Merge tag 'powerpc-5.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "A pretty small batch for us, and apologies for it being a bit late, I
  wanted to sneak Christophe's user_access_begin() series in.

  Summary:

   - Implement user_access_begin() and friends for our platforms that
     support controlling kernel access to userspace.

   - Enable CONFIG_VMAP_STACK on 32-bit Book3S and 8xx.

   - Some tweaks to our pseries IOMMU code to allow SVMs ("secure"
     virtual machines) to use the IOMMU.

   - Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE to the 32-bit
     VDSO, and some other improvements.

   - A series to use the PCI hotplug framework to control opencapi
     card's so that they can be reset and re-read after flashing a new
     FPGA image.

  As well as other minor fixes and improvements as usual.

  Thanks to: Alastair D'Silva, Alexandre Ghiti, Alexey Kardashevskiy,
  Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Bai Yingjie, Chen
  Zhou, Christophe Leroy, Frederic Barrat, Greg Kurz, Jason A.
  Donenfeld, Joel Stanley, Jordan Niethe, Julia Lawall, Krzysztof
  Kozlowski, Laurent Dufour, Laurentiu Tudor, Linus Walleij, Michael
  Bringmann, Nathan Chancellor, Nicholas Piggin, Nick Desaulniers,
  Oliver O'Halloran, Peter Ujfalusi, Pingfan Liu, Ram Pai, Randy Dunlap,
  Russell Currey, Sam Bobroff, Sebastian Andrzej Siewior, Shawn
  Anastasio, Stephen Rothwell, Steve Best, Sukadev Bhattiprolu, Thiago
  Jung Bauermann, Tyrel Datwyler, Vaibhav Jain"

* tag 'powerpc-5.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (131 commits)
  powerpc: configs: Cleanup old Kconfig options
  powerpc/configs/skiroot: Enable some more hardening options
  powerpc/configs/skiroot: Disable xmon default & enable reboot on panic
  powerpc/configs/skiroot: Enable security features
  powerpc/configs/skiroot: Update for symbol movement only
  powerpc/configs/skiroot: Drop default n CONFIG_CRYPTO_ECHAINIV
  powerpc/configs/skiroot: Drop HID_LOGITECH
  powerpc/configs: Drop NET_VENDOR_HP which moved to staging
  powerpc/configs: NET_CADENCE became NET_VENDOR_CADENCE
  powerpc/configs: Drop CONFIG_QLGE which moved to staging
  powerpc: Do not consider weak unresolved symbol relocations as bad
  powerpc/32s: Fix kasan_early_hash_table() for CONFIG_VMAP_STACK
  powerpc: indent to improve Kconfig readability
  powerpc: Provide initial documentation for PAPR hcalls
  powerpc: Implement user_access_save() and user_access_restore()
  powerpc: Implement user_access_begin and friends
  powerpc/32s: Prepare prevent_user_access() for user_access_end()
  powerpc/32s: Drop NULL addr verification
  powerpc/kuap: Fix set direction in allow/prevent_user_access()
  powerpc/32s: Fix bad_kuap_fault()
  ...

20 files changed, 357 insertions, 242 deletions

diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index 13631f35cd14..04bf6ecf7d55 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -434,9 +434,9 @@ static int mpc512x_lpbfifo_probe(struct platform_device *pdev)
 	memset(&lpbfifo, 0, sizeof(struct lpbfifo_data));
 	spin_lock_init(&lpbfifo.lock);
 
-	lpbfifo.chan = dma_request_slave_channel(&pdev->dev, "rx-tx");
-	if (lpbfifo.chan == NULL)
-		return -EPROBE_DEFER;
+	lpbfifo.chan = dma_request_chan(&pdev->dev, "rx-tx");
+	if (IS_ERR(lpbfifo.chan))
+		return PTR_ERR(lpbfifo.chan);
 
 	if (of_address_to_resource(pdev->dev.of_node, 0, &r) != 0) {
 		dev_err(&pdev->dev, "bad 'reg' in 'sclpc' device tree node\n");
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index 273145aed90a..b0d5471f620d 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -64,7 +64,7 @@ static void quirk_mpc8360e_qe_enet10(void)
 		return;
 	}
 
-	base = ioremap(res.start, res.end - res.start + 1);
+	base = ioremap(res.start, resource_size(&res));
 
