->rmr_region.source_len);
+	fadump_conf->boot_memory_size = fadump_conf->boot_mem_sz[0];
+
+	fadump_conf->boot_mem_top = fadump_conf->boot_memory_size;
+	fadump_conf->boot_mem_regs_cnt = 1;
+
+	/*
+	 * Start address of reserve dump area (permanent reservation) for
+	 * re-registering FADump after dump capture.
+	 */
+	fadump_conf->reserve_dump_area_start =
+		be64_to_cpu(fdm->cpu_state_data.destination_address);
+
+	rtas_fadump_update_config(fadump_conf, fdm);
+}
+
+static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
+{
+	u64 addr = fadump_conf->reserve_dump_area_start;
+
+	memset(&fdm, 0, sizeof(struct rtas_fadump_mem_struct));
+	addr = addr & PAGE_MASK;
+
+	fdm.header.dump_format_version = cpu_to_be32(0x00000001);
+	fdm.header.dump_num_sections = cpu_to_be16(3);
+	fdm.header.dump_status_flag = 0;
+	fdm.header.offset_first_dump_section =
+		cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct,
+					  cpu_state_data));
+
+	/*
+	 * Fields for disk dump option.
+	 * We are not using disk dump option, hence set these fields to 0.
+	 */
+	fdm.header.dd_block_size = 0;
+	fdm.header.dd_block_offset = 0;
+	fdm.header.dd_num_blocks = 0;
+	fdm.header.dd_offset_disk_path = 0;
+
+	/* set 0 to disable an automatic dump-reboot. */
+	fdm.header.max_time_auto = 0;
+
+	/* Kernel dump sections */
+	/* cpu state data section. */
+	fdm.cpu_state_data.request_flag =
+		cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm.cpu_state_data.source_data_type =
+		cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA);
+	fdm.cpu_state_data.source_address = 0;
+	fdm.cpu_state_data.source_len =
+		cpu_to_be64(fadump_conf->cpu_state_data_size);
+	fdm.cpu_state_data.destination_address = cpu_to_be64(addr);
+	addr += fadump_conf->cpu_state_data_size;
+
+	/* hpte region section */
+	fdm.hpte_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm.hpte_region.source_data_type =
+		cpu_to_be16(RTAS_FADUMP_HPTE_REGION);
+	fdm.hpte_region.source_address = 0;
+	fdm.hpte_region.source_len =
+		cpu_to_be64(fadump_conf->hpte_region_size);
+	fdm.hpte_region.destination_address = cpu_to_be64(addr);
+	addr += fadump_conf->hpte_region_size;
+
+	/* RMA region section */
+	fdm.rmr_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm.rmr_region.source_data_type =
+		cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION);
+	fdm.rmr_region.source_address = cpu_to_be64(0);
+	fdm.rmr_region.source_len = cpu_to_be64(fadump_conf->boot_memory_size);
+	fdm.rmr_region.destination_address = cpu_to_be64(addr);
+	addr += fadump_conf->boot_memory_size;
+
+	rtas_fadump_update_config(fadump_conf, &fdm);
+
+	return addr;
+}
+
+static u64 rtas_fadump_get_bootmem_min(void)
+{
+	return RTAS_FADUMP_MIN_BOOT_MEM;
+}
+
+static int rtas_fadump_register(struct fw_dump *fadump_conf)
+{
+	unsigned int wait_time;
+	int rc, err = -EIO;
+
+	/* TODO: Add upper time limit for the delay */
+	do {
+		rc =  rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
+				NULL, FADUMP_REGISTER, &fdm,
+				sizeof(struct rtas_fadump_mem_struct));
+
+		wait_time = rtas_busy_delay_time(rc);
+		if (wait_time)
+			mdelay(wait_time);
+
+	} while (wait_time);
+
+	switch (rc) {
+	case 0:
+		pr_info("Registration is successful!\n");
+		fadump_conf->dump_registered = 1;
+		err = 0;
+		break;
+	case -1:
+		pr_err("Failed to register. Hardware Error(%d).\n", rc);
+		break;
+	case -3:
+		if (!is_fadump_boot_mem_contiguous())
+			pr_err("Can't have holes in boot memory area.\n");
+		else if (!is_fadump_reserved_mem_contiguous())
+			pr_err("Can't have holes in reserved memory area.\n");
+
+		pr_err("Failed to register. Parameter Error(%d).\n", rc);
+		err = -EINVAL;
