Merge tag 'powerpc-4.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc updates from Michael Ellerman:

 - disable the 32-bit vdso when building LE, so we can build with a
   64-bit only toolchain.

 - EEH fixes from Gavin & Richard.

 - enable the sys_kcmp syscall from Laurent.

 - sysfs control for fastsleep workaround from Shreyas.

 - expose OPAL events as an irq chip by Alistair.

 - MSI ops moved to pci_controller_ops by Daniel.

 - fix for kernel to userspace backtraces for perf from Anton.

 - merge pseries and pseries_le defconfigs from Cyril.

 - CXL in-kernel API from Mikey.

 - OPAL prd driver from Jeremy.

 - fix for DSCR handling & tests from Anshuman.

 - Powernv flash mtd driver from Cyril.

 - dynamic DMA Window support on powernv from Alexey.

 - LLVM clang fixes & workarounds from Anton.

 - reworked version of the patch to abort syscalls when transactional.

 - fix the swap encoding to support 4TB, from Aneesh.

 - various fixes as usual.

 - Freescale updates from Scott: Highlights include more 8xx
   optimizations, an e6500 hugetlb optimization, QMan device tree nodes,
   t1024/t1023 support, and various fixes and cleanup.

* tag 'powerpc-4.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (180 commits)
  cxl: Fix typo in debug print
  cxl: Add CXL_KERNEL_API config option
  powerpc/powernv: Fix wrong IOMMU table in pnv_ioda_setup_bus_dma()
  powerpc/mm: Change the swap encoding in pte.
  powerpc/mm: PTE_RPN_MAX is not used, remove the same
  powerpc/tm: Abort syscalls in active transactions
  powerpc/iommu/ioda2: Enable compile with IOV=on and IOMMU_API=off
  powerpc/include: Add opal-prd to installed uapi headers
  powerpc/powernv: fix construction of opal PRD messages
  powerpc/powernv: Increase opal-irqchip initcall priority
  powerpc: Make doorbell check preemption safe
  powerpc/powernv: pnv_init_idle_states() should only run on powernv
  macintosh/nvram: Remove as unused
  powerpc: Don't use gcc specific options on clang
  powerpc: Don't use -mno-strict-align on clang
  powerpc: Only use -mtraceback=no, -mno-string and -msoft-float if toolchain supports it
  powerpc: Only use -mabi=altivec if toolchain supports it
  powerpc: Fix duplicate const clang warning in user access code
  vfio: powerpc/spapr: Support Dynamic DMA windows
  vfio: powerpc/spapr: Register memory and define IOMMU v2
  ...

22 files changed, 2270 insertions, 391 deletions

diff --git a/drivers/char/ipmi/ipmi_powernv.c b/drivers/char/ipmi/ipmi_powernv.c
index 8753b0f6a317..9b409c0f14f7 100644
--- a/drivers/char/ipmi/ipmi_powernv.c
+++ b/drivers/char/ipmi/ipmi_powernv.c
@@ -15,6 +15,8 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/interrupt.h>
 
 #include <asm/opal.h>
 
@@ -23,8 +25,7 @@ struct ipmi_smi_powernv {
 	u64			interface_id;
 	struct ipmi_device_id	ipmi_id;
 	ipmi_smi_t		intf;
-	u64			event;
-	struct notifier_block	event_nb;
+	unsigned int		irq;
 
 	/**
 	 * We assume that there can only be one outstanding request, so
@@ -197,15 +198,12 @@ static struct ipmi_smi_handlers ipmi_powernv_smi_handlers = {
 	.poll			= ipmi_powernv_poll,
 };
 
-static int ipmi_opal_event(struct notifier_block *nb,
-			  unsigned long events, void *change)
+static irqreturn_t ipmi_opal_event(int irq, void *data)
 {
-	struct ipmi_smi_powernv *smi = container_of(nb,
-					struct ipmi_smi_powernv, event_nb);
+	struct ipmi_smi_powernv *smi = data;
 
-	if (events & smi->event)
-		ipmi_powernv_recv(smi);
-	return 0;
+	ipmi_powernv_recv(smi);
+	return IRQ_HANDLED;
 }
 
 static int ipmi_powernv_probe(struct platform_device *pdev)
@@ -240,13 +238,16 @@ static int ipmi_powernv_probe(struct platform_device *pdev)
 		goto err_free;
 	}
 
-	ipmi->event = 1ull << prop;
-	ipmi->event_nb.notifier_call = ipmi_opal_event;
+	ipmi->irq = irq_of_parse_and_map(dev->of_node, 0);
+	if (!ipmi->irq) {
+		dev_info(dev, "Unable to map irq from device tree\n");
+		ipmi->irq = opal_event_request(prop);
+	}
 
-	rc = opal_notifier_register(&ipmi->event_nb);
-	if (rc) {
-		dev_warn(dev, "OPAL notifier registration failed (%d)\n", rc);
-		goto err_free;
+	if (request_irq(ipmi->irq, ipmi_opal_event, IRQ_TYPE_LEVEL_HIGH,
+				"opal-ipmi", ipmi)) {
+		dev_warn(dev, "Unable to request irq\n");
+		goto err_dispose;
 	}
 
 	ipmi->opal_msg = devm_kmalloc(dev,
@@ -271,7 +272,9 @@ static int ipmi_powernv_probe(struct platform_device *pdev)
 err_free_msg:
 	devm_kfree(dev, ipmi->opal_msg);
 err_unregister:
-	opal_notifier_unregister(&ipmi->event_nb);
+	free_irq(ipmi->irq, ipmi);
+err_dispose:
+	irq_dispose_mapping(ipmi->irq);
 err_free:
 	devm_kfree(dev, ipmi);
 	return rc;
@@ -282,7 +285,9 @@ static int ipmi_powernv_remove(struct platform_device *pdev)
 	struct ipmi_smi_powernv *smi = dev_get_drvdata(&pdev->dev);
 
 	ipmi_unregister_smi(smi->intf);
-	opal_notifier_unregister(&smi->event_nb);
+	free_irq(smi->irq, smi);
+	irq_dispose_mapping(smi->irq);
+
 	return 0;
 }
 
diff --git a/drivers/macintosh/nvram.c b/drivers/macintosh/nvram.c
deleted file mode 100644
index f0e03e7937e3..000000000000
--- a/drivers/macintosh/nvram.c
+++ /dev/null
@@ -1,130 +0,0 @@
-/*
- * /dev/nvram driver for Power Macintosh.
- */
-
-#define NVRAM_VERSION "1.0"
-
-#include <linux/module.h>
-
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
-#include <linux/fcntl.h>
-#include <linux/nvram.h>
-#include <linux/init.h>
-#include <asm/uaccess.h>
-#include <asm/nvram.h>
-
-#define NVRAM_SIZE	8192
-
-static loff_t nvram_llseek(struct file *file, loff_t offset, int origin)
-{
-	switch (origin) {
-	case 0:
-		break;
-	case 1:
-		offset += file->f_pos;
-		break;
-	case 2:
-		offset += NVRAM_SIZE;
-		break;
-	default:
-		offset = -1;
-	}
-	if (offset < 0)
-		return -EINVAL;
-
-	file->f_pos = offset;
-	return file->f_pos;
-}
-
-static ssize_t read_nvram(struct file *file, char __user *buf,
-			  size_t count, loff_t *ppos)
-{
-	unsigned int i;
-	char __user *p = buf;
-
-	if (!access_ok(VERIFY_WRITE, buf, count))
-		return -EFAULT;
-	if (*ppos >= NVRAM_SIZE)
-		return 0;
-	for (i = *ppos; count > 0 && i < NVRAM_SIZE; ++i, ++p, --count)
-		if (__put_user(nvram_read_byte(i), p))
-			return -EFAULT;
-	*ppos = i;
-	return p - buf;
-}
-
-static ssize_t write_nvram(struct file *file, const char __user *buf,
-			   size_t count, loff_t *ppos)
-{
-	unsigned int i;
-	const char __user *p = buf;
-	char c;
-
-	if (!access_ok(VERIFY_READ, buf, count))
-		return -EFAULT;
-	if (*ppos >= NVRAM_SIZE)
-		return 0;
-	for (i = *ppos; count > 0 && i < NVRAM_SIZE; ++i, ++p, --count) {
-		if (__get_user(c, p))
-			return -EFAULT;
-		nvram_write_byte(c, i);
-	}
-	*ppos = i;
-	return p - buf;
-}
-
-static long nvram_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	switch(cmd) {
-		case PMAC_NVRAM_GET_OFFSET:
-		{
-			int part, offset;
-			if (copy_from_user(&part, (void __user*)arg, sizeof(part)) != 0)
-				return -EFAULT;
-			if (part < pmac_nvram_OF || part > pmac_nvram_NR)
-				return -EINVAL;
-			offset = pmac_get_partition(part);
-			if (copy_to_user((void __user*)arg, &offset, sizeof(offset)) != 0)
-				return -EFAULT;
-			break;
-		}
-
-		default:
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-const struct file_operations nvram_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= nvram_llseek,
-	.read		= read_nvram,
-	.write		= write_nvram,
-	.unlocked_ioctl	= nvram_ioctl,
-};
-
-static struct miscdevice nvram_dev = {
-	NVRAM_MINOR,
-	"nvram",
-	&nvram_fops
-};
-
-int __init nvram_init(void)
-{
-	printk(KERN_INFO "Macintosh non-volatile memory driver v%s\n",
-		NVRAM_VERSION);
-	return misc_register(&nvram_dev);
-}
-
-void __exit nvram_cleanup(void)
-{
-        misc_deregister( &nvram_dev );
-}
-
-module_init(nvram_init);
-module_exit(nvram_cleanup);
-MODULE_LICENSE("GPL");
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index a990b39b4dfb..b6db9ebd52c2 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -7,10 +7,15 @@ config CXL_BASE
 	default n
 	select PPC_COPRO_BASE
 
+config CXL_KERNEL_API
+	bool
+	default n
+
 config CXL
 	tristate "Support for IBM Coherent Accelerators (CXL)"
 	depends on PPC_POWERNV && PCI_MSI
 	select CXL_BASE
+	select CXL_KERNEL_API
 	default m
 	help
 	  Select this option to enable driver support for IBM Coherent
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index edb494d3ff27..14e3f8219a11 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1,4 +1,6 @@
-cxl-y				+= main.o file.o irq.o fault.o native.o context.o sysfs.o debugfs.o pci.o trace.o
+cxl-y				+= main.o file.o irq.o fault.o native.o
+cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
+cxl-y				+= vphb.o api.o
 obj-$(CONFIG_CXL)		+= cxl.o
 obj-$(CONFIG_CXL_BASE)		+= base.o
 
