Merge tag 'powerpc-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - A series from Nick adding ARCH_WANT_IRQS_OFF_ACTIVATE_MM & selecting
   it for powerpc, as well as a related fix for sparc.

 - Remove support for PowerPC 601.

 - Some fixes for watchpoints & addition of a new ptrace flag for
   detecting ISA v3.1 (Power10) watchpoint features.

 - A fix for kernels using 4K pages and the hash MMU on bare metal
   Power9 systems with > 16TB of RAM, or RAM on the 2nd node.

 - A basic idle driver for shallow stop states on Power10.

 - Tweaks to our sched domains code to better inform the scheduler about
   the hardware topology on Power9/10, where two SMT4 cores can be
   presented by firmware as an SMT8 core.

 - A series doing further reworks & cleanups of our EEH code.

 - Addition of a filter for RTAS (firmware) calls done via sys_rtas(),
   to prevent root from overwriting kernel memory.

 - Other smaller features, fixes & cleanups.

Thanks to: Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V,
Athira Rajeev, Biwen Li, Cameron Berkenpas, Cédric Le Goater, Christophe
Leroy, Christoph Hellwig, Colin Ian King, Daniel Axtens, David Dai, Finn
Thain, Frederic Barrat, Gautham R. Shenoy, Greg Kurz, Gustavo Romero,
Ira Weiny, Jason Yan, Joel Stanley, Jordan Niethe, Kajol Jain, Konrad
Rzeszutek Wilk, Laurent Dufour, Leonardo Bras, Liu Shixin, Luca
Ceresoli, Madhavan Srinivasan, Mahesh Salgaonkar, Nathan Lynch, Nicholas
Mc Guire, Nicholas Piggin, Nick Desaulniers, Oliver O'Halloran, Pedro
Miraglia Franco de Carvalho, Pratik Rajesh Sampat, Qian Cai, Qinglang
Miao, Ravi Bangoria, Russell Currey, Satheesh Rajendran, Scott Cheloha,
Segher Boessenkool, Srikar Dronamraju, Stan Johnson, Stephen Kitt,
Stephen Rothwell, Thiago Jung Bauermann, Tyrel Datwyler, Vaibhav Jain,
Vaidyanathan Srinivasan, Vasant Hegde, Wang Wensheng, Wolfram Sang, Yang
Yingliang, zhengbin.

* tag 'powerpc-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (228 commits)
  Revert "powerpc/pci: unmap legacy INTx interrupts when a PHB is removed"
  selftests/powerpc: Fix eeh-basic.sh exit codes
  cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_reboot_notifier
  powerpc/time: Make get_tb() common to PPC32 and PPC64
  powerpc/time: Make get_tbl() common to PPC32 and PPC64
  powerpc/time: Remove get_tbu()
  powerpc/time: Avoid using get_tbl() and get_tbu() internally
  powerpc/time: Make mftb() common to PPC32 and PPC64
  powerpc/time: Rename mftbl() to mftb()
  powerpc/32s: Remove #ifdef CONFIG_PPC_BOOK3S_32 in head_book3s_32.S
  powerpc/32s: Rename head_32.S to head_book3s_32.S
  powerpc/32s: Setup the early hash table at all time.
  powerpc/time: Remove ifdef in get_dec() and set_dec()
  powerpc: Remove get_tb_or_rtc()
  powerpc: Remove __USE_RTC()
  powerpc: Tidy up a bit after removal of PowerPC 601.
  powerpc: Remove support for PowerPC 601
  powerpc: Remove PowerPC 601
  powerpc: Drop SYNC_601() ISYNC_601() and SYNC()
  powerpc: Remove CONFIG_PPC601_SYNC_FIX
  ...

11 files changed, 465 insertions, 344 deletions

diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index cb2d9a970b7b..cf024fa37bda 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -33,8 +33,6 @@
 #include <asm/ppc-pci.h>
 #include <asm/rtas.h>
 
-static int pseries_eeh_get_pe_addr(struct pci_dn *pdn);
-
 /* RTAS tokens */
 static int ibm_set_eeh_option;
 static int ibm_set_slot_reset;
@@ -86,42 +84,43 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
 
 
 /**
- * pseries_eeh_get_config_addr - Retrieve config address
+ * pseries_eeh_get_pe_config_addr - Find the pe_config_addr for a device
+ * @pdn: pci_dn of the input device
+ *
+ * The EEH RTAS calls use a tuple consisting of: (buid_hi, buid_lo,
+ * pe_config_addr) as a handle to a given PE. This function finds the
+ * pe_config_addr based on the device's config addr.
  *
- * Retrieve the assocated config address. Actually, there're 2 RTAS
- * function calls dedicated for the purpose. We need implement
- * it through the new function and then the old one. Besides,
- * you should make sure the config address is figured out from
- * FDT node before calling the function.
+ * Keep in mind that the pe_config_addr *might* be numerically identical to the
+ * device's config addr, but the two are conceptually distinct.
  *
- * It's notable that zero'ed return value means invalid PE config
- * address.
+ * Returns the pe_config_addr, or a negative error code.
  */
-static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_addr)
+static int pseries_eeh_get_pe_config_addr(struct pci_dn *pdn)
 {
-	int ret = 0;
-	int rets[3];
+	int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0);
+	struct pci_controller *phb = pdn->phb;
+	int ret, rets[3];
 
 	if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) {
 		/*
-		 * First of all, we need to make sure there has one PE
-		 * associated with the device. Otherwise, PE address is
-		 * meaningless.
+		 * First of all, use function 1 to determine if this device is
+		 * part of a PE or not. ret[0] being zero indicates it's not.
 		 */
 		ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
 				config_addr, BUID_HI(phb->buid),
 				BUID_LO(phb->buid), 1);
 		if (ret || (rets[0] == 0))
-			return 0;
+			return -ENOENT;
 