+		break;
+	case -9:
+		pr_err("Already registered!\n");
+		fadump_conf->dump_registered = 1;
+		err = -EEXIST;
+		break;
+	default:
+		pr_err("Failed to register. Unknown Error(%d).\n", rc);
+		break;
+	}
+
+	return err;
+}
+
+static int rtas_fadump_unregister(struct fw_dump *fadump_conf)
+{
+	unsigned int wait_time;
+	int rc;
+
+	/* TODO: Add upper time limit for the delay */
+	do {
+		rc =  rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
+				NULL, FADUMP_UNREGISTER, &fdm,
+				sizeof(struct rtas_fadump_mem_struct));
+
+		wait_time = rtas_busy_delay_time(rc);
+		if (wait_time)
+			mdelay(wait_time);
+	} while (wait_time);
+
+	if (rc) {
+		pr_err("Failed to un-register - unexpected error(%d).\n", rc);
+		return -EIO;
+	}
+
+	fadump_conf->dump_registered = 0;
+	return 0;
+}
+
+static int rtas_fadump_invalidate(struct fw_dump *fadump_conf)
+{
+	unsigned int wait_time;
+	int rc;
+
+	/* TODO: Add upper time limit for the delay */
+	do {
+		rc =  rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
+				NULL, FADUMP_INVALIDATE, fdm_active,
+				sizeof(struct rtas_fadump_mem_struct));
+
+		wait_time = rtas_busy_delay_time(rc);
+		if (wait_time)
+			mdelay(wait_time);
+	} while (wait_time);
+
+	if (rc) {
+		pr_err("Failed to invalidate - unexpected error (%d).\n", rc);
+		return -EIO;
+	}
+
+	fadump_conf->dump_active = 0;
+	fdm_active = NULL;
+	return 0;
+}
+
+#define RTAS_FADUMP_GPR_MASK		0xffffff0000000000
+static inline int rtas_fadump_gpr_index(u64 id)
+{
+	char str[3];
+	int i = -1;
+
+	if ((id & RTAS_FADUMP_GPR_MASK) == fadump_str_to_u64("GPR")) {
+		/* get the digits at the end */
+		id &= ~RTAS_FADUMP_GPR_MASK;
+		id >>= 24;
+		str[2] = '\0';
+		str[1] = id & 0xff;
+		str[0] = (id >> 8) & 0xff;
+		if (kstrtoint(str, 10, &i))
+			i = -EINVAL;
+		if (i > 31)
+			i = -1;
+	}
+	return i;
+}
+
+void rtas_fadump_set_regval(struct pt_regs *regs, u64 reg_id, u64 reg_val)
+{
+	int i;
+
+	i = rtas_fadump_gpr_index(reg_id);
+	if (i >= 0)
+		regs->gpr[i] = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("NIA"))
+		regs->nip = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("MSR"))
+		regs->msr = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("CTR"))
+		regs->ctr = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("LR"))
+		regs->link = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("XER"))
+		regs->xer = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("CR"))
+		regs->ccr = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("DAR"))
+		regs->dar = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("DSISR"))
+		regs->dsisr = (unsigned long)reg_val;
+}
+
+static struct rtas_fadump_reg_entry*
+rtas_fadump_read_regs(struct rtas_fadump_reg_entry *reg_entry,
+		      struct pt_regs *regs)
+{
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	while (be64_to_cpu(reg_entry->reg_id) != fadump_str_to_u64("CPUEND")) {
+		rtas_fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
+				       be64_to_cpu(reg_entry->reg_value));
+		reg_entry++;
+	}
+	reg_entry++;
+	return reg_entry;
+}
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
+ * used to access the data to allow for additional fields to be added without
+ * affecting compatibility. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
+ * 8 Byte ASCII identifier and 8 Byte register value. The register entry
+ * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
+ * of register value. For more details refer to PAPR document.
+ *
+ * Only for the crashing cpu we ignore the CPU dump data and get exact
+ * state from fadump crash info structure populated by first kernel at the
+ * time of crash.