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
new file mode 100644
index 000000000000..0c77240ae2fc
--- /dev/null
+++ b/drivers/misc/cxl/api.c
@@ -0,0 +1,331 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * 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/pci.h>
+#include <linux/slab.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
+{
+	struct cxl_afu *afu;
+	struct cxl_context  *ctx;
+	int rc;
+
+	afu = cxl_pci_to_afu(dev);
+
+	ctx = cxl_context_alloc();
+	if (IS_ERR(ctx))
+		return ctx;
+
+	/* Make it a slave context.  We can promote it later? */
+	rc = cxl_context_init(ctx, afu, false, NULL);
+	if (rc) {
+		kfree(ctx);
+		return ERR_PTR(-ENOMEM);
+	}
+	cxl_assign_psn_space(ctx);
+
+	return ctx;
+}
+EXPORT_SYMBOL_GPL(cxl_dev_context_init);
+
+struct cxl_context *cxl_get_context(struct pci_dev *dev)
+{
+	return dev->dev.archdata.cxl_ctx;
+}
+EXPORT_SYMBOL_GPL(cxl_get_context);
+
+struct device *cxl_get_phys_dev(struct pci_dev *dev)
+{
+	struct cxl_afu *afu;
+
+	afu = cxl_pci_to_afu(dev);
+
+	return afu->adapter->dev.parent;
+}
+EXPORT_SYMBOL_GPL(cxl_get_phys_dev);
+
+int cxl_release_context(struct cxl_context *ctx)
+{
+	if (ctx->status != CLOSED)
+		return -EBUSY;
+
+	cxl_context_free(ctx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_release_context);
+
+int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
+{
+	if (num == 0)
+		num = ctx->afu->pp_irqs;
+	return afu_allocate_irqs(ctx, num);
+}
+EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs);
+
+void cxl_free_afu_irqs(struct cxl_context *ctx)
+{
+	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
+}
+EXPORT_SYMBOL_GPL(cxl_free_afu_irqs);
+
+static irq_hw_number_t cxl_find_afu_irq(struct cxl_context *ctx, int num)
+{
+	__u16 range;
+	int r;
+
+	WARN_ON(num == 0);
+
+	for (r = 0; r < CXL_IRQ_RANGES; r++) {
+		range = ctx->irqs.range[r];
+		if (num < range) {
+			return ctx->irqs.offset[r] + num;
+		}
+		num -= range;
+	}
+	return 0;
+}
+
+int cxl_map_afu_irq(struct cxl_context *ctx, int num,
+		    irq_handler_t handler, void *cookie, char *name)
+{
+	irq_hw_number_t hwirq;
+
+	/*
+	 * Find interrupt we are to register.
+	 */
+	hwirq = cxl_find_afu_irq(ctx, num);
+	if (!hwirq)
+		return -ENOENT;
+
+	return cxl_map_irq(ctx->afu->adapter, hwirq, handler, cookie, name);
+}
+EXPORT_SYMBOL_GPL(cxl_map_afu_irq);
+
+void cxl_unmap_afu_irq(struct cxl_context *ctx, int num, void *cookie)
+{
+	irq_hw_number_t hwirq;
+	unsigned int virq;
+
+	hwirq = cxl_find_afu_irq(ctx, num);
+	if (!hwirq)
+		return;
+
+	virq = irq_find_mapping(NULL, hwirq);
+	if (virq)
+		cxl_unmap_irq(virq, cookie);
+}
+EXPORT_SYMBOL_GPL(cxl_unmap_afu_irq);
+
+/*
+ * Start a context
+ * Code here similar to afu_ioctl_start_work().
+ */
+int cxl_start_context(struct cxl_context *ctx, u64 wed,
+		      struct task_struct *task)
+{
+	int rc = 0;
+	bool kernel = true;
+
+	pr_devel("%s: pe: %i\n", __func__, ctx->pe);
+
+	mutex_lock(&ctx->status_mutex);
+	if (ctx->status == STARTED)
+		goto out; /* already started */
+
+	if (task) {
+		ctx->pid = get_task_pid(task, PIDTYPE_PID);
+		get_pid(ctx->pid);
+		kernel = false;
+	}
+
+	cxl_ctx_get();
+
+	if ((rc = cxl_attach_process(ctx, kernel, wed , 0))) {
+		put_pid(ctx->pid);
+		cxl_ctx_put();
+		goto out;
+	}
+
+	ctx->status = STARTED;
+	get_device(&ctx->afu->dev);
+out:
+	mutex_unlock(&ctx->status_mutex);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(cxl_start_context);
+
+int cxl_process_element(struct cxl_context *ctx)
+{
+	return ctx->pe;
+}
+EXPORT_SYMBOL_GPL(cxl_process_element);
+
+/* Stop a context.  Returns 0 on success, otherwise -Errno */
+int cxl_stop_context(struct cxl_context *ctx)
+{
+	int rc;
+
+	rc = __detach_context(ctx);
+	if (!rc)
+		put_device(&ctx->afu->dev);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(cxl_stop_context);
+
+void cxl_set_master(struct cxl_context *ctx)
+{
+	ctx->master = true;
+	cxl_assign_psn_space(ctx);
+}
+EXPORT_SYMBOL_GPL(cxl_set_master);
+
+/* wrappers around afu_* file ops which are EXPORTED */
+int cxl_fd_open(struct inode *inode, struct file *file)
+{
+	return afu_open(inode, file);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_open);
+int cxl_fd_release(struct inode *inode, struct file *file)
+{
+	return afu_release(inode, file);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_release);
+long cxl_fd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	return afu_ioctl(file, cmd, arg);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_ioctl);
+int cxl_fd_mmap(struct file *file, struct vm_area_struct *vm)
+{
+	return afu_mmap(file, vm);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_mmap);
+unsigned int cxl_fd_poll(struct file *file, struct poll_table_struct *poll)
+{
+	return afu_poll(file, poll);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_poll);
+ssize_t cxl_fd_read(struct file *file, char __user *buf, size_t count,
+			loff_t *off)
+{
+	return afu_read(file, buf, count, off);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_read);
+
+#define PATCH_FOPS(NAME) if (!fops->NAME) fops->NAME = afu_fops.NAME
+
+/* Get a struct file and fd for a context and attach the ops */
+struct file *cxl_get_fd(struct cxl_context *ctx, struct file_operations *fops,
+			int *fd)
+{
+	struct file *file;
+	int rc, flags, fdtmp;
+
+	flags = O_RDWR | O_CLOEXEC;
+
+	/* This code is similar to anon_inode_getfd() */
+	rc = get_unused_fd_flags(flags);
+	if (rc < 0)
+		return ERR_PTR(rc);
+	fdtmp = rc;
+
+	/*
+	 * Patch the file ops.  Needs to be careful that this is rentrant safe.
+	 */
+	if (fops) {
+		PATCH_FOPS(open);
+		PATCH_FOPS(poll);
+		PATCH_FOPS(read);
+		PATCH_FOPS(release);
+		PATCH_FOPS(unlocked_ioctl);
+		PATCH_FOPS(compat_ioctl);
+		PATCH_FOPS(mmap);
+	} else /* use default ops */
+		fops = (struct file_operations *)&afu_fops;
+
+	file = anon_inode_getfile("cxl", fops, ctx, flags);
+	if (IS_ERR(file))
+		put_unused_fd(fdtmp);
+	*fd = fdtmp;
+	return file;
+}
+EXPORT_SYMBOL_GPL(cxl_get_fd);
+
+struct cxl_context *cxl_fops_get_context(struct file *file)
+{
+	return file->private_data;
+}
+EXPORT_SYMBOL_GPL(cxl_fops_get_context);
+
+int cxl_start_work(struct cxl_context *ctx,
+		   struct cxl_ioctl_start_work *work)
+{
+	int rc;
+
+	/* code taken from afu_ioctl_start_work */
+	if (!(work->flags & CXL_START_WORK_NUM_IRQS))
+		work->num_interrupts = ctx->afu->pp_irqs;
+	else if ((work->num_interrupts < ctx->afu->pp_irqs) ||
+		 (work->num_interrupts > ctx->afu->irqs_max)) {
+		return -EINVAL;
+	}
+
+	rc = afu_register_irqs(ctx, work->num_interrupts);
+	if (rc)
+		return rc;
+
+	rc = cxl_start_context(ctx, work->work_element_descriptor, current);
+	if (rc < 0) {
+		afu_release_irqs(ctx, ctx);
+		return rc;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_start_work);
+
+void __iomem *cxl_psa_map(struct cxl_context *ctx)
+{
+	struct cxl_afu *afu = ctx->afu;
+	int rc;
+
+	rc = cxl_afu_check_and_enable(afu);
+	if (rc)
+		return NULL;
+
+	pr_devel("%s: psn_phys%llx size:%llx\n",
+		 __func__, afu->psn_phys, afu->adapter->ps_size);
+	return ioremap(ctx->psn_phys, ctx->psn_size);
+}
+EXPORT_SYMBOL_GPL(cxl_psa_map);
+
+void cxl_psa_unmap(void __iomem *addr)
+{
+	iounmap(addr);
+}
+EXPORT_SYMBOL_GPL(cxl_psa_unmap);
+
+int cxl_afu_reset(struct cxl_context *ctx)
+{
+	struct cxl_afu *afu = ctx->afu;
+	int rc;
+
+	rc = __cxl_afu_reset(afu);
+	if (rc)
+		return rc;
+
+	return cxl_afu_check_and_enable(afu);
+}
+EXPORT_SYMBOL_GPL(cxl_afu_reset);
diff --git a/drivers/misc/cxl/base.c b/drivers/misc/cxl/base.c
index 0654ad83675e..a9f0dd3255a2 100644
--- a/drivers/misc/cxl/base.c
+++ b/drivers/misc/cxl/base.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <asm/errno.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 #include "cxl.h"
 
 /* protected by rcu */
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index d1b55fe62817..2a4c80ac322a 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -174,7 +174,7 @@ int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma)
  * return until all outstanding interrupts for this context have completed. The
  * hardware should no longer access *ctx after this has returned.
  */
-static void __detach_context(struct cxl_context *ctx)
+int __detach_context(struct cxl_context *ctx)
 {
 	enum cxl_context_status status;
 
@@ -183,12 +183,13 @@ static void __detach_context(struct cxl_context *ctx)
 	ctx->status = CLOSED;
 	mutex_unlock(&ctx->status_mutex);
 	if (status != STARTED)
-		return;
+		return -EBUSY;
 
 	WARN_ON(cxl_detach_process(ctx));
-	afu_release_irqs(ctx);
 	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
-	wake_up_all(&ctx->wq);
+	put_pid(ctx->pid);
+	cxl_ctx_put();
+	return 0;
 }
 
 /*
@@ -199,7 +200,14 @@ static void __detach_context(struct cxl_context *ctx)
  */
 void cxl_context_detach(struct cxl_context *ctx)
 {
-	__detach_context(ctx);
+	int rc;
+
+	rc = __detach_context(ctx);
+	if (rc)
+		return;
+
+	afu_release_irqs(ctx, ctx);
+	wake_up_all(&ctx->wq);
 }
 
 /*
@@ -216,7 +224,7 @@ void cxl_context_detach_all(struct cxl_afu *afu)
 		 * Anything done in here needs to be setup before the IDR is
 		 * created and torn down after the IDR removed
 		 */
-		__detach_context(ctx);
+		cxl_context_detach(ctx);
 
 		/*
 		 * We are force detaching - remove any active PSA mappings so
@@ -232,16 +240,20 @@ void cxl_context_detach_all(struct cxl_afu *afu)
 	mutex_unlock(&afu->contexts_lock);
 }
 
-void cxl_context_free(struct cxl_context *ctx)
+static void reclaim_ctx(struct rcu_head *rcu)
 {
-	mutex_lock(&ctx->afu->contexts_lock);
-	idr_remove(&ctx->afu->contexts_idr, ctx->pe);
-	mutex_unlock(&ctx->afu->contexts_lock);
-	synchronize_rcu();
+	struct cxl_context *ctx = container_of(rcu, struct cxl_context, rcu);
 
 	free_page((u64)ctx->sstp);
 	ctx->sstp = NULL;
 
-	put_pid(ctx->pid);
 	kfree(ctx);
 }
+
+void cxl_context_free(struct cxl_context *ctx)
+{
+	mutex_lock(&ctx->afu->contexts_lock);
+	idr_remove(&ctx->afu->contexts_idr, ctx->pe);
+	mutex_unlock(&ctx->afu->contexts_lock);
+	call_rcu(&ctx->rcu, reclaim_ctx);
+}
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index a1cee4767ec6..4fd66cabde1e 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -18,10 +18,11 @@
 #include <linux/pid.h>
 #include <linux/io.h>
 #include <linux/pci.h>
+#include <linux/fs.h>
 #include <asm/cputable.h>
 #include <asm/mmu.h>
 #include <asm/reg.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include <uapi/misc/cxl.h>
 
@@ -315,8 +316,6 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
 #define CXL_MAX_SLICES 4
 #define MAX_AFU_MMIO_REGS 3
 
-#define CXL_MODE_DEDICATED   0x1
-#define CXL_MODE_DIRECTED    0x2
 #define CXL_MODE_TIME_SLICED 0x4
 #define CXL_SUPPORTED_MODES (CXL_MODE_DEDICATED | CXL_MODE_DIRECTED)
 
@@ -362,6 +361,10 @@ struct cxl_afu {
 	struct mutex spa_mutex;
 	spinlock_t afu_cntl_lock;
 
+	/* AFU error buffer fields and bin attribute for sysfs */
+	u64 eb_len, eb_offset;
+	struct bin_attribute attr_eb;
+
 	/*
 	 * Only the first part of the SPA is used for the process element
 	 * linked list. The only other part that software needs to worry about
@@ -375,6 +378,9 @@ struct cxl_afu {
 	int spa_max_procs;
 	unsigned int psl_virq;
 
+	/* pointer to the vphb */
+	struct pci_controller *phb;
+
 	int pp_irqs;
 	int irqs_max;
 	int num_procs;
@@ -455,6 +461,8 @@ struct cxl_context {
 	bool pending_irq;
 	bool pending_fault;
 	bool pending_afu_err;
+
+	struct rcu_head rcu;
 };
 
 struct cxl {
@@ -563,6 +571,9 @@ static inline void __iomem *_cxl_p2n_addr(struct cxl_afu *afu, cxl_p2n_reg_t reg
 u16 cxl_afu_cr_read16(struct cxl_afu *afu, int cr, u64 off);
 u8 cxl_afu_cr_read8(struct cxl_afu *afu, int cr, u64 off);
 
+ssize_t cxl_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
+				loff_t off, size_t count);
+
 
 struct cxl_calls {
 	void (*cxl_slbia)(struct mm_struct *mm);
@@ -606,7 +617,7 @@ void cxl_release_psl_err_irq(struct cxl *adapter);
 int cxl_register_serr_irq(struct cxl_afu *afu);
 void cxl_release_serr_irq(struct cxl_afu *afu);
 int afu_register_irqs(struct cxl_context *ctx, u32 count);
-void afu_release_irqs(struct cxl_context *ctx);
+void afu_release_irqs(struct cxl_context *ctx, void *cookie);
 irqreturn_t cxl_slice_irq_err(int irq, void *data);
 
 int cxl_debugfs_init(void);
@@ -629,6 +640,10 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 		     struct address_space *mapping);
 void cxl_context_free(struct cxl_context *ctx);
 int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma);
+unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
+			 irq_handler_t handler, void *cookie, const char *name);
+void cxl_unmap_irq(unsigned int virq, void *cookie);
+int __detach_context(struct cxl_context *ctx);
 
 /* This matches the layout of the H_COLLECT_CA_INT_INFO retbuf */
 struct cxl_irq_info {
@@ -642,6 +657,7 @@ struct cxl_irq_info {
 	u64 padding[3]; /* to match the expected retbuf size for plpar_hcall9 */
 };
 
+void cxl_assign_psn_space(struct cxl_context *ctx);
 int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed,
 			    u64 amr);
 int cxl_detach_process(struct cxl_context *ctx);
@@ -653,11 +669,23 @@ int cxl_check_error(struct cxl_afu *afu);
 int cxl_afu_slbia(struct cxl_afu *afu);
 int cxl_tlb_slb_invalidate(struct cxl *adapter);
 int cxl_afu_disable(struct cxl_afu *afu);
-int cxl_afu_reset(struct cxl_afu *afu);
+int __cxl_afu_reset(struct cxl_afu *afu);
+int cxl_afu_check_and_enable(struct cxl_afu *afu);
 int cxl_psl_purge(struct cxl_afu *afu);
 
 void cxl_stop_trace(struct cxl *cxl);
+int cxl_pci_vphb_add(struct cxl_afu *afu);
+void cxl_pci_vphb_remove(struct cxl_afu *afu);
 
 extern struct pci_driver cxl_pci_driver;
+int afu_allocate_irqs(struct cxl_context *ctx, u32 count);
+
+int afu_open(struct inode *inode, struct file *file);
+int afu_release(struct inode *inode, struct file *file);
+long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int afu_mmap(struct file *file, struct vm_area_struct *vm);
+unsigned int afu_poll(struct file *file, struct poll_table_struct *poll);
+ssize_t afu_read(struct file *file, char __user *buf, size_t count, loff_t *off);
+extern const struct file_operations afu_fops;
 
