Merge remote-tracking branch 'linus/master' into merge

Conflicts:
	Documentation/hwmon/ina2xx
	arch/powerpc/Kconfig
	arch/powerpc/boot/dts/b4860emu.dts
	arch/powerpc/boot/dts/b4qds.dtsi
	arch/powerpc/boot/dts/fsl/b4si-post.dtsi
	arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
	arch/powerpc/boot/dts/p1023rdb.dts
	arch/powerpc/boot/dts/t4240emu.dts
	arch/powerpc/boot/dts/t4240qds.dts
	arch/powerpc/configs/85xx/p1023_defconfig
	arch/powerpc/configs/corenet32_smp_defconfig
	arch/powerpc/configs/corenet64_smp_defconfig
	arch/powerpc/configs/mpc85xx_smp_defconfig
	arch/powerpc/include/asm/cputable.h
	arch/powerpc/include/asm/device.h
	arch/powerpc/include/asm/epapr_hcalls.h
	arch/powerpc/include/asm/kvm_host.h
	arch/powerpc/include/asm/mpic.h
	arch/powerpc/include/asm/pci.h
	arch/powerpc/include/asm/ppc-opcode.h
	arch/powerpc/include/asm/ppc_asm.h
	arch/powerpc/include/asm/reg_booke.h
	arch/powerpc/kernel/epapr_paravirt.c
	arch/powerpc/kernel/process.c
	arch/powerpc/kernel/prom.c
	arch/powerpc/kernel/setup-common.c
	arch/powerpc/kernel/setup_32.c
	arch/powerpc/kernel/setup_64.c
	arch/powerpc/kernel/smp.c
	arch/powerpc/kernel/swsusp_asm64.S
	arch/powerpc/kernel/swsusp_booke.S
	arch/powerpc/kvm/book3s_pr.c
	arch/powerpc/kvm/booke.c
	arch/powerpc/kvm/booke.h
	arch/powerpc/kvm/e500.c
	arch/powerpc/kvm/e500.h
	arch/powerpc/kvm/e500_emulate.c
	arch/powerpc/kvm/e500mc.c
	arch/powerpc/kvm/powerpc.c
	arch/powerpc/perf/e6500-pmu.c
	arch/powerpc/platforms/85xx/Kconfig
	arch/powerpc/platforms/85xx/Makefile
	arch/powerpc/platforms/85xx/b4_qds.c
	arch/powerpc/platforms/85xx/c293pcie.c
	arch/powerpc/platforms/85xx/corenet_ds.c
	arch/powerpc/platforms/85xx/corenet_ds.h
	arch/powerpc/platforms/85xx/p1023_rds.c
	arch/powerpc/platforms/85xx/p2041_rdb.c
	arch/powerpc/platforms/85xx/p3041_ds.c
	arch/powerpc/platforms/85xx/p4080_ds.c
	arch/powerpc/platforms/85xx/p5020_ds.c
	arch/powerpc/platforms/85xx/p5040_ds.c
	arch/powerpc/platforms/85xx/smp.c
	arch/powerpc/platforms/85xx/t4240_qds.c
	arch/powerpc/platforms/Kconfig
	arch/powerpc/sysdev/Makefile
	arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
	arch/powerpc/sysdev/fsl_msi.c
	arch/powerpc/sysdev/fsl_pci.c
	arch/powerpc/sysdev/fsl_pci.h
	arch/powerpc/sysdev/fsl_soc.h
	arch/powerpc/sysdev/mpic.c
	arch/powerpc/sysdev/mpic_timer.c
	drivers/Kconfig
	drivers/clk/Kconfig
	drivers/clk/clk-ppc-corenet.c
	drivers/cpufreq/Kconfig.powerpc
	drivers/cpufreq/Makefile
	drivers/cpufreq/ppc-corenet-cpufreq.c
	drivers/crypto/caam/Kconfig
	drivers/crypto/caam/Makefile
	drivers/crypto/caam/ctrl.c
	drivers/crypto/caam/desc_constr.h
	drivers/crypto/caam/intern.h
	drivers/crypto/caam/jr.c
	drivers/crypto/caam/regs.h
	drivers/dma/fsldma.c
	drivers/hwmon/ina2xx.c
	drivers/iommu/Kconfig
	drivers/iommu/fsl_pamu.c
	drivers/iommu/fsl_pamu.h
	drivers/iommu/fsl_pamu_domain.c
	drivers/iommu/fsl_pamu_domain.h
	drivers/misc/Makefile
	drivers/mmc/card/block.c
	drivers/mmc/core/core.c
	drivers/mmc/host/sdhci-esdhc.h
	drivers/mmc/host/sdhci-pltfm.c
	drivers/mtd/nand/fsl_ifc_nand.c
	drivers/net/ethernet/freescale/gianfar.c
	drivers/net/ethernet/freescale/gianfar.h
	drivers/net/ethernet/freescale/gianfar_ethtool.c
	drivers/net/phy/at803x.c
	drivers/net/phy/phy_device.c
	drivers/net/phy/vitesse.c
	drivers/pci/msi.c
	drivers/staging/Kconfig
	drivers/staging/Makefile
	drivers/uio/Kconfig
	drivers/uio/Makefile
	drivers/uio/uio.c
	drivers/usb/host/ehci-fsl.c
	drivers/vfio/Kconfig
	drivers/vfio/Makefile
	include/crypto/algapi.h
	include/linux/iommu.h
	include/linux/mmc/sdhci.h
	include/linux/msi.h
	include/linux/netdev_features.h
	include/linux/phy.h
	include/linux/skbuff.h
	include/net/ip.h
	include/uapi/linux/vfio.h
	net/core/ethtool.c
	net/ipv4/route.c
	net/ipv6/route.c

