Merge tag 'powerpc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights:

   - Enable support for memory protection keys aka "pkeys" on Power7/8/9
     when using the hash table MMU.

   - Extend our interrupt soft masking to support masking PMU interrupts
     as well as "normal" interrupts, and then use that to implement
     local_t for a ~4x speedup vs the current atomics-based
     implementation.

   - A new driver "ocxl" for "Open Coherent Accelerator Processor
     Interface (OpenCAPI)" devices.

   - Support for new device tree properties on PowerVM to describe
     hotpluggable memory and devices.

   - Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE to the 64-bit
     VDSO.

   - Freescale updates from Scott: fixes for CPM GPIO and an FSL PCI
     erratum workaround, plus a minor cleanup patch.

  As well as quite a lot of other changes all over the place, and small
  fixes and cleanups as always.

  Thanks to: Alan Modra, Alastair D'Silva, Alexey Kardashevskiy,
  Alistair Popple, Andreas Schwab, Andrew Donnellan, Aneesh Kumar K.V,
  Anju T Sudhakar, Anshuman Khandual, Anton Blanchard, Arnd Bergmann,
  Balbir Singh, Benjamin Herrenschmidt, Bhaktipriya Shridhar, Bryant G.
  Ly, Cédric Le Goater, Christophe Leroy, Christophe Lombard, Cyril Bur,
  David Gibson, Desnes A. Nunes do Rosario, Dmitry Torokhov, Frederic
  Barrat, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo A. R. Silva,
  Gustavo Romero, Ivan Mikhaylov, Joakim Tjernlund, Joe Perches, Josh
  Poimboeuf, Juan J. Alvarez, Julia Cartwright, Kamalesh Babulal,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael
  Bringmann, Michael Hanselmann, Michael Neuling, Nathan Fontenot,
  Naveen N. Rao, Nicholas Piggin, Paul Mackerras, Philippe Bergheaud,
  Ram Pai, Russell Currey, Santosh Sivaraj, Scott Wood, Seth Forshee,
  Simon Guo, Stewart Smith, Sukadev Bhattiprolu, Thiago Jung Bauermann,
  Vaibhav Jain, Vasyl Gomonovych"

* tag 'powerpc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (199 commits)
  powerpc/mm/radix: Fix build error when RADIX_MMU=n
  macintosh/ams-input: Use true and false for boolean values
  macintosh: change some data types from int to bool
  powerpc/watchdog: Print the NIP in soft_nmi_interrupt()
  powerpc/watchdog: regs can't be null in soft_nmi_interrupt()
  powerpc/watchdog: Tweak watchdog printks
  powerpc/cell: Remove axonram driver
  rtc-opal: Fix handling of firmware error codes, prevent busy loops
  powerpc/mpc52xx_gpt: make use of raw_spinlock variants
  macintosh/adb: Properly mark continued kernel messages
  powerpc/pseries: Fix cpu hotplug crash with memoryless nodes
  powerpc/numa: Ensure nodes initialized for hotplug
  powerpc/numa: Use ibm,max-associativity-domains to discover possible nodes
  powerpc/kernel: Block interrupts when updating TIDR
  powerpc/powernv/idoa: Remove unnecessary pcidev from pci_dn
  powerpc/mm/nohash: do not flush the entire mm when range is a single page
  powerpc/pseries: Add Initialization of VF Bars
  powerpc/pseries/pci: Associate PEs to VFs in configure SR-IOV
  powerpc/eeh: Add EEH notify resume sysfs
  powerpc/eeh: Add EEH operations to notify resume
  ...

14 files changed, 743 insertions, 131 deletions

diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 3732118a0482..6c9d5199a7e2 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
 obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
 obj-$(CONFIG_PPC_VAS)	+= vas.o vas-window.o vas-debug.o
 obj-$(CONFIG_PPC_FTW)	+= nx-ftw.o
+obj-$(CONFIG_OCXL_BASE)	+= ocxl.o
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 4650fb294e7a..33c86c1a1720 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -43,6 +43,22 @@
 
 static int eeh_event_irq = -EINVAL;
 
+void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+
+	if (!pdev->is_virtfn)
+		return;
+
+	/*
+	 * The following operations will fail if VF's sysfs files
+	 * aren't created or its resources aren't finalized.
+	 */
+	eeh_add_device_early(pdn);
+	eeh_add_device_late(pdev);
+	eeh_sysfs_add_device(pdev);
+}
+
 static int pnv_eeh_init(void)
 {
 	struct pci_controller *hose;
@@ -86,6 +102,7 @@ static int pnv_eeh_init(void)
 	}
 
 	eeh_set_pe_aux_size(max_diag_size);
+	ppc_md.pcibios_bus_add_device = pnv_pcibios_bus_add_device;
 
 	return 0;
 }
@@ -1638,70 +1655,11 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	return ret;
 }
 