+ */
+static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf)
+{
+	struct rtas_fadump_reg_save_area_header *reg_header;
+	struct fadump_crash_info_header *fdh = NULL;
+	struct rtas_fadump_reg_entry *reg_entry;
+	u32 num_cpus, *note_buf;
+	int i, rc = 0, cpu = 0;
+	struct pt_regs regs;
+	unsigned long addr;
+	void *vaddr;
+
+	addr = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
+	vaddr = __va(addr);
+
+	reg_header = vaddr;
+	if (be64_to_cpu(reg_header->magic_number) !=
+	    fadump_str_to_u64("REGSAVE")) {
+		pr_err("Unable to read register save area.\n");
+		return -ENOENT;
+	}
+
+	pr_debug("--------CPU State Data------------\n");
+	pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
+	pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));
+
+	vaddr += be32_to_cpu(reg_header->num_cpu_offset);
+	num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
+	pr_debug("NumCpus     : %u\n", num_cpus);
+	vaddr += sizeof(u32);
+	reg_entry = (struct rtas_fadump_reg_entry *)vaddr;
+
+	rc = fadump_setup_cpu_notes_buf(num_cpus);
+	if (rc != 0)
+		return rc;
+
+	note_buf = (u32 *)fadump_conf->cpu_notes_buf_vaddr;
+
+	if (fadump_conf->fadumphdr_addr)
+		fdh = __va(fadump_conf->fadumphdr_addr);
+
+	for (i = 0; i < num_cpus; i++) {
+		if (be64_to_cpu(reg_entry->reg_id) !=
+		    fadump_str_to_u64("CPUSTRT")) {
+			pr_err("Unable to read CPU state data\n");
+			rc = -ENOENT;
+			goto error_out;
+		}
+		/* Lower 4 bytes of reg_value contains logical cpu id */
+		cpu = (be64_to_cpu(reg_entry->reg_value) &
+		       RTAS_FADUMP_CPU_ID_MASK);
+		if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
+			RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
+			continue;
+		}
+		pr_debug("Reading register data for cpu %d...\n", cpu);
+		if (fdh && fdh->crashing_cpu == cpu) {
+			regs = fdh->regs;
+			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+			RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
+		} else {
+			reg_entry++;
+			reg_entry = rtas_fadump_read_regs(reg_entry, &regs);
+			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+		}
+	}
+	final_note(note_buf);
+
+	if (fdh) {
+		pr_debug("Updating elfcore header (%llx) with cpu notes\n",
+			 fdh->elfcorehdr_addr);
+		fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr));
+	}
+	return 0;
+
+error_out:
+	fadump_free_cpu_notes_buf();
+	return rc;
+
+}
+
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+static int __init rtas_fadump_process(struct fw_dump *fadump_conf)
+{
+	struct fadump_crash_info_header *fdh;
+	int rc = 0;
+
+	if (!fdm_active || !fadump_conf->fadumphdr_addr)
+		return -EINVAL;
+
+	/* Check if the dump data is valid. */
+	if ((be16_to_cpu(fdm_active->header.dump_status_flag) ==
+			RTAS_FADUMP_ERROR_FLAG) ||
+			(fdm_active->cpu_state_data.error_flags != 0) ||
+			(fdm_active->rmr_region.error_flags != 0)) {
+		pr_err("Dump taken by platform is not valid\n");
+		return -EINVAL;
+	}
+	if ((fdm_active->rmr_region.bytes_dumped !=
+			fdm_active->rmr_region.source_len) ||
+			!fdm_active->cpu_state_data.bytes_dumped) {
+		pr_err("Dump taken by platform is incomplete\n");
+		return -EINVAL;
+	}
+
+	/* Validate the fadump crash info header */
+	fdh = __va(fadump_conf->fadumphdr_addr);
+	if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+		pr_err("Crash info header is not valid.\n");
+		return -EINVAL;
+	}
+
+	rc = rtas_fadump_build_cpu_notes(fadump_conf);
+	if (rc)
+		return rc;
+
+	/*
+	 * We are done validating dump info and elfcore header is now ready
+	 * to be exported. set elfcorehdr_addr so that vmcore module will
+	 * export the elfcore header through '/proc/vmcore'.