 	/*
 	 * set output delay adjustments to default values according
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 8c7ea2486bc0..48f7d96ae37d 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -252,6 +252,15 @@ static int smp_85xx_start_cpu(int cpu)
 	out_be64((u64 *)(&spin_table->addr_h),
 		__pa(ppc_function_entry(generic_secondary_smp_init)));
 #else
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	/*
+	 * We need also to write addr_h to spin table for systems
+	 * in which their physical memory start address was configured
+	 * to above 4G, otherwise the secondary core can not get
+	 * correct entry to start from.
+	 */
+	out_be32(&spin_table->addr_h, __pa(__early_start) >> 32);
+#endif
 	out_be32(&spin_table->addr_l, __pa(__early_start));
 #endif
 	flush_spin_table(spin_table);
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index 6c3c0cdaee9a..b301ef9d6ce7 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -60,10 +60,6 @@ static void __init twr_p1025_pic_init(void)
  */
 static void __init twr_p1025_setup_arch(void)
 {
-#ifdef CONFIG_QUICC_ENGINE
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("twr_p1025_setup_arch()", 0);
 
@@ -77,6 +73,7 @@ static void __init twr_p1025_setup_arch(void)
 #if IS_ENABLED(CONFIG_UCC_GETH) || IS_ENABLED(CONFIG_SERIAL_QE)
 	if (machine_is(twr_p1025)) {
 		struct ccsr_guts __iomem *guts;
+		struct device_node *np;
 
 		np = of_find_compatible_node(NULL, NULL, "fsl,p1021-guts");
 		if (np) {
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index e28df298df56..1f8025383caa 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -177,6 +177,10 @@ config PPC_970_NAP
 config PPC_P7_NAP
 	bool
 
+config PPC_BOOK3S_IDLE
+	def_bool y
+	depends on (PPC_970_NAP || PPC_P7_NAP)
+
 config PPC_INDIRECT_PIO
 	bool
 	select GENERIC_IOMAP
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 8d7f9c3dc771..6caedc88474f 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,4 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
+config PPC32
+	bool
+	default y if !PPC64
+	select KASAN_VMALLOC if KASAN && MODULES
+
 config PPC64
 	bool "64-bit kernel"
 	select ZLIB_DEFLATE
@@ -31,12 +36,14 @@ config PPC_BOOK3S_6xx
 	select PPC_HAVE_PMU_SUPPORT
 	select PPC_HAVE_KUEP
 	select PPC_HAVE_KUAP
+	select HAVE_ARCH_VMAP_STACK
 
 config PPC_BOOK3S_601
 	bool "PowerPC 601"
 	select PPC_BOOK3S_32
 	select PPC_FPU
 	select PPC_HAVE_KUAP
+	select HAVE_ARCH_VMAP_STACK
 
 config PPC_85xx
 	bool "Freescale 85xx"
@@ -49,6 +56,7 @@ config PPC_8xx
 	select PPC_HAVE_KUEP
 	select PPC_HAVE_KUAP
 	select PPC_MM_SLICES if HUGETLB_PAGE
+	select HAVE_ARCH_VMAP_STACK
 
 config 40x
 	bool "AMCC 40x"
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 47f73103ef74..6f019df37916 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -229,7 +229,7 @@ static void __init maple_init_IRQ(void)
 	root = of_find_node_by_path("/");
 	naddr = of_n_addr_cells(root);
 	opprop = of_get_property(root, "platform-open-pic", &opplen);
-	if (opprop != 0) {
+	if (opprop) {
 		openpic_addr = of_read_number(opprop, naddr);
 		has_isus = (opplen > naddr);
 		printk(KERN_DEBUG "OpenPIC addr: %lx, has ISUs: %d\n",
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index a6ee08009f0f..2b3dfd0b6cdd 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -790,48 +790,81 @@ static int opal_sysfs_init(void)
 	return 0;
 }
 
-static ssize_t symbol_map_read(struct file *fp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr,
-			       char *buf, loff_t off, size_t count)
+static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
+				struct bin_attribute *bin_attr, char *buf,
+				loff_t off, size_t count)
 {
 	return memory_read_from_buffer(buf, count, &off, bin_attr->private,
 				       bin_attr->size);
 }
 
-static struct bin_attribute symbol_map_attr = {
-	.attr = {.name = "symbol_map", .mode = 0400},
-	.read = symbol_map_read
-};
-
-static void opal_export_symmap(void)
+static int opal_add_one_export(struct kobject *parent, const char *export_name,
+			       struct device_node *np, const char *prop_name)
 {
-	const __be64 *syms;
-	unsigned int size;
-	struct device_node *fw;
+	struct bin_attribute *attr = NULL;
+	const char *name = NULL;
+	u64 vals[2];
 	int rc;
 