-static int pnv_eeh_restore_vf_config(struct pci_dn *pdn)
-{
-	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
-	u32 devctl, cmd, cap2, aer_capctl;
-	int old_mps;
-
-	if (edev->pcie_cap) {
-		/* Restore MPS */
-		old_mps = (ffs(pdn->mps) - 8) << 5;
-		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				     2, &devctl);
-		devctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
-		devctl |= old_mps;
-		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				      2, devctl);
-
-		/* Disable Completion Timeout */
-		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2,
-				     4, &cap2);
-		if (cap2 & 0x10) {
-			eeh_ops->read_config(pdn,
-					     edev->pcie_cap + PCI_EXP_DEVCTL2,
-					     4, &cap2);
-			cap2 |= 0x10;
-			eeh_ops->write_config(pdn,
-					      edev->pcie_cap + PCI_EXP_DEVCTL2,
-					      4, cap2);
-		}
-	}
-
-	/* Enable SERR and parity checking */
-	eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd);
-	cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
-	eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd);
-
-	/* Enable report various errors */
-	if (edev->pcie_cap) {
-		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				     2, &devctl);
-		devctl &= ~PCI_EXP_DEVCTL_CERE;
-		devctl |= (PCI_EXP_DEVCTL_NFERE |
-			   PCI_EXP_DEVCTL_FERE |
-			   PCI_EXP_DEVCTL_URRE);
-		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
-				      2, devctl);
-	}
-
-	/* Enable ECRC generation and check */
-	if (edev->pcie_cap && edev->aer_cap) {
-		eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP,
-				     4, &aer_capctl);
-		aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
-		eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP,
-				      4, aer_capctl);
-	}
-
-	return 0;
-}
-
 static int pnv_eeh_restore_config(struct pci_dn *pdn)
 {
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	struct pnv_phb *phb;
-	s64 ret;
+	s64 ret = 0;
 	int config_addr = (pdn->busno << 8) | (pdn->devfn);
 
 	if (!edev)
@@ -1715,7 +1673,7 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 	 * to be exported by firmware in extendible way.
 	 */
 	if (edev->physfn) {
-		ret = pnv_eeh_restore_vf_config(pdn);
+		ret = eeh_restore_vf_config(pdn);
 	} else {
 		phb = pdn->phb->private_data;
 		ret = opal_pci_reinit(phb->opal_id,
@@ -1728,7 +1686,7 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 		return -EIO;
 	}
 
-	return 0;
+	return ret;
 }
 
 static struct eeh_ops pnv_eeh_ops = {
@@ -1746,25 +1704,10 @@ static struct eeh_ops pnv_eeh_ops = {
 	.read_config            = pnv_eeh_read_config,
 	.write_config           = pnv_eeh_write_config,
 	.next_error		= pnv_eeh_next_error,
-	.restore_config		= pnv_eeh_restore_config
+	.restore_config		= pnv_eeh_restore_config,
+	.notify_resume		= NULL
 };
 
-void pcibios_bus_add_device(struct pci_dev *pdev)
-{
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-
-	if (!pdev->is_virtfn)
-		return;
-
-	/*
-	 * The following operations will fail if VF's sysfs files
-	 * aren't created or its resources aren't finalized.
-	 */
-	eeh_add_device_early(pdn);
-	eeh_add_device_late(pdev);
-	eeh_sysfs_add_device(pdev);
-}
-
 #ifdef CONFIG_PCI_IOV
 static void pnv_pci_fixup_vf_mps(struct pci_dev *pdev)
 {
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index f6cbc1a71472..0a253b64ac5f 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -39,7 +39,10 @@
  */
 static struct pci_dev *get_pci_dev(struct device_node *dn)
 {
-	return PCI_DN(dn)->pcidev;
+	struct pci_dn *pdn = PCI_DN(dn);
+
+	return pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus),
+					   pdn->busno, pdn->devfn);
 }
 
 /* Given a NPU device get the associated PCI device. */
@@ -277,7 +280,7 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe)
 	int64_t rc = 0;
 	phys_addr_t top = memblock_end_of_DRAM();
 
-	if (phb->type != PNV_PHB_NPU || !npe->pdev)
+	if (phb->type != PNV_PHB_NPU_NVLINK || !npe->pdev)
 		return -EINVAL;
 