-		/* Retrieve the associated PE config address */
+		/* Retrieve the associated PE config address with function 0 */
 		ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
 				config_addr, BUID_HI(phb->buid),
 				BUID_LO(phb->buid), 0);
 		if (ret) {
 			pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
 				__func__, phb->global_number, config_addr);
-			return 0;
+			return -ENXIO;
 		}
 
 		return rets[0];
@@ -134,13 +133,20 @@ static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_ad
 		if (ret) {
 			pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
 				__func__, phb->global_number, config_addr);
-			return 0;
+			return -ENXIO;
 		}
 
 		return rets[0];
 	}
 
-	return ret;
+	/*
+	 * PAPR does describe a process for finding the pe_config_addr that was
+	 * used before the ibm,get-config-addr-info calls were added. However,
+	 * I haven't found *any* systems that don't have that RTAS call
+	 * implemented. If you happen to find one that needs the old DT based
+	 * process, patches are welcome!
+	 */
+	return -ENOENT;
 }
 
 /**
@@ -161,8 +167,7 @@ static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, in
 			BUID_LO(phb->buid), option);
 
 	/* If fundamental-reset not supported, try hot-reset */
-	if (option == EEH_RESET_FUNDAMENTAL &&
-	    ret == -8) {
+	if (option == EEH_RESET_FUNDAMENTAL && ret == -8) {
 		option = EEH_RESET_HOT;
 		ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
 				config_addr, BUID_HI(phb->buid),
@@ -170,8 +175,7 @@ static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, in
 	}
 
 	/* We need reset hold or settlement delay */
-	if (option == EEH_RESET_FUNDAMENTAL ||
-	    option == EEH_RESET_HOT)
+	if (option == EEH_RESET_FUNDAMENTAL || option == EEH_RESET_HOT)
 		msleep(EEH_PE_RST_HOLD_TIME);
 	else
 		msleep(EEH_PE_RST_SETTLE_TIME);
@@ -239,88 +243,6 @@ static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX];
 static DEFINE_SPINLOCK(slot_errbuf_lock);
 static int eeh_error_buf_size;
 
-/**
- * pseries_eeh_init - EEH platform dependent initialization
- *
- * EEH platform dependent initialization on pseries.
- */
-static int pseries_eeh_init(void)
-{
-	struct pci_controller *phb;
-	struct pci_dn *pdn;
-	int addr, config_addr;
-
-	/* figure out EEH RTAS function call tokens */
-	ibm_set_eeh_option		= rtas_token("ibm,set-eeh-option");
-	ibm_set_slot_reset		= rtas_token("ibm,set-slot-reset");
-	ibm_read_slot_reset_state2	= rtas_token("ibm,read-slot-reset-state2");
-	ibm_read_slot_reset_state	= rtas_token("ibm,read-slot-reset-state");
-	ibm_slot_error_detail		= rtas_token("ibm,slot-error-detail");
-	ibm_get_config_addr_info2	= rtas_token("ibm,get-config-addr-info2");
-	ibm_get_config_addr_info	= rtas_token("ibm,get-config-addr-info");
-	ibm_configure_pe		= rtas_token("ibm,configure-pe");
-
-	/*
-	 * ibm,configure-pe and ibm,configure-bridge have the same semantics,
-	 * however ibm,configure-pe can be faster.  If we can't find
-	 * ibm,configure-pe then fall back to using ibm,configure-bridge.
-	 */
-	if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE)
-		ibm_configure_pe 	= rtas_token("ibm,configure-bridge");
-
-	/*
-	 * Necessary sanity check. We needn't check "get-config-addr-info"
-	 * and its variant since the old firmware probably support address
-	 * of domain/bus/slot/function for EEH RTAS operations.
-	 */
-	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE		||
-	    ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE		||
-	    (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
-	     ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE)	||
-	    ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE	||
-	    ibm_configure_pe == RTAS_UNKNOWN_SERVICE) {
-		pr_info("EEH functionality not supported\n");
-		return -EINVAL;
-	}
-
-	/* Initialize error log lock and size */
-	spin_lock_init(&slot_errbuf_lock);
-	eeh_error_buf_size = rtas_token("rtas-error-log-max");
-	if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) {
-		pr_info("%s: unknown EEH error log size\n",
-			__func__);
-		eeh_error_buf_size = 1024;
-	} else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) {
-		pr_info("%s: EEH error log size %d exceeds the maximal %d\n",
-			__func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX);
-		eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
-	}
-
-	/* Set EEH probe mode */
-	eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG);
-
-	/* Set EEH machine dependent code */
-	ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device;
-
-	if (is_kdump_kernel() || reset_devices) {
-		pr_info("Issue PHB reset ...\n");
-		list_for_each_entry(phb, &hose_list, list_node) {
-			pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list);
-			addr = (pdn->busno << 16) | (pdn->devfn << 8);
-			config_addr = pseries_eeh_get_config_addr(phb, addr);
-			/* invalid PE config addr */
-			if (config_addr == 0)
-				continue;
-
-			pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL);
-			pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE);
-			pseries_eeh_phb_configure_bridge(phb, config_addr);
-		}
-	}
-
-	return 0;
-}
-
 static int pseries_eeh_cap_start(struct pci_dn *pdn)
 {
 	u32 status;
@@ -439,10 +361,9 @@ static struct eeh_pe *pseries_eeh_pe_get_parent(struct eeh_dev *edev)
  */
 void pseries_eeh_init_edev(struct pci_dn *pdn)
 {
+	struct eeh_pe pe, *parent;
 	struct eeh_dev *edev;
-	struct eeh_pe pe;
 	u32 pcie_flags;
-	int enable = 0;
 	int ret;
 
 	if (WARN_ON_ONCE(!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)))
@@ -499,51 +420,38 @@ void pseries_eeh_init_edev(struct pci_dn *pdn)
 		}
 	}
 
-	/* Initialize the fake PE */
+	/* first up, find the pe_config_addr for the PE containing the device */
+	ret = pseries_eeh_get_pe_config_addr(pdn);
+	if (ret < 0) {
+		eeh_edev_dbg(edev, "Unable to find pe_config_addr\n");
+		goto err;
+	}
+
+	/* Try enable EEH on the fake PE */
 	memset(&pe, 0, sizeof(struct eeh_pe));
 	pe.phb = pdn->phb;
-	pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8);
+	pe.addr = ret;
 
-	/* 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) {
 		eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret);
-	} else {
-		struct eeh_pe *parent;
+		goto err;
+	}
 
-		/* Retrieve PE address */
-		edev->pe_config_addr = pseries_eeh_get_pe_addr(pdn);
-		pe.addr = edev->pe_config_addr;
+	edev->pe_config_addr = pe.addr;
 