-	fw = of_find_node_by_path("/ibm,opal/firmware");
-	if (!fw)
-		return;
-	syms = of_get_property(fw, "symbol-map", &size);
-	if (!syms || size != 2 * sizeof(__be64))
-		return;
+	rc = of_property_read_u64_array(np, prop_name, &vals[0], 2);
+	if (rc)
+		goto out;
 
-	/* Setup attributes */
-	symbol_map_attr.private = __va(be64_to_cpu(syms[0]));
-	symbol_map_attr.size = be64_to_cpu(syms[1]);
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	name = kstrdup(export_name, GFP_KERNEL);
+	if (!name) {
+		rc = -ENOMEM;
+		goto out;
+	}
 
-	rc = sysfs_create_bin_file(opal_kobj, &symbol_map_attr);
-	if (rc)
-		pr_warn("Error %d creating OPAL symbols file\n", rc);
+	sysfs_bin_attr_init(attr);
+	attr->attr.name = name;
+	attr->attr.mode = 0400;
+	attr->read = export_attr_read;
+	attr->private = __va(vals[0]);
+	attr->size = vals[1];
+
+	rc = sysfs_create_bin_file(parent, attr);
+out:
+	if (rc) {
+		kfree(name);
+		kfree(attr);
+	}
+
+	return rc;
 }
 
-static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *buf,
-				loff_t off, size_t count)
+static void opal_add_exported_attrs(struct device_node *np,
+				    struct kobject *kobj)
 {
-	return memory_read_from_buffer(buf, count, &off, bin_attr->private,
-				       bin_attr->size);
+	struct device_node *child;
+	struct property *prop;
+
+	for_each_property_of_node(np, prop) {
+		int rc;
+
+		if (!strcmp(prop->name, "name") ||
+		    !strcmp(prop->name, "phandle"))
+			continue;
+
+		rc = opal_add_one_export(kobj, prop->name, np, prop->name);
+		if (rc) {
+			pr_warn("Unable to add export %pOF/%s, rc = %d!\n",
+				np, prop->name, rc);
+		}
+	}
+
+	for_each_child_of_node(np, child) {
+		struct kobject *child_kobj;
+
+		child_kobj = kobject_create_and_add(child->name, kobj);
+		if (!child_kobj) {
+			pr_err("Unable to create export dir for %pOF\n", child);
+			continue;
+		}
+
+		opal_add_exported_attrs(child, child_kobj);
+	}
 }
 
 /*
@@ -843,11 +876,8 @@ static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
  */
 static void opal_export_attrs(void)
 {
-	struct bin_attribute *attr;
 	struct device_node *np;
-	struct property *prop;
 	struct kobject *kobj;
-	u64 vals[2];
 	int rc;
 
 	np = of_find_node_by_path("/ibm,opal/firmware/exports");
@@ -861,41 +891,16 @@ static void opal_export_attrs(void)
 		return;
 	}
 
-	for_each_property_of_node(np, prop) {
-		if (!strcmp(prop->name, "name") || !strcmp(prop->name, "phandle"))
-			continue;
-
-		if (of_property_read_u64_array(np, prop->name, &vals[0], 2))
-			continue;
-
-		attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	opal_add_exported_attrs(np, kobj);
 
-		if (attr == NULL) {
-			pr_warn("Failed kmalloc for bin_attribute!");
-			continue;
-		}
-
-		sysfs_bin_attr_init(attr);
-		attr->attr.name = kstrdup(prop->name, GFP_KERNEL);
-		attr->attr.mode = 0400;
-		attr->read = export_attr_read;
-		attr->private = __va(vals[0]);
-		attr->size = vals[1];
-
-		if (attr->attr.name == NULL) {
-			pr_warn("Failed kstrdup for bin_attribute attr.name");
-			kfree(attr);
-			continue;
-		}
-
-		rc = sysfs_create_bin_file(kobj, attr);
-		if (rc) {
-			pr_warn("Error %d creating OPAL sysfs exports/%s file\n",
-				 rc, prop->name);
-			kfree(attr->attr.name);
-			kfree(attr);
-		}
-	}
+	/*
+	 * NB: symbol_map existed before the generic export interface so it
+	 * lives under the top level opal_kobj.
+	 */
+	rc = opal_add_one_export(opal_kobj, "symbol_map",
+				 np->parent, "symbol-map");
+	if (rc)
+		pr_warn("Error %d creating OPAL symbols file\n", rc);
 