8 files changed, 1205 insertions, 279 deletions

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index aba1d96..2990cb1 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -13,12 +13,18 @@ config VFIO_IOMMU_DUMMY
 	depends on VFIO
 	default n
 
+config VFIO_IOMMU_SPAPR_TCE
+	tristate
+	depends on VFIO && SPAPR_TCE_IOMMU
+	default n
+
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	depends on IOMMU_API
 	select VFIO_IOMMU_TYPE1 if X86
 	select VFIO_IOMMU_FSL_PAMU if FSL_PAMU
 	select VFIO_IOMMU_DUMMY if DUMMY_IOMMU
+	select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/vfio.txt for more details.
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index e4093c5..d997a16 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -2,5 +2,6 @@ obj-$(CONFIG_VFIO) += vfio.o
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_FSL_PAMU) += vfio_iommu_fsl_pamu.o
 obj-$(CONFIG_VFIO_IOMMU_DUMMY) += vfio_iommu_dummy.o
+obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
 obj-$(CONFIG_VFIO_PCI) += pci/
 obj-$(CONFIG_VFIO_FSL_PCI_EP) += fsl_pci_ep/
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index ac37254..6ab71b9 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -13,6 +13,7 @@
 
 #include <linux/device.h>
 #include <linux/eventfd.h>
+#include <linux/file.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
 #include <linux/module.h>
@@ -137,8 +138,27 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	 */
 	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
 
-	if (vdev->reset_works)
-		__pci_reset_function(pdev);
+	/*
+	 * Careful, device_lock may already be held.  This is the case if
+	 * a driver unbind is blocked.  Try to get the locks ourselves to
+	 * prevent a deadlock.
+	 */
+	if (vdev->reset_works) {
+		bool reset_done = false;
+
+		if (pci_cfg_access_trylock(pdev)) {
+			if (device_trylock(&pdev->dev)) {
+				__pci_reset_function_locked(pdev);
+				reset_done = true;
+				device_unlock(&pdev->dev);
+			}
+			pci_cfg_access_unlock(pdev);
+		}
+
+		if (!reset_done)
+			pr_warn("%s: Unable to acquire locks for reset of %s\n",
+				__func__, dev_name(&pdev->dev));
+	}
 
 	pci_restore_state(pdev);
 }
@@ -208,6 +228,110 @@ static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
 	return 0;
 }
 
