Merge tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for the kexec_file_load() syscall, which is a prereq for
     secure and trusted boot.

   - Prevent kernel execution of userspace on P9 Radix (similar to
     SMEP/PXN).

   - Sort the exception tables at build time, to save time at boot, and
     store them as relative offsets to save space in the kernel image &
     memory.

   - Allow building the kernel with thin archives, which should allow us
     to build an allyesconfig once some other fixes land.

   - Build fixes to allow us to correctly rebuild when changing the
     kernel endian from big to little or vice versa.

   - Plumbing so that we can avoid doing a full mm TLB flush on P9
     Radix.

   - Initial stack protector support (-fstack-protector).

   - Support for dumping the radix (aka. Linux) and hash page tables via
     debugfs.

   - Fix an oops in cxl coredump generation when cxl_get_fd() is used.

   - Freescale updates from Scott: "Highlights include 8xx hugepage
     support, qbman fixes/cleanup, device tree updates, and some misc
     cleanup."

   - Many and varied fixes and minor enhancements as always.

  Thanks to:
    Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anshuman
    Khandual, Anton Blanchard, Balbir Singh, Bartlomiej Zolnierkiewicz,
    Christophe Jaillet, Christophe Leroy, Denis Kirjanov, Elimar
    Riesebieter, Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff
    Levand, Jack Miller, Johan Hovold, Lars-Peter Clausen, Libin,
    Madhavan Srinivasan, Michael Neuling, Nathan Fontenot, Naveen N.
    Rao, Nicholas Piggin, Pan Xinhui, Peter Senna Tschudin, Rashmica
    Gupta, Rui Teng, Russell Currey, Scott Wood, Simon Guo, Suraj
    Jitindar Singh, Thiago Jung Bauermann, Tobias Klauser, Vaibhav Jain"

[ And thanks to Michael, who took time off from a new baby to get this
  pull request done.   - Linus ]

* tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (174 commits)
  powerpc/fsl/dts: add FMan node for t1042d4rdb
  powerpc/fsl/dts: add sg_2500_aqr105_phy4 alias on t1024rdb
  powerpc/fsl/dts: add QMan and BMan nodes on t1024
  powerpc/fsl/dts: add QMan and BMan nodes on t1023
  soc/fsl/qman: test: use DEFINE_SPINLOCK()
  powerpc/fsl-lbc: use DEFINE_SPINLOCK()
  powerpc/8xx: Implement support of hugepages
  powerpc: get hugetlbpage handling more generic
  powerpc: port 64 bits pgtable_cache to 32 bits
  powerpc/boot: Request no dynamic linker for boot wrapper
  soc/fsl/bman: Use resource_size instead of computation
  soc/fsl/qe: use builtin_platform_driver
  powerpc/fsl_pmc: use builtin_platform_driver
  powerpc/83xx/suspend: use builtin_platform_driver
  powerpc/ftrace: Fix the comments for ftrace_modify_code
  powerpc/perf: macros for power9 format encoding
  powerpc/perf: power9 raw event format encoding
  powerpc/perf: update attribute_group data structure
  powerpc/perf: factor out the event format field
  powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown
  ...

12 files changed, 2372 insertions, 56 deletions

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index bec90fb30425..e1c280a95d58 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -127,3 +127,14 @@ config HV_PERF_CTRS
 	  systems. 24x7 is available on Power 8 systems.
 
           If unsure, select Y.
+
+config IBMVIO
+	depends on PPC_PSERIES
+	bool
+	default y
+
+config IBMEBUS
+	depends on PPC_PSERIES && !CPU_LITTLE_ENDIAN
+	bool "Support for GX bus based adapters"
+	help
+	  Bus device driver for GX bus based adapters.
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index fedc2ccf029d..8f4ba089e802 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -8,7 +8,7 @@ obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   pci.o pci_dlpar.o eeh_pseries.o msi.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_SCANLOG)	+= scanlog.o
-obj-$(CONFIG_KEXEC)	+= kexec.o
+obj-$(CONFIG_KEXEC_CORE)	+= kexec.o
 obj-$(CONFIG_PSERIES_ENERGY)	+= pseries_energy.o
 
 obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug-cpu.o
@@ -21,6 +21,8 @@ obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DTL)		+= dtl.o
 obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
+obj-$(CONFIG_IBMVIO)		+= vio.o
+obj-$(CONFIG_IBMEBUS)		+= ibmebus.o
 
 ifeq ($(CONFIG_PPC_PSERIES),y)
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 66e7227469b8..972328829387 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -41,6 +41,8 @@
 #include <linux/memory.h>
 #include <asm/plpar_wrappers.h>
 
+#include "pseries.h"
+
 #define CMM_DRIVER_VERSION	"1.0.0"
 #define CMM_DEFAULT_DELAY	1
 #define CMM_HOTPLUG_DELAY	5
@@ -109,6 +111,38 @@ static int hotplug_occurred; /* protected by the hotplug mutex */
 
 static struct task_struct *cmm_thread_ptr;
 
+static long plpar_page_set_loaned(unsigned long vpa)
+{
+	unsigned long cmo_page_sz = cmo_get_page_size();
+	long rc = 0;
+	int i;
+
+	for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz)
+		rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa + i, 0);
+
+	for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz)
+		plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE,
+				   vpa + i - cmo_page_sz, 0);
+
+	return rc;
+}
+
+static long plpar_page_set_active(unsigned long vpa)
+{
+	unsigned long cmo_page_sz = cmo_get_page_size();
+	long rc = 0;
+	int i;
+
+	for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz)
+		rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa + i, 0);
+
+	for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz)
+		plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED,
+				   vpa + i - cmo_page_sz, 0);
+
+	return rc;
+}
+
 /**
  * cmm_alloc_pages - Allocate pages and mark them as loaned
  * @nr:	number of pages to allocate
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 423e450efe07..76caa4a45ccd 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -418,84 +418,136 @@ void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
 	}
 }
 
-static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
-			   const char *buf, size_t count)
+static int dlpar_parse_resource(char **cmd, struct pseries_hp_errorlog *hp_elog)
 {
-	struct pseries_hp_errorlog *hp_elog;
-	struct completion hotplug_done;
-	const char *arg;
-	int rc;
+	char *arg;
 
-	hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
-	if (!hp_elog) {
-		rc = -ENOMEM;
-		goto dlpar_store_out;
-	}
+	arg = strsep(cmd, " ");
+	if (!arg)
+		return -EINVAL;
 
-	/* Parse out the request from the user, this will be in the form
-	 * <resource> <action> <id_type> <id>
-	 */
-	arg = buf;
-	if (!strncmp(arg, "memory", 6)) {
+	if (sysfs_streq(arg, "memory")) {
 		hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM;
-		arg += strlen("memory ");
-	} else if (!strncmp(arg, "cpu", 3)) {
+	} else if (sysfs_streq(arg, "cpu")) {
 		hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_CPU;
-		arg += strlen("cpu ");
 	} else {
-		pr_err("Invalid resource specified: \"%s\"\n", buf);
-		rc = -EINVAL;
-		goto dlpar_store_out;
+		pr_err("Invalid resource specified.\n");
+		return -EINVAL;
 	}
 
-	if (!strncmp(arg, "add", 3)) {
+	return 0;
+}
+
+static int dlpar_parse_action(char **cmd, struct pseries_hp_errorlog *hp_elog)
+{
+	char *arg;
+
+	arg = strsep(cmd, " ");
+	if (!arg)
+		return -EINVAL;
+
+	if (sysfs_streq(arg, "add")) {
 		hp_elog->action = PSERIES_HP_ELOG_ACTION_ADD;
-		arg += strlen("add ");
-	} else if (!strncmp(arg, "remove", 6)) {
+	} else if (sysfs_streq(arg, "remove")) {
 		hp_elog->action = PSERIES_HP_ELOG_ACTION_REMOVE;
-		arg += strlen("remove ");
 	} else {
-		pr_err("Invalid action specified: \"%s\"\n", buf);
-		rc = -EINVAL;
-		goto dlpar_store_out;
+		pr_err("Invalid action specified.\n");
+		return -EINVAL;
 	}
 
-	if (!strncmp(arg, "index", 5)) {
-		u32 index;
+	return 0;
+}
 
+static int dlpar_parse_id_type(char **cmd, struct pseries_hp_errorlog *hp_elog)
+{
+	char *arg;
+	u32 count, index;
+
+	arg = strsep(cmd, " ");
+	if (!arg)
+		return -EINVAL;
+
+	if (sysfs_streq(arg, "index")) {
 		hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
-		arg += strlen("index ");
+		arg = strsep(cmd, " ");
+		if (!arg) {
+			pr_err("No DRC Index specified.\n");
+			return -EINVAL;
+		}
+
 		if (kstrtou32(arg, 0, &index)) {
-			rc = -EINVAL;
-			pr_err("Invalid drc_index specified: \"%s\"\n", buf);
-			goto dlpar_store_out;
+			pr_err("Invalid DRC Index specified.\n");
+			return -EINVAL;
 		}
 
 		hp_elog->_drc_u.drc_index = cpu_to_be32(index);
-	} else if (!strncmp(arg, "count", 5)) {
-		u32 count;
-
+	} else if (sysfs_streq(arg, "count")) {
 		hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_COUNT;
-		arg += strlen("count ");
+		arg = strsep(cmd, " ");
+		if (!arg) {
+			pr_err("No DRC count specified.\n");
+			return -EINVAL;
+		}
+
 		if (kstrtou32(arg, 0, &count)) {
-			rc = -EINVAL;
-			pr_err("Invalid count specified: \"%s\"\n", buf);
-			goto dlpar_store_out;
+			pr_err("Invalid DRC count specified.\n");
+			return -EINVAL;
 		}
 
 		hp_elog->_drc_u.drc_count = cpu_to_be32(count);
 	} else {
-		pr_err("Invalid id_type specified: \"%s\"\n", buf);
-		rc = -EINVAL;
-		goto dlpar_store_out;
+		pr_err("Invalid id_type specified.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
+			   const char *buf, size_t count)
+{
+	struct pseries_hp_errorlog *hp_elog;
+	struct completion hotplug_done;
+	char *argbuf;
+	char *args;
+	int rc;
+
+	args = argbuf = kstrdup(buf, GFP_KERNEL);
+	hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
+	if (!hp_elog || !argbuf) {
+		pr_info("Could not allocate resources for DLPAR operation\n");
+		kfree(argbuf);
+		kfree(hp_elog);
+		return -ENOMEM;
 	}
 