 	of_node_put(np);
 }
@@ -1042,8 +1047,6 @@ static int __init opal_init(void)
 	/* Create "opal" kobject under /sys/firmware */
 	rc = opal_sysfs_init();
 	if (rc == 0) {
-		/* Export symbol map to userspace */
-		opal_export_symmap();
 		/* Setup dump region interface */
 		opal_dump_region_init();
 		/* Setup error log interface */
@@ -1056,11 +1059,10 @@ static int __init opal_init(void)
 		opal_sys_param_init();
 		/* Setup message log sysfs interface. */
 		opal_msglog_sysfs_init();
+		/* Add all export properties*/
+		opal_export_attrs();
 	}
 
-	/* Export all properties */
-	opal_export_attrs();
-
 	/* Initialize platform devices: IPMI backend, PRD & flash interface */
 	opal_pdev_init("ibm,opal-ipmi");
 	opal_pdev_init("ibm,opal-flash");
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index da1068a9c263..22c22cd7bd82 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -188,7 +188,7 @@ static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 	unsigned int pe_num = pe->pe_number;
 
 	WARN_ON(pe->pdev);
-	WARN_ON(pe->npucomp); /* NPUs are not supposed to be freed */
+	WARN_ON(pe->npucomp); /* NPUs for nvlink are not supposed to be freed */
 	kfree(pe->npucomp);
 	memset(pe, 0, sizeof(struct pnv_ioda_pe));
 	clear_bit(pe_num, phb->ioda.pe_alloc);
@@ -777,6 +777,34 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 	return 0;
 }
 
+static void pnv_ioda_unset_peltv(struct pnv_phb *phb,
+				 struct pnv_ioda_pe *pe,
+				 struct pci_dev *parent)
+{
+	int64_t rc;
+
+	while (parent) {
+		struct pci_dn *pdn = pci_get_pdn(parent);
+
+		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
+						pe->pe_number,
+						OPAL_REMOVE_PE_FROM_DOMAIN);
+			/* XXX What to do in case of error ? */
+		}
+		parent = parent->bus->self;
+	}
+
+	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
+				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+	/* Disassociate PE in PELT */
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc);
+}
+
 static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
@@ -792,7 +820,7 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
 		parent = pe->pbus->self;
 		if (pe->flags & PNV_IODA_PE_BUS_ALL)
-			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+			count = resource_size(&pe->pbus->busn_res);
 		else
 			count = 1;
 
@@ -827,25 +855,13 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	for (rid = pe->rid; rid < rid_end; rid++)
 		phb->ioda.pe_rmap[rid] = IODA_INVALID_PE;
 
-	/* Release from all parents PELT-V */
-	while (parent) {
-		struct pci_dn *pdn = pci_get_pdn(parent);
-		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
-			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
-						pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
-			/* XXX What to do in case of error ? */
-		}
-		parent = parent->bus->self;
-	}
-
-	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
-				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+	/*
+	 * Release from all parents PELT-V. NPUs don't have a PELTV
+	 * table
+	 */
+	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+		pnv_ioda_unset_peltv(phb, pe, parent);
 
-	/* Disassociate PE in PELT */
-	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
-				pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
-	if (rc)
-		pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc);
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
 			     bcomp, dcomp, fcomp, OPAL_UNMAP_PE);
 	if (rc)
@@ -874,7 +890,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
 		parent = pe->pbus->self;
 		if (pe->flags & PNV_IODA_PE_BUS_ALL)
-			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+			count = resource_size(&pe->pbus->busn_res);
 		else
 			count = 1;
 
@@ -1062,20 +1078,20 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 		return NULL;
 	}
 
-	/* NOTE: We get only one ref to the pci_dev for the pdn, not for the
-	 * pointer in the PE data structure, both should be destroyed at the
-	 * same time. However, this needs to be looked at more closely again
-	 * once we actually start removing things (Hotplug, SR-IOV, ...)
+	/* NOTE: We don't get a reference for the pointer in the PE
+	 * data structure, both the device and PE structures should be
+	 * destroyed at the same time. However, removing nvlink
+	 * devices will need some work.
 	 *
 	 * At some point we want to remove the PDN completely anyways
 	 */
-	pci_dev_get(dev);
 	pdn->pe_number = pe->pe_number;
 	pe->flags = PNV_IODA_PE_DEV;
 	pe->pdev = dev;
 	pe->pbus = NULL;
 	pe->mve_number = -1;
 	pe->rid = dev->bus->number << 8 | pdn->devfn;
+	pe->device_count++;
 
 	pe_info(pe, "Associated device to PE\n");
 