+static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
+{
+	(*(int *)data)++;
+	return 0;
+}
+
+struct vfio_pci_fill_info {
+	int max;
+	int cur;
+	struct vfio_pci_dependent_device *devices;
+};
+
+static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_fill_info *fill = data;
+	struct iommu_group *iommu_group;
+
+	if (fill->cur == fill->max)
+		return -EAGAIN; /* Something changed, try again */
+
+	iommu_group = iommu_group_get(&pdev->dev);
+	if (!iommu_group)
+		return -EPERM; /* Cannot reset non-isolated devices */
+
+	fill->devices[fill->cur].group_id = iommu_group_id(iommu_group);
+	fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus);
+	fill->devices[fill->cur].bus = pdev->bus->number;
+	fill->devices[fill->cur].devfn = pdev->devfn;
+	fill->cur++;
+	iommu_group_put(iommu_group);
+	return 0;
+}
+
+struct vfio_pci_group_entry {
+	struct vfio_group *group;
+	int id;
+};
+
+struct vfio_pci_group_info {
+	int count;
+	struct vfio_pci_group_entry *groups;
+};
+
+static int vfio_pci_validate_devs(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_group_info *info = data;
+	struct iommu_group *group;
+	int id, i;
+
+	group = iommu_group_get(&pdev->dev);
+	if (!group)
+		return -EPERM;
+
+	id = iommu_group_id(group);
+
+	for (i = 0; i < info->count; i++)
+		if (info->groups[i].id == id)
+			break;
+
+	iommu_group_put(group);
+
+	return (i == info->count) ? -EINVAL : 0;
+}
+
+static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot)
+{
+	for (; pdev; pdev = pdev->bus->self)
+		if (pdev->bus == slot->bus)
+			return (pdev->slot == slot);
+	return false;
+}
+
+struct vfio_pci_walk_info {
+	int (*fn)(struct pci_dev *, void *data);
+	void *data;
+	struct pci_dev *pdev;
+	bool slot;
+	int ret;
+};
+
+static int vfio_pci_walk_wrapper(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_walk_info *walk = data;
+
+	if (!walk->slot || vfio_pci_dev_below_slot(pdev, walk->pdev->slot))
+		walk->ret = walk->fn(pdev, walk->data);
+
+	return walk->ret;
+}
+
+static int vfio_pci_for_each_slot_or_bus(struct pci_dev *pdev,
+					 int (*fn)(struct pci_dev *,
+						   void *data), void *data,
+					 bool slot)
+{
+	struct vfio_pci_walk_info walk = {
+		.fn = fn, .data = data, .pdev = pdev, .slot = slot, .ret = 0,
+	};
+
+	pci_walk_bus(pdev->bus, vfio_pci_walk_wrapper, &walk);
+
+	return walk.ret;
+}
+
 static long vfio_pci_ioctl(void *device_data,
 			   unsigned int cmd, unsigned long arg)
 {
@@ -388,10 +512,189 @@ static long vfio_pci_ioctl(void *device_data,
 
 		return ret;
 
-	} else if (cmd == VFIO_DEVICE_RESET)
+	} else if (cmd == VFIO_DEVICE_RESET) {
 		return vdev->reset_works ?
 			pci_reset_function(vdev->pdev) : -EINVAL;
 