+	/*
+	 * Parse out the request from the user, this will be in the form:
+	 * <resource> <action> <id_type> <id>
+	 */
+	rc = dlpar_parse_resource(&args, hp_elog);
+	if (rc)
+		goto dlpar_store_out;
+
+	rc = dlpar_parse_action(&args, hp_elog);
+	if (rc)
+		goto dlpar_store_out;
+
+	rc = dlpar_parse_id_type(&args, hp_elog);
+	if (rc)
+		goto dlpar_store_out;
+
 	init_completion(&hotplug_done);
 	queue_hotplug_event(hp_elog, &hotplug_done, &rc);
 	wait_for_completion(&hotplug_done);
 
 dlpar_store_out:
+	kfree(argbuf);
 	kfree(hp_elog);
+
+	if (rc)
+		pr_err("Could not handle DLPAR request \"%s\"\n", buf);
+
 	return rc ? rc : count;
 }
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 1c428f06b14c..1eef46d9cf30 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -270,7 +270,7 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
 			eeh_add_flag(EEH_ENABLED);
 			eeh_add_to_parent_pe(edev);
 
-			pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%d-PE#%x\n",
+			pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%x-PE#%x\n",
 				__func__, pdn->busno, PCI_SLOT(pdn->devfn),
 				PCI_FUNC(pdn->devfn), pe.phb->global_number,
 				pe.addr);
@@ -371,7 +371,7 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe)
 				pe->config_addr, BUID_HI(pe->phb->buid),
 				BUID_LO(pe->phb->buid), 0);
 		if (ret) {
-			pr_warn("%s: Failed to get address for PHB#%d-PE#%x\n",
+			pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
 				__func__, pe->phb->global_number, pe->config_addr);
 			return 0;
 		}
@@ -384,7 +384,7 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe)
 				pe->config_addr, BUID_HI(pe->phb->buid),
 				BUID_LO(pe->phb->buid), 0);
 		if (ret) {
-			pr_warn("%s: Failed to get address for PHB#%d-PE#%x\n",
+			pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n",
 				__func__, pe->phb->global_number, pe->config_addr);
 			return 0;
 		}
@@ -653,7 +653,7 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 		rtas_busy_delay(ret);
 	}
 
-	pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+	pr_warn("%s: Unable to configure bridge PHB#%x-PE#%x (%d)\n",
 		__func__, pe->phb->global_number, pe->addr, ret);
 	return ret;
 }
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 76ec104e88be..2617f9f356bd 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -472,12 +472,15 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove,
 
 	/* Validate that there are enough LMBs to satisfy the request */
 	for (i = 0; i < num_lmbs; i++) {
-		if (lmbs[i].flags & DRCONF_MEM_ASSIGNED)
+		if (lmb_is_removable(&lmbs[i]))
 			lmbs_available++;
 	}
 
-	if (lmbs_available < lmbs_to_remove)
+	if (lmbs_available < lmbs_to_remove) {
+		pr_info("Not enough LMBs available (%d of %d) to satisfy request\n",
+			lmbs_available, lmbs_to_remove);
 		return -EINVAL;
+	}
 
 	for (i = 0; i < num_lmbs && lmbs_removed < lmbs_to_remove; i++) {
 		rc = dlpar_remove_lmb(&lmbs[i]);
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
new file mode 100644
index 000000000000..614c28537141
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -0,0 +1,469 @@
+/*
+ * IBM PowerPC IBM eBus Infrastructure Support.
+ *
+ * Copyright (c) 2005 IBM Corporation
+ *  Joachim Fenkes <fenkes@de.ibm.com>
+ *  Heiko J Schick <schickhj@de.ibm.com>
+ *
+ * All rights reserved.
+ *
+ * This source code is distributed under a dual license of GPL v2.0 and OpenIB
+ * BSD.
+ *
+ * OpenIB BSD License
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * Redistributions of source code must retain the above copyright notice, this
+ * list of conditions and the following disclaimer.
+ *
+ * Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials
+ * provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
+ * IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/console.h>
+#include <linux/kobject.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/of_platform.h>
+#include <asm/ibmebus.h>
+
+static struct device ibmebus_bus_device = { /* fake "parent" device */
+	.init_name = "ibmebus",
+};
+
+struct bus_type ibmebus_bus_type;
+
+/* These devices will automatically be added to the bus during init */
+static const struct of_device_id ibmebus_matches[] __initconst = {
+	{ .compatible = "IBM,lhca" },
+	{ .compatible = "IBM,lhea" },
+	{},
+};
+
+static void *ibmebus_alloc_coherent(struct device *dev,
+				    size_t size,
+				    dma_addr_t *dma_handle,
+				    gfp_t flag,
+				    unsigned long attrs)
+{
+	void *mem;
+
+	mem = kmalloc(size, flag);
+	*dma_handle = (dma_addr_t)mem;
+
+	return mem;
+}
+
+static void ibmebus_free_coherent(struct device *dev,
+				  size_t size, void *vaddr,
+				  dma_addr_t dma_handle,
+				  unsigned long attrs)
+{
+	kfree(vaddr);
+}
+
+static dma_addr_t ibmebus_map_page(struct device *dev,
+				   struct page *page,
+				   unsigned long offset,
+				   size_t size,
+				   enum dma_data_direction direction,
+				   unsigned long attrs)
+{
+	return (dma_addr_t)(page_address(page) + offset);
+}
+
+static void ibmebus_unmap_page(struct device *dev,
+			       dma_addr_t dma_addr,
+			       size_t size,
+			       enum dma_data_direction direction,
+			       unsigned long attrs)
+{
+	return;
+}
+
+static int ibmebus_map_sg(struct device *dev,
+			  struct scatterlist *sgl,
+			  int nents, enum dma_data_direction direction,
+			  unsigned long attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = (dma_addr_t) sg_virt(sg);
+		sg->dma_length = sg->length;
+	}
+
+	return nents;
+}
+
+static void ibmebus_unmap_sg(struct device *dev,
+			     struct scatterlist *sg,
+			     int nents, enum dma_data_direction direction,
+			     unsigned long attrs)
+{
+	return;
+}
+
+static int ibmebus_dma_supported(struct device *dev, u64 mask)
+{
+	return mask == DMA_BIT_MASK(64);
+}
+
+static u64 ibmebus_dma_get_required_mask(struct device *dev)
+{
+	return DMA_BIT_MASK(64);
+}
+
+static struct dma_map_ops ibmebus_dma_ops = {
+	.alloc              = ibmebus_alloc_coherent,
+	.free               = ibmebus_free_coherent,
+	.map_sg             = ibmebus_map_sg,
+	.unmap_sg           = ibmebus_unmap_sg,
+	.dma_supported      = ibmebus_dma_supported,
+	.get_required_mask  = ibmebus_dma_get_required_mask,
+	.map_page           = ibmebus_map_page,
+	.unmap_page         = ibmebus_unmap_page,
+};
+
+static int ibmebus_match_path(struct device *dev, void *data)
+{
+	struct device_node *dn = to_platform_device(dev)->dev.of_node;
+	return (dn->full_name &&
+		(strcasecmp((char *)data, dn->full_name) == 0));
+}
+
+static int ibmebus_match_node(struct device *dev, void *data)
+{
+	return to_platform_device(dev)->dev.of_node == data;
+}
+
+static int ibmebus_create_device(struct device_node *dn)
+{
+	struct platform_device *dev;
+	int ret;
+
+	dev = of_device_alloc(dn, NULL, &ibmebus_bus_device);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->dev.bus = &ibmebus_bus_type;
+	dev->dev.archdata.dma_ops = &ibmebus_dma_ops;
+
+	ret = of_device_add(dev);
+	if (ret)
+		platform_device_put(dev);
+	return ret;
+}
+
+static int ibmebus_create_devices(const struct of_device_id *matches)
+{
+	struct device_node *root, *child;
+	struct device *dev;
+	int ret = 0;
+
+	root = of_find_node_by_path("/");
+
+	for_each_child_of_node(root, child) {
+		if (!of_match_node(matches, child))
+			continue;
+
+		dev = bus_find_device(&ibmebus_bus_type, NULL, child,
+				      ibmebus_match_node);
+		if (dev) {
+			put_device(dev);
+			continue;
+		}
+
+		ret = ibmebus_create_device(child);
+		if (ret) {
+			printk(KERN_ERR "%s: failed to create device (%i)",
+			       __func__, ret);
+			of_node_put(child);
+			break;
+		}
+	}
+
+	of_node_put(root);
+	return ret;
+}
+
+int ibmebus_register_driver(struct platform_driver *drv)
+{
+	/* If the driver uses devices that ibmebus doesn't know, add them */
+	ibmebus_create_devices(drv->driver.of_match_table);
+
+	drv->driver.bus = &ibmebus_bus_type;
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL(ibmebus_register_driver);
+
+void ibmebus_unregister_driver(struct platform_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL(ibmebus_unregister_driver);
+
+int ibmebus_request_irq(u32 ist, irq_handler_t handler,
+			unsigned long irq_flags, const char *devname,
+			void *dev_id)
+{
+	unsigned int irq = irq_create_mapping(NULL, ist);
+
+	if (!irq)
+		return -EINVAL;
+
+	return request_irq(irq, handler, irq_flags, devname, dev_id);
+}
+EXPORT_SYMBOL(ibmebus_request_irq);
+
+void ibmebus_free_irq(u32 ist, void *dev_id)
+{
+	unsigned int irq = irq_find_mapping(NULL, ist);
+
+	free_irq(irq, dev_id);
+	irq_dispose_mapping(irq);
+}
+EXPORT_SYMBOL(ibmebus_free_irq);
+
+static char *ibmebus_chomp(const char *in, size_t count)
+{
+	char *out = kmalloc(count + 1, GFP_KERNEL);
+
+	if (!out)
+		return NULL;
+
+	memcpy(out, in, count);
+	out[count] = '\0';
+	if (out[count - 1] == '\n')
+		out[count - 1] = '\0';
+
+	return out;
+}
+
+static ssize_t ibmebus_store_probe(struct bus_type *bus,
+				   const char *buf, size_t count)
+{
+	struct device_node *dn = NULL;
+	struct device *dev;
+	char *path;
+	ssize_t rc = 0;
+
+	path = ibmebus_chomp(buf, count);
+	if (!path)
+		return -ENOMEM;
+
+	dev = bus_find_device(&ibmebus_bus_type, NULL, path,
+			      ibmebus_match_path);
+	if (dev) {
+		put_device(dev);
+		printk(KERN_WARNING "%s: %s has already been probed\n",
+		       __func__, path);
+		rc = -EEXIST;
+		goto out;
+	}
+
+	if ((dn = of_find_node_by_path(path))) {
+		rc = ibmebus_create_device(dn);
+		of_node_put(dn);
+	} else {
+		printk(KERN_WARNING "%s: no such device node: %s\n",
+		       __func__, path);
+		rc = -ENODEV;
+	}
+
+out:
+	kfree(path);
+	if (rc)
+		return rc;
+	return count;
+}
+static BUS_ATTR(probe, S_IWUSR, NULL, ibmebus_store_probe);
+
+static ssize_t ibmebus_store_remove(struct bus_type *bus,
+				    const char *buf, size_t count)
+{
+	struct device *dev;
+	char *path;
+
+	path = ibmebus_chomp(buf, count);
+	if (!path)
+		return -ENOMEM;
+
+	if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path,
+				   ibmebus_match_path))) {
+		of_device_unregister(to_platform_device(dev));
+		put_device(dev);
+
+		kfree(path);
+		return count;
+	} else {
+		printk(KERN_WARNING "%s: %s not on the bus\n",
+		       __func__, path);
+
+		kfree(path);
+		return -ENODEV;
+	}
+}
+static BUS_ATTR(remove, S_IWUSR, NULL, ibmebus_store_remove);
+
+static struct attribute *ibmbus_bus_attrs[] = {
+	&bus_attr_probe.attr,
+	&bus_attr_remove.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(ibmbus_bus);
+
+static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv)
+{
+	const struct of_device_id *matches = drv->of_match_table;
+
+	if (!matches)
+		return 0;
+
+	return of_match_device(matches, dev) != NULL;
+}
+
+static int ibmebus_bus_device_probe(struct device *dev)
+{
+	int error = -ENODEV;
+	struct platform_driver *drv;
+	struct platform_device *of_dev;
+
+	drv = to_platform_driver(dev->driver);
+	of_dev = to_platform_device(dev);
+
+	if (!drv->probe)
+		return error;
+
+	of_dev_get(of_dev);
+
+	if (of_driver_match_device(dev, dev->driver))
+		error = drv->probe(of_dev);
+	if (error)
+		of_dev_put(of_dev);
+
+	return error;
+}
+
+static int ibmebus_bus_device_remove(struct device *dev)
+{
+	struct platform_device *of_dev = to_platform_device(dev);
+	struct platform_driver *drv = to_platform_driver(dev->driver);
+
+	if (dev->driver && drv->remove)
+		drv->remove(of_dev);
+	return 0;
+}
+
+static void ibmebus_bus_device_shutdown(struct device *dev)
+{
+	struct platform_device *of_dev = to_platform_device(dev);
+	struct platform_driver *drv = to_platform_driver(dev->driver);
+
+	if (dev->driver && drv->shutdown)
+		drv->shutdown(of_dev);
+}
+
+/*
+ * ibmebus_bus_device_attrs
+ */
+static ssize_t devspec_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct platform_device *ofdev;
+
+	ofdev = to_platform_device(dev);
+	return sprintf(buf, "%s\n", ofdev->dev.of_node->full_name);
+}
+
+static ssize_t name_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct platform_device *ofdev;
+
+	ofdev = to_platform_device(dev);
+	return sprintf(buf, "%s\n", ofdev->dev.of_node->name);
+}
+
+static ssize_t modalias_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	ssize_t len = of_device_get_modalias(dev, buf, PAGE_SIZE - 2);
+	buf[len] = '\n';
+	buf[len+1] = 0;
+	return len+1;
+}
+
+static struct device_attribute ibmebus_bus_device_attrs[] = {
+	__ATTR_RO(devspec),
+	__ATTR_RO(name),
+	__ATTR_RO(modalias),
+	__ATTR_NULL
+};
+
+struct bus_type ibmebus_bus_type = {
+	.name      = "ibmebus",
+	.uevent    = of_device_uevent_modalias,
+	.bus_groups = ibmbus_bus_groups,
+	.match     = ibmebus_bus_bus_match,
+	.probe     = ibmebus_bus_device_probe,
+	.remove    = ibmebus_bus_device_remove,
+	.shutdown  = ibmebus_bus_device_shutdown,
+	.dev_attrs = ibmebus_bus_device_attrs,
+};
+EXPORT_SYMBOL(ibmebus_bus_type);
+
+static int __init ibmebus_bus_init(void)
+{
+	int err;
+
+	printk(KERN_INFO "IBM eBus Device Driver\n");
+
+	err = bus_register(&ibmebus_bus_type);
+	if (err) {
+		printk(KERN_ERR "%s: failed to register IBM eBus.\n",
+		       __func__);
+		return err;
+	}
+
+	err = device_register(&ibmebus_bus_device);
+	if (err) {
+		printk(KERN_WARNING "%s: device_register returned %i\n",
+		       __func__, err);
+		bus_unregister(&ibmebus_bus_type);
+
+		return err;
+	}
+
+	err = ibmebus_create_devices(ibmebus_matches);
+	if (err) {
+		device_unregister(&ibmebus_bus_device);
+		bus_unregister(&ibmebus_bus_type);
+		return err;
+	}
+
+	return 0;
+}
+postcore_initcall(ibmebus_bus_init);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index a78da511ffeb..5dc1c3c6e716 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -221,7 +221,7 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
 	return -1;
 }
 