-		/* Some older systems (Power4) allow the ibm,set-eeh-option
-		 * call to succeed even on nodes where EEH is not supported.
-		 * Verify support explicitly.
-		 */
-		ret = eeh_ops->get_state(&pe, NULL);
-		if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT)
-			enable = 1;
+	eeh_add_flag(EEH_ENABLED);
 
-		/*
-		 * This device doesn't support EEH, but it may have an
-		 * EEH parent. In this case any error on the device will
-		 * freeze the PE of it's upstream bridge, so added it to
-		 * the upstream PE.
-		 */
-		parent = pseries_eeh_pe_get_parent(edev);
-		if (parent && !enable)
-			edev->pe_config_addr = parent->addr;
+	parent = pseries_eeh_pe_get_parent(edev);
+	eeh_pe_tree_insert(edev, parent);
+	eeh_save_bars(edev);
+	eeh_edev_dbg(edev, "EEH enabled for device");
 
-		if (enable || parent) {
-			eeh_add_flag(EEH_ENABLED);
-			eeh_pe_tree_insert(edev, parent);
-		}
-		eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n",
-			     (enable ? "enabled" : "unsupported"), ret);
-	}
+	return;
 
-	/* Save memory bars */
-	eeh_save_bars(edev);
+err:
+	eeh_edev_dbg(edev, "EEH is unsupported on device (code = %d)\n", ret);
 }
 
 static struct eeh_dev *pseries_eeh_probe(struct pci_dev *pdev)
@@ -600,7 +508,6 @@ EXPORT_SYMBOL_GPL(pseries_eeh_init_edev_recursive);
 static int pseries_eeh_set_option(struct eeh_pe *pe, int option)
 {
 	int ret = 0;
-	int config_addr;
 
 	/*
 	 * When we're enabling or disabling EEH functioality on
@@ -613,85 +520,23 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option)
 	case EEH_OPT_ENABLE:
 	case EEH_OPT_THAW_MMIO:
 	case EEH_OPT_THAW_DMA:
-		config_addr = pe->config_addr;
-		if (pe->addr)
-			config_addr = pe->addr;
 		break;
 	case EEH_OPT_FREEZE_PE:
 		/* Not support */
 		return 0;
 	default:
-		pr_err("%s: Invalid option %d\n",
-			__func__, option);
+		pr_err("%s: Invalid option %d\n", __func__, option);
 		return -EINVAL;
 	}
 
 	ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL,
-			config_addr, BUID_HI(pe->phb->buid),
+			pe->addr, BUID_HI(pe->phb->buid),
 			BUID_LO(pe->phb->buid), option);
 
 	return ret;
 }
 
 /**
- * pseries_eeh_get_pe_addr - Retrieve PE address
- * @pe: EEH PE
- *
- * Retrieve the assocated PE address. Actually, there're 2 RTAS
- * function calls dedicated for the purpose. We need implement
- * it through the new function and then the old one. Besides,
- * you should make sure the config address is figured out from
- * FDT node before calling the function.
- *
- * It's notable that zero'ed return value means invalid PE config
- * address.
- */
-static int pseries_eeh_get_pe_addr(struct pci_dn *pdn)
-{
-	int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0);
-	unsigned long buid = pdn->phb->buid;
-	int ret = 0;
-	int rets[3];
-
-	if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) {
-		/*
-		 * First of all, we need to make sure there has one PE
-		 * associated with the device. Otherwise, PE address is
-		 * meaningless.
-		 */
-		ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
-				config_addr, BUID_HI(buid), BUID_LO(buid), 1);
-		if (ret || (rets[0] == 0))
-			return 0;
-
-		/* Retrieve the associated PE config address */
-		ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
-				config_addr, BUID_HI(buid), BUID_LO(buid), 0);
-		if (ret) {
-			pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
-				__func__, pdn->phb->global_number, config_addr);
-			return 0;
-		}
-
-		return rets[0];
-	}
-
-	if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets,
-				config_addr, BUID_HI(buid), BUID_LO(buid), 0);
-		if (ret) {
-			pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
-				__func__, pdn->phb->global_number, config_addr);
-			return 0;
-		}
-
-		return rets[0];
-	}
-
-	return ret;
-}
-
-/**
  * pseries_eeh_get_state - Retrieve PE state
  * @pe: EEH PE
  * @delay: suggested time to wait if state is unavailable
@@ -706,25 +551,19 @@ static int pseries_eeh_get_pe_addr(struct pci_dn *pdn)
  */
 static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay)
 {
-	int config_addr;
 	int ret;
 	int rets[4];
 	int result;
 
-	/* Figure out PE config address if possible */
-	config_addr = pe->config_addr;
-	if (pe->addr)
-		config_addr = pe->addr;
-
 	if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) {
 		ret = rtas_call(ibm_read_slot_reset_state2, 3, 4, rets,
-				config_addr, BUID_HI(pe->phb->buid),
+				pe->addr, BUID_HI(pe->phb->buid),
 				BUID_LO(pe->phb->buid));
 	} else if (ibm_read_slot_reset_state != RTAS_UNKNOWN_SERVICE) {
 		/* Fake PE unavailable info */
 		rets[2] = 0;
 		ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets,
-				config_addr, BUID_HI(pe->phb->buid),
+				pe->addr, BUID_HI(pe->phb->buid),
 				BUID_LO(pe->phb->buid));
 	} else {
 		return EEH_STATE_NOT_SUPPORT;
@@ -778,14 +617,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay)
  */
 static int pseries_eeh_reset(struct eeh_pe *pe, int option)
 {
-	int config_addr;
-
-	/* Figure out PE address */
-	config_addr = pe->config_addr;
-	if (pe->addr)
-		config_addr = pe->addr;
-
-	return pseries_eeh_phb_reset(pe->phb, config_addr, option);
+	return pseries_eeh_phb_reset(pe->phb, pe->addr, option);
 }
 
 /**
@@ -801,19 +633,13 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option)
  */
 static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len)
 {
-	int config_addr;
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&slot_errbuf_lock, flags);
 	memset(slot_errbuf, 0, eeh_error_buf_size);
 