@@ -1084,13 +1100,13 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 		pnv_ioda_free_pe(pe);
 		pdn->pe_number = IODA_INVALID_PE;
 		pe->pdev = NULL;
-		pci_dev_put(dev);
 		return NULL;
 	}
 
 	/* Put PE to the list */
+	mutex_lock(&phb->ioda.pe_list_mutex);
 	list_add_tail(&pe->list, &phb->ioda.pe_list);
-
+	mutex_unlock(&phb->ioda.pe_list_mutex);
 	return pe;
 }
 
@@ -1206,6 +1222,14 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 	struct pnv_phb *phb = hose->private_data;
 
 	/*
+	 * Intentionally leak a reference on the npu device (for
+	 * nvlink only; this is not an opencapi path) to make sure it
+	 * never goes away, as it's been the case all along and some
+	 * work is needed otherwise.
+	 */
+	pci_dev_get(npu_pdev);
+
+	/*
 	 * Due to a hardware errata PE#0 on the NPU is reserved for
 	 * error handling. This means we only have three PEs remaining
 	 * which need to be assigned to four links, implying some
@@ -1228,11 +1252,11 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 			 */
 			dev_info(&npu_pdev->dev,
 				"Associating to existing PE %x\n", pe_num);
-			pci_dev_get(npu_pdev);
 			npu_pdn = pci_get_pdn(npu_pdev);
 			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
 			npu_pdn->pe_number = pe_num;
 			phb->ioda.pe_rmap[rid] = pe->pe_number;
+			pe->device_count++;
 
 			/* Map the PE to this link */
 			rc = opal_pci_set_pe(phb->opal_id, pe_num, rid,
@@ -1268,8 +1292,6 @@ static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
-	struct pci_bus *bus;
-	struct pci_dev *pdev;
 	struct pnv_ioda_pe *pe;
 
 	list_for_each_entry(hose, &hose_list, list_node) {
@@ -1281,11 +1303,6 @@ static void pnv_pci_ioda_setup_PEs(void)
 			if (phb->model == PNV_PHB_MODEL_NPU2)
 				WARN_ON_ONCE(pnv_npu2_init(hose));
 		}
-		if (phb->type == PNV_PHB_NPU_OCAPI) {
-			bus = hose->bus;
-			list_for_each_entry(pdev, &bus->devices, bus_list)
-				pnv_ioda_setup_dev_PE(pdev);
-		}
 	}
 	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
@@ -1558,6 +1575,10 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 
 	/* Reserve PE for each VF */
 	for (vf_index = 0; vf_index < num_vfs; vf_index++) {
+		int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index);
+		int vf_bus = pci_iov_virtfn_bus(pdev, vf_index);
+		struct pci_dn *vf_pdn;
+
 		if (pdn->m64_single_mode)
 			pe_num = pdn->pe_num_map[vf_index];
 		else
@@ -1570,13 +1591,11 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		pe->pbus = NULL;
 		pe->parent_dev = pdev;
 		pe->mve_number = -1;
-		pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
-			   pci_iov_virtfn_devfn(pdev, vf_index);
+		pe->rid = (vf_bus << 8) | vf_devfn;
 
 		pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n",
 			hose->global_number, pdev->bus->number,
-			PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
-			PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);
+			PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num);
 
 		if (pnv_ioda_configure_pe(phb, pe)) {
 			/* XXX What do we do here ? */
@@ -1590,6 +1609,15 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		list_add_tail(&pe->list, &phb->ioda.pe_list);
 		mutex_unlock(&phb->ioda.pe_list_mutex);
 
+		/* associate this pe to it's pdn */
+		list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) {
+			if (vf_pdn->busno == vf_bus &&
+			    vf_pdn->devfn == vf_devfn) {
+				vf_pdn->pe_number = pe_num;
+				break;
+			}
+		}
+
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
 #ifdef CONFIG_IOMMU_API
 		iommu_register_group(&pe->table_group,
@@ -1719,21 +1747,23 @@ int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
 	pnv_pci_sriov_disable(pdev);
 