-static void pSeries_lpar_hptab_clear(void)
+static void manual_hpte_clear_all(void)
 {
 	unsigned long size_bytes = 1UL << ppc64_pft_size;
 	unsigned long hpte_count = size_bytes >> 4;
@@ -249,6 +249,26 @@ static void pSeries_lpar_hptab_clear(void)
 					&(ptes[j].pteh), &(ptes[j].ptel));
 		}
 	}
+}
+
+static int hcall_hpte_clear_all(void)
+{
+	int rc;
+
+	do {
+		rc = plpar_hcall_norets(H_CLEAR_HPT);
+	} while (rc == H_CONTINUE);
+
+	return rc;
+}
+
+static void pseries_hpte_clear_all(void)
+{
+	int rc;
+
+	rc = hcall_hpte_clear_all();
+	if (rc != H_SUCCESS)
+		manual_hpte_clear_all();
 
 #ifdef __LITTLE_ENDIAN__
 	/*
@@ -598,7 +618,7 @@ void __init hpte_init_pseries(void)
 	mmu_hash_ops.hpte_remove	 = pSeries_lpar_hpte_remove;
 	mmu_hash_ops.hpte_removebolted   = pSeries_lpar_hpte_removebolted;
 	mmu_hash_ops.flush_hash_range	 = pSeries_lpar_flush_hash_range;
-	mmu_hash_ops.hpte_clear_all      = pSeries_lpar_hptab_clear;
+	mmu_hash_ops.hpte_clear_all      = pseries_hpte_clear_all;
 	mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
 }
 
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index afa05a2cb702..e6397976060e 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -37,6 +37,7 @@
 #include <asm/mmu.h>
 #include <asm/machdep.h>
 
+#include "pseries.h"
 
 /*
  * This isn't a module but we expose that to userspace
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index b1be7b713fe6..1361a9db534b 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -79,4 +79,23 @@ extern struct pci_controller_ops pseries_pci_controller_ops;
 
 unsigned long pseries_memory_block_size(void);
 