-	/* Figure out the PE address */
-	config_addr = pe->config_addr;
-	if (pe->addr)
-		config_addr = pe->addr;
-
-	ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, config_addr,
+	ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, pe->addr,
 			BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid),
 			virt_to_phys(drv_log), len,
 			virt_to_phys(slot_errbuf), eeh_error_buf_size,
@@ -832,14 +658,7 @@ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, u
  */
 static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 {
-	int config_addr;
-
-	/* Figure out the PE address */
-	config_addr = pe->config_addr;
-	if (pe->addr)
-		config_addr = pe->addr;
-
-	return pseries_eeh_phb_configure_bridge(pe->phb, config_addr);
+	return pseries_eeh_phb_configure_bridge(pe->phb, pe->addr);
 }
 
 /**
@@ -954,8 +773,7 @@ static int pseries_notify_resume(struct eeh_dev *edev)
 	if (!edev)
 		return -EEXIST;
 
-	if (rtas_token("ibm,open-sriov-allow-unfreeze")
-	    == RTAS_UNKNOWN_SERVICE)
+	if (rtas_token("ibm,open-sriov-allow-unfreeze") == RTAS_UNKNOWN_SERVICE)
 		return -EINVAL;
 
 	if (edev->pdev->is_physfn || edev->pdev->is_virtfn)
@@ -967,7 +785,6 @@ static int pseries_notify_resume(struct eeh_dev *edev)
 
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
-	.init			= pseries_eeh_init,
 	.probe			= pseries_eeh_probe,
 	.set_option		= pseries_eeh_set_option,
 	.get_state		= pseries_eeh_get_state,
@@ -992,15 +809,84 @@ static struct eeh_ops pseries_eeh_ops = {
  */
 static int __init eeh_pseries_init(void)
 {
-	int ret;
+	struct pci_controller *phb;
+	struct pci_dn *pdn;
+	int ret, config_addr;
 
-	ret = eeh_ops_register(&pseries_eeh_ops);
+	/* figure out EEH RTAS function call tokens */
+	ibm_set_eeh_option		= rtas_token("ibm,set-eeh-option");
+	ibm_set_slot_reset		= rtas_token("ibm,set-slot-reset");
+	ibm_read_slot_reset_state2	= rtas_token("ibm,read-slot-reset-state2");
+	ibm_read_slot_reset_state	= rtas_token("ibm,read-slot-reset-state");
+	ibm_slot_error_detail		= rtas_token("ibm,slot-error-detail");
+	ibm_get_config_addr_info2	= rtas_token("ibm,get-config-addr-info2");
+	ibm_get_config_addr_info	= rtas_token("ibm,get-config-addr-info");
+	ibm_configure_pe		= rtas_token("ibm,configure-pe");
+
+	/*
+	 * ibm,configure-pe and ibm,configure-bridge have the same semantics,
+	 * however ibm,configure-pe can be faster.  If we can't find
+	 * ibm,configure-pe then fall back to using ibm,configure-bridge.
+	 */
+	if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE)
+		ibm_configure_pe	= rtas_token("ibm,configure-bridge");
+
+	/*
+	 * Necessary sanity check. We needn't check "get-config-addr-info"
+	 * and its variant since the old firmware probably support address
+	 * of domain/bus/slot/function for EEH RTAS operations.
+	 */
+	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE		||
+	    ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE		||
+	    (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
+	     ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE)	||
+	    ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE	||
+	    ibm_configure_pe == RTAS_UNKNOWN_SERVICE) {
+		pr_info("EEH functionality not supported\n");
+		return -EINVAL;
+	}
+
+	/* Initialize error log lock and size */
+	spin_lock_init(&slot_errbuf_lock);
+	eeh_error_buf_size = rtas_token("rtas-error-log-max");
+	if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) {
+		pr_info("%s: unknown EEH error log size\n",
+			__func__);
+		eeh_error_buf_size = 1024;
+	} else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) {
+		pr_info("%s: EEH error log size %d exceeds the maximal %d\n",
+			__func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX);
+		eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
+	}
+
+	/* Set EEH probe mode */
+	eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG);
+
+	/* Set EEH machine dependent code */
+	ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device;
+
+	if (is_kdump_kernel() || reset_devices) {
+		pr_info("Issue PHB reset ...\n");
+		list_for_each_entry(phb, &hose_list, list_node) {
+			pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list);
+			config_addr = pseries_eeh_get_pe_config_addr(pdn);
+
+			/* invalid PE config addr */
+			if (config_addr < 0)
+				continue;
+
+			pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL);
+			pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE);
+			pseries_eeh_phb_configure_bridge(phb, config_addr);
+		}
+	}
+
+	ret = eeh_init(&pseries_eeh_ops);
 	if (!ret)
 		pr_info("EEH: pSeries platform initialized\n");
 	else
 		pr_info("EEH: pSeries platform initialization failure (%d)\n",
 			ret);
-
 	return ret;
 }
-machine_early_initcall(pseries, eeh_pseries_init);
+machine_arch_initcall(pseries, eeh_pseries_init);
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 7a974ed6b240..f2837e33bf5d 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -55,7 +55,7 @@ static void rtas_stop_self(void)
 	panic("Alas, I survived.\n");
 }
 
-static void pseries_mach_cpu_die(void)
+static void pseries_cpu_offline_self(void)
 {
 	unsigned int hwcpu = hard_smp_processor_id();
 
@@ -102,7 +102,7 @@ static int pseries_cpu_disable(void)
  * to self-destroy so that the cpu-offline thread can send the CPU_DEAD
  * notifications.
  *
- * OTOH, pseries_mach_cpu_die() is called by the @cpu when it wants to
+ * OTOH, pseries_cpu_offline_self() is called by the @cpu when it wants to
  * self-destruct.
  */
 static void pseries_cpu_die(unsigned int cpu)
@@ -901,7 +901,7 @@ static int __init pseries_cpu_hotplug_init(void)
 		return 0;
 	}
 
-	ppc_md.cpu_die = pseries_mach_cpu_die;
+	smp_ops->cpu_offline_self = pseries_cpu_offline_self;
 	smp_ops->cpu_disable = pseries_cpu_disable;
 	smp_ops->cpu_die = pseries_cpu_die;
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index d8bbf0cc1601..7efe6ec5d14a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -30,12 +30,17 @@ unsigned long pseries_memory_block_size(void)
 