+	 */
+	elfcorehdr_addr = fdh->elfcorehdr_addr;
+
+	return 0;
+}
+
+static void rtas_fadump_region_show(struct fw_dump *fadump_conf,
+				    struct seq_file *m)
+{
+	const struct rtas_fadump_section *cpu_data_section;
+	const struct rtas_fadump_mem_struct *fdm_ptr;
+
+	if (fdm_active)
+		fdm_ptr = fdm_active;
+	else
+		fdm_ptr = &fdm;
+
+	cpu_data_section = &(fdm_ptr->cpu_state_data);
+	seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
+		   be64_to_cpu(cpu_data_section->destination_address),
+		   be64_to_cpu(cpu_data_section->destination_address) +
+		   be64_to_cpu(cpu_data_section->source_len) - 1,
+		   be64_to_cpu(cpu_data_section->source_len),
+		   be64_to_cpu(cpu_data_section->bytes_dumped));
+
+	seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
+		   be64_to_cpu(fdm_ptr->hpte_region.destination_address),
+		   be64_to_cpu(fdm_ptr->hpte_region.destination_address) +
+		   be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1,
+		   be64_to_cpu(fdm_ptr->hpte_region.source_len),
+		   be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped));
+
+	seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ",
+		   be64_to_cpu(fdm_ptr->rmr_region.source_address),
+		   be64_to_cpu(fdm_ptr->rmr_region.destination_address));
+	seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
+		   be64_to_cpu(fdm_ptr->rmr_region.source_len),
+		   be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));
+
+	/* Dump is active. Show reserved area start address. */
+	if (fdm_active) {
+		seq_printf(m, "\nMemory above %#016lx is reserved for saving crash dump\n",
+			   fadump_conf->reserve_dump_area_start);
+	}
+}
+
+static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh,
+				const char *msg)
+{
+	/* Call ibm,os-term rtas call to trigger firmware assisted dump */
+	rtas_os_term((char *)msg);
+}
+
+static struct fadump_ops rtas_fadump_ops = {
+	.fadump_init_mem_struct		= rtas_fadump_init_mem_struct,
+	.fadump_get_bootmem_min		= rtas_fadump_get_bootmem_min,
+	.fadump_register		= rtas_fadump_register,
+	.fadump_unregister		= rtas_fadump_unregister,
+	.fadump_invalidate		= rtas_fadump_invalidate,
+	.fadump_process			= rtas_fadump_process,
+	.fadump_region_show		= rtas_fadump_region_show,
+	.fadump_trigger			= rtas_fadump_trigger,
+};
+
+void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
+{
+	int i, size, num_sections;
+	const __be32 *sections;
+	const __be32 *token;
+
+	/*
+	 * Check if Firmware Assisted dump is supported. if yes, check
+	 * if dump has been initiated on last reboot.
+	 */
+	token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+	if (!token)
+		return;
+
+	fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token);
+	fadump_conf->ops		= &rtas_fadump_ops;
+	fadump_conf->fadump_supported	= 1;
+
+	/* Firmware supports 64-bit value for size, align it to pagesize. */
+	fadump_conf->max_copy_size = _ALIGN_DOWN(U64_MAX, PAGE_SIZE);
+
+	/*
+	 * The 'ibm,kernel-dump' rtas node is present only if there is
+	 * dump data waiting for us.
+	 */
+	fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
+	if (fdm_active) {
+		pr_info("Firmware-assisted dump is active.\n");
+		fadump_conf->dump_active = 1;
+		rtas_fadump_get_config(fadump_conf, (void *)__pa(fdm_active));
+	}
+
+	/* Get the sizes required to store dump data for the firmware provided
+	 * dump sections.
+	 * For each dump section type supported, a 32bit cell which defines
+	 * the ID of a supported section followed by two 32 bit cells which
+	 * gives the size of the section in bytes.
+	 */
+	sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+					&size);
+
+	if (!sections)
+		return;
+
+	num_sections = size / (3 * sizeof(u32));
+
+	for (i = 0; i < num_sections; i++, sections += 3) {
+		u32 type = (u32)of_read_number(sections, 1);
+
+		switch (type) {
+		case RTAS_FADUMP_CPU_STATE_DATA:
+			fadump_conf->cpu_state_data_size =
+					of_read_ulong(&sections[1], 2);
+			break;
+		case RTAS_FADUMP_HPTE_REGION:
+			fadump_conf->hpte_region_size =
+					of_read_ulong(&sections[1], 2);
+			break;
+		}
+	}
+}
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h
new file mode 100644
index 000000000000..fd59bd7ca9c3
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2011, Mahesh Salgaonkar, IBM Corporation.
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#ifndef _PSERIES_RTAS_FADUMP_H
+#define _PSERIES_RTAS_FADUMP_H
+
+/*
+ * On some Power systems where RMO is 128MB, it still requires minimum of
+ * 256MB for kernel to boot successfully. When kdump infrastructure is
+ * configured to save vmcore over network, we run into OOM issue while
+ * loading modules related to network setup. Hence we need additional 64M
+ * of memory to avoid OOM issue.