+extern int CMO_PrPSP;
+extern int CMO_SecPSP;
+extern unsigned long CMO_PageSize;
+
+static inline int cmo_get_primary_psp(void)
+{
+	return CMO_PrPSP;
+}
+
+static inline int cmo_get_secondary_psp(void)
+{
+	return CMO_SecPSP;
+}
+
+static inline unsigned long cmo_get_page_size(void)
+{
+	return CMO_PageSize;
+}
+
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 97aa3f332f24..7736352f7279 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -367,7 +367,7 @@ void pseries_disable_reloc_on_exc(void)
 }
 EXPORT_SYMBOL(pseries_disable_reloc_on_exc);
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static void pSeries_machine_kexec(struct kimage *image)
 {
 	if (firmware_has_feature(FW_FEATURE_SET_MODE))
@@ -725,7 +725,7 @@ define_machine(pseries) {
 	.progress		= rtas_progress,
 	.system_reset_exception = pSeries_system_reset_exception,
 	.machine_check_exception = pSeries_machine_check_exception,
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.machine_kexec          = pSeries_machine_kexec,
 	.kexec_cpu_down         = pseries_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
new file mode 100644
index 000000000000..2c8fb3ec989e
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -0,0 +1,1705 @@
+/*
+ * IBM PowerPC Virtual I/O Infrastructure Support.
+ *
+ *    Copyright (c) 2003,2008 IBM Corp.
+ *     Dave Engebretsen engebret@us.ibm.com
+ *     Santiago Leon santil@us.ibm.com
+ *     Hollis Blanchard <hollisb@us.ibm.com>
+ *     Stephen Rothwell
+ *     Robert Jennings <rcjenn@us.ibm.com>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/cpu.h>
+#include <linux/types.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/console.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/kobject.h>
+
+#include <asm/iommu.h>
+#include <asm/dma.h>
+#include <asm/vio.h>
+#include <asm/prom.h>
+#include <asm/firmware.h>
+#include <asm/tce.h>
+#include <asm/page.h>
+#include <asm/hvcall.h>
+
+static struct vio_dev vio_bus_device  = { /* fake "parent" device */
+	.name = "vio",
+	.type = "",
+	.dev.init_name = "vio",
+	.dev.bus = &vio_bus_type,
+};
+
+#ifdef CONFIG_PPC_SMLPAR
+/**
+ * vio_cmo_pool - A pool of IO memory for CMO use
+ *
+ * @size: The size of the pool in bytes
+ * @free: The amount of free memory in the pool
+ */
+struct vio_cmo_pool {
+	size_t size;
+	size_t free;
+};
+
+/* How many ms to delay queued balance work */
+#define VIO_CMO_BALANCE_DELAY 100
+
+/* Portion out IO memory to CMO devices by this chunk size */
+#define VIO_CMO_BALANCE_CHUNK 131072
+
+/**
+ * vio_cmo_dev_entry - A device that is CMO-enabled and requires entitlement
+ *
+ * @vio_dev: struct vio_dev pointer
+ * @list: pointer to other devices on bus that are being tracked
+ */
+struct vio_cmo_dev_entry {
+	struct vio_dev *viodev;
+	struct list_head list;
+};
+
+/**
+ * vio_cmo - VIO bus accounting structure for CMO entitlement
+ *
+ * @lock: spinlock for entire structure
+ * @balance_q: work queue for balancing system entitlement
+ * @device_list: list of CMO-enabled devices requiring entitlement
+ * @entitled: total system entitlement in bytes
+ * @reserve: pool of memory from which devices reserve entitlement, incl. spare
+ * @excess: pool of excess entitlement not needed for device reserves or spare
+ * @spare: IO memory for device hotplug functionality
+ * @min: minimum necessary for system operation
+ * @desired: desired memory for system operation
+ * @curr: bytes currently allocated
+ * @high: high water mark for IO data usage
+ */
+static struct vio_cmo {
+	spinlock_t lock;
+	struct delayed_work balance_q;
+	struct list_head device_list;
+	size_t entitled;
+	struct vio_cmo_pool reserve;
+	struct vio_cmo_pool excess;
+	size_t spare;
+	size_t min;
+	size_t desired;
+	size_t curr;
+	size_t high;
+} vio_cmo;
+
+/**
+ * vio_cmo_OF_devices - Count the number of OF devices that have DMA windows
+ */
+static int vio_cmo_num_OF_devs(void)
+{
+	struct device_node *node_vroot;
+	int count = 0;
+
+	/*
+	 * Count the number of vdevice entries with an
+	 * ibm,my-dma-window OF property
+	 */
+	node_vroot = of_find_node_by_name(NULL, "vdevice");
+	if (node_vroot) {
+		struct device_node *of_node;
+		struct property *prop;
+
+		for_each_child_of_node(node_vroot, of_node) {
+			prop = of_find_property(of_node, "ibm,my-dma-window",
+			                       NULL);
+			if (prop)
+				count++;
+		}
+	}
+	of_node_put(node_vroot);
+	return count;
+}
+
+/**
+ * vio_cmo_alloc - allocate IO memory for CMO-enable devices
+ *
+ * @viodev: VIO device requesting IO memory
+ * @size: size of allocation requested
+ *
+ * Allocations come from memory reserved for the devices and any excess
+ * IO memory available to all devices.  The spare pool used to service
+ * hotplug must be equal to %VIO_CMO_MIN_ENT for the excess pool to be
+ * made available.
+ *
+ * Return codes:
+ *  0 for successful allocation and -ENOMEM for a failure
+ */
+static inline int vio_cmo_alloc(struct vio_dev *viodev, size_t size)
+{
+	unsigned long flags;
+	size_t reserve_free = 0;
+	size_t excess_free = 0;
+	int ret = -ENOMEM;
+
+	spin_lock_irqsave(&vio_cmo.lock, flags);
+
+	/* Determine the amount of free entitlement available in reserve */
+	if (viodev->cmo.entitled > viodev->cmo.allocated)
+		reserve_free = viodev->cmo.entitled - viodev->cmo.allocated;
+
+	/* If spare is not fulfilled, the excess pool can not be used. */
+	if (vio_cmo.spare >= VIO_CMO_MIN_ENT)
+		excess_free = vio_cmo.excess.free;
+
+	/* The request can be satisfied */
+	if ((reserve_free + excess_free) >= size) {
+		vio_cmo.curr += size;
+		if (vio_cmo.curr > vio_cmo.high)
+			vio_cmo.high = vio_cmo.curr;
+		viodev->cmo.allocated += size;
+		size -= min(reserve_free, size);
+		vio_cmo.excess.free -= size;
+		ret = 0;
+	}
+
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+	return ret;
+}
+
+/**
+ * vio_cmo_dealloc - deallocate IO memory from CMO-enable devices
+ * @viodev: VIO device freeing IO memory
+ * @size: size of deallocation
+ *
+ * IO memory is freed by the device back to the correct memory pools.
+ * The spare pool is replenished first from either memory pool, then
+ * the reserve pool is used to reduce device entitlement, the excess
+ * pool is used to increase the reserve pool toward the desired entitlement
+ * target, and then the remaining memory is returned to the pools.
+ *
+ */
+static inline void vio_cmo_dealloc(struct vio_dev *viodev, size_t size)
+{
+	unsigned long flags;
+	size_t spare_needed = 0;
+	size_t excess_freed = 0;
+	size_t reserve_freed = size;
+	size_t tmp;
+	int balance = 0;
+
+	spin_lock_irqsave(&vio_cmo.lock, flags);
+	vio_cmo.curr -= size;
+
+	/* Amount of memory freed from the excess pool */
+	if (viodev->cmo.allocated > viodev->cmo.entitled) {
+		excess_freed = min(reserve_freed, (viodev->cmo.allocated -
+		                                   viodev->cmo.entitled));
+		reserve_freed -= excess_freed;
+	}
+
+	/* Remove allocation from device */
+	viodev->cmo.allocated -= (reserve_freed + excess_freed);
+
+	/* Spare is a subset of the reserve pool, replenish it first. */
+	spare_needed = VIO_CMO_MIN_ENT - vio_cmo.spare;
+
+	/*
+	 * Replenish the spare in the reserve pool from the excess pool.
+	 * This moves entitlement into the reserve pool.
+	 */
+	if (spare_needed && excess_freed) {
+		tmp = min(excess_freed, spare_needed);
+		vio_cmo.excess.size -= tmp;
+		vio_cmo.reserve.size += tmp;
+		vio_cmo.spare += tmp;
+		excess_freed -= tmp;
+		spare_needed -= tmp;
+		balance = 1;
+	}
+
+	/*
+	 * Replenish the spare in the reserve pool from the reserve pool.
+	 * This removes entitlement from the device down to VIO_CMO_MIN_ENT,
+	 * if needed, and gives it to the spare pool. The amount of used
+	 * memory in this pool does not change.
+	 */
+	if (spare_needed && reserve_freed) {
+		tmp = min3(spare_needed, reserve_freed, (viodev->cmo.entitled - VIO_CMO_MIN_ENT));
+
+		vio_cmo.spare += tmp;
+		viodev->cmo.entitled -= tmp;
+		reserve_freed -= tmp;
+		spare_needed -= tmp;
+		balance = 1;
+	}
+
+	/*
+	 * Increase the reserve pool until the desired allocation is met.
+	 * Move an allocation freed from the excess pool into the reserve
+	 * pool and schedule a balance operation.
+	 */
+	if (excess_freed && (vio_cmo.desired > vio_cmo.reserve.size)) {
+		tmp = min(excess_freed, (vio_cmo.desired - vio_cmo.reserve.size));
+
+		vio_cmo.excess.size -= tmp;
+		vio_cmo.reserve.size += tmp;
+		excess_freed -= tmp;
+		balance = 1;
+	}
+
+	/* Return memory from the excess pool to that pool */
+	if (excess_freed)
+		vio_cmo.excess.free += excess_freed;
+
+	if (balance)
+		schedule_delayed_work(&vio_cmo.balance_q, VIO_CMO_BALANCE_DELAY);
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+}
+
+/**
+ * vio_cmo_entitlement_update - Manage system entitlement changes
+ *
+ * @new_entitlement: new system entitlement to attempt to accommodate
+ *
+ * Increases in entitlement will be used to fulfill the spare entitlement
+ * and the rest is given to the excess pool.  Decreases, if they are
+ * possible, come from the excess pool and from unused device entitlement
+ *
+ * Returns: 0 on success, -ENOMEM when change can not be made
+ */
+int vio_cmo_entitlement_update(size_t new_entitlement)
+{
+	struct vio_dev *viodev;
+	struct vio_cmo_dev_entry *dev_ent;
+	unsigned long flags;
+	size_t avail, delta, tmp;
+
+	spin_lock_irqsave(&vio_cmo.lock, flags);
+
+	/* Entitlement increases */
+	if (new_entitlement > vio_cmo.entitled) {
+		delta = new_entitlement - vio_cmo.entitled;
+
+		/* Fulfill spare allocation */
+		if (vio_cmo.spare < VIO_CMO_MIN_ENT) {
+			tmp = min(delta, (VIO_CMO_MIN_ENT - vio_cmo.spare));
+			vio_cmo.spare += tmp;
+			vio_cmo.reserve.size += tmp;
+			delta -= tmp;
+		}
+
+		/* Remaining new allocation goes to the excess pool */
+		vio_cmo.entitled += delta;
+		vio_cmo.excess.size += delta;
+		vio_cmo.excess.free += delta;
+
+		goto out;
+	}
+
+	/* Entitlement decreases */
+	delta = vio_cmo.entitled - new_entitlement;
+	avail = vio_cmo.excess.free;
+
+	/*
+	 * Need to check how much unused entitlement each device can
+	 * sacrifice to fulfill entitlement change.
+	 */
+	list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
+		if (avail >= delta)
+			break;
+