 	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (np) {
-		const __be64 *size;
+		int len;
+		int size_cells;
+		const __be32 *prop;
 
-		size = of_get_property(np, "ibm,lmb-size", NULL);
-		if (size)
-			memblock_size = be64_to_cpup(size);
+		size_cells = of_n_size_cells(np);
+
+		prop = of_get_property(np, "ibm,lmb-size", &len);
+		if (prop && len >= size_cells * sizeof(__be32))
+			memblock_size = of_read_number(prop, size_cells);
 		of_node_put(np);
+
 	} else  if (machine_is(pseries)) {
 		/* This fallback really only applies to pseries */
 		unsigned int memzero_size = 0;
@@ -277,7 +282,7 @@ static int dlpar_offline_lmb(struct drmem_lmb *lmb)
 	return dlpar_change_lmb_state(lmb, false);
 }
 
-static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
+static int pseries_remove_memblock(unsigned long base, unsigned long memblock_size)
 {
 	unsigned long block_sz, start_pfn;
 	int sections_per_block;
@@ -308,10 +313,11 @@ out:
 
 static int pseries_remove_mem_node(struct device_node *np)
 {
-	const __be32 *regs;
+	const __be32 *prop;
 	unsigned long base;
-	unsigned int lmb_size;
+	unsigned long lmb_size;
 	int ret = -EINVAL;
+	int addr_cells, size_cells;
 
 	/*
 	 * Check to see if we are actually removing memory
@@ -322,12 +328,19 @@ static int pseries_remove_mem_node(struct device_node *np)
 	/*
 	 * Find the base address and size of the memblock
 	 */
-	regs = of_get_property(np, "reg", NULL);
-	if (!regs)
+	prop = of_get_property(np, "reg", NULL);
+	if (!prop)
 		return ret;
 
-	base = be64_to_cpu(*(unsigned long *)regs);
-	lmb_size = be32_to_cpu(regs[3]);
+	addr_cells = of_n_addr_cells(np);
+	size_cells = of_n_size_cells(np);
+
+	/*
+	 * "reg" property represents (addr,size) tuple.
+	 */
+	base = of_read_number(prop, addr_cells);
+	prop += addr_cells;
+	lmb_size = of_read_number(prop, size_cells);
 
 	pseries_remove_memblock(base, lmb_size);
 	return 0;
@@ -354,25 +367,32 @@ static int dlpar_add_lmb(struct drmem_lmb *);
 
 static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 {
+	struct memory_block *mem_block;
 	unsigned long block_sz;
 	int rc;
 
 	if (!lmb_is_removable(lmb))
 		return -EINVAL;
 
+	mem_block = lmb_to_memblock(lmb);
+	if (mem_block == NULL)
+		return -EINVAL;
+
 	rc = dlpar_offline_lmb(lmb);
-	if (rc)
+	if (rc) {
+		put_device(&mem_block->dev);
 		return rc;
+	}
 
 	block_sz = pseries_memory_block_size();
 
-	__remove_memory(lmb->nid, lmb->base_addr, block_sz);
+	__remove_memory(mem_block->nid, lmb->base_addr, block_sz);
+	put_device(&mem_block->dev);
 
 	/* Update memory regions for memory remove */
 	memblock_remove(lmb->base_addr, block_sz);
 
 	invalidate_lmb_associativity_index(lmb);
-	lmb_clear_nid(lmb);
 	lmb->flags &= ~DRCONF_MEM_ASSIGNED;
 
 	return 0;
@@ -557,7 +577,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 
 #else
 static inline int pseries_remove_memblock(unsigned long base,
-					  unsigned int memblock_size)
+					  unsigned long memblock_size)
 {
 	return -EOPNOTSUPP;
 }
@@ -591,7 +611,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 static int dlpar_add_lmb(struct drmem_lmb *lmb)
 {
 	unsigned long block_sz;
-	int rc;
+	int nid, rc;
 
 	if (lmb->flags & DRCONF_MEM_ASSIGNED)
 		return -EINVAL;
@@ -602,11 +622,15 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 		return rc;
 	}
 
-	lmb_set_nid(lmb);
 	block_sz = memory_block_size_bytes();
 
+	/* Find the node id for this LMB.  Fake one if necessary. */
+	nid = of_drconf_to_nid_single(lmb);
+	if (nid < 0 || !node_possible(nid))
+		nid = first_online_node;
+
 	/* Add the memory */
-	rc = __add_memory(lmb->nid, lmb->base_addr, block_sz, MHP_NONE);
+	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE);
 	if (rc) {
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
@@ -614,9 +638,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 
 	rc = dlpar_online_lmb(lmb);
 	if (rc) {
-		__remove_memory(lmb->nid, lmb->base_addr, block_sz);
+		__remove_memory(nid, lmb->base_addr, block_sz);
 		invalidate_lmb_associativity_index(lmb);
-		lmb_clear_nid(lmb);
 	} else {
 		lmb->flags |= DRCONF_MEM_ASSIGNED;
 	}
@@ -878,10 +901,11 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 
 static int pseries_add_mem_node(struct device_node *np)
 {
-	const __be32 *regs;
+	const __be32 *prop;
 	unsigned long base;
-	unsigned int lmb_size;
+	unsigned long lmb_size;
 	int ret = -EINVAL;
+	int addr_cells, size_cells;
 
 	/*
 	 * Check to see if we are actually adding memory
@@ -892,12 +916,18 @@ static int pseries_add_mem_node(struct device_node *np)
 	/*
 	 * Find the base and size of the memblock
 	 */
-	regs = of_get_property(np, "reg", NULL);
-	if (!regs)
+	prop = of_get_property(np, "reg", NULL);
+	if (!prop)
 		return ret;
 
-	base = be64_to_cpu(*(unsigned long *)regs);
-	lmb_size = be32_to_cpu(regs[3]);
+	addr_cells = of_n_addr_cells(np);
+	size_cells = of_n_size_cells(np);
+	/*
+	 * "reg" property represents (addr,size) tuple.
+	 */
+	base = of_read_number(prop, addr_cells);
+	prop += addr_cells;
+	lmb_size = of_read_number(prop, size_cells);
 