 #endif
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 5286b8b704f5..25a5418c55cb 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -172,8 +172,8 @@ void cxl_handle_fault(struct work_struct *fault_work)
 		container_of(fault_work, struct cxl_context, fault_work);
 	u64 dsisr = ctx->dsisr;
 	u64 dar = ctx->dar;
-	struct task_struct *task;
-	struct mm_struct *mm;
+	struct task_struct *task = NULL;
+	struct mm_struct *mm = NULL;
 
 	if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
 	    cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An) != dar ||
@@ -194,17 +194,19 @@ void cxl_handle_fault(struct work_struct *fault_work)
 	pr_devel("CXL BOTTOM HALF handling fault for afu pe: %i. "
 		"DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_handle_fault unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		cxl_ack_ae(ctx);
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
-		pr_devel("cxl_handle_fault unable to get mm %i\n",
-			 pid_nr(ctx->pid));
-		cxl_ack_ae(ctx);
-		goto out;
+	if (!ctx->kernel) {
+		if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+			pr_devel("cxl_handle_fault unable to get task %i\n",
+				 pid_nr(ctx->pid));
+			cxl_ack_ae(ctx);
+			return;
+		}
+		if (!(mm = get_task_mm(task))) {
+			pr_devel("cxl_handle_fault unable to get mm %i\n",
+				 pid_nr(ctx->pid));
+			cxl_ack_ae(ctx);
+			goto out;
+		}
 	}
 
 	if (dsisr & CXL_PSL_DSISR_An_DS)
@@ -214,9 +216,11 @@ void cxl_handle_fault(struct work_struct *fault_work)
 	else
 		WARN(1, "cxl_handle_fault has nothing to handle\n");
 
-	mmput(mm);
+	if (mm)
+		mmput(mm);
 out:
-	put_task_struct(task);
+	if (task)
+		put_task_struct(task);
 }
 
 static void cxl_prefault_one(struct cxl_context *ctx, u64 ea)
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 2364bcadb9a9..e3f4b69527a9 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -96,7 +96,8 @@ err_put_adapter:
 	put_device(&adapter->dev);
 	return rc;
 }
-static int afu_open(struct inode *inode, struct file *file)
+
+int afu_open(struct inode *inode, struct file *file)
 {
 	return __afu_open(inode, file, false);
 }
@@ -106,7 +107,7 @@ static int afu_master_open(struct inode *inode, struct file *file)
 	return __afu_open(inode, file, true);
 }
 
-static int afu_release(struct inode *inode, struct file *file)
+int afu_release(struct inode *inode, struct file *file)
 {
 	struct cxl_context *ctx = file->private_data;
 
@@ -128,7 +129,6 @@ static int afu_release(struct inode *inode, struct file *file)
 	 */
 	cxl_context_free(ctx);
 
-	cxl_ctx_put();
 	return 0;
 }
 
@@ -191,7 +191,7 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 
 	if ((rc = cxl_attach_process(ctx, false, work.work_element_descriptor,
 				     amr))) {
-		afu_release_irqs(ctx);
+		afu_release_irqs(ctx, ctx);
 		goto out;
 	}
 
@@ -212,7 +212,26 @@ static long afu_ioctl_process_element(struct cxl_context *ctx,
 	return 0;
 }
 
-static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static long afu_ioctl_get_afu_id(struct cxl_context *ctx,
+				 struct cxl_afu_id __user *upafuid)
+{
+	struct cxl_afu_id afuid = { 0 };
+
+	afuid.card_id = ctx->afu->adapter->adapter_num;
+	afuid.afu_offset = ctx->afu->slice;
+	afuid.afu_mode = ctx->afu->current_mode;
+
+	/* set the flag bit in case the afu is a slave */
+	if (ctx->afu->current_mode == CXL_MODE_DIRECTED && !ctx->master)
+		afuid.flags |= CXL_AFUID_FLAG_SLAVE;
+
+	if (copy_to_user(upafuid, &afuid, sizeof(afuid)))
+		return -EFAULT;
+
+	return 0;
+}
+
+long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct cxl_context *ctx = file->private_data;
 
@@ -225,17 +244,20 @@ static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return afu_ioctl_start_work(ctx, (struct cxl_ioctl_start_work __user *)arg);
 	case CXL_IOCTL_GET_PROCESS_ELEMENT:
 		return afu_ioctl_process_element(ctx, (__u32 __user *)arg);
+	case CXL_IOCTL_GET_AFU_ID:
+		return afu_ioctl_get_afu_id(ctx, (struct cxl_afu_id __user *)
+					    arg);
 	}
 	return -EINVAL;
 }
 
-static long afu_compat_ioctl(struct file *file, unsigned int cmd,
+long afu_compat_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
 	return afu_ioctl(file, cmd, arg);
 }
 
-static int afu_mmap(struct file *file, struct vm_area_struct *vm)
+int afu_mmap(struct file *file, struct vm_area_struct *vm)
 {
 	struct cxl_context *ctx = file->private_data;
 
@@ -246,7 +268,7 @@ static int afu_mmap(struct file *file, struct vm_area_struct *vm)
 	return cxl_context_iomap(ctx, vm);
 }
 
-static unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
+unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
 {
 	struct cxl_context *ctx = file->private_data;
 	int mask = 0;
@@ -278,7 +300,7 @@ static inline int ctx_event_pending(struct cxl_context *ctx)
 	    ctx->pending_afu_err || (ctx->status == CLOSED));
 }
 
-static ssize_t afu_read(struct file *file, char __user *buf, size_t count,
+ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 			loff_t *off)
 {
 	struct cxl_context *ctx = file->private_data;
@@ -359,7 +381,11 @@ out:
 	return rc;
 }
 
-static const struct file_operations afu_fops = {
+/* 
+ * Note: if this is updated, we need to update api.c to patch the new ones in
+ * too
+ */
+const struct file_operations afu_fops = {
 	.owner		= THIS_MODULE,
 	.open           = afu_open,
 	.poll		= afu_poll,
@@ -370,7 +396,7 @@ static const struct file_operations afu_fops = {
 	.mmap           = afu_mmap,
 };
 
-static const struct file_operations afu_master_fops = {
+const struct file_operations afu_master_fops = {
 	.owner		= THIS_MODULE,
 	.open           = afu_master_open,
 	.poll		= afu_poll,
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index c8929c526691..680cd263436d 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -14,7 +14,7 @@
 #include <linux/slab.h>
 #include <linux/pid.h>
 #include <asm/cputable.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include "cxl.h"
 #include "trace.h"
@@ -416,9 +416,8 @@ void afu_irq_name_free(struct cxl_context *ctx)
 	}
 }
 
-int afu_register_irqs(struct cxl_context *ctx, u32 count)
+int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 {
-	irq_hw_number_t hwirq;
 	int rc, r, i, j = 1;
 	struct cxl_irq_name *irq_name;
 
@@ -458,6 +457,18 @@ int afu_register_irqs(struct cxl_context *ctx, u32 count)
 			j++;
 		}
 	}
+	return 0;
+
+out:
+	afu_irq_name_free(ctx);
+	return -ENOMEM;
+}
+
+void afu_register_hwirqs(struct cxl_context *ctx)
+{
+	irq_hw_number_t hwirq;
+	struct cxl_irq_name *irq_name;
+	int r,i;
 
 	/* We've allocated all memory now, so let's do the irq allocations */
 	irq_name = list_first_entry(&ctx->irq_names, struct cxl_irq_name, list);
@@ -469,15 +480,21 @@ int afu_register_irqs(struct cxl_context *ctx, u32 count)
 			irq_name = list_next_entry(irq_name, list);
 		}
 	}
+}
 
-	return 0;
+int afu_register_irqs(struct cxl_context *ctx, u32 count)
+{
+	int rc;
 
-out:
-	afu_irq_name_free(ctx);
-	return -ENOMEM;
-}
+	rc = afu_allocate_irqs(ctx, count);
+	if (rc)
+		return rc;
+
+	afu_register_hwirqs(ctx);
+	return 0;
+ }
 
-void afu_release_irqs(struct cxl_context *ctx)
+void afu_release_irqs(struct cxl_context *ctx, void *cookie)
 {
 	irq_hw_number_t hwirq;
 	unsigned int virq;
@@ -488,7 +505,7 @@ void afu_release_irqs(struct cxl_context *ctx)
 		for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
 			virq = irq_find_mapping(NULL, hwirq);
 			if (virq)
-				cxl_unmap_irq(virq, ctx);
+				cxl_unmap_irq(virq, cookie);
 		}
 	}
 
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index 8ccddceead66..833348e2c9cb 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -20,7 +20,7 @@
 #include <linux/idr.h>
 #include <linux/pci.h>
 #include <asm/cputable.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include "cxl.h"
 #include "trace.h"
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 29185fc61276..10567f245818 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -15,7 +15,7 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <asm/synch.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include "cxl.h"
 #include "trace.h"
@@ -73,7 +73,7 @@ int cxl_afu_disable(struct cxl_afu *afu)
 }
 
 /* This will disable as well as reset */
-int cxl_afu_reset(struct cxl_afu *afu)
+int __cxl_afu_reset(struct cxl_afu *afu)
 {
 	pr_devel("AFU reset request\n");
 
@@ -83,7 +83,7 @@ int cxl_afu_reset(struct cxl_afu *afu)
 			   false);
 }
 
-static int afu_check_and_enable(struct cxl_afu *afu)
+int cxl_afu_check_and_enable(struct cxl_afu *afu)
 {
 	if (afu->enabled)
 		return 0;
@@ -379,7 +379,7 @@ static int remove_process_element(struct cxl_context *ctx)
 }
 
 
-static void assign_psn_space(struct cxl_context *ctx)
+void cxl_assign_psn_space(struct cxl_context *ctx)
 {
 	if (!ctx->afu->pp_size || ctx->master) {
 		ctx->psn_phys = ctx->afu->psn_phys;
@@ -430,34 +430,46 @@ err:
 #define set_endian(sr) ((sr) &= ~(CXL_PSL_SR_An_LE))
 #endif
 
+static u64 calculate_sr(struct cxl_context *ctx)
+{
+	u64 sr = 0;
+
+	if (ctx->master)
+		sr |= CXL_PSL_SR_An_MP;
+	if (mfspr(SPRN_LPCR) & LPCR_TC)
+		sr |= CXL_PSL_SR_An_TC;
+	if (ctx->kernel) {
+		sr |= CXL_PSL_SR_An_R | (mfmsr() & MSR_SF);
+		sr |= CXL_PSL_SR_An_HV;
+	} else {
+		sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
+		set_endian(sr);
+		sr &= ~(CXL_PSL_SR_An_HV);
+		if (!test_tsk_thread_flag(current, TIF_32BIT))
+			sr |= CXL_PSL_SR_An_SF;
+	}
+	return sr;
+}
+
 static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
 {
-	u64 sr;
+	u32 pid;
 	int r, result;
 
-	assign_psn_space(ctx);
+	cxl_assign_psn_space(ctx);
 
 	ctx->elem->ctxtime = 0; /* disable */
 	ctx->elem->lpid = cpu_to_be32(mfspr(SPRN_LPID));
 	ctx->elem->haurp = 0; /* disable */
 	ctx->elem->sdr = cpu_to_be64(mfspr(SPRN_SDR1));
 
-	sr = 0;
-	if (ctx->master)
-		sr |= CXL_PSL_SR_An_MP;
-	if (mfspr(SPRN_LPCR) & LPCR_TC)
-		sr |= CXL_PSL_SR_An_TC;
-	/* HV=0, PR=1, R=1 for userspace
-	 * For kernel contexts: this would need to change
-	 */
-	sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
-	set_endian(sr);
-	sr &= ~(CXL_PSL_SR_An_HV);
-	if (!test_tsk_thread_flag(current, TIF_32BIT))
-		sr |= CXL_PSL_SR_An_SF;
-	ctx->elem->common.pid = cpu_to_be32(current->pid);
+	pid = current->pid;
+	if (ctx->kernel)
+		pid = 0;
 	ctx->elem->common.tid = 0;
-	ctx->elem->sr = cpu_to_be64(sr);
+	ctx->elem->common.pid = cpu_to_be32(pid);
+
+	ctx->elem->sr = cpu_to_be64(calculate_sr(ctx));
 
 	ctx->elem->common.csrp = 0; /* disable */
 	ctx->elem->common.aurp0 = 0; /* disable */
@@ -477,7 +489,7 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
 	ctx->elem->common.wed = cpu_to_be64(wed);
 
 	/* first guy needs to enable */
-	if ((result = afu_check_and_enable(ctx->afu)))
+	if ((result = cxl_afu_check_and_enable(ctx->afu)))
 		return result;
 
 	add_process_element(ctx);
@@ -495,7 +507,7 @@ static int deactivate_afu_directed(struct cxl_afu *afu)
 	cxl_sysfs_afu_m_remove(afu);
 	cxl_chardev_afu_remove(afu);
 
-	cxl_afu_reset(afu);
+	__cxl_afu_reset(afu);
 	cxl_afu_disable(afu);
 	cxl_psl_purge(afu);
 
@@ -530,20 +542,15 @@ static int activate_dedicated_process(struct cxl_afu *afu)
 static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
 {
 	struct cxl_afu *afu = ctx->afu;
-	u64 sr;
+	u64 pid;
 	int rc;
 
-	sr = 0;
-	set_endian(sr);
-	if (ctx->master)
-		sr |= CXL_PSL_SR_An_MP;
-	if (mfspr(SPRN_LPCR) & LPCR_TC)
-		sr |= CXL_PSL_SR_An_TC;
-	sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
-	if (!test_tsk_thread_flag(current, TIF_32BIT))
-		sr |= CXL_PSL_SR_An_SF;
-	cxl_p2n_write(afu, CXL_PSL_PID_TID_An, (u64)current->pid << 32);
-	cxl_p1n_write(afu, CXL_PSL_SR_An, sr);
+	pid = (u64)current->pid << 32;
+	if (ctx->kernel)
+		pid = 0;
+	cxl_p2n_write(afu, CXL_PSL_PID_TID_An, pid);
+
+	cxl_p1n_write(afu, CXL_PSL_SR_An, calculate_sr(ctx));
 
 	if ((rc = cxl_write_sstp(afu, ctx->sstp0, ctx->sstp1)))
 		return rc;
@@ -564,9 +571,9 @@ static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
 	cxl_p2n_write(afu, CXL_PSL_AMR_An, amr);
 
 	/* master only context for dedicated */
-	assign_psn_space(ctx);
+	cxl_assign_psn_space(ctx);
 
-	if ((rc = cxl_afu_reset(afu)))
+	if ((rc = __cxl_afu_reset(afu)))
 		return rc;
 
 	cxl_p2n_write(afu, CXL_PSL_WED_An, wed);
@@ -629,7 +636,7 @@ int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr)
 
 static inline int detach_process_native_dedicated(struct cxl_context *ctx)
 {
-	cxl_afu_reset(ctx->afu);
+	__cxl_afu_reset(ctx->afu);
 	cxl_afu_disable(ctx->afu);
 	cxl_psl_purge(ctx->afu);
 	return 0;
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 1ef01647265f..c68ef5806dbe 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -90,6 +90,7 @@
 /* This works a little different than the p1/p2 register accesses to make it
  * easier to pull out individual fields */
 #define AFUD_READ(afu, off)		in_be64(afu->afu_desc_mmio + off)
+#define AFUD_READ_LE(afu, off)		in_le64(afu->afu_desc_mmio + off)
 #define EXTRACT_PPC_BIT(val, bit)	(!!(val & PPC_BIT(bit)))
 #define EXTRACT_PPC_BITS(val, bs, be)	((val & PPC_BITMASK(bs, be)) >> PPC_BITLSHIFT(be))
 