 	rc = pnv_npu_unset_window(npe, 0);
diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c
new file mode 100644
index 000000000000..fa9b53af3c7b
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/ocxl.c
@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2017 IBM Corp.
+#include <asm/pnv-ocxl.h>
+#include <asm/opal.h>
+#include <asm/xive.h>
+#include <misc/ocxl-config.h>
+#include "pci.h"
+
+#define PNV_OCXL_TL_P9_RECV_CAP		0x000000000000000Full
+#define PNV_OCXL_ACTAG_MAX		64
+/* PASIDs are 20-bit, but on P9, NPU can only handle 15 bits */
+#define PNV_OCXL_PASID_BITS		15
+#define PNV_OCXL_PASID_MAX		((1 << PNV_OCXL_PASID_BITS) - 1)
+
+#define AFU_PRESENT (1 << 31)
+#define AFU_INDEX_MASK 0x3F000000
+#define AFU_INDEX_SHIFT 24
+#define ACTAG_MASK 0xFFF
+
+
+struct actag_range {
+	u16 start;
+	u16 count;
+};
+
+struct npu_link {
+	struct list_head list;
+	int domain;
+	int bus;
+	int dev;
+	u16 fn_desired_actags[8];
+	struct actag_range fn_actags[8];
+	bool assignment_done;
+};
+static struct list_head links_list = LIST_HEAD_INIT(links_list);
+static DEFINE_MUTEX(links_list_lock);
+
+
+/*
+ * opencapi actags handling:
+ *
+ * When sending commands, the opencapi device references the memory
+ * context it's targeting with an 'actag', which is really an alias
+ * for a (BDF, pasid) combination. When it receives a command, the NPU
+ * must do a lookup of the actag to identify the memory context. The
+ * hardware supports a finite number of actags per link (64 for
+ * POWER9).
+ *
+ * The device can carry multiple functions, and each function can have
+ * multiple AFUs. Each AFU advertises in its config space the number
+ * of desired actags. The host must configure in the config space of
+ * the AFU how many actags the AFU is really allowed to use (which can
+ * be less than what the AFU desires).
+ *
+ * When a PCI function is probed by the driver, it has no visibility
+ * about the other PCI functions and how many actags they'd like,
+ * which makes it impossible to distribute actags fairly among AFUs.
+ *
+ * Unfortunately, the only way to know how many actags a function
+ * desires is by looking at the data for each AFU in the config space
+ * and add them up. Similarly, the only way to know how many actags
+ * all the functions of the physical device desire is by adding the
+ * previously computed function counts. Then we can match that against
+ * what the hardware supports.
+ *
+ * To get a comprehensive view, we use a 'pci fixup': at the end of
+ * PCI enumeration, each function counts how many actags its AFUs
+ * desire and we save it in a 'npu_link' structure, shared between all
+ * the PCI functions of a same device. Therefore, when the first
+ * function is probed by the driver, we can get an idea of the total
+ * count of desired actags for the device, and assign the actags to
+ * the AFUs, by pro-rating if needed.
+ */
+
+static int find_dvsec_from_pos(struct pci_dev *dev, int dvsec_id, int pos)
+{
+	int vsec = pos;
+	u16 vendor, id;
+
+	while ((vsec = pci_find_next_ext_capability(dev, vsec,
+						    OCXL_EXT_CAP_ID_DVSEC))) {
+		pci_read_config_word(dev, vsec + OCXL_DVSEC_VENDOR_OFFSET,
+				&vendor);
+		pci_read_config_word(dev, vsec + OCXL_DVSEC_ID_OFFSET, &id);
+		if (vendor == PCI_VENDOR_ID_IBM && id == dvsec_id)
+			return vsec;
+	}
+	return 0;
+}
+
+static int find_dvsec_afu_ctrl(struct pci_dev *dev, u8 afu_idx)
+{
+	int vsec = 0;
+	u8 idx;
+
+	while ((vsec = find_dvsec_from_pos(dev, OCXL_DVSEC_AFU_CTRL_ID,
+					   vsec))) {
+		pci_read_config_byte(dev, vsec + OCXL_DVSEC_AFU_CTRL_AFU_IDX,
+				&idx);
+		if (idx == afu_idx)
+			return vsec;
+	}
+	return 0;
+}
+
+static int get_max_afu_index(struct pci_dev *dev, int *afu_idx)
+{
+	int pos;
+	u32 val;
+
+	pos = find_dvsec_from_pos(dev, OCXL_DVSEC_FUNC_ID, 0);
+	if (!pos)
+		return -ESRCH;
+
+	pci_read_config_dword(dev, pos + OCXL_DVSEC_FUNC_OFF_INDEX, &val);
+	if (val & AFU_PRESENT)
+		*afu_idx = (val & AFU_INDEX_MASK) >> AFU_INDEX_SHIFT;
+	else
+		*afu_idx = -1;
+	return 0;
+}
+
+static int get_actag_count(struct pci_dev *dev, int afu_idx, int *actag)
+{
+	int pos;
+	u16 actag_sup;
+
+	pos = find_dvsec_afu_ctrl(dev, afu_idx);
+	if (!pos)
+		return -ESRCH;
+
+	pci_read_config_word(dev, pos + OCXL_DVSEC_AFU_CTRL_ACTAG_SUP,
+			&actag_sup);
+	*actag = actag_sup & ACTAG_MASK;
+	return 0;
+}
+
+static struct npu_link *find_link(struct pci_dev *dev)
+{
+	struct npu_link *link;
+
+	list_for_each_entry(link, &links_list, list) {
+		/* The functions of a device all share the same link */
+		if (link->domain == pci_domain_nr(dev->bus) &&
+			link->bus == dev->bus->number &&
+			link->dev == PCI_SLOT(dev->devfn)) {
+			return link;
+		}
+	}
+
+	/* link doesn't exist yet. Allocate one */
+	link = kzalloc(sizeof(struct npu_link), GFP_KERNEL);
+	if (!link)
+		return NULL;
+	link->domain = pci_domain_nr(dev->bus);