 	/* Release PCI data */
-	remove_dev_pci_data(pdev);
+	remove_sriov_vf_pdns(pdev);
 	return 0;
 }
 
 int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 {
 	/* Allocate PCI data */
-	add_dev_pci_data(pdev);
+	add_sriov_vf_pdns(pdev);
 
 	return pnv_pci_sriov_enable(pdev, num_vfs);
 }
 #endif /* CONFIG_PCI_IOV */
 
-static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
+static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev)
 {
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 
@@ -2889,9 +2919,6 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	struct pci_dn *pdn;
 	int mul, total_vfs;
 
-	if (!pdev->is_physfn || pci_dev_is_added(pdev))
-		return;
-
 	pdn = pci_get_pdn(pdev);
 	pdn->vfs_expanded = 0;
 	pdn->m64_single_mode = false;
@@ -2966,6 +2993,30 @@ truncate_iov:
 		res->end = res->start - 1;
 	}
 }
+
+static void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev)
+{
+	if (WARN_ON(pci_dev_is_added(pdev)))
+		return;
+
+	if (pdev->is_virtfn) {
+		struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev);
+
+		/*
+		 * VF PEs are single-device PEs so their pdev pointer needs to
+		 * be set. The pdev doesn't exist when the PE is allocated (in
+		 * (pcibios_sriov_enable()) so we fix it up here.
+		 */
+		pe->pdev = pdev;
+		WARN_ON(!(pe->flags & PNV_IODA_PE_VF));
+	} else if (pdev->is_physfn) {
+		/*
+		 * For PFs adjust their allocated IOV resources to match what
+		 * the PHB can support using it's M64 BAR table.
+		 */
+		pnv_pci_ioda_fixup_iov_resources(pdev);
+	}
+}
 #endif /* CONFIG_PCI_IOV */
 
 static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
@@ -3062,19 +3113,9 @@ static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
 #ifdef CONFIG_DEBUG_FS
 static int pnv_pci_diag_data_set(void *data, u64 val)
 {
-	struct pci_controller *hose;
-	struct pnv_phb *phb;
+	struct pnv_phb *phb = data;
 	s64 ret;
 
-	if (val != 1ULL)
-		return -EINVAL;
-
-	hose = (struct pci_controller *)data;
-	if (!hose || !hose->private_data)
-		return -ENODEV;
-
-	phb = hose->private_data;
-
 	/* Retrieve the diag data from firmware */
 	ret = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag_data,
 					  phb->diag_data_size);
@@ -3089,6 +3130,33 @@ static int pnv_pci_diag_data_set(void *data, u64 val)
 DEFINE_DEBUGFS_ATTRIBUTE(pnv_pci_diag_data_fops, NULL, pnv_pci_diag_data_set,
 			 "%llu\n");
 
+static int pnv_pci_ioda_pe_dump(void *data, u64 val)
+{
+	struct pnv_phb *phb = data;
+	int pe_num;
+
+	for (pe_num = 0; pe_num < phb->ioda.total_pe_num; pe_num++) {
+		struct pnv_ioda_pe *pe = &phb->ioda.pe_array[pe_num];
+
+		if (!test_bit(pe_num, phb->ioda.pe_alloc))
+			continue;
+
+		pe_warn(pe, "rid: %04x dev count: %2d flags: %s%s%s%s%s%s\n",
+			pe->rid, pe->device_count,
+			(pe->flags & PNV_IODA_PE_DEV) ? "dev " : "",
+			(pe->flags & PNV_IODA_PE_BUS) ? "bus " : "",
+			(pe->flags & PNV_IODA_PE_BUS_ALL) ? "all " : "",
+			(pe->flags & PNV_IODA_PE_MASTER) ? "master " : "",
+			(pe->flags & PNV_IODA_PE_SLAVE) ? "slave " : "",
+			(pe->flags & PNV_IODA_PE_VF) ? "vf " : "");
+	}
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(pnv_pci_ioda_pe_dump_fops, NULL,
+			 pnv_pci_ioda_pe_dump, "%llu\n");
+
 #endif /* CONFIG_DEBUG_FS */
 
 static void pnv_pci_ioda_create_dbgfs(void)
@@ -3113,7 +3181,9 @@ static void pnv_pci_ioda_create_dbgfs(void)
 		}
 
 		debugfs_create_file_unsafe("dump_diag_regs", 0200, phb->dbgfs,
-					   hose, &pnv_pci_diag_data_fops);
+					   phb, &pnv_pci_diag_data_fops);
+		debugfs_create_file_unsafe("dump_ioda_pe_state", 0200, phb->dbgfs,
+					   phb, &pnv_pci_ioda_pe_dump_fops);
 	}
 #endif /* CONFIG_DEBUG_FS */
 }
@@ -3383,6 +3453,28 @@ static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 	return true;
 }
 