@@ -204,7 +205,7 @@ static void dump_cxl_config_space(struct pci_dev *dev)
 	dev_info(&dev->dev, "p1 regs: %#llx, len: %#llx\n",
 		p1_base(dev), p1_size(dev));
 	dev_info(&dev->dev, "p2 regs: %#llx, len: %#llx\n",
-		p1_base(dev), p2_size(dev));
+		p2_base(dev), p2_size(dev));
 	dev_info(&dev->dev, "BAR 4/5: %#llx, len: %#llx\n",
 		pci_resource_start(dev, 4), pci_resource_len(dev, 4));
 
@@ -286,7 +287,8 @@ static void dump_cxl_config_space(struct pci_dev *dev)
 
 static void dump_afu_descriptor(struct cxl_afu *afu)
 {
-	u64 val;
+	u64 val, afu_cr_num, afu_cr_off, afu_cr_len;
+	int i;
 
 #define show_reg(name, what) \
 	dev_info(&afu->dev, "afu desc: %30s: %#llx\n", name, what)
@@ -296,6 +298,7 @@ static void dump_afu_descriptor(struct cxl_afu *afu)
 	show_reg("num_of_processes", AFUD_NUM_PROCS(val));
 	show_reg("num_of_afu_CRs", AFUD_NUM_CRS(val));
 	show_reg("req_prog_mode", val & 0xffffULL);
+	afu_cr_num = AFUD_NUM_CRS(val);
 
 	val = AFUD_READ(afu, 0x8);
 	show_reg("Reserved", val);
@@ -307,8 +310,10 @@ static void dump_afu_descriptor(struct cxl_afu *afu)
 	val = AFUD_READ_CR(afu);
 	show_reg("Reserved", (val >> (63-7)) & 0xff);
 	show_reg("AFU_CR_len", AFUD_CR_LEN(val));
+	afu_cr_len = AFUD_CR_LEN(val) * 256;
 
 	val = AFUD_READ_CR_OFF(afu);
+	afu_cr_off = val;
 	show_reg("AFU_CR_offset", val);
 
 	val = AFUD_READ_PPPSA(afu);
@@ -325,6 +330,11 @@ static void dump_afu_descriptor(struct cxl_afu *afu)
 	val = AFUD_READ_EB_OFF(afu);
 	show_reg("AFU_EB_offset", val);
 
+	for (i = 0; i < afu_cr_num; i++) {
+		val = AFUD_READ_LE(afu, afu_cr_off + i * afu_cr_len);
+		show_reg("CR Vendor", val & 0xffff);
+		show_reg("CR Device", (val >> 16) & 0xffff);
+	}
 #undef show_reg
 }
 
@@ -593,6 +603,22 @@ static int cxl_read_afu_descriptor(struct cxl_afu *afu)
 	afu->crs_len = AFUD_CR_LEN(val) * 256;
 	afu->crs_offset = AFUD_READ_CR_OFF(afu);
 
+
+	/* eb_len is in multiple of 4K */
+	afu->eb_len = AFUD_EB_LEN(AFUD_READ_EB(afu)) * 4096;
+	afu->eb_offset = AFUD_READ_EB_OFF(afu);
+
+	/* eb_off is 4K aligned so lower 12 bits are always zero */
+	if (EXTRACT_PPC_BITS(afu->eb_offset, 0, 11) != 0) {
+		dev_warn(&afu->dev,
+			 "Invalid AFU error buffer offset %Lx\n",
+			 afu->eb_offset);
+		dev_info(&afu->dev,
+			 "Ignoring AFU error buffer in the descriptor\n");
+		/* indicate that no afu buffer exists */
+		afu->eb_len = 0;
+	}
+
 	return 0;
 }
 
@@ -631,7 +657,7 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 	reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
 	if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
 		dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#.16llx\n", reg);
-		if (cxl_afu_reset(afu))
+		if (__cxl_afu_reset(afu))
 			return -EIO;
 		if (cxl_afu_disable(afu))
 			return -EIO;
@@ -672,6 +698,50 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 	return 0;
 }
 
+#define ERR_BUFF_MAX_COPY_SIZE PAGE_SIZE
+/*
+ * afu_eb_read:
+ * Called from sysfs and reads the afu error info buffer. The h/w only supports
+ * 4/8 bytes aligned access. So in case the requested offset/count arent 8 byte
+ * aligned the function uses a bounce buffer which can be max PAGE_SIZE.
+ */
+ssize_t cxl_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
+				loff_t off, size_t count)
+{
+	loff_t aligned_start, aligned_end;
+	size_t aligned_length;
+	void *tbuf;
+	const void __iomem *ebuf = afu->afu_desc_mmio + afu->eb_offset;
+
+	if (count == 0 || off < 0 || (size_t)off >= afu->eb_len)
+		return 0;
+
+	/* calculate aligned read window */
+	count = min((size_t)(afu->eb_len - off), count);
+	aligned_start = round_down(off, 8);
+	aligned_end = round_up(off + count, 8);
+	aligned_length = aligned_end - aligned_start;
+
+	/* max we can copy in one read is PAGE_SIZE */
+	if (aligned_length > ERR_BUFF_MAX_COPY_SIZE) {
+		aligned_length = ERR_BUFF_MAX_COPY_SIZE;
+		count = ERR_BUFF_MAX_COPY_SIZE - (off & 0x7);
+	}
+
+	/* use bounce buffer for copy */
+	tbuf = (void *)__get_free_page(GFP_TEMPORARY);
+	if (!tbuf)
+		return -ENOMEM;
+
+	/* perform aligned read from the mmio region */
+	memcpy_fromio(tbuf, ebuf + aligned_start, aligned_length);
+	memcpy(buf, tbuf + (off & 0x7), count);
+
+	free_page((unsigned long)tbuf);
+
+	return count;
+}
+
 static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 {
 	struct cxl_afu *afu;
@@ -691,7 +761,7 @@ static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 		goto err2;
 
 	/* We need to reset the AFU before we can read the AFU descriptor */
-	if ((rc = cxl_afu_reset(afu)))
+	if ((rc = __cxl_afu_reset(afu)))
 		goto err2;
 
 	if (cxl_verbose)
@@ -731,6 +801,9 @@ static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 
 	adapter->afu[afu->slice] = afu;
 
+	if ((rc = cxl_pci_vphb_add(afu)))
+		dev_info(&afu->dev, "Can't register vPHB\n");
+
 	return 0;
 
 err_put2:
@@ -783,8 +856,10 @@ int cxl_reset(struct cxl *adapter)
 
 	dev_info(&dev->dev, "CXL reset\n");
 
-	for (i = 0; i < adapter->slices; i++)
+	for (i = 0; i < adapter->slices; i++) {
+		cxl_pci_vphb_remove(adapter->afu[i]);
 		cxl_remove_afu(adapter->afu[i]);
+	}
 
 	/* pcie_warm_reset requests a fundamental pci reset which includes a
 	 * PERST assert/deassert.  PERST triggers a loading of the image
@@ -857,13 +932,13 @@ static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
 	u8 image_state;
 
 	if (!(vsec = find_cxl_vsec(dev))) {
-		dev_err(&adapter->dev, "ABORTING: CXL VSEC not found!\n");
+		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
 		return -ENODEV;
 	}
 
 	CXL_READ_VSEC_LENGTH(dev, vsec, &vseclen);
 	if (vseclen < CXL_VSEC_MIN_SIZE) {
-		pr_err("ABORTING: CXL VSEC too short\n");
+		dev_err(&dev->dev, "ABORTING: CXL VSEC too short\n");
 		return -EINVAL;
 	}
 
@@ -902,24 +977,24 @@ static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev)
 		return -EBUSY;
 
 	if (adapter->vsec_status & CXL_UNSUPPORTED_FEATURES) {
-		dev_err(&adapter->dev, "ABORTING: CXL requires unsupported features\n");
+		dev_err(&dev->dev, "ABORTING: CXL requires unsupported features\n");
 		return -EINVAL;
 	}
 
 	if (!adapter->slices) {
 		/* Once we support dynamic reprogramming we can use the card if
 		 * it supports loadable AFUs */
-		dev_err(&adapter->dev, "ABORTING: Device has no AFUs\n");
+		dev_err(&dev->dev, "ABORTING: Device has no AFUs\n");
 		return -EINVAL;
 	}
 
 	if (!adapter->afu_desc_off || !adapter->afu_desc_size) {
-		dev_err(&adapter->dev, "ABORTING: VSEC shows no AFU descriptors\n");
+		dev_err(&dev->dev, "ABORTING: VSEC shows no AFU descriptors\n");
 		return -EINVAL;
 	}
 
 	if (adapter->ps_size > p2_size(dev) - adapter->ps_off) {
-		dev_err(&adapter->dev, "ABORTING: Problem state size larger than "
+		dev_err(&dev->dev, "ABORTING: Problem state size larger than "
 				   "available in BAR2: 0x%llx > 0x%llx\n",
 			 adapter->ps_size, p2_size(dev) - adapter->ps_off);
 		return -EINVAL;
@@ -968,6 +1043,15 @@ static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 	if (!(adapter = cxl_alloc_adapter(dev)))
 		return ERR_PTR(-ENOMEM);
 
+	if ((rc = cxl_read_vsec(adapter, dev)))
+		goto err1;
+
+	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
+		goto err1;
+
+	if ((rc = setup_cxl_bars(dev)))
+		goto err1;
+
 	if ((rc = switch_card_to_cxl(dev)))
 		goto err1;
 
@@ -977,12 +1061,6 @@ static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 	if ((rc = dev_set_name(&adapter->dev, "card%i", adapter->adapter_num)))
 		goto err2;
 
-	if ((rc = cxl_read_vsec(adapter, dev)))
-		goto err2;
-
-	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
-		goto err2;
-
 	if ((rc = cxl_update_image_control(adapter)))
 		goto err2;
 
@@ -1067,9 +1145,6 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (cxl_verbose)
 		dump_cxl_config_space(dev);
 
-	if ((rc = setup_cxl_bars(dev)))
-		return rc;
-
 	if ((rc = pci_enable_device(dev))) {
 		dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
 		return rc;
@@ -1078,6 +1153,7 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	adapter = cxl_init_adapter(dev);
 	if (IS_ERR(adapter)) {
 		dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter));
+		pci_disable_device(dev);
 		return PTR_ERR(adapter);
 	}
 
@@ -1092,16 +1168,18 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 static void cxl_remove(struct pci_dev *dev)
 {
 	struct cxl *adapter = pci_get_drvdata(dev);
-	int afu;
-
-	dev_warn(&dev->dev, "pci remove\n");
+	struct cxl_afu *afu;
+	int i;
 
 	/*
 	 * Lock to prevent someone grabbing a ref through the adapter list as
 	 * we are removing it
 	 */
-	for (afu = 0; afu < adapter->slices; afu++)
-		cxl_remove_afu(adapter->afu[afu]);
+	for (i = 0; i < adapter->slices; i++) {
+		afu = adapter->afu[i];
+		cxl_pci_vphb_remove(afu);
+		cxl_remove_afu(afu);
+	}
 	cxl_remove_adapter(adapter);
 }
 
@@ -1110,4 +1188,5 @@ struct pci_driver cxl_pci_driver = {
 	.id_table = cxl_pci_tbl,
 	.probe = cxl_probe,
 	.remove = cxl_remove,
+	.shutdown = cxl_remove,
 };
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index d0c38c7bc0c4..31f38bc71a3d 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -185,7 +185,7 @@ static ssize_t reset_store_afu(struct device *device,
 		goto err;
 	}
 
-	if ((rc = cxl_afu_reset(afu)))
+	if ((rc = __cxl_afu_reset(afu)))
 		goto err;
 
 	rc = count;
@@ -356,6 +356,16 @@ static ssize_t api_version_compatible_show(struct device *device,
 	return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION_COMPATIBLE);
 }
 
+static ssize_t afu_eb_read(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *bin_attr, char *buf,
+			       loff_t off, size_t count)
+{
+	struct cxl_afu *afu = to_cxl_afu(container_of(kobj,
+						      struct device, kobj));
+
+	return cxl_afu_read_err_buffer(afu, buf, off, count);
+}
+
 static struct device_attribute afu_attrs[] = {
 	__ATTR_RO(mmio_size),
 	__ATTR_RO(irqs_min),
@@ -534,6 +544,10 @@ void cxl_sysfs_afu_remove(struct cxl_afu *afu)
 	struct afu_config_record *cr, *tmp;
 	int i;
 
+	/* remove the err buffer bin attribute */
+	if (afu->eb_len)
+		device_remove_bin_file(&afu->dev, &afu->attr_eb);
+
 	for (i = 0; i < ARRAY_SIZE(afu_attrs); i++)
 		device_remove_file(&afu->dev, &afu_attrs[i]);
 
@@ -555,6 +569,22 @@ int cxl_sysfs_afu_add(struct cxl_afu *afu)
 			goto err;
 	}
 