+	link->bus = dev->bus->number;
+	link->dev = PCI_SLOT(dev->devfn);
+	list_add(&link->list, &links_list);
+	return link;
+}
+
+static void pnv_ocxl_fixup_actag(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct npu_link *link;
+	int rc, afu_idx = -1, i, actag;
+
+	if (!machine_is(powernv))
+		return;
+
+	if (phb->type != PNV_PHB_NPU_OCAPI)
+		return;
+
+	mutex_lock(&links_list_lock);
+
+	link = find_link(dev);
+	if (!link) {
+		dev_warn(&dev->dev, "couldn't update actag information\n");
+		mutex_unlock(&links_list_lock);
+		return;
+	}
+
+	/*
+	 * Check how many actags are desired for the AFUs under that
+	 * function and add it to the count for the link
+	 */
+	rc = get_max_afu_index(dev, &afu_idx);
+	if (rc) {
+		/* Most likely an invalid config space */
+		dev_dbg(&dev->dev, "couldn't find AFU information\n");
+		afu_idx = -1;
+	}
+
+	link->fn_desired_actags[PCI_FUNC(dev->devfn)] = 0;
+	for (i = 0; i <= afu_idx; i++) {
+		/*
+		 * AFU index 'holes' are allowed. So don't fail if we
+		 * can't read the actag info for an index
+		 */
+		rc = get_actag_count(dev, i, &actag);
+		if (rc)
+			continue;
+		link->fn_desired_actags[PCI_FUNC(dev->devfn)] += actag;
+	}
+	dev_dbg(&dev->dev, "total actags for function: %d\n",
+		link->fn_desired_actags[PCI_FUNC(dev->devfn)]);
+
+	mutex_unlock(&links_list_lock);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_ocxl_fixup_actag);
+
+static u16 assign_fn_actags(u16 desired, u16 total)
+{
+	u16 count;
+
+	if (total <= PNV_OCXL_ACTAG_MAX)
+		count = desired;
+	else
+		count = PNV_OCXL_ACTAG_MAX * desired / total;
+
+	return count;
+}
+
+static void assign_actags(struct npu_link *link)
+{
+	u16 actag_count, range_start = 0, total_desired = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		total_desired += link->fn_desired_actags[i];
+
+	for (i = 0; i < 8; i++) {
+		if (link->fn_desired_actags[i]) {
+			actag_count = assign_fn_actags(
+				link->fn_desired_actags[i],
+				total_desired);
+			link->fn_actags[i].start = range_start;
+			link->fn_actags[i].count = actag_count;
+			range_start += actag_count;
+			WARN_ON(range_start >= PNV_OCXL_ACTAG_MAX);
+		}
+		pr_debug("link %x:%x:%x fct %d actags: start=%d count=%d (desired=%d)\n",
+			link->domain, link->bus, link->dev, i,
+			link->fn_actags[i].start, link->fn_actags[i].count,
+			link->fn_desired_actags[i]);
+	}
+	link->assignment_done = true;
+}
+
+int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled,
+		u16 *supported)
+{
+	struct npu_link *link;
+
+	mutex_lock(&links_list_lock);
+
+	link = find_link(dev);
+	if (!link) {
+		dev_err(&dev->dev, "actag information not found\n");
+		mutex_unlock(&links_list_lock);
+		return -ENODEV;
+	}
+	/*
+	 * On p9, we only have 64 actags per link, so they must be
+	 * shared by all the functions of the same adapter. We counted
+	 * the desired actag counts during PCI enumeration, so that we
+	 * can allocate a pro-rated number of actags to each function.
+	 */
+	if (!link->assignment_done)
+		assign_actags(link);
+
+	*base      = link->fn_actags[PCI_FUNC(dev->devfn)].start;
+	*enabled   = link->fn_actags[PCI_FUNC(dev->devfn)].count;
+	*supported = link->fn_desired_actags[PCI_FUNC(dev->devfn)];
+
+	mutex_unlock(&links_list_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_actag);
+
+int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count)
+{
+	struct npu_link *link;
+	int i, rc = -EINVAL;
+
+	/*
+	 * The number of PASIDs (process address space ID) which can
+	 * be used by a function depends on how many functions exist
+	 * on the device. The NPU needs to be configured to know how
+	 * many bits are available to PASIDs and how many are to be
+	 * used by the function BDF indentifier.
+	 *
+	 * We only support one AFU-carrying function for now.
+	 */
+	mutex_lock(&links_list_lock);
+
+	link = find_link(dev);
+	if (!link) {
+		dev_err(&dev->dev, "actag information not found\n");
+		mutex_unlock(&links_list_lock);
+		return -ENODEV;
+	}
+
+	for (i = 0; i < 8; i++)
+		if (link->fn_desired_actags[i] && (i == PCI_FUNC(dev->devfn))) {
+			*count = PNV_OCXL_PASID_MAX;
+			rc = 0;
+			break;
+		}
+
+	mutex_unlock(&links_list_lock);
+	dev_dbg(&dev->dev, "%d PASIDs available for function\n",
+		rc ? 0 : *count);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_pasid_count);
+
+static void set_templ_rate(unsigned int templ, unsigned int rate, char *buf)
+{
+	int shift, idx;
+
+	WARN_ON(templ > PNV_OCXL_TL_MAX_TEMPLATE);
+	idx = (PNV_OCXL_TL_MAX_TEMPLATE - templ) / 2;
+	shift = 4 * (1 - ((PNV_OCXL_TL_MAX_TEMPLATE - templ) % 2));
+	buf[idx] |= rate << shift;
+}
+
+int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap,
+			char *rate_buf, int rate_buf_size)
+{
+	if (rate_buf_size != PNV_OCXL_TL_RATE_BUF_SIZE)
+		return -EINVAL;
+	/*
+	 * The TL capabilities are a characteristic of the NPU, so
+	 * we go with hard-coded values.