+ */
+#define RTAS_FADUMP_MIN_BOOT_MEM	((0x1UL << 28) + (0x1UL << 26))
+
+/* Firmware provided dump sections */
+#define RTAS_FADUMP_CPU_STATE_DATA	0x0001
+#define RTAS_FADUMP_HPTE_REGION		0x0002
+#define RTAS_FADUMP_REAL_MODE_REGION	0x0011
+
+/* Dump request flag */
+#define RTAS_FADUMP_REQUEST_FLAG	0x00000001
+
+/* Dump status flag */
+#define RTAS_FADUMP_ERROR_FLAG		0x2000
+
+/* Kernel Dump section info */
+struct rtas_fadump_section {
+	__be32	request_flag;
+	__be16	source_data_type;
+	__be16	error_flags;
+	__be64	source_address;
+	__be64	source_len;
+	__be64	bytes_dumped;
+	__be64	destination_address;
+};
+
+/* ibm,configure-kernel-dump header. */
+struct rtas_fadump_section_header {
+	__be32	dump_format_version;
+	__be16	dump_num_sections;
+	__be16	dump_status_flag;
+	__be32	offset_first_dump_section;
+
+	/* Fields for disk dump option. */
+	__be32	dd_block_size;
+	__be64	dd_block_offset;
+	__be64	dd_num_blocks;
+	__be32	dd_offset_disk_path;
+
+	/* Maximum time allowed to prevent an automatic dump-reboot. */
+	__be32	max_time_auto;
+};
+
+/*
+ * Firmware Assisted dump memory structure. This structure is required for
+ * registering future kernel dump with power firmware through rtas call.
+ *
+ * No disk dump option. Hence disk dump path string section is not included.
+ */
+struct rtas_fadump_mem_struct {
+	struct rtas_fadump_section_header	header;
+
+	/* Kernel dump sections */
+	struct rtas_fadump_section		cpu_state_data;
+	struct rtas_fadump_section		hpte_region;
+
+	/*
+	 * TODO: Extend multiple boot memory regions support in the kernel
+	 *       for this platform.
+	 */
+	struct rtas_fadump_section		rmr_region;
+};
+
+/*
+ * The firmware-assisted dump format.
+ *
+ * The register save area is an area in the partition's memory used to preserve
+ * the register contents (CPU state data) for the active CPUs during a firmware
+ * assisted dump. The dump format contains register save area header followed
+ * by register entries. Each list of registers for a CPU starts with "CPUSTRT"
+ * and ends with "CPUEND".
+ */
+
+/* Register save area header. */
+struct rtas_fadump_reg_save_area_header {
+	__be64		magic_number;
+	__be32		version;
+	__be32		num_cpu_offset;
+};
+
+/* Register entry. */
+struct rtas_fadump_reg_entry {
+	__be64		reg_id;
+	__be64		reg_value;
+};
+
+/* Utility macros */
+#define RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry)				\
+({									\
+	while (be64_to_cpu(reg_entry->reg_id) !=			\
+	       fadump_str_to_u64("CPUEND"))				\
+		reg_entry++;						\
+	reg_entry++;							\
+})
+
+#define RTAS_FADUMP_CPU_ID_MASK			((1UL << 32) - 1)
+
+#endif /* _PSERIES_RTAS_FADUMP_H */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index f5940cc71c37..f8adcd0e4589 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -69,6 +69,7 @@
 #include <asm/security_features.h>
 #include <asm/asm-const.h>
 #include <asm/swiotlb.h>
+#include <asm/svm.h>
 
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
@@ -141,17 +142,19 @@ static void __init fwnmi_init(void)
 	}
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	/* Allocate per cpu slb area to save old slb contents during MCE */
-	size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
-	slb_ptr = memblock_alloc_try_nid_raw(size, sizeof(struct slb_entry),
-					MEMBLOCK_LOW_LIMIT, ppc64_rma_size,
-					NUMA_NO_NODE);
-	if (!slb_ptr)
-		panic("Failed to allocate %zu bytes below %pa for slb area\n",
-		      size, &ppc64_rma_size);
-
-	for_each_possible_cpu(i)
-		paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
+	if (!radix_enabled()) {
+		/* Allocate per cpu area to save old slb contents during MCE */
+		size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
+		slb_ptr = memblock_alloc_try_nid_raw(size,
+				sizeof(struct slb_entry), MEMBLOCK_LOW_LIMIT,