+		viodev = dev_ent->viodev;
+		if ((viodev->cmo.entitled > viodev->cmo.allocated) &&
+		    (viodev->cmo.entitled > VIO_CMO_MIN_ENT))
+				avail += viodev->cmo.entitled -
+				         max_t(size_t, viodev->cmo.allocated,
+				               VIO_CMO_MIN_ENT);
+	}
+
+	if (delta <= avail) {
+		vio_cmo.entitled -= delta;
+
+		/* Take entitlement from the excess pool first */
+		tmp = min(vio_cmo.excess.free, delta);
+		vio_cmo.excess.size -= tmp;
+		vio_cmo.excess.free -= tmp;
+		delta -= tmp;
+
+		/*
+		 * Remove all but VIO_CMO_MIN_ENT bytes from devices
+		 * until entitlement change is served
+		 */
+		list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
+			if (!delta)
+				break;
+
+			viodev = dev_ent->viodev;
+			tmp = 0;
+			if ((viodev->cmo.entitled > viodev->cmo.allocated) &&
+			    (viodev->cmo.entitled > VIO_CMO_MIN_ENT))
+				tmp = viodev->cmo.entitled -
+				      max_t(size_t, viodev->cmo.allocated,
+				            VIO_CMO_MIN_ENT);
+			viodev->cmo.entitled -= min(tmp, delta);
+			delta -= min(tmp, delta);
+		}
+	} else {
+		spin_unlock_irqrestore(&vio_cmo.lock, flags);
+		return -ENOMEM;
+	}
+
+out:
+	schedule_delayed_work(&vio_cmo.balance_q, 0);
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+	return 0;
+}
+
+/**
+ * vio_cmo_balance - Balance entitlement among devices
+ *
+ * @work: work queue structure for this operation
+ *
+ * Any system entitlement above the minimum needed for devices, or
+ * already allocated to devices, can be distributed to the devices.
+ * The list of devices is iterated through to recalculate the desired
+ * entitlement level and to determine how much entitlement above the
+ * minimum entitlement is allocated to devices.
+ *
+ * Small chunks of the available entitlement are given to devices until
+ * their requirements are fulfilled or there is no entitlement left to give.
+ * Upon completion sizes of the reserve and excess pools are calculated.
+ *
+ * The system minimum entitlement level is also recalculated here.
+ * Entitlement will be reserved for devices even after vio_bus_remove to
+ * accommodate reloading the driver.  The OF tree is walked to count the
+ * number of devices present and this will remove entitlement for devices
+ * that have actually left the system after having vio_bus_remove called.
+ */
+static void vio_cmo_balance(struct work_struct *work)
+{
+	struct vio_cmo *cmo;
+	struct vio_dev *viodev;
+	struct vio_cmo_dev_entry *dev_ent;
+	unsigned long flags;
+	size_t avail = 0, level, chunk, need;
+	int devcount = 0, fulfilled;
+
+	cmo = container_of(work, struct vio_cmo, balance_q.work);
+
+	spin_lock_irqsave(&vio_cmo.lock, flags);
+
+	/* Calculate minimum entitlement and fulfill spare */
+	cmo->min = vio_cmo_num_OF_devs() * VIO_CMO_MIN_ENT;
+	BUG_ON(cmo->min > cmo->entitled);
+	cmo->spare = min_t(size_t, VIO_CMO_MIN_ENT, (cmo->entitled - cmo->min));
+	cmo->min += cmo->spare;
+	cmo->desired = cmo->min;
+
+	/*
+	 * Determine how much entitlement is available and reset device
+	 * entitlements
+	 */
+	avail = cmo->entitled - cmo->spare;
+	list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
+		viodev = dev_ent->viodev;
+		devcount++;
+		viodev->cmo.entitled = VIO_CMO_MIN_ENT;
+		cmo->desired += (viodev->cmo.desired - VIO_CMO_MIN_ENT);
+		avail -= max_t(size_t, viodev->cmo.allocated, VIO_CMO_MIN_ENT);
+	}
+
+	/*
+	 * Having provided each device with the minimum entitlement, loop
+	 * over the devices portioning out the remaining entitlement
+	 * until there is nothing left.
+	 */
+	level = VIO_CMO_MIN_ENT;
+	while (avail) {
+		fulfilled = 0;
+		list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
+			viodev = dev_ent->viodev;
+
+			if (viodev->cmo.desired <= level) {
+				fulfilled++;
+				continue;
+			}
+
+			/*
+			 * Give the device up to VIO_CMO_BALANCE_CHUNK
+			 * bytes of entitlement, but do not exceed the
+			 * desired level of entitlement for the device.
+			 */
+			chunk = min_t(size_t, avail, VIO_CMO_BALANCE_CHUNK);
+			chunk = min(chunk, (viodev->cmo.desired -
+			                    viodev->cmo.entitled));
+			viodev->cmo.entitled += chunk;
+
+			/*
+			 * If the memory for this entitlement increase was
+			 * already allocated to the device it does not come
+			 * from the available pool being portioned out.
+			 */
+			need = max(viodev->cmo.allocated, viodev->cmo.entitled)-
+			       max(viodev->cmo.allocated, level);
+			avail -= need;
+
+		}
+		if (fulfilled == devcount)
+			break;
+		level += VIO_CMO_BALANCE_CHUNK;
+	}
+
+	/* Calculate new reserve and excess pool sizes */
+	cmo->reserve.size = cmo->min;
+	cmo->excess.free = 0;
+	cmo->excess.size = 0;
+	need = 0;
+	list_for_each_entry(dev_ent, &vio_cmo.device_list, list) {
+		viodev = dev_ent->viodev;
+		/* Calculated reserve size above the minimum entitlement */
+		if (viodev->cmo.entitled)
+			cmo->reserve.size += (viodev->cmo.entitled -
+			                      VIO_CMO_MIN_ENT);
+		/* Calculated used excess entitlement */
+		if (viodev->cmo.allocated > viodev->cmo.entitled)
+			need += viodev->cmo.allocated - viodev->cmo.entitled;
+	}
+	cmo->excess.size = cmo->entitled - cmo->reserve.size;
+	cmo->excess.free = cmo->excess.size - need;
+
+	cancel_delayed_work(to_delayed_work(work));
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+}
+
+static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
+					  dma_addr_t *dma_handle, gfp_t flag,
+					  unsigned long attrs)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	void *ret;
+
+	if (vio_cmo_alloc(viodev, roundup(size, PAGE_SIZE))) {
+		atomic_inc(&viodev->cmo.allocs_failed);
+		return NULL;
+	}
+
+	ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
+	if (unlikely(ret == NULL)) {
+		vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
+		atomic_inc(&viodev->cmo.allocs_failed);
+	}
+
+	return ret;
+}
+
+static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
+					void *vaddr, dma_addr_t dma_handle,
+					unsigned long attrs)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+
+	dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
+
+	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
+}
+
+static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
+                                         unsigned long offset, size_t size,
+                                         enum dma_data_direction direction,
+                                         unsigned long attrs)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
+	dma_addr_t ret = DMA_ERROR_CODE;
+
+	tbl = get_iommu_table_base(dev);
+	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
+		atomic_inc(&viodev->cmo.allocs_failed);
+		return ret;
+	}
+
+	ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs);
+	if (unlikely(dma_mapping_error(dev, ret))) {
+		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
+		atomic_inc(&viodev->cmo.allocs_failed);
+	}
+
+	return ret;
+}
+
+static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
+				     size_t size,
+				     enum dma_data_direction direction,
+				     unsigned long attrs)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
+
+	tbl = get_iommu_table_base(dev);
+	dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs);
+
+	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
+}
+
+static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
+                                int nelems, enum dma_data_direction direction,
+                                unsigned long attrs)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
+	struct scatterlist *sgl;
+	int ret, count;
+	size_t alloc_size = 0;
+
+	tbl = get_iommu_table_base(dev);
+	for_each_sg(sglist, sgl, nelems, count)
+		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
+
+	if (vio_cmo_alloc(viodev, alloc_size)) {
+		atomic_inc(&viodev->cmo.allocs_failed);
+		return 0;
+	}
+
+	ret = dma_iommu_ops.map_sg(dev, sglist, nelems, direction, attrs);
+
+	if (unlikely(!ret)) {
+		vio_cmo_dealloc(viodev, alloc_size);
+		atomic_inc(&viodev->cmo.allocs_failed);
+		return ret;
+	}
+
+	for_each_sg(sglist, sgl, ret, count)
+		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
+	if (alloc_size)
+		vio_cmo_dealloc(viodev, alloc_size);
+
+	return ret;
+}
+
+static void vio_dma_iommu_unmap_sg(struct device *dev,
+		struct scatterlist *sglist, int nelems,
+		enum dma_data_direction direction,
+		unsigned long attrs)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
+	struct scatterlist *sgl;
+	size_t alloc_size = 0;
+	int count;
+
+	tbl = get_iommu_table_base(dev);
+	for_each_sg(sglist, sgl, nelems, count)
+		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
+
+	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
+
+	vio_cmo_dealloc(viodev, alloc_size);
+}
+
+static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
+{
+        return dma_iommu_ops.dma_supported(dev, mask);
+}
+
+static u64 vio_dma_get_required_mask(struct device *dev)
+{
+        return dma_iommu_ops.get_required_mask(dev);
+}
+
+static struct dma_map_ops vio_dma_mapping_ops = {
+	.alloc             = vio_dma_iommu_alloc_coherent,
+	.free              = vio_dma_iommu_free_coherent,
+	.mmap		   = dma_direct_mmap_coherent,
+	.map_sg            = vio_dma_iommu_map_sg,
+	.unmap_sg          = vio_dma_iommu_unmap_sg,
+	.map_page          = vio_dma_iommu_map_page,
+	.unmap_page        = vio_dma_iommu_unmap_page,
+	.dma_supported     = vio_dma_iommu_dma_supported,
+	.get_required_mask = vio_dma_get_required_mask,
+};
+
+/**
+ * vio_cmo_set_dev_desired - Set desired entitlement for a device
+ *
+ * @viodev: struct vio_dev for device to alter
+ * @desired: new desired entitlement level in bytes
+ *
+ * For use by devices to request a change to their entitlement at runtime or
+ * through sysfs.  The desired entitlement level is changed and a balancing
+ * of system resources is scheduled to run in the future.
+ */
+void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired)
+{
+	unsigned long flags;
+	struct vio_cmo_dev_entry *dev_ent;
+	int found = 0;
+
+	if (!firmware_has_feature(FW_FEATURE_CMO))
+		return;
+
+	spin_lock_irqsave(&vio_cmo.lock, flags);
+	if (desired < VIO_CMO_MIN_ENT)
+		desired = VIO_CMO_MIN_ENT;
+
+	/*
+	 * Changes will not be made for devices not in the device list.