+	/* conditionally create the add the binary file for error info buffer */
+	if (afu->eb_len) {
+		afu->attr_eb.attr.name = "afu_err_buff";
+		afu->attr_eb.attr.mode = S_IRUGO;
+		afu->attr_eb.size = afu->eb_len;
+		afu->attr_eb.read = afu_eb_read;
+
+		rc = device_create_bin_file(&afu->dev, &afu->attr_eb);
+		if (rc) {
+			dev_err(&afu->dev,
+				"Unable to create eb attr for the afu. Err(%d)\n",
+				rc);
+			goto err;
+		}
+	}
+
 	for (i = 0; i < afu->crs_num; i++) {
 		cr = cxl_sysfs_afu_new_cr(afu, i);
 		if (IS_ERR(cr)) {
@@ -570,6 +600,9 @@ err1:
 	cxl_sysfs_afu_remove(afu);
 	return rc;
 err:
+	/* reset the eb_len as we havent created the bin attr */
+	afu->eb_len = 0;
+
 	for (i--; i >= 0; i--)
 		device_remove_file(&afu->dev, &afu_attrs[i]);
 	return rc;
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
new file mode 100644
index 000000000000..b1d1983a84a5
--- /dev/null
+++ b/drivers/misc/cxl/vphb.c
@@ -0,0 +1,270 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * 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/pci.h>
+#include <misc/cxl.h>
+#include "cxl.h"
+
+static int cxl_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	if (dma_mask < DMA_BIT_MASK(64)) {
+		pr_info("%s only 64bit DMA supported on CXL", __func__);
+		return -EIO;
+	}
+
+	*(pdev->dev.dma_mask) = dma_mask;
+	return 0;
+}
+
+static int cxl_pci_probe_mode(struct pci_bus *bus)
+{
+	return PCI_PROBE_NORMAL;
+}
+
+static int cxl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	return -ENODEV;
+}
+
+static void cxl_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	/*
+	 * MSI should never be set but need still need to provide this call
+	 * back.
+	 */
+}
+
+static bool cxl_pci_enable_device_hook(struct pci_dev *dev)
+{
+	struct pci_controller *phb;
+	struct cxl_afu *afu;
+	struct cxl_context *ctx;
+
+	phb = pci_bus_to_host(dev->bus);
+	afu = (struct cxl_afu *)phb->private_data;
+	set_dma_ops(&dev->dev, &dma_direct_ops);
+	set_dma_offset(&dev->dev, PAGE_OFFSET);
+
+	/*
+	 * Allocate a context to do cxl things too.  If we eventually do real
+	 * DMA ops, we'll need a default context to attach them to
+	 */
+	ctx = cxl_dev_context_init(dev);
+	if (!ctx)
+		return false;
+	dev->dev.archdata.cxl_ctx = ctx;
+
+	return (cxl_afu_check_and_enable(afu) == 0);
+}
+
+static void cxl_pci_disable_device(struct pci_dev *dev)
+{
+	struct cxl_context *ctx = cxl_get_context(dev);
+
+	if (ctx) {
+		if (ctx->status == STARTED) {
+			dev_err(&dev->dev, "Default context started\n");
+			return;
+		}
+		dev->dev.archdata.cxl_ctx = NULL;
+		cxl_release_context(ctx);
+	}
+}
+
+static resource_size_t cxl_pci_window_alignment(struct pci_bus *bus,
+						unsigned long type)
+{
+	return 1;
+}
+
+static void cxl_pci_reset_secondary_bus(struct pci_dev *dev)
+{
+	/* Should we do an AFU reset here ? */
+}
+
+static int cxl_pcie_cfg_record(u8 bus, u8 devfn)
+{
+	return (bus << 8) + devfn;
+}
+
+static unsigned long cxl_pcie_cfg_addr(struct pci_controller* phb,
+				       u8 bus, u8 devfn, int offset)
+{
+	int record = cxl_pcie_cfg_record(bus, devfn);
+
+	return (unsigned long)phb->cfg_addr + ((unsigned long)phb->cfg_data * record) + offset;
+}
+
+
+static int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn,
+				int offset, int len,
+				volatile void __iomem **ioaddr,
+				u32 *mask, int *shift)
+{
+	struct pci_controller *phb;
+	struct cxl_afu *afu;
+	unsigned long addr;
+
+	phb = pci_bus_to_host(bus);
+	afu = (struct cxl_afu *)phb->private_data;
+	if (phb == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (cxl_pcie_cfg_record(bus->number, devfn) > afu->crs_num)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (offset >= (unsigned long)phb->cfg_data)
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	addr = cxl_pcie_cfg_addr(phb, bus->number, devfn, offset);
+
+	*ioaddr = (void *)(addr & ~0x3ULL);
+	*shift = ((addr & 0x3) * 8);
+	switch (len) {
+	case 1:
+		*mask = 0xff;
+		break;
+	case 2:
+		*mask = 0xffff;
+		break;
+	default:
+		*mask = 0xffffffff;
+		break;
+	}
+	return 0;
+}
+
+static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+				int offset, int len, u32 *val)
+{
+	volatile void __iomem *ioaddr;
+	int shift, rc;
+	u32 mask;
+
+	rc = cxl_pcie_config_info(bus, devfn, offset, len, &ioaddr,
+				  &mask, &shift);
+	if (rc)
+		return rc;
+
+	/* Can only read 32 bits */
+	*val = (in_le32(ioaddr) >> shift) & mask;
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+				 int offset, int len, u32 val)
+{
+	volatile void __iomem *ioaddr;
+	u32 v, mask;
+	int shift, rc;
+
+	rc = cxl_pcie_config_info(bus, devfn, offset, len, &ioaddr,
+				  &mask, &shift);
+	if (rc)
+		return rc;
+
+	/* Can only write 32 bits so do read-modify-write */
+	mask <<= shift;
+	val <<= shift;
+
+	v = (in_le32(ioaddr) & ~mask) || (val & mask);
+
+	out_le32(ioaddr, v);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops cxl_pcie_pci_ops =
+{
+	.read = cxl_pcie_read_config,
+	.write = cxl_pcie_write_config,
+};
+
+
+static struct pci_controller_ops cxl_pci_controller_ops =
+{
+	.probe_mode = cxl_pci_probe_mode,
+	.enable_device_hook = cxl_pci_enable_device_hook,
+	.disable_device = cxl_pci_disable_device,
+	.release_device = cxl_pci_disable_device,
+	.window_alignment = cxl_pci_window_alignment,
+	.reset_secondary_bus = cxl_pci_reset_secondary_bus,
+	.setup_msi_irqs = cxl_setup_msi_irqs,
+	.teardown_msi_irqs = cxl_teardown_msi_irqs,
+	.dma_set_mask = cxl_dma_set_mask,
+};
+
+int cxl_pci_vphb_add(struct cxl_afu *afu)
+{
+	struct pci_dev *phys_dev;
+	struct pci_controller *phb, *phys_phb;
+
+	phys_dev = to_pci_dev(afu->adapter->dev.parent);
+	phys_phb = pci_bus_to_host(phys_dev->bus);
+
+	/* Alloc and setup PHB data structure */
+	phb = pcibios_alloc_controller(phys_phb->dn);
+
+	if (!phb)
+		return -ENODEV;
+
+	/* Setup parent in sysfs */
+	phb->parent = &phys_dev->dev;
+
+	/* Setup the PHB using arch provided callback */
+	phb->ops = &cxl_pcie_pci_ops;
+	phb->cfg_addr = afu->afu_desc_mmio + afu->crs_offset;
+	phb->cfg_data = (void *)(u64)afu->crs_len;
+	phb->private_data = afu;
+	phb->controller_ops = cxl_pci_controller_ops;
+
+	/* Scan the bus */
+	pcibios_scan_phb(phb);
+	if (phb->bus == NULL)
+		return -ENXIO;
+
+	/* Claim resources. This might need some rework as well depending
+	 * whether we are doing probe-only or not, like assigning unassigned
+	 * resources etc...
+	 */
+	pcibios_claim_one_bus(phb->bus);
+
+	/* Add probed PCI devices to the device model */
+	pci_bus_add_devices(phb->bus);
+
+	afu->phb = phb;
+
+	return 0;
+}
+
+
+void cxl_pci_vphb_remove(struct cxl_afu *afu)
+{
+	struct pci_controller *phb;
+
+	/* If there is no configuration record we won't have one of these */
+	if (!afu || !afu->phb)
+		return;
+
+	phb = afu->phb;
+
+	pci_remove_root_bus(phb->bus);
+}
+
+struct cxl_afu *cxl_pci_to_afu(struct pci_dev *dev)
+{
+	struct pci_controller *phb;
+
+	phb = pci_bus_to_host(dev->bus);
+
+	return (struct cxl_afu *)phb->private_data;
+}
+EXPORT_SYMBOL_GPL(cxl_pci_to_afu);
+
+unsigned int cxl_pci_to_cfg_record(struct pci_dev *dev)
+{
+	return cxl_pcie_cfg_record(dev->bus->number, dev->devfn);
+}
+EXPORT_SYMBOL_GPL(cxl_pci_to_cfg_record);
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index c49d0b127fef..f73c41697a00 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -195,6 +195,14 @@ config MTD_BLOCK2MTD
 	  Testing MTD users (eg JFFS2) on large media and media that might
 	  be removed during a write (using the floppy drive).
 
+config MTD_POWERNV_FLASH
+	tristate "powernv flash MTD driver"
+	depends on PPC_POWERNV
+	help
+	  This provides an MTD device to access flash on powernv OPAL
+	  platforms from Linux. This device abstracts away the
+	  firmware interface for flash access.
+
 comment "Disk-On-Chip Device Drivers"
 
 config MTD_DOCG3
diff --git a/drivers/mtd/devices/Makefile b/drivers/mtd/devices/Makefile
index f0b0e611d1d6..7912d3a0ee34 100644
--- a/drivers/mtd/devices/Makefile
+++ b/drivers/mtd/devices/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_MTD_SPEAR_SMI)	+= spear_smi.o
 obj-$(CONFIG_MTD_SST25L)	+= sst25l.o
 obj-$(CONFIG_MTD_BCM47XXSFLASH)	+= bcm47xxsflash.o
 obj-$(CONFIG_MTD_ST_SPI_FSM)    += st_spi_fsm.o
+obj-$(CONFIG_MTD_POWERNV_FLASH)	+= powernv_flash.o
 
 
 CFLAGS_docg3.o			+= -I$(src)
diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
new file mode 100644
index 000000000000..d5b870b3fd4e
--- /dev/null
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -0,0 +1,285 @@
+/*
+ * OPAL PNOR flash MTD abstraction
+ *
+ * Copyright IBM 2015
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <asm/opal.h>
+
+
+/*
+ * This driver creates the a Linux MTD abstraction for platform PNOR flash
+ * backed by OPAL calls
+ */
+
+struct powernv_flash {
+	struct mtd_info	mtd;
+	u32 id;
+};
+
+enum flash_op {
+	FLASH_OP_READ,
+	FLASH_OP_WRITE,
+	FLASH_OP_ERASE,
+};
+
+static int powernv_flash_async_op(struct mtd_info *mtd, enum flash_op op,
+		loff_t offset, size_t len, size_t *retlen, u_char *buf)
+{
+	struct powernv_flash *info = (struct powernv_flash *)mtd->priv;
+	struct device *dev = &mtd->dev;
+	int token;
+	struct opal_msg msg;
+	int rc;
+
+	dev_dbg(dev, "%s(op=%d, offset=0x%llx, len=%zu)\n",
+			__func__, op, offset, len);
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			dev_err(dev, "Failed to get an async token\n");
+
+		return token;
+	}
+
+	switch (op) {
+	case FLASH_OP_READ:
+		rc = opal_flash_read(info->id, offset, __pa(buf), len, token);
+		break;
+	case FLASH_OP_WRITE:
+		rc = opal_flash_write(info->id, offset, __pa(buf), len, token);
+		break;
+	case FLASH_OP_ERASE:
+		rc = opal_flash_erase(info->id, offset, len, token);
+		break;
+	default:
+		BUG_ON(1);
+	}
+
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		dev_err(dev, "opal_flash_async_op(op=%d) failed (rc %d)\n",
+				op, rc);
+		opal_async_release_token(token);
+		return -EIO;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	opal_async_release_token(token);
+	if (rc) {
+		dev_err(dev, "opal async wait failed (rc %d)\n", rc);
+		return -EIO;
+	}
+
+	rc = be64_to_cpu(msg.params[1]);
+	if (rc == OPAL_SUCCESS) {
+		rc = 0;
+		if (retlen)
+			*retlen = len;
+	} else {
+		rc = -EIO;
+	}
+
+	return rc;
+}
+
+/**
+ * @mtd: the device
+ * @from: the offset to read from
+ * @len: the number of bytes to read
+ * @retlen: the number of bytes actually read
+ * @buf: the filled in buffer
+ *
+ * Returns 0 if read successful, or -ERRNO if an error occurred
+ */
+static int powernv_flash_read(struct mtd_info *mtd, loff_t from, size_t len,
+	     size_t *retlen, u_char *buf)
+{
+	return powernv_flash_async_op(mtd, FLASH_OP_READ, from,
+			len, retlen, buf);
+}
+
+/**
+ * @mtd: the device
+ * @to: the offset to write to
+ * @len: the number of bytes to write
+ * @retlen: the number of bytes actually written
+ * @buf: the buffer to get bytes from
+ *
+ * Returns 0 if write successful, -ERRNO if error occurred
+ */
+static int powernv_flash_write(struct mtd_info *mtd, loff_t to, size_t len,
+		     size_t *retlen, const u_char *buf)
+{
+	return powernv_flash_async_op(mtd, FLASH_OP_WRITE, to,
+			len, retlen, (u_char *)buf);
+}
+
+/**
+ * @mtd: the device
+ * @erase: the erase info
+ * Returns 0 if erase successful or -ERRNO if an error occurred
+ */
+static int powernv_flash_erase(struct mtd_info *mtd, struct erase_info *erase)
+{
+	int rc;
+
+	erase->state = MTD_ERASING;
+
+	/* todo: register our own notifier to do a true async implementation */
+	rc =  powernv_flash_async_op(mtd, FLASH_OP_ERASE, erase->addr,
+			erase->len, NULL, NULL);
+
+	if (rc) {
+		erase->fail_addr = erase->addr;
+		erase->state = MTD_ERASE_FAILED;
+	} else {
+		erase->state = MTD_ERASE_DONE;
+	}
+	mtd_erase_callback(erase);
+	return rc;
+}
+
+/**
+ * powernv_flash_set_driver_info - Fill the mtd_info structure and docg3
+ * structure @pdev: The platform device
+ * @mtd: The structure to fill
+ */
+static int powernv_flash_set_driver_info(struct device *dev,
+		struct mtd_info *mtd)
+{
+	u64 size;
+	u32 erase_size;
+	int rc;
+
+	rc = of_property_read_u32(dev->of_node, "ibm,flash-block-size",
+			&erase_size);
+	if (rc) {
+		dev_err(dev, "couldn't get resource block size information\n");
+		return rc;
+	}
+
+	rc = of_property_read_u64(dev->of_node, "reg", &size);
+	if (rc) {
+		dev_err(dev, "couldn't get resource size information\n");
+		return rc;
+	}
+
+	/*
+	 * Going to have to check what details I need to set and how to
+	 * get them
+	 */
+	mtd->name = of_get_property(dev->of_node, "name", NULL);
+	mtd->type = MTD_NORFLASH;
+	mtd->flags = MTD_WRITEABLE;
+	mtd->size = size;
+	mtd->erasesize = erase_size;
+	mtd->writebufsize = mtd->writesize = 1;
+	mtd->owner = THIS_MODULE;
+	mtd->_erase = powernv_flash_erase;
+	mtd->_read = powernv_flash_read;
+	mtd->_write = powernv_flash_write;
+	mtd->dev.parent = dev;
+	return 0;
+}
+
+/**
+ * powernv_flash_probe
+ * @pdev: platform device
+ *
+ * Returns 0 on success, -ENOMEM, -ENXIO on error
+ */
+static int powernv_flash_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct powernv_flash *data;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	data->mtd.priv = data;
+
+	ret = of_property_read_u32(dev->of_node, "ibm,opal-id", &(data->id));
+	if (ret) {
+		dev_err(dev, "no device property 'ibm,opal-id'\n");
+		goto out;
+	}
+
+	ret = powernv_flash_set_driver_info(dev, &data->mtd);
+	if (ret)
+		goto out;
+
+	dev_set_drvdata(dev, data);
+
+	/*
+	 * The current flash that skiboot exposes is one contiguous flash chip
+	 * with an ffs partition at the start, it should prove easier for users
+	 * to deal with partitions or not as they see fit
+	 */
+	ret = mtd_device_register(&data->mtd, NULL, 0);
+
+out:
+	return ret;
+}
+
+/**
+ * op_release - Release the driver
+ * @pdev: the platform device
+ *
+ * Returns 0
+ */
+static int powernv_flash_release(struct platform_device *pdev)
+{
+	struct powernv_flash *data = dev_get_drvdata(&(pdev->dev));
+
+	/* All resources should be freed automatically */
+	return mtd_device_unregister(&(data->mtd));
+}
+
+static const struct of_device_id powernv_flash_match[] = {
+	{ .compatible = "ibm,opal-flash" },
+	{}
+};
+
+static struct platform_driver powernv_flash_driver = {
+	.driver		= {
+		.name		= "powernv_flash",
+		.of_match_table	= powernv_flash_match,
+	},
+	.remove		= powernv_flash_release,
+	.probe		= powernv_flash_probe,
+};
+
+module_platform_driver(powernv_flash_driver);
+
+MODULE_DEVICE_TABLE(of, powernv_flash_match);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Cyril Bur <cyril.bur@au1.ibm.com>");
+MODULE_DESCRIPTION("MTD abstraction for OPAL flash");
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 543b234e70fc..47b54c6aefd2 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -29,6 +29,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/export.h>
+#include <linux/interrupt.h>
 