+	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
+		struct vfio_pci_hot_reset_info hdr;
+		struct vfio_pci_fill_info fill = { 0 };
+		struct vfio_pci_dependent_device *devices = NULL;
+		bool slot = false;
+		int ret = 0;
+
+		minsz = offsetofend(struct vfio_pci_hot_reset_info, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz)
+			return -EINVAL;
+
+		hdr.flags = 0;
+
+		/* Can we do a slot or bus reset or neither? */
+		if (!pci_probe_reset_slot(vdev->pdev->slot))
+			slot = true;
+		else if (pci_probe_reset_bus(vdev->pdev->bus))
+			return -ENODEV;
+
+		/* How many devices are affected? */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_count_devs,
+						    &fill.max, slot);
+		if (ret)
+			return ret;
+
+		WARN_ON(!fill.max); /* Should always be at least one */
+
+		/*
+		 * If there's enough space, fill it now, otherwise return
+		 * -ENOSPC and the number of devices affected.
+		 */
+		if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) {
+			ret = -ENOSPC;
+			hdr.count = fill.max;
+			goto reset_info_exit;
+		}
+
+		devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL);
+		if (!devices)
+			return -ENOMEM;
+
+		fill.devices = devices;
+
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_fill_devs,
+						    &fill, slot);
+
+		/*
+		 * If a device was removed between counting and filling,
+		 * we may come up short of fill.max.  If a device was
+		 * added, we'll have a return of -EAGAIN above.
+		 */
+		if (!ret)
+			hdr.count = fill.cur;
+
+reset_info_exit:
+		if (copy_to_user((void __user *)arg, &hdr, minsz))
+			ret = -EFAULT;
+
+		if (!ret) {
+			if (copy_to_user((void __user *)(arg + minsz), devices,
+					 hdr.count * sizeof(*devices)))
+				ret = -EFAULT;
+		}
+
+		kfree(devices);
+		return ret;
+
+	} else if (cmd == VFIO_DEVICE_PCI_HOT_RESET) {
+		struct vfio_pci_hot_reset hdr;
+		int32_t *group_fds;
+		struct vfio_pci_group_entry *groups;
+		struct vfio_pci_group_info info;
+		bool slot = false;
+		int i, count = 0, ret = 0;
+
+		minsz = offsetofend(struct vfio_pci_hot_reset, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz || hdr.flags)
+			return -EINVAL;
+
+		/* Can we do a slot or bus reset or neither? */
+		if (!pci_probe_reset_slot(vdev->pdev->slot))
+			slot = true;
+		else if (pci_probe_reset_bus(vdev->pdev->bus))
+			return -ENODEV;
+
+		/*
+		 * We can't let userspace give us an arbitrarily large
+		 * buffer to copy, so verify how many we think there
+		 * could be.  Note groups can have multiple devices so
+		 * one group per device is the max.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_count_devs,
+						    &count, slot);
+		if (ret)
+			return ret;
+
+		/* Somewhere between 1 and count is OK */
+		if (!hdr.count || hdr.count > count)
+			return -EINVAL;
+
+		group_fds = kcalloc(hdr.count, sizeof(*group_fds), GFP_KERNEL);
+		groups = kcalloc(hdr.count, sizeof(*groups), GFP_KERNEL);
+		if (!group_fds || !groups) {
+			kfree(group_fds);
+			kfree(groups);
+			return -ENOMEM;
+		}
+
+		if (copy_from_user(group_fds, (void __user *)(arg + minsz),
+				   hdr.count * sizeof(*group_fds))) {
+			kfree(group_fds);
+			kfree(groups);
+			return -EFAULT;
+		}
+
+		/*
+		 * For each group_fd, get the group through the vfio external
+		 * user interface and store the group and iommu ID.  This
+		 * ensures the group is held across the reset.
+		 */
+		for (i = 0; i < hdr.count; i++) {
+			struct vfio_group *group;
+			struct fd f = fdget(group_fds[i]);
+			if (!f.file) {
+				ret = -EBADF;
+				break;
+			}
+
+			group = vfio_group_get_external_user(f.file);
+			fdput(f);
+			if (IS_ERR(group)) {
+				ret = PTR_ERR(group);
+				break;
+			}
+
+			groups[i].group = group;
+			groups[i].id = vfio_external_user_iommu_id(group);
+		}
+
+		kfree(group_fds);
+
+		/* release reference to groups on error */
+		if (ret)
+			goto hot_reset_release;
+
+		info.count = hdr.count;
+		info.groups = groups;
+
+		/*
+		 * Test whether all the affected devices are contained
+		 * by the set of groups provided by the user.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_validate_devs,
+						    &info, slot);
+		if (!ret)
+			/* User has access, do the reset */
+			ret = slot ? pci_reset_slot(vdev->pdev->slot) :
+				     pci_reset_bus(vdev->pdev->bus);
+
+hot_reset_release:
+		for (i--; i >= 0; i--)
+			vfio_group_put_external_user(groups[i].group);
+
+		kfree(groups);
+		return ret;
+	}
+
 	return -ENOTTY;
 }
 
@@ -499,7 +802,6 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	}
 
 	vma->vm_private_data = vdev;
-	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
 
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index affa347..ffd0632 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1012,6 +1012,7 @@ static int vfio_vc_cap_len(struct vfio_pci_device *vdev, u16 pos)
 static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
 {
 	struct pci_dev *pdev = vdev->pdev;
+	u32 dword;
 	u16 word;
 	u8 byte;
 	int ret;
@@ -1025,7 +1026,9 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
 			return pcibios_err_to_errno(ret);
 
 		if (PCI_X_CMD_VERSION(word)) {
-			vdev->extended_caps = true;
+			/* Test for extended capabilities */
+			pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+			vdev->extended_caps = (dword != 0);
 			return PCI_CAP_PCIX_SIZEOF_V2;
 		} else
 			return PCI_CAP_PCIX_SIZEOF_V0;
@@ -1037,9 +1040,11 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
 
 		return byte;
 	case PCI_CAP_ID_EXP:
-		/* length based on version */
-		vdev->extended_caps = true;
+		/* Test for extended capabilities */
+		pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+		vdev->extended_caps = (dword != 0);
 