+				ppc64_rma_size, NUMA_NO_NODE);
+		if (!slb_ptr)
+			panic("Failed to allocate %zu bytes below %pa for slb area\n",
+			      size, &ppc64_rma_size);
+
+		for_each_possible_cpu(i)
+			paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
+	}
 #endif
 }
 
@@ -297,8 +300,10 @@ static inline int alloc_dispatch_logs(void)
 
 static int alloc_dispatch_log_kmem_cache(void)
 {
+	void (*ctor)(void *) = get_dtl_cache_ctor();
+
 	dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
-						DISPATCH_LOG_BYTES, 0, NULL);
+						DISPATCH_LOG_BYTES, 0, ctor);
 	if (!dtl_cache) {
 		pr_warn("Failed to create dispatch trace log buffer cache\n");
 		pr_warn("Stolen time statistics will be unreliable\n");
@@ -316,6 +321,9 @@ static void pseries_lpar_idle(void)
 	 * low power mode by ceding processor to hypervisor
 	 */
 
+	if (!prep_irq_for_idle())
+		return;
+
 	/* Indicate to hypervisor that we are idle. */
 	get_lppaca()->idle = 1;
 
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 4b3ef8d9c63f..ad61e90032da 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -41,6 +41,7 @@
 #include <asm/dbell.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/code-patching.h>
+#include <asm/svm.h>
 
 #include "pseries.h"
 #include "offline_states.h"
@@ -221,7 +222,7 @@ static __init void pSeries_smp_probe_xics(void)
 {
 	xics_smp_probe();
 
-	if (cpu_has_feature(CPU_FTR_DBELL))
+	if (cpu_has_feature(CPU_FTR_DBELL) && !is_secure_guest())
 		smp_ops->cause_ipi = smp_pseries_cause_ipi;
 	else
 		smp_ops->cause_ipi = icp_ops->cause_ipi;
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
new file mode 100644
index 000000000000..40c0637203d5
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Secure VM platform
+ *
+ * Copyright 2018 IBM Corporation
+ * Author: Anshuman Khandual <khandual@linux.vnet.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <asm/machdep.h>
+#include <asm/svm.h>
+#include <asm/swiotlb.h>
+#include <asm/ultravisor.h>
+
+static int __init init_svm(void)
+{
+	if (!is_secure_guest())
+		return 0;
+
+	/* Don't release the SWIOTLB buffer. */
+	ppc_swiotlb_enable = 1;
+
+	/*
+	 * Since the guest memory is inaccessible to the host, devices always
+	 * need to use the SWIOTLB buffer for DMA even if dma_capable() says
+	 * otherwise.
+	 */
+	swiotlb_force = SWIOTLB_FORCE;
+
+	/* Share the SWIOTLB buffer with the host. */
+	swiotlb_update_mem_attributes();
+
+	return 0;
+}
+machine_early_initcall(pseries, init_svm);
+
+int set_memory_encrypted(unsigned long addr, int numpages)
+{
+	if (!PAGE_ALIGNED(addr))
+		return -EINVAL;
+
+	uv_unshare_page(PHYS_PFN(__pa(addr)), numpages);
+
+	return 0;
+}
+
+int set_memory_decrypted(unsigned long addr, int numpages)
+{
+	if (!PAGE_ALIGNED(addr))
+		return -EINVAL;
+
+	uv_share_page(PHYS_PFN(__pa(addr)), numpages);
+
+	return 0;
+}
+
+/* There's one dispatch log per CPU. */
+#define NR_DTL_PAGE (DISPATCH_LOG_BYTES * CONFIG_NR_CPUS / PAGE_SIZE)
+
+static struct page *dtl_page_store[NR_DTL_PAGE];
+static long dtl_nr_pages;
+
+static bool is_dtl_page_shared(struct page *page)
+{
+	long i;
+
+	for (i = 0; i < dtl_nr_pages; i++)
+		if (dtl_page_store[i] == page)
+			return true;
+
+	return false;
+}
+
+void dtl_cache_ctor(void *addr)
+{
+	unsigned long pfn = PHYS_PFN(__pa(addr));
+	struct page *page = pfn_to_page(pfn);
+
+	if (!is_dtl_page_shared(page)) {
+		dtl_page_store[dtl_nr_pages] = page;
+		dtl_nr_pages++;
+		WARN_ON(dtl_nr_pages >= NR_DTL_PAGE);
+		uv_share_page(pfn, 1);
+	}
+}
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 3473eef7628c..79e2287991db 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1193,7 +1193,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 	else
 		tbl->it_ops = &iommu_table_pseries_ops;
 
-	return iommu_init_table(tbl, -1);
+	return iommu_init_table(tbl, -1, 0, 0);
 }
 
 /**