 	/*
 	 * Update memory region to represent the memory add
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index c40c62ec432e..2c59b4986ea5 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -70,31 +70,14 @@ static int hc_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-static const struct seq_operations hcall_inst_seq_ops = {
+static const struct seq_operations hcall_inst_sops = {
         .start = hc_start,
         .next  = hc_next,
         .stop  = hc_stop,
         .show  = hc_show
 };
 
-static int hcall_inst_seq_open(struct inode *inode, struct file *file)
-{
-	int rc;
-	struct seq_file *seq;
-
-	rc = seq_open(file, &hcall_inst_seq_ops);
-	seq = file->private_data;
-	seq->private = file_inode(file)->i_private;
-
-	return rc;
-}
-
-static const struct file_operations hcall_inst_seq_fops = {
-	.open = hcall_inst_seq_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release,
-};
+DEFINE_SEQ_ATTRIBUTE(hcall_inst);
 
 #define	HCALL_ROOT_DIR		"hcall_inst"
 #define CPU_NAME_BUF_SIZE	32
@@ -149,7 +132,7 @@ static int __init hcall_inst_init(void)
 		snprintf(cpu_name_buf, CPU_NAME_BUF_SIZE, "cpu%d", cpu);
 		debugfs_create_file(cpu_name_buf, 0444, hcall_root,
 				    per_cpu(hcall_stats, cpu),
-				    &hcall_inst_seq_fops);
+				    &hcall_inst_fops);
 	}
 
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 6d47b4a3ce39..e4198700ed1a 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -39,6 +39,20 @@
 
 #include "pseries.h"
 
+enum {
+	DDW_QUERY_PE_DMA_WIN  = 0,
+	DDW_CREATE_PE_DMA_WIN = 1,
+	DDW_REMOVE_PE_DMA_WIN = 2,
+
+	DDW_APPLICABLE_SIZE
+};
+
+enum {
+	DDW_EXT_SIZE = 0,
+	DDW_EXT_RESET_DMA_WIN = 1,
+	DDW_EXT_QUERY_OUT_SIZE = 2
+};
+
 static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 {
 	struct iommu_table_group *table_group;
@@ -334,7 +348,7 @@ struct direct_window {
 /* Dynamic DMA Window support */
 struct ddw_query_response {
 	u32 windows_available;
-	u32 largest_available_block;
+	u64 largest_available_block;
 	u32 page_size;
 	u32 migration_capable;
 };
@@ -767,25 +781,14 @@ static int __init disable_ddw_setup(char *str)
 
 early_param("disable_ddw", disable_ddw_setup);
 
-static void remove_ddw(struct device_node *np, bool remove_prop)
+static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
+			      struct property *win)
 {
 	struct dynamic_dma_window_prop *dwp;
-	struct property *win64;
-	u32 ddw_avail[3];
 	u64 liobn;
-	int ret = 0;
-
-	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
-					 &ddw_avail[0], 3);
-
-	win64 = of_find_property(np, DIRECT64_PROPNAME, NULL);
-	if (!win64)
-		return;
-
-	if (ret || win64->length < sizeof(*dwp))
-		goto delprop;
+	int ret;
 
-	dwp = win64->value;
+	dwp = win->value;
 	liobn = (u64)be32_to_cpu(dwp->liobn);
 
 	/* clear the whole window, note the arg is in kernel pages */
@@ -798,19 +801,39 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 		pr_debug("%pOF successfully cleared tces in window.\n",
 			 np);
 
-	ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn);
+	ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn);
 	if (ret)
 		pr_warn("%pOF: failed to remove direct window: rtas returned "
 			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
-			np, ret, ddw_avail[2], liobn);
+			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
 	else
 		pr_debug("%pOF: successfully removed direct window: rtas returned "
 			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
-			np, ret, ddw_avail[2], liobn);
+			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
+}
+
+static void remove_ddw(struct device_node *np, bool remove_prop)
+{
+	struct property *win;
+	u32 ddw_avail[DDW_APPLICABLE_SIZE];
+	int ret = 0;
 
-delprop:
-	if (remove_prop)
-		ret = of_remove_property(np, win64);
+	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
+					 &ddw_avail[0], DDW_APPLICABLE_SIZE);
+	if (ret)
+		return;
+
+	win = of_find_property(np, DIRECT64_PROPNAME, NULL);
+	if (!win)
+		return;
+
+	if (win->length >= sizeof(struct dynamic_dma_window_prop))
+		remove_dma_window(np, ddw_avail, win);
+
+	if (!remove_prop)
+		return;
+
+	ret = of_remove_property(np, win);
 	if (ret)
 		pr_warn("%pOF: failed to remove direct window property: %d\n",
 			np, ret);
@@ -869,14 +892,62 @@ static int find_existing_ddw_windows(void)
 }
 machine_arch_initcall(pseries, find_existing_ddw_windows);
 
+/**
+ * ddw_read_ext - Get the value of an DDW extension
+ * @np:		device node from which the extension value is to be read.
+ * @extnum:	index number of the extension.
+ * @value:	pointer to return value, modified when extension is available.
+ *
+ * Checks if "ibm,ddw-extensions" exists for this node, and get the value
+ * on index 'extnum'.
+ * It can be used only to check if a property exists, passing value == NULL.
+ *
+ * Returns:
+ *	0 if extension successfully read
+ *	-EINVAL if the "ibm,ddw-extensions" does not exist,
+ *	-ENODATA if "ibm,ddw-extensions" does not have a value, and
+ *	-EOVERFLOW if "ibm,ddw-extensions" does not contain this extension.
+ */
+static inline int ddw_read_ext(const struct device_node *np, int extnum,
+			       u32 *value)
+{
+	static const char propname[] = "ibm,ddw-extensions";
+	u32 count;
+	int ret;
+
+	ret = of_property_read_u32_index(np, propname, DDW_EXT_SIZE, &count);
+	if (ret)
+		return ret;
+
+	if (count < extnum)
+		return -EOVERFLOW;
+
+	if (!value)
+		value = &count;
+
+	return of_property_read_u32_index(np, propname, extnum, value);
+}
+
 static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
-			struct ddw_query_response *query)
+		     struct ddw_query_response *query,
+		     struct device_node *parent)
 {
 	struct device_node *dn;
 	struct pci_dn *pdn;
-	u32 cfg_addr;
+	u32 cfg_addr, ext_query, query_out[5];
 	u64 buid;
-	int ret;
+	int ret, out_sz;
+
+	/*
+	 * From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can rule how many
+	 * output parameters ibm,query-pe-dma-windows will have, ranging from
+	 * 5 to 6.
+	 */
+	ret = ddw_read_ext(parent, DDW_EXT_QUERY_OUT_SIZE, &ext_query);
+	if (!ret && ext_query == 1)
+		out_sz = 6;
+	else
+		out_sz = 5;
 