+	 * If it is not in the device list, then no driver is loaded
+	 * for the device and it can not receive entitlement.
+	 */
+	list_for_each_entry(dev_ent, &vio_cmo.device_list, list)
+		if (viodev == dev_ent->viodev) {
+			found = 1;
+			break;
+		}
+	if (!found) {
+		spin_unlock_irqrestore(&vio_cmo.lock, flags);
+		return;
+	}
+
+	/* Increase/decrease in desired device entitlement */
+	if (desired >= viodev->cmo.desired) {
+		/* Just bump the bus and device values prior to a balance*/
+		vio_cmo.desired += desired - viodev->cmo.desired;
+		viodev->cmo.desired = desired;
+	} else {
+		/* Decrease bus and device values for desired entitlement */
+		vio_cmo.desired -= viodev->cmo.desired - desired;
+		viodev->cmo.desired = desired;
+		/*
+		 * If less entitlement is desired than current entitlement, move
+		 * any reserve memory in the change region to the excess pool.
+		 */
+		if (viodev->cmo.entitled > desired) {
+			vio_cmo.reserve.size -= viodev->cmo.entitled - desired;
+			vio_cmo.excess.size += viodev->cmo.entitled - desired;
+			/*
+			 * If entitlement moving from the reserve pool to the
+			 * excess pool is currently unused, add to the excess
+			 * free counter.
+			 */
+			if (viodev->cmo.allocated < viodev->cmo.entitled)
+				vio_cmo.excess.free += viodev->cmo.entitled -
+				                       max(viodev->cmo.allocated, desired);
+			viodev->cmo.entitled = desired;
+		}
+	}
+	schedule_delayed_work(&vio_cmo.balance_q, 0);
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+}
+
+/**
+ * vio_cmo_bus_probe - Handle CMO specific bus probe activities
+ *
+ * @viodev - Pointer to struct vio_dev for device
+ *
+ * Determine the devices IO memory entitlement needs, attempting
+ * to satisfy the system minimum entitlement at first and scheduling
+ * a balance operation to take care of the rest at a later time.
+ *
+ * Returns: 0 on success, -EINVAL when device doesn't support CMO, and
+ *          -ENOMEM when entitlement is not available for device or
+ *          device entry.
+ *
+ */
+static int vio_cmo_bus_probe(struct vio_dev *viodev)
+{
+	struct vio_cmo_dev_entry *dev_ent;
+	struct device *dev = &viodev->dev;
+	struct iommu_table *tbl;
+	struct vio_driver *viodrv = to_vio_driver(dev->driver);
+	unsigned long flags;
+	size_t size;
+	bool dma_capable = false;
+
+	tbl = get_iommu_table_base(dev);
+
+	/* A device requires entitlement if it has a DMA window property */
+	switch (viodev->family) {
+	case VDEVICE:
+		if (of_get_property(viodev->dev.of_node,
+					"ibm,my-dma-window", NULL))
+			dma_capable = true;
+		break;
+	case PFO:
+		dma_capable = false;
+		break;
+	default:
+		dev_warn(dev, "unknown device family: %d\n", viodev->family);
+		BUG();
+		break;
+	}
+
+	/* Configure entitlement for the device. */
+	if (dma_capable) {
+		/* Check that the driver is CMO enabled and get desired DMA */
+		if (!viodrv->get_desired_dma) {
+			dev_err(dev, "%s: device driver does not support CMO\n",
+			        __func__);
+			return -EINVAL;
+		}
+
+		viodev->cmo.desired =
+			IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev), tbl);
+		if (viodev->cmo.desired < VIO_CMO_MIN_ENT)
+			viodev->cmo.desired = VIO_CMO_MIN_ENT;
+		size = VIO_CMO_MIN_ENT;
+
+		dev_ent = kmalloc(sizeof(struct vio_cmo_dev_entry),
+		                  GFP_KERNEL);
+		if (!dev_ent)
+			return -ENOMEM;
+
+		dev_ent->viodev = viodev;
+		spin_lock_irqsave(&vio_cmo.lock, flags);
+		list_add(&dev_ent->list, &vio_cmo.device_list);
+	} else {
+		viodev->cmo.desired = 0;
+		size = 0;
+		spin_lock_irqsave(&vio_cmo.lock, flags);
+	}
+
+	/*
+	 * If the needs for vio_cmo.min have not changed since they
+	 * were last set, the number of devices in the OF tree has
+	 * been constant and the IO memory for this is already in
+	 * the reserve pool.
+	 */
+	if (vio_cmo.min == ((vio_cmo_num_OF_devs() + 1) *
+	                    VIO_CMO_MIN_ENT)) {
+		/* Updated desired entitlement if device requires it */
+		if (size)
+			vio_cmo.desired += (viodev->cmo.desired -
+		                        VIO_CMO_MIN_ENT);
+	} else {
+		size_t tmp;
+
+		tmp = vio_cmo.spare + vio_cmo.excess.free;
+		if (tmp < size) {
+			dev_err(dev, "%s: insufficient free "
+			        "entitlement to add device. "
+			        "Need %lu, have %lu\n", __func__,
+				size, (vio_cmo.spare + tmp));
+			spin_unlock_irqrestore(&vio_cmo.lock, flags);
+			return -ENOMEM;
+		}
+
+		/* Use excess pool first to fulfill request */
+		tmp = min(size, vio_cmo.excess.free);
+		vio_cmo.excess.free -= tmp;
+		vio_cmo.excess.size -= tmp;
+		vio_cmo.reserve.size += tmp;
+
+		/* Use spare if excess pool was insufficient */
+		vio_cmo.spare -= size - tmp;
+
+		/* Update bus accounting */
+		vio_cmo.min += size;
+		vio_cmo.desired += viodev->cmo.desired;
+	}
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+	return 0;
+}
+
+/**
+ * vio_cmo_bus_remove - Handle CMO specific bus removal activities
+ *
+ * @viodev - Pointer to struct vio_dev for device
+ *
+ * Remove the device from the cmo device list.  The minimum entitlement
+ * will be reserved for the device as long as it is in the system.  The
+ * rest of the entitlement the device had been allocated will be returned
+ * to the system.
+ */
+static void vio_cmo_bus_remove(struct vio_dev *viodev)
+{
+	struct vio_cmo_dev_entry *dev_ent;
+	unsigned long flags;
+	size_t tmp;
+
+	spin_lock_irqsave(&vio_cmo.lock, flags);
+	if (viodev->cmo.allocated) {
+		dev_err(&viodev->dev, "%s: device had %lu bytes of IO "
+		        "allocated after remove operation.\n",
+		        __func__, viodev->cmo.allocated);
+		BUG();
+	}
+
+	/*
+	 * Remove the device from the device list being maintained for
+	 * CMO enabled devices.
+	 */
+	list_for_each_entry(dev_ent, &vio_cmo.device_list, list)
+		if (viodev == dev_ent->viodev) {
+			list_del(&dev_ent->list);
+			kfree(dev_ent);
+			break;
+		}
+
+	/*
+	 * Devices may not require any entitlement and they do not need
+	 * to be processed.  Otherwise, return the device's entitlement
+	 * back to the pools.
+	 */
+	if (viodev->cmo.entitled) {
+		/*
+		 * This device has not yet left the OF tree, it's
+		 * minimum entitlement remains in vio_cmo.min and
+		 * vio_cmo.desired
+		 */
+		vio_cmo.desired -= (viodev->cmo.desired - VIO_CMO_MIN_ENT);
+
+		/*
+		 * Save min allocation for device in reserve as long
+		 * as it exists in OF tree as determined by later
+		 * balance operation
+		 */
+		viodev->cmo.entitled -= VIO_CMO_MIN_ENT;
+
+		/* Replenish spare from freed reserve pool */
+		if (viodev->cmo.entitled && (vio_cmo.spare < VIO_CMO_MIN_ENT)) {
+			tmp = min(viodev->cmo.entitled, (VIO_CMO_MIN_ENT -
+			                                 vio_cmo.spare));
+			vio_cmo.spare += tmp;
+			viodev->cmo.entitled -= tmp;
+		}
+
+		/* Remaining reserve goes to excess pool */
+		vio_cmo.excess.size += viodev->cmo.entitled;
+		vio_cmo.excess.free += viodev->cmo.entitled;
+		vio_cmo.reserve.size -= viodev->cmo.entitled;
+
+		/*
+		 * Until the device is removed it will keep a
+		 * minimum entitlement; this will guarantee that
+		 * a module unload/load will result in a success.
+		 */
+		viodev->cmo.entitled = VIO_CMO_MIN_ENT;
+		viodev->cmo.desired = VIO_CMO_MIN_ENT;
+		atomic_set(&viodev->cmo.allocs_failed, 0);
+	}
+
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+}
+
+static void vio_cmo_set_dma_ops(struct vio_dev *viodev)
+{
+	set_dma_ops(&viodev->dev, &vio_dma_mapping_ops);
+}
+
+/**
+ * vio_cmo_bus_init - CMO entitlement initialization at bus init time
+ *
+ * Set up the reserve and excess entitlement pools based on available
+ * system entitlement and the number of devices in the OF tree that
+ * require entitlement in the reserve pool.
+ */
+static void vio_cmo_bus_init(void)
+{
+	struct hvcall_mpp_data mpp_data;
+	int err;
+
+	memset(&vio_cmo, 0, sizeof(struct vio_cmo));
+	spin_lock_init(&vio_cmo.lock);
+	INIT_LIST_HEAD(&vio_cmo.device_list);
+	INIT_DELAYED_WORK(&vio_cmo.balance_q, vio_cmo_balance);
+
+	/* Get current system entitlement */
+	err = h_get_mpp(&mpp_data);
+
+	/*
+	 * On failure, continue with entitlement set to 0, will panic()
+	 * later when spare is reserved.
+	 */
+	if (err != H_SUCCESS) {
+		printk(KERN_ERR "%s: unable to determine system IO "\
+		       "entitlement. (%d)\n", __func__, err);
+		vio_cmo.entitled = 0;
+	} else {
+		vio_cmo.entitled = mpp_data.entitled_mem;
+	}
+
+	/* Set reservation and check against entitlement */
+	vio_cmo.spare = VIO_CMO_MIN_ENT;
+	vio_cmo.reserve.size = vio_cmo.spare;
+	vio_cmo.reserve.size += (vio_cmo_num_OF_devs() *
+	                         VIO_CMO_MIN_ENT);
+	if (vio_cmo.reserve.size > vio_cmo.entitled) {
+		printk(KERN_ERR "%s: insufficient system entitlement\n",
+		       __func__);
+		panic("%s: Insufficient system entitlement", __func__);
+	}
+
+	/* Set the remaining accounting variables */
+	vio_cmo.excess.size = vio_cmo.entitled - vio_cmo.reserve.size;
+	vio_cmo.excess.free = vio_cmo.excess.size;
+	vio_cmo.min = vio_cmo.reserve.size;
+	vio_cmo.desired = vio_cmo.reserve.size;
+}
+
+/* sysfs device functions and data structures for CMO */
+
+#define viodev_cmo_rd_attr(name)                                        \
+static ssize_t viodev_cmo_##name##_show(struct device *dev,             \
+                                        struct device_attribute *attr,  \
+                                         char *buf)                     \
+{                                                                       \
+	return sprintf(buf, "%lu\n", to_vio_dev(dev)->cmo.name);        \
+}
+
+static ssize_t viodev_cmo_allocs_failed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	return sprintf(buf, "%d\n", atomic_read(&viodev->cmo.allocs_failed));
+}
+
+static ssize_t viodev_cmo_allocs_failed_reset(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	atomic_set(&viodev->cmo.allocs_failed, 0);
+	return count;
+}
+
+static ssize_t viodev_cmo_desired_set(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	size_t new_desired;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &new_desired);
+	if (ret)
+		return ret;
+
+	vio_cmo_set_dev_desired(viodev, new_desired);
+	return count;
+}
+
+viodev_cmo_rd_attr(desired);
+viodev_cmo_rd_attr(entitled);