+	 *
+	 * The receiving rate of each template is encoded on 4 bits.
+	 *
+	 * On P9:
+	 * - templates 0 -> 3 are supported
+	 * - templates 0, 1 and 3 have a 0 receiving rate
+	 * - template 2 has receiving rate of 1 (extra cycle)
+	 */
+	memset(rate_buf, 0, rate_buf_size);
+	set_templ_rate(2, 1, rate_buf);
+	*cap = PNV_OCXL_TL_P9_RECV_CAP;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_tl_cap);
+
+int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap,
+			uint64_t rate_buf_phys, int rate_buf_size)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int rc;
+
+	if (rate_buf_size != PNV_OCXL_TL_RATE_BUF_SIZE)
+		return -EINVAL;
+
+	rc = opal_npu_tl_set(phb->opal_id, dev->devfn, cap,
+			rate_buf_phys, rate_buf_size);
+	if (rc) {
+		dev_err(&dev->dev, "Can't configure host TL: %d\n", rc);
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_set_tl_conf);
+
+int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq)
+{
+	int rc;
+
+	rc = of_property_read_u32(dev->dev.of_node, "ibm,opal-xsl-irq", hwirq);
+	if (rc) {
+		dev_err(&dev->dev,
+			"Can't get translation interrupt for device\n");
+		return rc;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_get_xsl_irq);
+
+void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar,
+			void __iomem *tfc, void __iomem *pe_handle)
+{
+	iounmap(dsisr);
+	iounmap(dar);
+	iounmap(tfc);
+	iounmap(pe_handle);
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_unmap_xsl_regs);
+
+int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr,
+			void __iomem **dar, void __iomem **tfc,
+			void __iomem **pe_handle)
+{
+	u64 reg;
+	int i, j, rc = 0;
+	void __iomem *regs[4];
+
+	/*
+	 * opal stores the mmio addresses of the DSISR, DAR, TFC and
+	 * PE_HANDLE registers in a device tree property, in that
+	 * order
+	 */
+	for (i = 0; i < 4; i++) {
+		rc = of_property_read_u64_index(dev->dev.of_node,
+						"ibm,opal-xsl-mmio", i, &reg);
+		if (rc)
+			break;
+		regs[i] = ioremap(reg, 8);
+		if (!regs[i]) {
+			rc = -EINVAL;
+			break;
+		}
+	}
+	if (rc) {
+		dev_err(&dev->dev, "Can't map translation mmio registers\n");
+		for (j = i - 1; j >= 0; j--)
+			iounmap(regs[j]);
+	} else {
+		*dsisr = regs[0];
+		*dar = regs[1];
+		*tfc = regs[2];
+		*pe_handle = regs[3];
+	}
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_map_xsl_regs);
+
+struct spa_data {
+	u64 phb_opal_id;
+	u32 bdfn;
+};
+
+int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask,
+		void **platform_data)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct spa_data *data;
+	u32 bdfn;
+	int rc;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	bdfn = (dev->bus->number << 8) | dev->devfn;
+	rc = opal_npu_spa_setup(phb->opal_id, bdfn, virt_to_phys(spa_mem),
+				PE_mask);
+	if (rc) {
+		dev_err(&dev->dev, "Can't setup Shared Process Area: %d\n", rc);
+		kfree(data);
+		return rc;
+	}
+	data->phb_opal_id = phb->opal_id;
+	data->bdfn = bdfn;
+	*platform_data = (void *) data;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_spa_setup);
+
+void pnv_ocxl_spa_release(void *platform_data)
+{
+	struct spa_data *data = (struct spa_data *) platform_data;
+	int rc;
+
+	rc = opal_npu_spa_setup(data->phb_opal_id, data->bdfn, 0, 0);
+	WARN_ON(rc);
+	kfree(data);
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_spa_release);
+
+int pnv_ocxl_spa_remove_pe(void *platform_data, int pe_handle)
+{
+	struct spa_data *data = (struct spa_data *) platform_data;
+	int rc;
+
+	rc = opal_npu_spa_clear_cache(data->phb_opal_id, data->bdfn, pe_handle);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_spa_remove_pe);
+
+int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr)
+{
+	__be64 flags, trigger_page;
+	s64 rc;
+	u32 hwirq;
+
+	hwirq = xive_native_alloc_irq();
+	if (!hwirq)
+		return -ENOENT;
+
+	rc = opal_xive_get_irq_info(hwirq, &flags, NULL, &trigger_page, NULL,
+				NULL);
+	if (rc || !trigger_page) {
+		xive_native_free_irq(hwirq);
+		return -ENOENT;
+	}
+	*irq = hwirq;
+	*trigger_addr = be64_to_cpu(trigger_page);
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_alloc_xive_irq);
+
+void pnv_ocxl_free_xive_irq(u32 irq)
+{
+	xive_native_free_irq(irq);
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_free_xive_irq);
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 4c827826c05e..0dc8fa4e0af2 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -103,9 +103,9 @@ static ssize_t dump_ack_store(struct dump_obj *dump_obj,
  * due to the dynamic size of the dump
  */
 static struct dump_attribute id_attribute =
-	__ATTR(id, S_IRUGO, dump_id_show, NULL);
+	__ATTR(id, 0444, dump_id_show, NULL);
 static struct dump_attribute type_attribute =
-	__ATTR(type, S_IRUGO, dump_type_show, NULL);
+	__ATTR(type, 0444, dump_type_show, NULL);
 static struct dump_attribute ack_attribute =
 	__ATTR(acknowledge, 0660, dump_ack_show, dump_ack_store);
 