 #include <asm/hvconsole.h>
 #include <asm/prom.h>
@@ -61,7 +62,6 @@ static struct hvc_opal_priv *hvc_opal_privs[MAX_NR_HVC_CONSOLES];
 /* For early boot console */
 static struct hvc_opal_priv hvc_opal_boot_priv;
 static u32 hvc_opal_boot_termno;
-static bool hvc_opal_event_registered;
 
 static const struct hv_ops hvc_opal_raw_ops = {
 	.get_chars = opal_get_chars,
@@ -162,28 +162,15 @@ static const struct hv_ops hvc_opal_hvsi_ops = {
 	.tiocmset = hvc_opal_hvsi_tiocmset,
 };
 
-static int hvc_opal_console_event(struct notifier_block *nb,
-				  unsigned long events, void *change)
-{
-	if (events & OPAL_EVENT_CONSOLE_INPUT)
-		hvc_kick();
-	return 0;
-}
-
-static struct notifier_block hvc_opal_console_nb = {
-	.notifier_call	= hvc_opal_console_event,
-};
-
 static int hvc_opal_probe(struct platform_device *dev)
 {
 	const struct hv_ops *ops;
 	struct hvc_struct *hp;
 	struct hvc_opal_priv *pv;
 	hv_protocol_t proto;
-	unsigned int termno, boot = 0;
+	unsigned int termno, irq, boot = 0;
 	const __be32 *reg;
 
-
 	if (of_device_is_compatible(dev->dev.of_node, "ibm,opal-console-raw")) {
 		proto = HV_PROTOCOL_RAW;
 		ops = &hvc_opal_raw_ops;
@@ -227,18 +214,18 @@ static int hvc_opal_probe(struct platform_device *dev)
 		dev->dev.of_node->full_name,
 		boot ? " (boot console)" : "");
 
-	/* We don't do IRQ ... */
-	hp = hvc_alloc(termno, 0, ops, MAX_VIO_PUT_CHARS);
+	irq = opal_event_request(ilog2(OPAL_EVENT_CONSOLE_INPUT));
+	if (!irq) {
+		pr_err("hvc_opal: Unable to map interrupt for device %s\n",
+			dev->dev.of_node->full_name);
+		return irq;
+	}
+
+	hp = hvc_alloc(termno, irq, ops, MAX_VIO_PUT_CHARS);
 	if (IS_ERR(hp))
 		return PTR_ERR(hp);
 	dev_set_drvdata(&dev->dev, hp);
 
-	/* ...  but we use OPAL event to kick the console */
-	if (!hvc_opal_event_registered) {
-		opal_notifier_register(&hvc_opal_console_nb);
-		hvc_opal_event_registered = true;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 730b4ef3e0cc..0582b72ef377 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -19,8 +19,10 @@
 #include <linux/uaccess.h>
 #include <linux/err.h>
 #include <linux/vfio.h>
+#include <linux/vmalloc.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
+#include <asm/mmu_context.h>
 
 #define DRIVER_VERSION  "0.1"
 #define DRIVER_AUTHOR   "aik@ozlabs.ru"
@@ -29,6 +31,51 @@
 static void tce_iommu_detach_group(void *iommu_data,
 		struct iommu_group *iommu_group);
 
+static long try_increment_locked_vm(long npages)
+{
+	long ret = 0, locked, lock_limit;
+
+	if (!current || !current->mm)
+		return -ESRCH; /* process exited */
+
+	if (!npages)
+		return 0;
+
+	down_write(&current->mm->mmap_sem);
+	locked = current->mm->locked_vm + npages;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+		ret = -ENOMEM;
+	else
+		current->mm->locked_vm += npages;
+
+	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
+			npages << PAGE_SHIFT,
+			current->mm->locked_vm << PAGE_SHIFT,
+			rlimit(RLIMIT_MEMLOCK),
+			ret ? " - exceeded" : "");
+
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static void decrement_locked_vm(long npages)
+{
+	if (!current || !current->mm || !npages)
+		return; /* process exited */
+
+	down_write(&current->mm->mmap_sem);
+	if (WARN_ON_ONCE(npages > current->mm->locked_vm))
+		npages = current->mm->locked_vm;
+	current->mm->locked_vm -= npages;
+	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
+			npages << PAGE_SHIFT,
+			current->mm->locked_vm << PAGE_SHIFT,
+			rlimit(RLIMIT_MEMLOCK));
+	up_write(&current->mm->mmap_sem);
+}
+
 /*
  * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
  *
@@ -36,6 +83,11 @@ static void tce_iommu_detach_group(void *iommu_data,
  * into DMA'ble space using the IOMMU
  */
 
+struct tce_iommu_group {
+	struct list_head next;
+	struct iommu_group *grp;
+};
+
 /*
  * The container descriptor supports only a single group per container.
  * Required by the API as the container is not supplied with the IOMMU group
@@ -43,18 +95,140 @@ static void tce_iommu_detach_group(void *iommu_data,
  */
 struct tce_container {
 	struct mutex lock;
-	struct iommu_table *tbl;
 	bool enabled;
+	bool v2;
+	unsigned long locked_pages;
+	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
+	struct list_head group_list;
 };
 
+static long tce_iommu_unregister_pages(struct tce_container *container,
+		__u64 vaddr, __u64 size)
+{
+	struct mm_iommu_table_group_mem_t *mem;
+
+	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
+		return -EINVAL;
+
+	mem = mm_iommu_find(vaddr, size >> PAGE_SHIFT);
+	if (!mem)
+		return -ENOENT;
+
+	return mm_iommu_put(mem);
+}
+
+static long tce_iommu_register_pages(struct tce_container *container,
+		__u64 vaddr, __u64 size)
+{
+	long ret = 0;
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	unsigned long entries = size >> PAGE_SHIFT;
+
+	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
+			((vaddr + size) < vaddr))
+		return -EINVAL;
+
+	ret = mm_iommu_get(vaddr, entries, &mem);
+	if (ret)
+		return ret;
+
+	container->enabled = true;
+
+	return 0;
+}
+
+static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
+{
+	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
+			tbl->it_size, PAGE_SIZE);
+	unsigned long *uas;
+	long ret;
+
+	BUG_ON(tbl->it_userspace);
+
+	ret = try_increment_locked_vm(cb >> PAGE_SHIFT);
+	if (ret)
+		return ret;
+
+	uas = vzalloc(cb);
+	if (!uas) {
+		decrement_locked_vm(cb >> PAGE_SHIFT);
+		return -ENOMEM;
+	}
+	tbl->it_userspace = uas;
+
+	return 0;
+}
+
+static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
+{
+	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
+			tbl->it_size, PAGE_SIZE);
+
+	if (!tbl->it_userspace)
+		return;
+
+	vfree(tbl->it_userspace);
+	tbl->it_userspace = NULL;
+	decrement_locked_vm(cb >> PAGE_SHIFT);
+}
+
+static bool tce_page_is_contained(struct page *page, unsigned page_shift)
+{
+	/*
+	 * Check that the TCE table granularity is not bigger than the size of
+	 * a page we just found. Otherwise the hardware can get access to
+	 * a bigger memory chunk that it should.
+	 */
+	return (PAGE_SHIFT + compound_order(compound_head(page))) >= page_shift;
+}
+
+static inline bool tce_groups_attached(struct tce_container *container)
+{
+	return !list_empty(&container->group_list);
+}
+
+static long tce_iommu_find_table(struct tce_container *container,
+		phys_addr_t ioba, struct iommu_table **ptbl)
+{
+	long i;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = container->tables[i];
+
+		if (tbl) {
+			unsigned long entry = ioba >> tbl->it_page_shift;
+			unsigned long start = tbl->it_offset;
+			unsigned long end = start + tbl->it_size;
+
+			if ((start <= entry) && (entry < end)) {
+				*ptbl = tbl;
+				return i;
+			}
+		}
+	}
+
+	return -1;
+}
+
+static int tce_iommu_find_free_table(struct tce_container *container)
+{
+	int i;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		if (!container->tables[i])
+			return i;
+	}
+
+	return -ENOSPC;
+}
+
 static int tce_iommu_enable(struct tce_container *container)
 {
 	int ret = 0;
-	unsigned long locked, lock_limit, npages;
-	struct iommu_table *tbl = container->tbl;
-
-	if (!container->tbl)
-		return -ENXIO;
+	unsigned long locked;
+	struct iommu_table_group *table_group;
+	struct tce_iommu_group *tcegrp;
 
 	if (!current->mm)
 		return -ESRCH; /* process exited */
@@ -79,21 +253,38 @@ static int tce_iommu_enable(struct tce_container *container)
 	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
 	 * that would effectively kill the guest at random points, much better
 	 * enforcing the limit based on the max that the guest can map.
+	 *
+	 * Unfortunately at the moment it counts whole tables, no matter how
+	 * much memory the guest has. I.e. for 4GB guest and 4 IOMMU groups
+	 * each with 2GB DMA window, 8GB will be counted here. The reason for
+	 * this is that we cannot tell here the amount of RAM used by the guest
+	 * as this information is only available from KVM and VFIO is
+	 * KVM agnostic.
+	 *
+	 * So we do not allow enabling a container without a group attached
+	 * as there is no way to know how much we should increment
+	 * the locked_vm counter.
 	 */
-	down_write(&current->mm->mmap_sem);
-	npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
-	locked = current->mm->locked_vm + npages;
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
-		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
-				rlimit(RLIMIT_MEMLOCK));
-		ret = -ENOMEM;
-	} else {
+	if (!tce_groups_attached(container))
+		return -ENODEV;
 
-		current->mm->locked_vm += npages;
-		container->enabled = true;
-	}
-	up_write(&current->mm->mmap_sem);
+	tcegrp = list_first_entry(&container->group_list,
+			struct tce_iommu_group, next);
+	table_group = iommu_group_get_iommudata(tcegrp->grp);
+	if (!table_group)
+		return -ENODEV;
+
+	if (!table_group->tce32_size)
+		return -EPERM;
+
+	locked = table_group->tce32_size >> PAGE_SHIFT;
+	ret = try_increment_locked_vm(locked);
+	if (ret)
+		return ret;
+
+	container->locked_pages = locked;
+
+	container->enabled = true;
 
 	return ret;
 }
@@ -105,20 +296,17 @@ static void tce_iommu_disable(struct tce_container *container)
 
 	container->enabled = false;
 
-	if (!container->tbl || !current->mm)
+	if (!current->mm)
 		return;
 
-	down_write(&current->mm->mmap_sem);
-	current->mm->locked_vm -= (container->tbl->it_size <<
-			IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
-	up_write(&current->mm->mmap_sem);
+	decrement_locked_vm(container->locked_pages);
 }
 
 static void *tce_iommu_open(unsigned long arg)
 {
 	struct tce_container *container;
 
-	if (arg != VFIO_SPAPR_TCE_IOMMU) {
+	if ((arg != VFIO_SPAPR_TCE_IOMMU) && (arg != VFIO_SPAPR_TCE_v2_IOMMU)) {
 		pr_err("tce_vfio: Wrong IOMMU type\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -128,36 +316,411 @@ static void *tce_iommu_open(unsigned long arg)
 		return ERR_PTR(-ENOMEM);
 
 	mutex_init(&container->lock);
+	INIT_LIST_HEAD_RCU(&container->group_list);
+
+	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
 
 	return container;
 }
 
+static int tce_iommu_clear(struct tce_container *container,
+		struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages);
+static void tce_iommu_free_table(struct iommu_table *tbl);
+
 static void tce_iommu_release(void *iommu_data)
 {
 	struct tce_container *container = iommu_data;
+	struct iommu_table_group *table_group;
+	struct tce_iommu_group *tcegrp;
+	long i;
+
+	while (tce_groups_attached(container)) {
+		tcegrp = list_first_entry(&container->group_list,
+				struct tce_iommu_group, next);
+		table_group = iommu_group_get_iommudata(tcegrp->grp);
+		tce_iommu_detach_group(iommu_data, tcegrp->grp);
+	}
 