+		/* length based on version */
 		if ((pcie_caps_reg(pdev) & PCI_EXP_FLAGS_VERS) == 1)
 			return PCI_CAP_EXP_ENDPOINT_SIZEOF_V1;
 		else
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 4bc704e..641bc87 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -130,8 +130,8 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 			 void (*thread)(struct vfio_pci_device *, void *),
 			 void *data, struct virqfd **pvirqfd, int fd)
 {
-	struct file *file = NULL;
-	struct eventfd_ctx *ctx = NULL;
+	struct fd irqfd;
+	struct eventfd_ctx *ctx;
 	struct virqfd *virqfd;
 	int ret = 0;
 	unsigned int events;
@@ -149,16 +149,16 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
 	INIT_WORK(&virqfd->inject, virqfd_inject);
 
-	file = eventfd_fget(fd);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
-		goto fail;
+	irqfd = fdget(fd);
+	if (!irqfd.file) {
+		ret = -EBADF;
+		goto err_fd;
 	}
 
-	ctx = eventfd_ctx_fileget(file);
+	ctx = eventfd_ctx_fileget(irqfd.file);
 	if (IS_ERR(ctx)) {
 		ret = PTR_ERR(ctx);
-		goto fail;
+		goto err_ctx;
 	}
 
 	virqfd->eventfd = ctx;
@@ -174,7 +174,7 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	if (*pvirqfd) {
 		spin_unlock_irq(&vdev->irqlock);
 		ret = -EBUSY;
-		goto fail;
+		goto err_busy;
 	}
 	*pvirqfd = virqfd;
 
@@ -187,7 +187,7 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
 	init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
 
-	events = file->f_op->poll(file, &virqfd->pt);
+	events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
 
 	/*
 	 * Check if there was an event already pending on the eventfd
@@ -202,17 +202,14 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	 * Do not drop the file until the irqfd is fully initialized,
 	 * otherwise we might race against the POLLHUP.
 	 */
-	fput(file);
+	fdput(irqfd);
 
 	return 0;
-
-fail:
-	if (ctx && !IS_ERR(ctx))
-		eventfd_ctx_put(ctx);
-
-	if (file && !IS_ERR(file))
-		fput(file);
-
+err_busy:
+	eventfd_ctx_put(ctx);
+err_ctx:
+	fdput(irqfd);
+err_fd:
 	kfree(virqfd);
 
 	return ret;
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 83f48ad..b23e9ff 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -76,6 +76,7 @@ struct vfio_group {
 	struct notifier_block		nb;
 	struct list_head		vfio_next;
 	struct list_head		container_next;
+	atomic_t			opened;
 };
 
 struct vfio_device {
@@ -206,6 +207,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 	INIT_LIST_HEAD(&group->device_list);
 	mutex_init(&group->device_lock);
 	atomic_set(&group->container_users, 0);
+	atomic_set(&group->opened, 0);
 	group->iommu_group = iommu_group;
 
 	group->nb.notifier_call = vfio_iommu_group_notifier;
@@ -494,27 +496,6 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
 	return 0;
 }
 
-static int vfio_group_nb_del_dev(struct vfio_group *group, struct device *dev)
-{
-	struct vfio_device *device;
-
-	/*
-	 * Expect to fall out here.  If a device was in use, it would
-	 * have been bound to a vfio sub-driver, which would have blocked
-	 * in .remove at vfio_del_group_dev.  Sanity check that we no
-	 * longer track the device, so it's safe to remove.
-	 */
-	device = vfio_group_get_device(group, dev);
-	if (likely(!device))
-		return 0;
-
-	WARN("Device %s removed from live group %d!\n", dev_name(dev),
-	     iommu_group_id(group->iommu_group));
-
-	vfio_device_put(device);
-	return 0;
-}
-
 static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
 {
 	/* We don't care what happens when the group isn't in use */
@@ -531,13 +512,11 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 	struct device *dev = data;
 
 	/*
-	 * Need to go through a group_lock lookup to get a reference or
-	 * we risk racing a group being removed.  Leave a WARN_ON for
-	 * debuging, but if the group no longer exists, a spurious notify
-	 * is harmless.
+	 * Need to go through a group_lock lookup to get a reference or we
+	 * risk racing a group being removed.  Ignore spurious notifies.
 	 */
 	group = vfio_group_try_get(group);
-	if (WARN_ON(!group))
+	if (!group)
 		return NOTIFY_OK;
 