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index ecd6d9177d13..ba6e437abb4b 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -83,9 +83,9 @@ static ssize_t elog_ack_store(struct elog_obj *elog_obj,
 }
 
 static struct elog_attribute id_attribute =
-	__ATTR(id, S_IRUGO, elog_id_show, NULL);
+	__ATTR(id, 0444, elog_id_show, NULL);
 static struct elog_attribute type_attribute =
-	__ATTR(type, S_IRUGO, elog_type_show, NULL);
+	__ATTR(type, 0444, elog_type_show, NULL);
 static struct elog_attribute ack_attribute =
 	__ATTR(acknowledge, 0660, elog_ack_show, elog_ack_store);
 
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 465ea105b771..dd4c9b8b8a81 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -21,6 +21,78 @@
 #include <asm/io.h>
 #include <asm/imc-pmu.h>
 #include <asm/cputhreads.h>
+#include <asm/debugfs.h>
+
+static struct dentry *imc_debugfs_parent;
+
+/* Helpers to export imc command and mode via debugfs */
+static int imc_mem_get(void *data, u64 *val)
+{
+	*val = cpu_to_be64(*(u64 *)data);
+	return 0;
+}
+
+static int imc_mem_set(void *data, u64 val)
+{
+	*(u64 *)data = cpu_to_be64(val);
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_imc_x64, imc_mem_get, imc_mem_set, "0x%016llx\n");
+
+static struct dentry *imc_debugfs_create_x64(const char *name, umode_t mode,
+					     struct dentry *parent, u64  *value)
+{
+	return debugfs_create_file_unsafe(name, mode, parent,
+					  value, &fops_imc_x64);
+}
+
+/*
+ * export_imc_mode_and_cmd: Create a debugfs interface
+ *                     for imc_cmd and imc_mode
+ *                     for each node in the system.
+ *  imc_mode and imc_cmd can be changed by echo into
+ *  this interface.
+ */
+static void export_imc_mode_and_cmd(struct device_node *node,
+				    struct imc_pmu *pmu_ptr)
+{
+	static u64 loc, *imc_mode_addr, *imc_cmd_addr;
+	int chip = 0, nid;
+	char mode[16], cmd[16];
+	u32 cb_offset;
+
+	imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root);
+
+	/*
+	 * Return here, either because 'imc' directory already exists,
+	 * Or failed to create a new one.
+	 */
+	if (!imc_debugfs_parent)
+		return;
+
+	if (of_property_read_u32(node, "cb_offset", &cb_offset))
+		cb_offset = IMC_CNTL_BLK_OFFSET;
+
+	for_each_node(nid) {
+		loc = (u64)(pmu_ptr->mem_info[chip].vbase) + cb_offset;
+		imc_mode_addr = (u64 *)(loc + IMC_CNTL_BLK_MODE_OFFSET);
+		sprintf(mode, "imc_mode_%d", nid);
+		if (!imc_debugfs_create_x64(mode, 0600, imc_debugfs_parent,
+					    imc_mode_addr))
+			goto err;
+
+		imc_cmd_addr = (u64 *)(loc + IMC_CNTL_BLK_CMD_OFFSET);
+		sprintf(cmd, "imc_cmd_%d", nid);
+		if (!imc_debugfs_create_x64(cmd, 0600, imc_debugfs_parent,
+					    imc_cmd_addr))
+			goto err;
+		chip++;
+	}
+	return;
+
+err:
+	debugfs_remove_recursive(imc_debugfs_parent);
+}
 
 /*
  * imc_get_mem_addr_nest: Function to get nest counter memory region
@@ -65,6 +137,7 @@ static int imc_get_mem_addr_nest(struct device_node *node,
 	}
 
 	pmu_ptr->imc_counter_mmaped = true;
+	export_imc_mode_and_cmd(node, pmu_ptr);
 	kfree(base_addr_arr);
 	kfree(chipid_arr);
 	return 0;
@@ -213,6 +286,10 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
 		}
 	}
 
+	/* If none of the nest units are registered, remove debugfs interface */
+	if (pmu_count == 0)
+		debugfs_remove_recursive(imc_debugfs_parent);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 23fb6647dced..6fd4092798d5 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -260,13 +260,13 @@ void __init opal_sys_param_init(void)
 		/* If the parameter is read-only or read-write */
 		switch (perm[i] & 3) {
 		case OPAL_SYSPARAM_READ:
-			attr[i].kobj_attr.attr.mode = S_IRUGO;
+			attr[i].kobj_attr.attr.mode = 0444;
 			break;
 		case OPAL_SYSPARAM_WRITE:
-			attr[i].kobj_attr.attr.mode = S_IWUSR;
+			attr[i].kobj_attr.attr.mode = 0200;
 			break;
 		case OPAL_SYSPARAM_RW:
-			attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUSR;
+			attr[i].kobj_attr.attr.mode = 0644;
 			break;
 		default:
 			break;
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6f4b00a2ac46..1b2936ba6040 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -320,3 +320,6 @@ OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
 OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
 OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
 OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
+OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
+OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
+OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 041ddbd1fc57..c15182765ff5 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -127,7 +127,7 @@ int __init early_init_dt_scan_opal(unsigned long node,
 
 	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
 		powerpc_firmware_features |= FW_FEATURE_OPAL;
-		pr_info("OPAL detected !\n");
+		pr_debug("OPAL detected !\n");
 	} else {
 		panic("OPAL != V3 detected, no longer supported.\n");
 	}
@@ -239,8 +239,8 @@ int opal_message_notifier_register(enum opal_msg_type msg_type,
 					struct notifier_block *nb)
 {
 	if (!nb || msg_type >= OPAL_MSG_TYPE_MAX) {
-		pr_warning("%s: Invalid arguments, msg_type:%d\n",
-			   __func__, msg_type);
+		pr_warn("%s: Invalid arguments, msg_type:%d\n",
+			__func__, msg_type);
 		return -EINVAL;
 	}
 
@@ -281,8 +281,8 @@ static void opal_handle_message(void)
 
 	/* check for errors. */
 	if (ret) {
-		pr_warning("%s: Failed to retrieve opal message, err=%lld\n",
-				__func__, ret);
+		pr_warn("%s: Failed to retrieve opal message, err=%lld\n",
+			__func__, ret);
 		return;
 	}
 