+viodev_cmo_rd_attr(allocated);
+
+static ssize_t name_show(struct device *, struct device_attribute *, char *);
+static ssize_t devspec_show(struct device *, struct device_attribute *, char *);
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+			     char *buf);
+static struct device_attribute vio_cmo_dev_attrs[] = {
+	__ATTR_RO(name),
+	__ATTR_RO(devspec),
+	__ATTR_RO(modalias),
+	__ATTR(cmo_desired,       S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH,
+	       viodev_cmo_desired_show, viodev_cmo_desired_set),
+	__ATTR(cmo_entitled,      S_IRUGO, viodev_cmo_entitled_show,      NULL),
+	__ATTR(cmo_allocated,     S_IRUGO, viodev_cmo_allocated_show,     NULL),
+	__ATTR(cmo_allocs_failed, S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH,
+	       viodev_cmo_allocs_failed_show, viodev_cmo_allocs_failed_reset),
+	__ATTR_NULL
+};
+
+/* sysfs bus functions and data structures for CMO */
+
+#define viobus_cmo_rd_attr(name)                                        \
+static ssize_t cmo_##name##_show(struct bus_type *bt, char *buf)        \
+{                                                                       \
+	return sprintf(buf, "%lu\n", vio_cmo.name);                     \
+}                                                                       \
+static BUS_ATTR_RO(cmo_##name)
+
+#define viobus_cmo_pool_rd_attr(name, var)                              \
+static ssize_t                                                          \
+cmo_##name##_##var##_show(struct bus_type *bt, char *buf)               \
+{                                                                       \
+	return sprintf(buf, "%lu\n", vio_cmo.name.var);                 \
+}                                                                       \
+static BUS_ATTR_RO(cmo_##name##_##var)
+
+viobus_cmo_rd_attr(entitled);
+viobus_cmo_rd_attr(spare);
+viobus_cmo_rd_attr(min);
+viobus_cmo_rd_attr(desired);
+viobus_cmo_rd_attr(curr);
+viobus_cmo_pool_rd_attr(reserve, size);
+viobus_cmo_pool_rd_attr(excess, size);
+viobus_cmo_pool_rd_attr(excess, free);
+
+static ssize_t cmo_high_show(struct bus_type *bt, char *buf)
+{
+	return sprintf(buf, "%lu\n", vio_cmo.high);
+}
+
+static ssize_t cmo_high_store(struct bus_type *bt, const char *buf,
+			      size_t count)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vio_cmo.lock, flags);
+	vio_cmo.high = vio_cmo.curr;
+	spin_unlock_irqrestore(&vio_cmo.lock, flags);
+
+	return count;
+}
+static BUS_ATTR_RW(cmo_high);
+
+static struct attribute *vio_bus_attrs[] = {
+	&bus_attr_cmo_entitled.attr,
+	&bus_attr_cmo_spare.attr,
+	&bus_attr_cmo_min.attr,
+	&bus_attr_cmo_desired.attr,
+	&bus_attr_cmo_curr.attr,
+	&bus_attr_cmo_high.attr,
+	&bus_attr_cmo_reserve_size.attr,
+	&bus_attr_cmo_excess_size.attr,
+	&bus_attr_cmo_excess_free.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(vio_bus);
+
+static void vio_cmo_sysfs_init(void)
+{
+	vio_bus_type.dev_attrs = vio_cmo_dev_attrs;
+	vio_bus_type.bus_groups = vio_bus_groups;
+}
+#else /* CONFIG_PPC_SMLPAR */
+int vio_cmo_entitlement_update(size_t new_entitlement) { return 0; }
+void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) {}
+static int vio_cmo_bus_probe(struct vio_dev *viodev) { return 0; }
+static void vio_cmo_bus_remove(struct vio_dev *viodev) {}
+static void vio_cmo_set_dma_ops(struct vio_dev *viodev) {}
+static void vio_cmo_bus_init(void) {}
+static void vio_cmo_sysfs_init(void) { }
+#endif /* CONFIG_PPC_SMLPAR */
+EXPORT_SYMBOL(vio_cmo_entitlement_update);
+EXPORT_SYMBOL(vio_cmo_set_dev_desired);
+
+
+/*
+ * Platform Facilities Option (PFO) support
+ */
+
+/**
+ * vio_h_cop_sync - Perform a synchronous PFO co-processor operation
+ *
+ * @vdev - Pointer to a struct vio_dev for device
+ * @op - Pointer to a struct vio_pfo_op for the operation parameters
+ *
+ * Calls the hypervisor to synchronously perform the PFO operation
+ * described in @op.  In the case of a busy response from the hypervisor,
+ * the operation will be re-submitted indefinitely unless a non-zero timeout
+ * is specified or an error occurs. The timeout places a limit on when to
+ * stop re-submitting a operation, the total time can be exceeded if an
+ * operation is in progress.
+ *
+ * If op->hcall_ret is not NULL, this will be set to the return from the
+ * last h_cop_op call or it will be 0 if an error not involving the h_call
+ * was encountered.
+ *
+ * Returns:
+ *	0 on success,
+ *	-EINVAL if the h_call fails due to an invalid parameter,
+ *	-E2BIG if the h_call can not be performed synchronously,
+ *	-EBUSY if a timeout is specified and has elapsed,
+ *	-EACCES if the memory area for data/status has been rescinded, or
+ *	-EPERM if a hardware fault has been indicated
+ */
+int vio_h_cop_sync(struct vio_dev *vdev, struct vio_pfo_op *op)
+{
+	struct device *dev = &vdev->dev;
+	unsigned long deadline = 0;
+	long hret = 0;
+	int ret = 0;
+
+	if (op->timeout)
+		deadline = jiffies + msecs_to_jiffies(op->timeout);
+
+	while (true) {
+		hret = plpar_hcall_norets(H_COP, op->flags,
+				vdev->resource_id,
+				op->in, op->inlen, op->out,
+				op->outlen, op->csbcpb);
+
+		if (hret == H_SUCCESS ||
+		    (hret != H_NOT_ENOUGH_RESOURCES &&
+		     hret != H_BUSY && hret != H_RESOURCE) ||
+		    (op->timeout && time_after(deadline, jiffies)))
+			break;
+
+		dev_dbg(dev, "%s: hcall ret(%ld), retrying.\n", __func__, hret);
+	}
+
+	switch (hret) {
+	case H_SUCCESS:
+		ret = 0;
+		break;
+	case H_OP_MODE:
+	case H_TOO_BIG:
+		ret = -E2BIG;
+		break;
+	case H_RESCINDED:
+		ret = -EACCES;
+		break;
+	case H_HARDWARE:
+		ret = -EPERM;
+		break;
+	case H_NOT_ENOUGH_RESOURCES:
+	case H_RESOURCE:
+	case H_BUSY:
+		ret = -EBUSY;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	if (ret)
+		dev_dbg(dev, "%s: Sync h_cop_op failure (ret:%d) (hret:%ld)\n",
+				__func__, ret, hret);
+
+	op->hcall_err = hret;
+	return ret;
+}
+EXPORT_SYMBOL(vio_h_cop_sync);
+
+static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
+{
+	const __be32 *dma_window;
+	struct iommu_table *tbl;
+	unsigned long offset, size;
+
+	dma_window = of_get_property(dev->dev.of_node,
+				  "ibm,my-dma-window", NULL);
+	if (!dma_window)
+		return NULL;
+
+	tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+	if (tbl == NULL)
+		return NULL;
+
+	of_parse_dma_window(dev->dev.of_node, dma_window,
+			    &tbl->it_index, &offset, &size);
+
+	/* TCE table size - measured in tce entries */
+	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
+	tbl->it_size = size >> tbl->it_page_shift;
+	/* offset for VIO should always be 0 */
+	tbl->it_offset = offset >> tbl->it_page_shift;
+	tbl->it_busno = 0;
+	tbl->it_type = TCE_VB;
+	tbl->it_blocksize = 16;
+
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		tbl->it_ops = &iommu_table_lpar_multi_ops;
+	else
+		tbl->it_ops = &iommu_table_pseries_ops;
+
+	return iommu_init_table(tbl, -1);
+}
+
+/**
+ * vio_match_device: - Tell if a VIO device has a matching
+ *			VIO device id structure.
+ * @ids:	array of VIO device id structures to search in
+ * @dev:	the VIO device structure to match against
+ *
+ * Used by a driver to check whether a VIO device present in the
+ * system is in its list of supported devices. Returns the matching
+ * vio_device_id structure or NULL if there is no match.
+ */
+static const struct vio_device_id *vio_match_device(
+		const struct vio_device_id *ids, const struct vio_dev *dev)
+{
+	while (ids->type[0] != '\0') {
+		if ((strncmp(dev->type, ids->type, strlen(ids->type)) == 0) &&
+		    of_device_is_compatible(dev->dev.of_node,
+					 ids->compat))
+			return ids;
+		ids++;
+	}
+	return NULL;
+}
+
+/*
+ * Convert from struct device to struct vio_dev and pass to driver.
+ * dev->driver has already been set by generic code because vio_bus_match
+ * succeeded.
+ */
+static int vio_bus_probe(struct device *dev)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	struct vio_driver *viodrv = to_vio_driver(dev->driver);
+	const struct vio_device_id *id;
+	int error = -ENODEV;
+
+	if (!viodrv->probe)
+		return error;
+
+	id = vio_match_device(viodrv->id_table, viodev);
+	if (id) {
+		memset(&viodev->cmo, 0, sizeof(viodev->cmo));
+		if (firmware_has_feature(FW_FEATURE_CMO)) {
+			error = vio_cmo_bus_probe(viodev);
+			if (error)
+				return error;
+		}
+		error = viodrv->probe(viodev, id);
+		if (error && firmware_has_feature(FW_FEATURE_CMO))
+			vio_cmo_bus_remove(viodev);
+	}
+
+	return error;
+}
+
+/* convert from struct device to struct vio_dev and pass to driver. */
+static int vio_bus_remove(struct device *dev)
+{
+	struct vio_dev *viodev = to_vio_dev(dev);
+	struct vio_driver *viodrv = to_vio_driver(dev->driver);
+	struct device *devptr;
+	int ret = 1;
+
+	/*
+	 * Hold a reference to the device after the remove function is called
+	 * to allow for CMO accounting cleanup for the device.
+	 */
+	devptr = get_device(dev);
+
+	if (viodrv->remove)
+		ret = viodrv->remove(viodev);
+
+	if (!ret && firmware_has_feature(FW_FEATURE_CMO))
+		vio_cmo_bus_remove(viodev);
+
+	put_device(devptr);
+	return ret;
+}
+
+/**
+ * vio_register_driver: - Register a new vio driver
+ * @viodrv:	The vio_driver structure to be registered.
+ */
+int __vio_register_driver(struct vio_driver *viodrv, struct module *owner,
+			  const char *mod_name)
+{
+	pr_debug("%s: driver %s registering\n", __func__, viodrv->name);
+
+	/* fill in 'struct driver' fields */
+	viodrv->driver.name = viodrv->name;
+	viodrv->driver.pm = viodrv->pm;
+	viodrv->driver.bus = &vio_bus_type;
+	viodrv->driver.owner = owner;
+	viodrv->driver.mod_name = mod_name;
+
+	return driver_register(&viodrv->driver);
+}
+EXPORT_SYMBOL(__vio_register_driver);
+
+/**
+ * vio_unregister_driver - Remove registration of vio driver.
+ * @viodrv:	The vio_driver struct to be removed form registration
+ */
+void vio_unregister_driver(struct vio_driver *viodrv)
+{
+	driver_unregister(&viodrv->driver);
+}
+EXPORT_SYMBOL(vio_unregister_driver);
+
+/* vio_dev refcount hit 0 */
+static void vio_dev_release(struct device *dev)
+{
+	struct iommu_table *tbl = get_iommu_table_base(dev);
+
+	if (tbl)
+		iommu_free_table(tbl, of_node_full_name(dev->of_node));
+	of_node_put(dev->of_node);
+	kfree(to_vio_dev(dev));