 	/*
 	 * Get the config address and phb buid of the PE window.
@@ -889,11 +960,28 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	buid = pdn->phb->buid;
 	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
 
-	ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
-		  cfg_addr, BUID_HI(buid), BUID_LO(buid));
-	dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x"
-		" returned %d\n", ddw_avail[0], cfg_addr, BUID_HI(buid),
-		BUID_LO(buid), ret);
+	ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out,
+			cfg_addr, BUID_HI(buid), BUID_LO(buid));
+	dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d\n",
+		 ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid),
+		 BUID_LO(buid), ret);
+
+	switch (out_sz) {
+	case 5:
+		query->windows_available = query_out[0];
+		query->largest_available_block = query_out[1];
+		query->page_size = query_out[2];
+		query->migration_capable = query_out[3];
+		break;
+	case 6:
+		query->windows_available = query_out[0];
+		query->largest_available_block = ((u64)query_out[1] << 32) |
+						 query_out[2];
+		query->page_size = query_out[3];
+		query->migration_capable = query_out[4];
+		break;
+	}
+
 	return ret;
 }
 
@@ -920,15 +1008,16 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
-		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create,
-				cfg_addr, BUID_HI(buid), BUID_LO(buid),
-				page_shift, window_shift);
+		ret = rtas_call(ddw_avail[DDW_CREATE_PE_DMA_WIN], 5, 4,
+				(u32 *)create, cfg_addr, BUID_HI(buid),
+				BUID_LO(buid), page_shift, window_shift);
 	} while (rtas_busy_delay(ret));
 	dev_info(&dev->dev,
 		"ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d "
-		"(liobn = 0x%x starting addr = %x %x)\n", ddw_avail[1],
-		 cfg_addr, BUID_HI(buid), BUID_LO(buid), page_shift,
-		 window_shift, ret, create->liobn, create->addr_hi, create->addr_lo);
+		"(liobn = 0x%x starting addr = %x %x)\n",
+		 ddw_avail[DDW_CREATE_PE_DMA_WIN], cfg_addr, BUID_HI(buid),
+		 BUID_LO(buid), page_shift, window_shift, ret, create->liobn,
+		 create->addr_hi, create->addr_lo);
 
 	return ret;
 }
@@ -978,6 +1067,38 @@ static phys_addr_t ddw_memory_hotplug_max(void)
 }
 
 /*
+ * Platforms supporting the DDW option starting with LoPAR level 2.7 implement
+ * ibm,ddw-extensions, which carries the rtas token for
+ * ibm,reset-pe-dma-windows.
+ * That rtas-call can be used to restore the default DMA window for the device.
+ */
+static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
+{
+	int ret;
+	u32 cfg_addr, reset_dma_win;
+	u64 buid;
+	struct device_node *dn;
+	struct pci_dn *pdn;
+
+	ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win);
+	if (ret)
+		return;
+
+	dn = pci_device_to_OF_node(dev);
+	pdn = PCI_DN(dn);
+	buid = pdn->phb->buid;
+	cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8);
+
+	ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid),
+			BUID_LO(buid));
+	if (ret)
+		dev_info(&dev->dev,
+			 "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ",
+			 reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
+			 ret);
+}
+
+/*
  * If the PE supports dynamic dma windows, and there is space for a table
  * that can map all pages in a linear offset, then setup such a table,
  * and record the dma-offset in the struct device.
@@ -996,11 +1117,12 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	int page_shift;
 	u64 dma_addr, max_addr;
 	struct device_node *dn;
-	u32 ddw_avail[3];
+	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	struct direct_window *window;
 	struct property *win64;
 	struct dynamic_dma_window_prop *ddwprop;
 	struct failed_ddw_pdn *fpdn;
+	bool default_win_removed = false;
 
 	mutex_lock(&direct_window_init_mutex);
 
@@ -1029,7 +1151,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * the property is actually in the parent, not the PE
 	 */
 	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
-					 &ddw_avail[0], 3);
+					 &ddw_avail[0], DDW_APPLICABLE_SIZE);
 	if (ret)
 		goto out_failed;
 
@@ -1040,18 +1162,42 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * of page sizes: supported and supported for migrate-dma.
 	 */
 	dn = pci_device_to_OF_node(dev);
-	ret = query_ddw(dev, ddw_avail, &query);
+	ret = query_ddw(dev, ddw_avail, &query, pdn);
 	if (ret != 0)
 		goto out_failed;
 
+	/*
+	 * If there is no window available, remove the default DMA window,
+	 * if it's present. This will make all the resources available to the
+	 * new DDW window.
+	 * If anything fails after this, we need to restore it, so also check
+	 * for extensions presence.
+	 */
 	if (query.windows_available == 0) {
-		/*
-		 * no additional windows are available for this device.
-		 * We might be able to reallocate the existing window,
-		 * trading in for a larger page size.
-		 */
-		dev_dbg(&dev->dev, "no free dynamic windows");
-		goto out_failed;
+		struct property *default_win;
+		int reset_win_ext;
+
+		default_win = of_find_property(pdn, "ibm,dma-window", NULL);
+		if (!default_win)
+			goto out_failed;
+
+		reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL);
+		if (reset_win_ext)
+			goto out_failed;
+
+		remove_dma_window(pdn, ddw_avail, default_win);
+		default_win_removed = true;
+
+		/* Query again, to check if the window is available */
+		ret = query_ddw(dev, ddw_avail, &query, pdn);
+		if (ret != 0)
+			goto out_failed;
+
+		if (query.windows_available == 0) {
+			/* no windows are available for this device. */
+			dev_dbg(&dev->dev, "no free dynamic windows");
+			goto out_failed;
+		}
 	}
 	if (query.page_size & 4) {
 		page_shift = 24; /* 16MB */
@@ -1068,7 +1214,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	/* check largest block * page size > max memory hotplug addr */
 	max_addr = ddw_memory_hotplug_max();
 	if (query.largest_available_block < (max_addr >> page_shift)) {
-		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u "
+		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
 			  1ULL << page_shift);
 		goto out_failed;
@@ -1142,6 +1288,8 @@ out_free_prop:
 	kfree(win64);
 
 out_failed:
+	if (default_win_removed)
+		reset_dma_window(dev, pdn);
 