@@ -461,24 +461,14 @@ static int opal_recover_mce(struct pt_regs *regs,
 
 void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
 {
-	/*
-	 * This is mostly taken from kernel/panic.c, but tries to do
-	 * relatively minimal work. Don't use delay functions (TB may
-	 * be broken), don't crash dump (need to set a firmware log),
-	 * don't run notifiers. We do want to get some information to
-	 * Linux console.
-	 */
-	console_verbose();
-	bust_spinlocks(1);
+	panic_flush_kmsg_start();
+
 	pr_emerg("Hardware platform error: %s\n", msg);
 	if (regs)
 		show_regs(regs);
 	smp_send_stop();
-	printk_safe_flush_on_panic();
-	kmsg_dump(KMSG_DUMP_PANIC);
-	bust_spinlocks(0);
-	debug_locks_off();
-	console_flush_on_panic();
+
+	panic_flush_kmsg_end();
 
 	/*
 	 * Don't bother to shut things down because this will
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 9582aeb1fe4c..496e47696ed0 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -54,7 +54,8 @@
 #define POWERNV_IOMMU_DEFAULT_LEVELS	1
 #define POWERNV_IOMMU_MAX_LEVELS	5
 
-static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU" };
+static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
+					      "NPU_OCAPI" };
 static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
 
 void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
@@ -89,6 +90,7 @@ void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 }
 
 static bool pnv_iommu_bypass_disabled __read_mostly;
+static bool pci_reset_phbs __read_mostly;
 
 static int __init iommu_setup(char *str)
 {
@@ -110,6 +112,14 @@ static int __init iommu_setup(char *str)
 }
 early_param("iommu", iommu_setup);
 
+static int __init pci_reset_phbs_setup(char *str)
+{
+	pci_reset_phbs = true;
+	return 0;
+}
+
+early_param("ppc_pci_reset_phbs", pci_reset_phbs_setup);
+
 static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
 {
 	/*
@@ -924,7 +934,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	 * Configure PELTV. NPUs don't have a PELTV table so skip
 	 * configuration on them.
 	 */
-	if (phb->type != PNV_PHB_NPU)
+	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
 		pnv_ioda_set_peltv(phb, pe, true);
 
 	/* Setup reverse map */
@@ -1059,8 +1069,8 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 
 	pe = pnv_ioda_alloc_pe(phb);
 	if (!pe) {
-		pr_warning("%s: Not enough PE# available, disabling device\n",
-			   pci_name(dev));
+		pr_warn("%s: Not enough PE# available, disabling device\n",
+			pci_name(dev));
 		return NULL;
 	}
 
@@ -1072,7 +1082,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 	 * At some point we want to remove the PDN completely anyways
 	 */
 	pci_dev_get(dev);
-	pdn->pcidev = dev;
 	pdn->pe_number = pe->pe_number;
 	pe->flags = PNV_IODA_PE_DEV;
 	pe->pdev = dev;
@@ -1119,7 +1128,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 			continue;
 
 		pe->device_count++;
-		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
 			pnv_ioda_setup_same_PE(dev->subordinate, pe);
@@ -1164,7 +1172,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 		pe = pnv_ioda_alloc_pe(phb);
 
 	if (!pe) {
-		pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
+		pr_warn("%s: Not enough PE# available for PCI bus %04x:%02x\n",
 			__func__, pci_domain_nr(bus), bus->number);
 		return NULL;
 	}
@@ -1234,7 +1242,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 			pci_dev_get(npu_pdev);
 			npu_pdn = pci_get_pdn(npu_pdev);
 			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
-			npu_pdn->pcidev = npu_pdev;
 			npu_pdn->pe_number = pe_num;
 			phb->ioda.pe_rmap[rid] = pe->pe_number;
 
@@ -1272,16 +1279,23 @@ static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose, *tmp;
 	struct pnv_phb *phb;
+	struct pci_bus *bus;
+	struct pci_dev *pdev;
 
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
-		if (phb->type == PNV_PHB_NPU) {
+		if (phb->type == PNV_PHB_NPU_NVLINK) {
 			/* PE#0 is needed for error reporting */
 			pnv_ioda_reserve_pe(phb, 0);
 			pnv_ioda_setup_npu_PEs(hose->bus);
 			if (phb->model == PNV_PHB_MODEL_NPU2)
 				pnv_npu2_init(phb);
 		}
+		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);
+		}
 	}
 }
 
@@ -1692,7 +1706,7 @@ m64_failed:
 	return ret;
 }
 
-int pcibios_sriov_disable(struct pci_dev *pdev)
+int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
 {
 	pnv_pci_sriov_disable(pdev);
 
@@ -1701,7 +1715,7 @@ int pcibios_sriov_disable(struct pci_dev *pdev)
 	return 0;
 }
 
-int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 {
 	/* Allocate PCI data */
 	add_dev_pci_data(pdev);
@@ -2572,7 +2586,6 @@ static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
 	unsigned long direct_table_size;
 
 	if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) ||
-			(window_size > memory_hotplug_max()) ||
 			!is_power_of_2(window_size))
 		return 0;
 
@@ -2640,7 +2653,7 @@ static int gpe_table_group_to_npe_cb(struct device *dev, void *opaque)
 
 	hose = pci_bus_to_host(pdev->bus);
 	phb = hose->private_data;
-	if (phb->type != PNV_PHB_NPU)
+	if (phb->type != PNV_PHB_NPU_NVLINK)
 		return 0;
 
 	*ptmppe = &phb->ioda.pe_array[pdn->pe_number];
@@ -2724,7 +2737,7 @@ static void pnv_pci_ioda_setup_iommu_api(void)
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
 
-		if (phb->type != PNV_PHB_NPU)
+		if (phb->type != PNV_PHB_NPU_NVLINK)
 			continue;
 