-	WARN_ON(container->tbl && !container->tbl->it_group);
-	tce_iommu_disable(container);
+	/*
+	 * If VFIO created a table, it was not disposed
+	 * by tce_iommu_detach_group() so do it now.
+	 */
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = container->tables[i];
+
+		if (!tbl)
+			continue;
 
-	if (container->tbl && container->tbl->it_group)
-		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
+		tce_iommu_free_table(tbl);
+	}
 
+	tce_iommu_disable(container);
 	mutex_destroy(&container->lock);
 
 	kfree(container);
 }
 
+static void tce_iommu_unuse_page(struct tce_container *container,
+		unsigned long hpa)
+{
+	struct page *page;
+
+	page = pfn_to_page(hpa >> PAGE_SHIFT);
+	put_page(page);
+}
+
+static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
+		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
+{
+	long ret = 0;
+	struct mm_iommu_table_group_mem_t *mem;
+
+	mem = mm_iommu_lookup(tce, size);
+	if (!mem)
+		return -EINVAL;
+
+	ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+	if (ret)
+		return -EINVAL;
+
+	*pmem = mem;
+
+	return 0;
+}
+
+static void tce_iommu_unuse_page_v2(struct iommu_table *tbl,
+		unsigned long entry)
+{
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	int ret;
+	unsigned long hpa = 0;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+	if (!pua || !current || !current->mm)
+		return;
+
+	ret = tce_iommu_prereg_ua_to_hpa(*pua, IOMMU_PAGE_SIZE(tbl),
+			&hpa, &mem);
+	if (ret)
+		pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
+				__func__, *pua, entry, ret);
+	if (mem)
+		mm_iommu_mapped_dec(mem);
+
+	*pua = 0;
+}
+
+static int tce_iommu_clear(struct tce_container *container,
+		struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	unsigned long oldhpa;
+	long ret;
+	enum dma_data_direction direction;
+
+	for ( ; pages; --pages, ++entry) {
+		direction = DMA_NONE;
+		oldhpa = 0;
+		ret = iommu_tce_xchg(tbl, entry, &oldhpa, &direction);
+		if (ret)
+			continue;
+
+		if (direction == DMA_NONE)
+			continue;
+
+		if (container->v2) {
+			tce_iommu_unuse_page_v2(tbl, entry);
+			continue;
+		}
+
+		tce_iommu_unuse_page(container, oldhpa);
+	}
+
+	return 0;
+}
+
+static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
+{
+	struct page *page = NULL;
+	enum dma_data_direction direction = iommu_tce_direction(tce);
+
+	if (get_user_pages_fast(tce & PAGE_MASK, 1,
+			direction != DMA_TO_DEVICE, &page) != 1)
+		return -EFAULT;
+
+	*hpa = __pa((unsigned long) page_address(page));
+
+	return 0;
+}
+
+static long tce_iommu_build(struct tce_container *container,
+		struct iommu_table *tbl,
+		unsigned long entry, unsigned long tce, unsigned long pages,
+		enum dma_data_direction direction)
+{
+	long i, ret = 0;
+	struct page *page;
+	unsigned long hpa;
+	enum dma_data_direction dirtmp;
+
+	for (i = 0; i < pages; ++i) {
+		unsigned long offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
+
+		ret = tce_iommu_use_page(tce, &hpa);
+		if (ret)
+			break;
+
+		page = pfn_to_page(hpa >> PAGE_SHIFT);
+		if (!tce_page_is_contained(page, tbl->it_page_shift)) {
+			ret = -EPERM;
+			break;
+		}
+
+		hpa |= offset;
+		dirtmp = direction;
+		ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
+		if (ret) {
+			tce_iommu_unuse_page(container, hpa);
+			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
+					__func__, entry << tbl->it_page_shift,
+					tce, ret);
+			break;
+		}
+
+		if (dirtmp != DMA_NONE)
+			tce_iommu_unuse_page(container, hpa);
+
+		tce += IOMMU_PAGE_SIZE(tbl);
+	}
+
+	if (ret)
+		tce_iommu_clear(container, tbl, entry, i);
+
+	return ret;
+}
+
+static long tce_iommu_build_v2(struct tce_container *container,
+		struct iommu_table *tbl,
+		unsigned long entry, unsigned long tce, unsigned long pages,
+		enum dma_data_direction direction)
+{
+	long i, ret = 0;
+	struct page *page;
+	unsigned long hpa;
+	enum dma_data_direction dirtmp;
+
+	for (i = 0; i < pages; ++i) {
+		struct mm_iommu_table_group_mem_t *mem = NULL;
+		unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl,
+				entry + i);
+
+		ret = tce_iommu_prereg_ua_to_hpa(tce, IOMMU_PAGE_SIZE(tbl),
+				&hpa, &mem);
+		if (ret)
+			break;
+
+		page = pfn_to_page(hpa >> PAGE_SHIFT);
+		if (!tce_page_is_contained(page, tbl->it_page_shift)) {
+			ret = -EPERM;
+			break;
+		}
+
+		/* Preserve offset within IOMMU page */
+		hpa |= tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
+		dirtmp = direction;
+
+		/* The registered region is being unregistered */
+		if (mm_iommu_mapped_inc(mem))
+			break;
+
+		ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
+		if (ret) {
+			/* dirtmp cannot be DMA_NONE here */
+			tce_iommu_unuse_page_v2(tbl, entry + i);
+			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
+					__func__, entry << tbl->it_page_shift,
+					tce, ret);
+			break;
+		}
+
+		if (dirtmp != DMA_NONE)
+			tce_iommu_unuse_page_v2(tbl, entry + i);
+
+		*pua = tce;
+
+		tce += IOMMU_PAGE_SIZE(tbl);
+	}
+
+	if (ret)
+		tce_iommu_clear(container, tbl, entry, i);
+
+	return ret;
+}
+
+static long tce_iommu_create_table(struct tce_container *container,
+			struct iommu_table_group *table_group,
+			int num,
+			__u32 page_shift,
+			__u64 window_size,
+			__u32 levels,
+			struct iommu_table **ptbl)
+{
+	long ret, table_size;
+
+	table_size = table_group->ops->get_table_size(page_shift, window_size,
+			levels);
+	if (!table_size)
+		return -EINVAL;
+
+	ret = try_increment_locked_vm(table_size >> PAGE_SHIFT);
+	if (ret)
+		return ret;
+
+	ret = table_group->ops->create_table(table_group, num,
+			page_shift, window_size, levels, ptbl);
+
+	WARN_ON(!ret && !(*ptbl)->it_ops->free);
+	WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size));
+
+	if (!ret && container->v2) {
+		ret = tce_iommu_userspace_view_alloc(*ptbl);
+		if (ret)
+			(*ptbl)->it_ops->free(*ptbl);
+	}
+
+	if (ret)
+		decrement_locked_vm(table_size >> PAGE_SHIFT);
+
+	return ret;
+}
+
+static void tce_iommu_free_table(struct iommu_table *tbl)
+{
+	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
+
+	tce_iommu_userspace_view_free(tbl);
+	tbl->it_ops->free(tbl);
+	decrement_locked_vm(pages);
+}
+
+static long tce_iommu_create_window(struct tce_container *container,
+		__u32 page_shift, __u64 window_size, __u32 levels,
+		__u64 *start_addr)
+{
+	struct tce_iommu_group *tcegrp;
+	struct iommu_table_group *table_group;
+	struct iommu_table *tbl = NULL;
+	long ret, num;
+
+	num = tce_iommu_find_free_table(container);
+	if (num < 0)
+		return num;
+
+	/* Get the first group for ops::create_table */
+	tcegrp = list_first_entry(&container->group_list,
+			struct tce_iommu_group, next);
+	table_group = iommu_group_get_iommudata(tcegrp->grp);
+	if (!table_group)
+		return -EFAULT;
+
+	if (!(table_group->pgsizes & (1ULL << page_shift)))
+		return -EINVAL;
+
+	if (!table_group->ops->set_window || !table_group->ops->unset_window ||
+			!table_group->ops->get_table_size ||
+			!table_group->ops->create_table)
+		return -EPERM;
+
+	/* Create TCE table */
+	ret = tce_iommu_create_table(container, table_group, num,
+			page_shift, window_size, levels, &tbl);
+	if (ret)
+		return ret;
+
+	BUG_ON(!tbl->it_ops->free);
+
+	/*
+	 * Program the table to every group.
+	 * Groups have been tested for compatibility at the attach time.
+	 */
+	list_for_each_entry(tcegrp, &container->group_list, next) {
+		table_group = iommu_group_get_iommudata(tcegrp->grp);
+
+		ret = table_group->ops->set_window(table_group, num, tbl);
+		if (ret)
+			goto unset_exit;
+	}
+
+	container->tables[num] = tbl;
+
+	/* Return start address assigned by platform in create_table() */
+	*start_addr = tbl->it_offset << tbl->it_page_shift;
+
+	return 0;
+
+unset_exit:
+	list_for_each_entry(tcegrp, &container->group_list, next) {
+		table_group = iommu_group_get_iommudata(tcegrp->grp);
+		table_group->ops->unset_window(table_group, num);
+	}
+	tce_iommu_free_table(tbl);
+
+	return ret;
+}
+
+static long tce_iommu_remove_window(struct tce_container *container,
+		__u64 start_addr)
+{
+	struct iommu_table_group *table_group = NULL;
+	struct iommu_table *tbl;
+	struct tce_iommu_group *tcegrp;
+	int num;
+
+	num = tce_iommu_find_table(container, start_addr, &tbl);
+	if (num < 0)
+		return -EINVAL;
+
+	BUG_ON(!tbl->it_size);
+
+	/* Detach groups from IOMMUs */
+	list_for_each_entry(tcegrp, &container->group_list, next) {
+		table_group = iommu_group_get_iommudata(tcegrp->grp);
+
+		/*
+		 * SPAPR TCE IOMMU exposes the default DMA window to
+		 * the guest via dma32_window_start/size of
+		 * VFIO_IOMMU_SPAPR_TCE_GET_INFO. Some platforms allow
+		 * the userspace to remove this window, some do not so
+		 * here we check for the platform capability.
+		 */
+		if (!table_group->ops || !table_group->ops->unset_window)
+			return -EPERM;
+
+		table_group->ops->unset_window(table_group, num);
+	}
+
+	/* Free table */
+	tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
+	tce_iommu_free_table(tbl);
+	container->tables[num] = NULL;
+
+	return 0;
+}
+
 static long tce_iommu_ioctl(void *iommu_data,
 				 unsigned int cmd, unsigned long arg)
 {
 	struct tce_container *container = iommu_data;
-	unsigned long minsz;
+	unsigned long minsz, ddwsz;
 	long ret;
 
 	switch (cmd) {
 	case VFIO_CHECK_EXTENSION:
 		switch (arg) {
 		case VFIO_SPAPR_TCE_IOMMU:
+		case VFIO_SPAPR_TCE_v2_IOMMU:
 			ret = 1;
 			break;
 		default:
@@ -169,9 +732,17 @@ static long tce_iommu_ioctl(void *iommu_data,
 
 	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
 		struct vfio_iommu_spapr_tce_info info;
-		struct iommu_table *tbl = container->tbl;
+		struct tce_iommu_group *tcegrp;
+		struct iommu_table_group *table_group;
+
+		if (!tce_groups_attached(container))
+			return -ENXIO;
+
+		tcegrp = list_first_entry(&container->group_list,
+				struct tce_iommu_group, next);
+		table_group = iommu_group_get_iommudata(tcegrp->grp);
 
-		if (WARN_ON(!tbl))
+		if (!table_group)
 			return -ENXIO;
 
 		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
@@ -183,9 +754,24 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT_4K;
-		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT_4K;
+		info.dma32_window_start = table_group->tce32_start;
+		info.dma32_window_size = table_group->tce32_size;
 		info.flags = 0;
+		memset(&info.ddw, 0, sizeof(info.ddw));
+
+		if (table_group->max_dynamic_windows_supported &&
+				container->v2) {
+			info.flags |= VFIO_IOMMU_SPAPR_INFO_DDW;
+			info.ddw.pgsizes = table_group->pgsizes;
+			info.ddw.max_dynamic_windows_supported =
+				table_group->max_dynamic_windows_supported;
+			info.ddw.levels = table_group->max_levels;
+		}
+
+		ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info, ddw);
+
+		if (info.argsz >= ddwsz)
+			minsz = ddwsz;
 
 		if (copy_to_user((void __user *)arg, &info, minsz))
 			return -EFAULT;
@@ -194,13 +780,12 @@ static long tce_iommu_ioctl(void *iommu_data,
 	}
 	case VFIO_IOMMU_MAP_DMA: {
 		struct vfio_iommu_type1_dma_map param;
-		struct iommu_table *tbl = container->tbl;
-		unsigned long tce, i;
+		struct iommu_table *tbl = NULL;
+		long num;
+		enum dma_data_direction direction;
 
-		if (!tbl)
-			return -ENXIO;
-
-		BUG_ON(!tbl->it_group);
+		if (!container->enabled)
+			return -EPERM;
 
 		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
 
@@ -214,32 +799,43 @@ static long tce_iommu_ioctl(void *iommu_data,
 				VFIO_DMA_MAP_FLAG_WRITE))
 			return -EINVAL;
 
-		if ((param.size & ~IOMMU_PAGE_MASK_4K) ||
-				(param.vaddr & ~IOMMU_PAGE_MASK_4K))
+		num = tce_iommu_find_table(container, param.iova, &tbl);
+		if (num < 0)
+			return -ENXIO;
+
+		if ((param.size & ~IOMMU_PAGE_MASK(tbl)) ||
+				(param.vaddr & ~IOMMU_PAGE_MASK(tbl)))
 			return -EINVAL;
 
 		/* iova is checked by the IOMMU API */
-		tce = param.vaddr;
-		if (param.flags & VFIO_DMA_MAP_FLAG_READ)
-			tce |= TCE_PCI_READ;
-		if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
-			tce |= TCE_PCI_WRITE;
+		if (param.flags & VFIO_DMA_MAP_FLAG_READ) {
+			if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
+				direction = DMA_BIDIRECTIONAL;
+			else
+				direction = DMA_TO_DEVICE;
+		} else {
+			if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
+				direction = DMA_FROM_DEVICE;
+			else
+				return -EINVAL;
+		}
 