 	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
 	if (!fpdn)
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index baf24eacd268..764170fdb0f7 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -1724,6 +1724,7 @@ void __init hpte_init_pseries(void)
 		pseries_lpar_register_process_table(0, 0, 0);
 }
 
+#ifdef CONFIG_PPC_RADIX_MMU
 void radix_init_pseries(void)
 {
 	pr_info("Using radix MMU under hypervisor\n");
@@ -1731,6 +1732,7 @@ void radix_init_pseries(void)
 	pseries_lpar_register_process_table(__pa(process_tb),
 						0, PRTB_SIZE_SHIFT - 12);
 }
+#endif
 
 #ifdef CONFIG_PPC_SMLPAR
 #define CMO_FREE_HINT_DEFAULT 1
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index b8d28ab88178..e278390ab28d 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -136,6 +136,39 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
 	return rc;
 }
 
+static void show_gpci_data(struct seq_file *m)
+{
+	struct hv_gpci_request_buffer *buf;
+	unsigned int affinity_score;
+	long ret;
+
+	buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+	if (buf == NULL)
+		return;
+
+	/*
+	 * Show the local LPAR's affinity score.
+	 *
+	 * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall.
+	 * The score is at byte 0xB in the output buffer.
+	 */
+	memset(&buf->params, 0, sizeof(buf->params));
+	buf->params.counter_request = cpu_to_be32(0xB1);
+	buf->params.starting_index = cpu_to_be32(-1);	/* local LPAR */
+	buf->params.counter_info_version_in = 0x5;	/* v5+ for score */
+	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf),
+				 sizeof(*buf));
+	if (ret != H_SUCCESS) {
+		pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n",
+			 ret, be32_to_cpu(buf->params.detail_rc));
+		goto out;
+	}
+	affinity_score = buf->bytes[0xB];
+	seq_printf(m, "partition_affinity_score=%u\n", affinity_score);
+out:
+	kfree(buf);
+}
+
 static unsigned h_pic(unsigned long *pool_idle_time,
 		      unsigned long *num_procs)
 {
@@ -487,6 +520,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 			   partition_active_processors * 100);
 	}
 
+	show_gpci_data(m);
+
 	seq_printf(m, "partition_active_processors=%d\n",
 		   partition_active_processors);
 
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index a88a707a608a..835163f54244 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -785,7 +785,8 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
 static ssize_t perf_stats_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
-	int index, rc;
+	int index;
+	ssize_t rc;
 	struct seq_buf s;
 	struct papr_scm_perf_stat *stat;
 	struct papr_scm_perf_stats *stats;
@@ -820,9 +821,9 @@ static ssize_t perf_stats_show(struct device *dev,
 
 free_stats:
 	kfree(stats);
-	return rc ? rc : seq_buf_used(&s);
+	return rc ? rc : (ssize_t)seq_buf_used(&s);
 }
-DEVICE_ATTR_ADMIN_RO(perf_stats);
+static DEVICE_ATTR_ADMIN_RO(perf_stats);
 
 static ssize_t flags_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)
@@ -897,6 +898,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	p->bus_desc.of_node = p->pdev->dev.of_node;
 	p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL);
 
+	/* Set the dimm command family mask to accept PDSMs */
+	set_bit(NVDIMM_FAMILY_PAPR, &p->bus_desc.dimm_family_mask);
+
 	if (!p->bus_desc.provider_name)
 		return -ENOMEM;
 
diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c
index bbb97169bf63..6268545947b8 100644
--- a/arch/powerpc/platforms/pseries/rng.c
+++ b/arch/powerpc/platforms/pseries/rng.c
@@ -36,6 +36,7 @@ static __init int rng_init(void)
 
 	ppc_md.get_random_seed = pseries_get_random_long;
 
+	of_node_put(dn);
 	return 0;
 }
 machine_subsys_initcall(pseries, rng_init);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 2f4ee0a90284..633c45ec406d 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -519,9 +519,15 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result)
 	if (result->character & H_CPU_CHAR_BCCTR_FLUSH_ASSIST)
 		security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST);
 
+	if (result->character & H_CPU_CHAR_BCCTR_LINK_FLUSH_ASSIST)
+		security_ftr_set(SEC_FTR_BCCTR_LINK_FLUSH_ASSIST);
+
 	if (result->behaviour & H_CPU_BEHAV_FLUSH_COUNT_CACHE)
 		security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE);
 
+	if (result->behaviour & H_CPU_BEHAV_FLUSH_LINK_STACK)
+		security_ftr_set(SEC_FTR_FLUSH_LINK_STACK);
+
 	/*
 	 * The features below are enabled by default, so we instead look to see
 	 * if firmware has *disabled* them, and clear them if so.
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index e6d7a344d9f2..7b739cc7a8a9 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/memblock.h>
 #include <asm/machdep.h>
 #include <asm/svm.h>
 #include <asm/swiotlb.h>
@@ -35,6 +36,31 @@ static int __init init_svm(void)
 }
 machine_early_initcall(pseries, init_svm);
 
+/*
+ * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it
+ * can allocate the buffer anywhere in memory. Since the hypervisor doesn't have
+ * any addressing limitation, we don't need to allocate it in low addresses.
+ */
+void __init svm_swiotlb_init(void)
+{
+	unsigned char *vstart;
+	unsigned long bytes, io_tlb_nslabs;
+
+	io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT);
+	io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+
+	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+	vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE);
+	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false))
+		return;
+
+	if (io_tlb_start)
+		memblock_free_early(io_tlb_start,
+				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+	panic("SVM: Cannot allocate SWIOTLB buffer");
+}
+
 int set_memory_encrypted(unsigned long addr, int numpages)
 {
 	if (!PAGE_ALIGNED(addr))