 		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
@@ -3293,7 +3306,7 @@ static void pnv_pci_ioda_create_dbgfs(void)
 		sprintf(name, "PCI%04x", hose->global_number);
 		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
 		if (!phb->dbgfs) {
-			pr_warning("%s: Error on creating debugfs on PHB#%x\n",
+			pr_warn("%s: Error on creating debugfs on PHB#%x\n",
 				__func__, hose->global_number);
 			continue;
 		}
@@ -3774,6 +3787,13 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
+static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
+	.enable_device_hook	= pnv_pci_enable_device_hook,
+	.window_alignment	= pnv_pci_window_alignment,
+	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
+	.shutdown		= pnv_pci_ioda_shutdown,
+};
+
 #ifdef CONFIG_CXL_BASE
 const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
@@ -4007,9 +4027,14 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 */
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 
-	if (phb->type == PNV_PHB_NPU) {
+	switch (phb->type) {
+	case PNV_PHB_NPU_NVLINK:
 		hose->controller_ops = pnv_npu_ioda_controller_ops;
-	} else {
+		break;
+	case PNV_PHB_NPU_OCAPI:
+		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;
 	}
@@ -4019,6 +4044,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 #ifdef CONFIG_PCI_IOV
 	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
 	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;
 #endif
 
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
@@ -4026,15 +4053,16 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	/* Reset IODA tables to a clean state */
 	rc = opal_pci_reset(phb_id, OPAL_RESET_PCI_IODA_TABLE, OPAL_ASSERT_RESET);
 	if (rc)
-		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
+		pr_warn("  OPAL Error %ld performing IODA table reset !\n", rc);
 
 	/*
 	 * If we're running in kdump kernel, the previous kernel never
 	 * shutdown PCI devices correctly. We already got IODA table
 	 * cleaned out. So we have to issue PHB reset to stop all PCI
-	 * transactions from previous kernel.
+	 * transactions from previous kernel. The ppc_pci_reset_phbs
+	 * kernel parameter will force this reset too.
 	 */
-	if (is_kdump_kernel()) {
+	if (is_kdump_kernel() || pci_reset_phbs) {
 		pr_info("  Issue PHB reset ...\n");
 		pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
 		pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
@@ -4052,8 +4080,26 @@ void __init pnv_pci_init_ioda2_phb(struct device_node *np)
 
 void __init pnv_pci_init_npu_phb(struct device_node *np)
 {
-	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU);
+	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_NVLINK);
+}
+
+void __init pnv_pci_init_npu2_opencapi_phb(struct device_node *np)
+{
+	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_OCAPI);
+}
+
+static void pnv_npu2_opencapi_cfg_size_fixup(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (!machine_is(powernv))
+		return;
+
+	if (phb->type == PNV_PHB_NPU_OCAPI)
+		dev->cfg_size = PCI_CFG_SPACE_EXP_SIZE;
 }
+DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pnv_npu2_opencapi_cfg_size_fixup);
 
 void __init pnv_pci_init_ioda_hub(struct device_node *np)
 {
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 5422f4a6317c..69d102cbf48f 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -1142,6 +1142,10 @@ void __init pnv_pci_init(void)
 	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-phb")
 		pnv_pci_init_npu_phb(np);
 
+	/* Look for NPU2 OpenCAPI PHBs */
+	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-opencapi-phb")
+		pnv_pci_init_npu2_opencapi_phb(np);
+
 	/* Configure IOMMU DMA hooks */
 	set_pci_dma_ops(&dma_iommu_ops);
 }
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index b772d7473896..eada4b6068cb 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -12,9 +12,10 @@ struct pci_dn;
 #define NV_NMMU_ATSD_REGS 8
 
 enum pnv_phb_type {
-	PNV_PHB_IODA1	= 0,
-	PNV_PHB_IODA2	= 1,
-	PNV_PHB_NPU	= 2,
+	PNV_PHB_IODA1		= 0,
+	PNV_PHB_IODA2		= 1,
+	PNV_PHB_NPU_NVLINK	= 2,
+	PNV_PHB_NPU_OCAPI	= 3,
 };
 
 /* Precise PHB model for error management */
@@ -227,6 +228,7 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_init_npu_phb(struct device_node *np);
+extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index ba030669eca1..9664c8461f03 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -37,6 +37,8 @@
 #include <asm/kvm_ppc.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cpuidle.h>
+#include <asm/kexec.h>
+#include <asm/reg.h>
 
 #include "powernv.h"
 
@@ -209,9 +211,32 @@ static void pnv_smp_cpu_kill_self(void)
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
+		} else if ((srr1 & wmask) == SRR1_WAKERESET) {
+			irq_set_pending_from_srr1(srr1);
+			/* Does not return */
 		}
+
 		smp_mb();
 
+		/*
+		 * For kdump kernels, we process the ipi and jump to
+		 * crash_ipi_callback
+		 */
+		if (kdump_in_progress()) {
+			/*
+			 * If we got to this point, we've not used
+			 * NMI's, otherwise we would have gone
+			 * via the SRR1_WAKERESET path. We are
+			 * using regular IPI's for waking up offline
+			 * threads.
+			 */
+			struct pt_regs regs;
+
+			ppc_save_regs(&regs);
+			crash_ipi_callback(&regs);
+			/* Does not return */
+		}
+
 		if (cpu_core_split_required())
 			continue;
 
@@ -371,5 +396,8 @@ void __init pnv_smp_init(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	ppc_md.cpu_die	= pnv_smp_cpu_kill_self;
+#ifdef CONFIG_KEXEC_CORE
+	crash_wake_offline = 1;
+#endif
 #endif
 }