-		ret = iommu_tce_put_param_check(tbl, param.iova, tce);
+		ret = iommu_tce_put_param_check(tbl, param.iova, param.vaddr);
 		if (ret)
 			return ret;
 
-		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) {
-			ret = iommu_put_tce_user_mode(tbl,
-					(param.iova >> IOMMU_PAGE_SHIFT_4K) + i,
-					tce);
-			if (ret)
-				break;
-			tce += IOMMU_PAGE_SIZE_4K;
-		}
-		if (ret)
-			iommu_clear_tces_and_put_pages(tbl,
-					param.iova >> IOMMU_PAGE_SHIFT_4K, i);
+		if (container->v2)
+			ret = tce_iommu_build_v2(container, tbl,
+					param.iova >> tbl->it_page_shift,
+					param.vaddr,
+					param.size >> tbl->it_page_shift,
+					direction);
+		else
+			ret = tce_iommu_build(container, tbl,
+					param.iova >> tbl->it_page_shift,
+					param.vaddr,
+					param.size >> tbl->it_page_shift,
+					direction);
 
 		iommu_flush_tce(tbl);
 
@@ -247,10 +843,11 @@ static long tce_iommu_ioctl(void *iommu_data,
 	}
 	case VFIO_IOMMU_UNMAP_DMA: {
 		struct vfio_iommu_type1_dma_unmap param;
-		struct iommu_table *tbl = container->tbl;
+		struct iommu_table *tbl = NULL;
+		long num;
 
-		if (WARN_ON(!tbl))
-			return -ENXIO;
+		if (!container->enabled)
+			return -EPERM;
 
 		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
 				size);
@@ -265,22 +862,81 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (param.flags)
 			return -EINVAL;
 
-		if (param.size & ~IOMMU_PAGE_MASK_4K)
+		num = tce_iommu_find_table(container, param.iova, &tbl);
+		if (num < 0)
+			return -ENXIO;
+
+		if (param.size & ~IOMMU_PAGE_MASK(tbl))
 			return -EINVAL;
 
 		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
-				param.size >> IOMMU_PAGE_SHIFT_4K);
+				param.size >> tbl->it_page_shift);
 		if (ret)
 			return ret;
 
-		ret = iommu_clear_tces_and_put_pages(tbl,
-				param.iova >> IOMMU_PAGE_SHIFT_4K,
-				param.size >> IOMMU_PAGE_SHIFT_4K);
+		ret = tce_iommu_clear(container, tbl,
+				param.iova >> tbl->it_page_shift,
+				param.size >> tbl->it_page_shift);
 		iommu_flush_tce(tbl);
 
 		return ret;
 	}
+	case VFIO_IOMMU_SPAPR_REGISTER_MEMORY: {
+		struct vfio_iommu_spapr_register_memory param;
+
+		if (!container->v2)
+			break;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
+				size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		/* No flag is supported now */
+		if (param.flags)
+			return -EINVAL;
+
+		mutex_lock(&container->lock);
+		ret = tce_iommu_register_pages(container, param.vaddr,
+				param.size);
+		mutex_unlock(&container->lock);
+
+		return ret;
+	}
+	case VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY: {
+		struct vfio_iommu_spapr_register_memory param;
+
+		if (!container->v2)
+			break;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
+				size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		/* No flag is supported now */
+		if (param.flags)
+			return -EINVAL;
+
+		mutex_lock(&container->lock);
+		ret = tce_iommu_unregister_pages(container, param.vaddr,
+				param.size);
+		mutex_unlock(&container->lock);
+
+		return ret;
+	}
 	case VFIO_IOMMU_ENABLE:
+		if (container->v2)
+			break;
+
 		mutex_lock(&container->lock);
 		ret = tce_iommu_enable(container);
 		mutex_unlock(&container->lock);
@@ -288,48 +944,280 @@ static long tce_iommu_ioctl(void *iommu_data,
 
 
 	case VFIO_IOMMU_DISABLE:
+		if (container->v2)
+			break;
+
 		mutex_lock(&container->lock);
 		tce_iommu_disable(container);
 		mutex_unlock(&container->lock);
 		return 0;
-	case VFIO_EEH_PE_OP:
-		if (!container->tbl || !container->tbl->it_group)
-			return -ENODEV;
 
-		return vfio_spapr_iommu_eeh_ioctl(container->tbl->it_group,
-						  cmd, arg);
+	case VFIO_EEH_PE_OP: {
+		struct tce_iommu_group *tcegrp;
+
+		ret = 0;
+		list_for_each_entry(tcegrp, &container->group_list, next) {
+			ret = vfio_spapr_iommu_eeh_ioctl(tcegrp->grp,
+					cmd, arg);
+			if (ret)
+				return ret;
+		}
+		return ret;
+	}
+
+	case VFIO_IOMMU_SPAPR_TCE_CREATE: {
+		struct vfio_iommu_spapr_tce_create create;
+
+		if (!container->v2)
+			break;
+
+		if (!tce_groups_attached(container))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_tce_create,
+				start_addr);
+
+		if (copy_from_user(&create, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (create.argsz < minsz)
+			return -EINVAL;
+
+		if (create.flags)
+			return -EINVAL;
+
+		mutex_lock(&container->lock);
+
+		ret = tce_iommu_create_window(container, create.page_shift,
+				create.window_size, create.levels,
+				&create.start_addr);
+
+		mutex_unlock(&container->lock);
+
+		if (!ret && copy_to_user((void __user *)arg, &create, minsz))
+			ret = -EFAULT;
+
+		return ret;
+	}
+	case VFIO_IOMMU_SPAPR_TCE_REMOVE: {
+		struct vfio_iommu_spapr_tce_remove remove;
+
+		if (!container->v2)
+			break;
+
+		if (!tce_groups_attached(container))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_tce_remove,
+				start_addr);
+
+		if (copy_from_user(&remove, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (remove.argsz < minsz)
+			return -EINVAL;
+
+		if (remove.flags)
+			return -EINVAL;
+
+		mutex_lock(&container->lock);
+
+		ret = tce_iommu_remove_window(container, remove.start_addr);
+
+		mutex_unlock(&container->lock);
+
+		return ret;
+	}
 	}
 
 	return -ENOTTY;
 }
 
+static void tce_iommu_release_ownership(struct tce_container *container,
+		struct iommu_table_group *table_group)
+{
+	int i;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = container->tables[i];
+
+		if (!tbl)
+			continue;
+
+		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
+		tce_iommu_userspace_view_free(tbl);
+		if (tbl->it_map)
+			iommu_release_ownership(tbl);
+
+		container->tables[i] = NULL;
+	}
+}
+
+static int tce_iommu_take_ownership(struct tce_container *container,
+		struct iommu_table_group *table_group)
+{
+	int i, j, rc = 0;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = table_group->tables[i];
+
+		if (!tbl || !tbl->it_map)
+			continue;
+
+		rc = tce_iommu_userspace_view_alloc(tbl);
+		if (!rc)
+			rc = iommu_take_ownership(tbl);
+
+		if (rc) {
+			for (j = 0; j < i; ++j)
+				iommu_release_ownership(
+						table_group->tables[j]);
+
+			return rc;
+		}
+	}
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
+		container->tables[i] = table_group->tables[i];
+
+	return 0;
+}
+
+static void tce_iommu_release_ownership_ddw(struct tce_container *container,
+		struct iommu_table_group *table_group)
+{
+	long i;
+
+	if (!table_group->ops->unset_window) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
+		table_group->ops->unset_window(table_group, i);
+
+	table_group->ops->release_ownership(table_group);
+}
+
+static long tce_iommu_take_ownership_ddw(struct tce_container *container,
+		struct iommu_table_group *table_group)
+{
+	long i, ret = 0;
+	struct iommu_table *tbl = NULL;
+
+	if (!table_group->ops->create_table || !table_group->ops->set_window ||
+			!table_group->ops->release_ownership) {
+		WARN_ON_ONCE(1);
+		return -EFAULT;
+	}
+
+	table_group->ops->take_ownership(table_group);
+
+	/*
+	 * If it the first group attached, check if there is
+	 * a default DMA window and create one if none as
+	 * the userspace expects it to exist.
+	 */
+	if (!tce_groups_attached(container) && !container->tables[0]) {
+		ret = tce_iommu_create_table(container,
+				table_group,
+				0, /* window number */
+				IOMMU_PAGE_SHIFT_4K,
+				table_group->tce32_size,
+				1, /* default levels */
+				&tbl);
+		if (ret)
+			goto release_exit;
+		else
+			container->tables[0] = tbl;
+	}
+
+	/* Set all windows to the new group */
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		tbl = container->tables[i];
+
+		if (!tbl)
+			continue;
+
+		/* Set the default window to a new group */
+		ret = table_group->ops->set_window(table_group, i, tbl);
+		if (ret)
+			goto release_exit;
+	}
+
+	return 0;
+
+release_exit:
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
+		table_group->ops->unset_window(table_group, i);
+
+	table_group->ops->release_ownership(table_group);
+
+	return ret;
+}
+
 static int tce_iommu_attach_group(void *iommu_data,
 		struct iommu_group *iommu_group)
 {
 	int ret;
 	struct tce_container *container = iommu_data;
-	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+	struct iommu_table_group *table_group;
+	struct tce_iommu_group *tcegrp = NULL;
 
-	BUG_ON(!tbl);
 	mutex_lock(&container->lock);
 
 	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
 			iommu_group_id(iommu_group), iommu_group); */
-	if (container->tbl) {
-		pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
-				iommu_group_id(container->tbl->it_group),
-				iommu_group_id(iommu_group));
-		ret = -EBUSY;
-	} else if (container->enabled) {
-		pr_err("tce_vfio: attaching group #%u to enabled container\n",
-				iommu_group_id(iommu_group));
+	table_group = iommu_group_get_iommudata(iommu_group);
+
+	if (tce_groups_attached(container) && (!table_group->ops ||
+			!table_group->ops->take_ownership ||
+			!table_group->ops->release_ownership)) {
 		ret = -EBUSY;
-	} else {
-		ret = iommu_take_ownership(tbl);
-		if (!ret)
-			container->tbl = tbl;
+		goto unlock_exit;
+	}
+
+	/* Check if new group has the same iommu_ops (i.e. compatible) */
+	list_for_each_entry(tcegrp, &container->group_list, next) {
+		struct iommu_table_group *table_group_tmp;
+
+		if (tcegrp->grp == iommu_group) {
+			pr_warn("tce_vfio: Group %d is already attached\n",
+					iommu_group_id(iommu_group));
+			ret = -EBUSY;
+			goto unlock_exit;
+		}
+		table_group_tmp = iommu_group_get_iommudata(tcegrp->grp);
+		if (table_group_tmp->ops != table_group->ops) {
+			pr_warn("tce_vfio: Group %d is incompatible with group %d\n",
+					iommu_group_id(iommu_group),
+					iommu_group_id(tcegrp->grp));
+			ret = -EPERM;
+			goto unlock_exit;
+		}
+	}
+
+	tcegrp = kzalloc(sizeof(*tcegrp), GFP_KERNEL);
+	if (!tcegrp) {
+		ret = -ENOMEM;
+		goto unlock_exit;
 	}
 
+	if (!table_group->ops || !table_group->ops->take_ownership ||
+			!table_group->ops->release_ownership)
+		ret = tce_iommu_take_ownership(container, table_group);
+	else
+		ret = tce_iommu_take_ownership_ddw(container, table_group);
+
+	if (!ret) {
+		tcegrp->grp = iommu_group;
+		list_add(&tcegrp->next, &container->group_list);
+	}
+
+unlock_exit:
+	if (ret && tcegrp)
+		kfree(tcegrp);
+
 	mutex_unlock(&container->lock);
 
 	return ret;
@@ -339,26 +1227,37 @@ static void tce_iommu_detach_group(void *iommu_data,
 		struct iommu_group *iommu_group)
 {
 	struct tce_container *container = iommu_data;
-	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+	struct iommu_table_group *table_group;
+	bool found = false;
+	struct tce_iommu_group *tcegrp;
 
-	BUG_ON(!tbl);
 	mutex_lock(&container->lock);
-	if (tbl != container->tbl) {
-		pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
-				iommu_group_id(iommu_group),
-				iommu_group_id(tbl->it_group));
-	} else {
-		if (container->enabled) {
-			pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
-					iommu_group_id(tbl->it_group));
-			tce_iommu_disable(container);
+
+	list_for_each_entry(tcegrp, &container->group_list, next) {
+		if (tcegrp->grp == iommu_group) {
+			found = true;
+			break;
 		}
+	}
 
-		/* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
-				iommu_group_id(iommu_group), iommu_group); */
-		container->tbl = NULL;
-		iommu_release_ownership(tbl);
+	if (!found) {
+		pr_warn("tce_vfio: detaching unattached group #%u\n",
+				iommu_group_id(iommu_group));
+		goto unlock_exit;
 	}
+
+	list_del(&tcegrp->next);
+	kfree(tcegrp);
+
+	table_group = iommu_group_get_iommudata(iommu_group);
+	BUG_ON(!table_group);
+
+	if (!table_group->ops || !table_group->ops->release_ownership)
+		tce_iommu_release_ownership(container, table_group);
+	else
+		tce_iommu_release_ownership_ddw(container, table_group);
+
+unlock_exit:
 	mutex_unlock(&container->lock);
 }
 
diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c
index 5fa42db769ee..38edeb4729a9 100644
--- a/drivers/vfio/vfio_spapr_eeh.c
+++ b/drivers/vfio/vfio_spapr_eeh.c
@@ -85,6 +85,16 @@ long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
 		case VFIO_EEH_PE_CONFIGURE:
 			ret = eeh_pe_configure(pe);
 			break;
+		case VFIO_EEH_PE_INJECT_ERR:
+			minsz = offsetofend(struct vfio_eeh_pe_op, err.mask);
+			if (op.argsz < minsz)
+				return -EINVAL;
+			if (copy_from_user(&op, (void __user *)arg, minsz))
+				return -EFAULT;
+
+			ret = eeh_pe_inject_err(pe, op.err.type, op.err.func,
+						op.err.addr, op.err.mask);
+			break;
 		default:
 			ret = -EINVAL;
 		}