+}
+
+/**
+ * vio_register_device_node: - Register a new vio device.
+ * @of_node:	The OF node for this device.
+ *
+ * Creates and initializes a vio_dev structure from the data in
+ * of_node and adds it to the list of virtual devices.
+ * Returns a pointer to the created vio_dev or NULL if node has
+ * NULL device_type or compatible fields.
+ */
+struct vio_dev *vio_register_device_node(struct device_node *of_node)
+{
+	struct vio_dev *viodev;
+	struct device_node *parent_node;
+	const __be32 *prop;
+	enum vio_dev_family family;
+	const char *of_node_name = of_node->name ? of_node->name : "<unknown>";
+
+	/*
+	 * Determine if this node is a under the /vdevice node or under the
+	 * /ibm,platform-facilities node.  This decides the device's family.
+	 */
+	parent_node = of_get_parent(of_node);
+	if (parent_node) {
+		if (!strcmp(parent_node->full_name, "/ibm,platform-facilities"))
+			family = PFO;
+		else if (!strcmp(parent_node->full_name, "/vdevice"))
+			family = VDEVICE;
+		else {
+			pr_warn("%s: parent(%s) of %s not recognized.\n",
+					__func__,
+					parent_node->full_name,
+					of_node_name);
+			of_node_put(parent_node);
+			return NULL;
+		}
+		of_node_put(parent_node);
+	} else {
+		pr_warn("%s: could not determine the parent of node %s.\n",
+				__func__, of_node_name);
+		return NULL;
+	}
+
+	if (family == PFO) {
+		if (of_get_property(of_node, "interrupt-controller", NULL)) {
+			pr_debug("%s: Skipping the interrupt controller %s.\n",
+					__func__, of_node_name);
+			return NULL;
+		}
+	}
+
+	/* allocate a vio_dev for this node */
+	viodev = kzalloc(sizeof(struct vio_dev), GFP_KERNEL);
+	if (viodev == NULL) {
+		pr_warn("%s: allocation failure for VIO device.\n", __func__);
+		return NULL;
+	}
+
+	/* we need the 'device_type' property, in order to match with drivers */
+	viodev->family = family;
+	if (viodev->family == VDEVICE) {
+		unsigned int unit_address;
+
+		if (of_node->type != NULL)
+			viodev->type = of_node->type;
+		else {
+			pr_warn("%s: node %s is missing the 'device_type' "
+					"property.\n", __func__, of_node_name);
+			goto out;
+		}
+
+		prop = of_get_property(of_node, "reg", NULL);
+		if (prop == NULL) {
+			pr_warn("%s: node %s missing 'reg'\n",
+					__func__, of_node_name);
+			goto out;
+		}
+		unit_address = of_read_number(prop, 1);
+		dev_set_name(&viodev->dev, "%x", unit_address);
+		viodev->irq = irq_of_parse_and_map(of_node, 0);
+		viodev->unit_address = unit_address;
+	} else {
+		/* PFO devices need their resource_id for submitting COP_OPs
+		 * This is an optional field for devices, but is required when
+		 * performing synchronous ops */
+		prop = of_get_property(of_node, "ibm,resource-id", NULL);
+		if (prop != NULL)
+			viodev->resource_id = of_read_number(prop, 1);
+
+		dev_set_name(&viodev->dev, "%s", of_node_name);
+		viodev->type = of_node_name;
+		viodev->irq = 0;
+	}
+
+	viodev->name = of_node->name;
+	viodev->dev.of_node = of_node_get(of_node);
+
+	set_dev_node(&viodev->dev, of_node_to_nid(of_node));
+
+	/* init generic 'struct device' fields: */
+	viodev->dev.parent = &vio_bus_device.dev;
+	viodev->dev.bus = &vio_bus_type;
+	viodev->dev.release = vio_dev_release;
+
+	if (of_get_property(viodev->dev.of_node, "ibm,my-dma-window", NULL)) {
+		if (firmware_has_feature(FW_FEATURE_CMO))
+			vio_cmo_set_dma_ops(viodev);
+		else
+			set_dma_ops(&viodev->dev, &dma_iommu_ops);
+
+		set_iommu_table_base(&viodev->dev,
+				     vio_build_iommu_table(viodev));
+
+		/* needed to ensure proper operation of coherent allocations
+		 * later, in case driver doesn't set it explicitly */
+		viodev->dev.coherent_dma_mask = DMA_BIT_MASK(64);
+		viodev->dev.dma_mask = &viodev->dev.coherent_dma_mask;
+	}
+
+	/* register with generic device framework */
+	if (device_register(&viodev->dev)) {
+		printk(KERN_ERR "%s: failed to register device %s\n",
+				__func__, dev_name(&viodev->dev));
+		put_device(&viodev->dev);
+		return NULL;
+	}
+
+	return viodev;
+
+out:	/* Use this exit point for any return prior to device_register */
+	kfree(viodev);
+
+	return NULL;
+}
+EXPORT_SYMBOL(vio_register_device_node);
+
+/*
+ * vio_bus_scan_for_devices - Scan OF and register each child device
+ * @root_name - OF node name for the root of the subtree to search.
+ *		This must be non-NULL
+ *
+ * Starting from the root node provide, register the device node for
+ * each child beneath the root.
+ */
+static void vio_bus_scan_register_devices(char *root_name)
+{
+	struct device_node *node_root, *node_child;
+
+	if (!root_name)
+		return;
+
+	node_root = of_find_node_by_name(NULL, root_name);
+	if (node_root) {
+
+		/*
+		 * Create struct vio_devices for each virtual device in
+		 * the device tree. Drivers will associate with them later.
+		 */
+		node_child = of_get_next_child(node_root, NULL);
+		while (node_child) {
+			vio_register_device_node(node_child);
+			node_child = of_get_next_child(node_root, node_child);
+		}
+		of_node_put(node_root);
+	}
+}
+
+/**
+ * vio_bus_init: - Initialize the virtual IO bus
+ */
+static int __init vio_bus_init(void)
+{
+	int err;
+
+	if (firmware_has_feature(FW_FEATURE_CMO))
+		vio_cmo_sysfs_init();
+
+	err = bus_register(&vio_bus_type);
+	if (err) {
+		printk(KERN_ERR "failed to register VIO bus\n");
+		return err;
+	}
+
+	/*
+	 * The fake parent of all vio devices, just to give us
+	 * a nice directory
+	 */
+	err = device_register(&vio_bus_device.dev);
+	if (err) {
+		printk(KERN_WARNING "%s: device_register returned %i\n",
+				__func__, err);
+		return err;
+	}
+
+	if (firmware_has_feature(FW_FEATURE_CMO))
+		vio_cmo_bus_init();
+
+	return 0;
+}
+postcore_initcall(vio_bus_init);
+
+static int __init vio_device_init(void)
+{
+	vio_bus_scan_register_devices("vdevice");
+	vio_bus_scan_register_devices("ibm,platform-facilities");
+
+	return 0;
+}
+device_initcall(vio_device_init);
+
+static ssize_t name_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%s\n", to_vio_dev(dev)->name);
+}
+
+static ssize_t devspec_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct device_node *of_node = dev->of_node;
+
+	return sprintf(buf, "%s\n", of_node_full_name(of_node));
+}
+
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	const struct vio_dev *vio_dev = to_vio_dev(dev);
+	struct device_node *dn;
+	const char *cp;
+
+	dn = dev->of_node;
+	if (!dn) {
+		strcpy(buf, "\n");
+		return strlen(buf);
+	}
+	cp = of_get_property(dn, "compatible", NULL);
+	if (!cp) {
+		strcpy(buf, "\n");
+		return strlen(buf);
+	}
+
+	return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp);
+}
+
+static struct device_attribute vio_dev_attrs[] = {
+	__ATTR_RO(name),
+	__ATTR_RO(devspec),
+	__ATTR_RO(modalias),
+	__ATTR_NULL
+};
+
+void vio_unregister_device(struct vio_dev *viodev)
+{
+	device_unregister(&viodev->dev);
+}
+EXPORT_SYMBOL(vio_unregister_device);
+
+static int vio_bus_match(struct device *dev, struct device_driver *drv)
+{
+	const struct vio_dev *vio_dev = to_vio_dev(dev);
+	struct vio_driver *vio_drv = to_vio_driver(drv);
+	const struct vio_device_id *ids = vio_drv->id_table;
+
+	return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL);
+}
+
+static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env)
+{
+	const struct vio_dev *vio_dev = to_vio_dev(dev);
+	struct device_node *dn;
+	const char *cp;
+
+	dn = dev->of_node;
+	if (!dn)
+		return -ENODEV;
+	cp = of_get_property(dn, "compatible", NULL);
+	if (!cp)
+		return -ENODEV;
+
+	add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp);
+	return 0;
+}
+
+struct bus_type vio_bus_type = {
+	.name = "vio",
+	.dev_attrs = vio_dev_attrs,
+	.uevent = vio_hotplug,
+	.match = vio_bus_match,
+	.probe = vio_bus_probe,
+	.remove = vio_bus_remove,
+};
+
+/**
+ * vio_get_attribute: - get attribute for virtual device
+ * @vdev:	The vio device to get property.
+ * @which:	The property/attribute to be extracted.
+ * @length:	Pointer to length of returned data size (unused if NULL).
+ *
+ * Calls prom.c's of_get_property() to return the value of the
+ * attribute specified by @which
+*/
+const void *vio_get_attribute(struct vio_dev *vdev, char *which, int *length)
+{
+	return of_get_property(vdev->dev.of_node, which, length);
+}
+EXPORT_SYMBOL(vio_get_attribute);
+
+#ifdef CONFIG_PPC_PSERIES
+/* vio_find_name() - internal because only vio.c knows how we formatted the
+ * kobject name
+ */
+static struct vio_dev *vio_find_name(const char *name)
+{
+	struct device *found;
+
+	found = bus_find_device_by_name(&vio_bus_type, NULL, name);
+	if (!found)
+		return NULL;
+
+	return to_vio_dev(found);
+}
+
+/**
+ * vio_find_node - find an already-registered vio_dev
+ * @vnode: device_node of the virtual device we're looking for
+ *
+ * Takes a reference to the embedded struct device which needs to be dropped
+ * after use.
+ */
+struct vio_dev *vio_find_node(struct device_node *vnode)
+{
+	char kobj_name[20];
+	struct device_node *vnode_parent;
+	const char *dev_type;
+
+	vnode_parent = of_get_parent(vnode);
+	if (!vnode_parent)
+		return NULL;
+
+	dev_type = of_get_property(vnode_parent, "device_type", NULL);
+	of_node_put(vnode_parent);
+	if (!dev_type)
+		return NULL;
+
+	/* construct the kobject name from the device node */
+	if (!strcmp(dev_type, "vdevice")) {
+		const __be32 *prop;
+		
+		prop = of_get_property(vnode, "reg", NULL);
+		if (!prop)
+			return NULL;
+		snprintf(kobj_name, sizeof(kobj_name), "%x",
+			 (uint32_t)of_read_number(prop, 1));
+	} else if (!strcmp(dev_type, "ibm,platform-facilities"))
+		snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name);
+	else
+		return NULL;
+
+	return vio_find_name(kobj_name);
+}
+EXPORT_SYMBOL(vio_find_node);
+
+int vio_enable_interrupts(struct vio_dev *dev)
+{
+	int rc = h_vio_signal(dev->unit_address, VIO_IRQ_ENABLE);
+	if (rc != H_SUCCESS)
+		printk(KERN_ERR "vio: Error 0x%x enabling interrupts\n", rc);
+	return rc;
+}
+EXPORT_SYMBOL(vio_enable_interrupts);
+
+int vio_disable_interrupts(struct vio_dev *dev)
+{
+	int rc = h_vio_signal(dev->unit_address, VIO_IRQ_DISABLE);
+	if (rc != H_SUCCESS)
+		printk(KERN_ERR "vio: Error 0x%x disabling interrupts\n", rc);
+	return rc;
+}
+EXPORT_SYMBOL(vio_disable_interrupts);
+#endif /* CONFIG_PPC_PSERIES */