+static bool pnv_ocapi_enable_device_hook(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dn *pdn;
+	struct pnv_ioda_pe *pe;
+
+	if (!phb->initialized)
+		return true;
+
+	pdn = pci_get_pdn(dev);
+	if (!pdn)
+		return false;
+
+	if (pdn->pe_number == IODA_INVALID_PE) {
+		pe = pnv_ioda_setup_dev_PE(dev);
+		if (!pe)
+			return false;
+	}
+	return true;
+}
+
 static long pnv_pci_ioda1_unset_window(struct iommu_table_group *table_group,
 				       int num)
 {
@@ -3512,7 +3604,10 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 	struct pnv_phb *phb = pe->phb;
 	struct pnv_ioda_pe *slave, *tmp;
 
+	mutex_lock(&phb->ioda.pe_list_mutex);
 	list_del(&pe->list);
+	mutex_unlock(&phb->ioda.pe_list_mutex);
+
 	switch (phb->type) {
 	case PNV_PHB_IODA1:
 		pnv_pci_ioda1_release_pe_dma(pe);
@@ -3520,6 +3615,8 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 	case PNV_PHB_IODA2:
 		pnv_pci_ioda2_release_pe_dma(pe);
 		break;
+	case PNV_PHB_NPU_OCAPI:
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -3594,9 +3691,29 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 		       OPAL_ASSERT_RESET);
 }
 
+static void pnv_pci_ioda_dma_bus_setup(struct pci_bus *bus)
+{
+	struct pci_controller *hose = bus->sysdata;
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+
+	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+		if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)))
+			continue;
+
+		if (!pe->pbus)
+			continue;
+
+		if (bus->number == ((pe->rid >> 8) & 0xFF)) {
+			pe->pbus = bus;
+			break;
+		}
+	}
+}
+
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
-	.dma_dev_setup		= pnv_pci_dma_dev_setup,
-	.dma_bus_setup		= pnv_pci_dma_bus_setup,
+	.dma_dev_setup		= pnv_pci_ioda_dma_dev_setup,
+	.dma_bus_setup		= pnv_pci_ioda_dma_bus_setup,
 	.iommu_bypass_supported	= pnv_pci_ioda_iommu_bypass_supported,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
@@ -3609,7 +3726,6 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 };
 
 static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
-	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
 	.enable_device_hook	= pnv_pci_enable_device_hook,
@@ -3620,7 +3736,8 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 };
 
 static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
-	.enable_device_hook	= pnv_pci_enable_device_hook,
+	.enable_device_hook	= pnv_ocapi_enable_device_hook,
+	.release_device		= pnv_pci_release_device,
 	.window_alignment	= pnv_pci_window_alignment,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
 	.shutdown		= pnv_pci_ioda_shutdown,
@@ -3855,14 +3972,13 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		hose->controller_ops = pnv_npu_ocapi_ioda_controller_ops;
 		break;
 	default:
-		phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 		hose->controller_ops = pnv_pci_ioda_controller_ops;
 	}
 
 	ppc_md.pcibios_default_alignment = pnv_pci_default_alignment;
 
 #ifdef CONFIG_PCI_IOV
-	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
+	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov;
 	ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
 	ppc_md.pcibios_sriov_enable = pnv_pcibios_sriov_enable;
 	ppc_md.pcibios_sriov_disable = pnv_pcibios_sriov_disable;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index c0bea75ac27b..5bf818246339 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -38,7 +38,7 @@ static DEFINE_MUTEX(tunnel_mutex);
 
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 {
-	struct device_node *parent = np;
+	struct device_node *node = np;
 	u32 bdfn;
 	u64 phbid;
 	int ret;
@@ -48,25 +48,29 @@ int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 		return -ENXIO;
 
 	bdfn = ((bdfn & 0x00ffff00) >> 8);
-	while ((parent = of_get_parent(parent))) {
-		if (!PCI_DN(parent)) {