 	switch (action) {
@@ -545,7 +524,13 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 		vfio_group_nb_add_dev(group, dev);
 		break;
 	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
-		vfio_group_nb_del_dev(group, dev);
+		/*
+		 * Nothing to do here.  If the device is in use, then the
+		 * vfio sub-driver should block the remove callback until
+		 * it is unused.  If the device is unused or attached to a
+		 * stub driver, then it should be released and we don't
+		 * care that it will be going away.
+		 */
 		break;
 	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
 		pr_debug("%s: Device %s, group %d binding to driver\n",
@@ -1126,7 +1111,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 		 * We can't use anon_inode_getfd() because we need to modify
 		 * the f_mode flags directly to allow more than just ioctls
 		 */
-		ret = get_unused_fd();
+		ret = get_unused_fd_flags(O_CLOEXEC);
 		if (ret < 0) {
 			device->ops->release(device->device_data);
 			break;
@@ -1238,12 +1223,22 @@ static long vfio_group_fops_compat_ioctl(struct file *filep,
 static int vfio_group_fops_open(struct inode *inode, struct file *filep)
 {
 	struct vfio_group *group;
+	int opened;
 
 	group = vfio_group_get_from_minor(iminor(inode));
 	if (!group)
 		return -ENODEV;
 
+	/* Do we need multiple instances of the group open?  Seems not. */
+	opened = atomic_cmpxchg(&group->opened, 0, 1);
+	if (opened) {
+		vfio_group_put(group);
+		return -EBUSY;
+	}
+
+	/* Is something still in use from a previous open? */
 	if (group->container) {
+		atomic_dec(&group->opened);
 		vfio_group_put(group);
 		return -EBUSY;
 	}
@@ -1261,6 +1256,8 @@ static int vfio_group_fops_release(struct inode *inode, struct file *filep)
 
 	vfio_group_try_dissolve_container(group);
 
+	atomic_dec(&group->opened);
+
 	vfio_group_put(group);
 
 	return 0;
@@ -1358,6 +1355,68 @@ static const struct file_operations vfio_device_fops = {
 };
 
 /**
+ * External user API, exported by symbols to be linked dynamically.
+ *
+ * The protocol includes:
+ *  1. do normal VFIO init operation:
+ *	- opening a new container;
+ *	- attaching group(s) to it;
+ *	- setting an IOMMU driver for a container.
+ * When IOMMU is set for a container, all groups in it are
+ * considered ready to use by an external user.
+ *
+ * 2. User space passes a group fd to an external user.
+ * The external user calls vfio_group_get_external_user()
+ * to verify that:
+ *	- the group is initialized;
+ *	- IOMMU is set for it.
+ * If both checks passed, vfio_group_get_external_user()
+ * increments the container user counter to prevent
+ * the VFIO group from disposal before KVM exits.
+ *
+ * 3. The external user calls vfio_external_user_iommu_id()
+ * to know an IOMMU ID.
+ *
+ * 4. When the external KVM finishes, it calls
+ * vfio_group_put_external_user() to release the VFIO group.
+ * This call decrements the container user counter.
+ */
+struct vfio_group *vfio_group_get_external_user(struct file *filep)
+{
+	struct vfio_group *group = filep->private_data;
+
+	if (filep->f_op != &vfio_group_fops)
+		return ERR_PTR(-EINVAL);
+
+	if (!atomic_inc_not_zero(&group->container_users))
+		return ERR_PTR(-EINVAL);
+
+	if (!group->container->iommu_driver ||
+			!vfio_group_viable(group)) {
+		atomic_dec(&group->container_users);
+		return ERR_PTR(-EINVAL);
+	}
+
+	vfio_group_get(group);
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
+
+void vfio_group_put_external_user(struct vfio_group *group)
+{
+	vfio_group_put(group);
+	vfio_group_try_dissolve_container(group);
+}
+EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
+
+int vfio_external_user_iommu_id(struct vfio_group *group)
+{
+	return iommu_group_id(group->iommu_group);
+}
+EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);
+
+/**
  * Module/class support
  */
 static char *vfio_devnode(struct device *dev, umode_t *mode)
@@ -1417,6 +1476,7 @@ static int __init vfio_init(void)
 	 * drivers.
 	 */
 	request_module_nowait("vfio_iommu_type1");
+	request_module_nowait("vfio_iommu_spapr_tce");
 
 	return 0;
 
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 0000000..bdae7a0
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,377 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2013 IBM Corp.  All rights reserved.
+ *     Author: Alexey Kardashevskiy <aik@ozlabs.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Derived from original vfio_iommu_type1.c:
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/err.h>
+#include <linux/vfio.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "aik@ozlabs.ru"
+#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group);
+
+/*
+ * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
+ *
+ * This code handles mapping and unmapping of user data buffers
+ * into DMA'ble space using the IOMMU
+ */
+
+/*
+ * The container descriptor supports only a single group per container.
+ * Required by the API as the container is not supplied with the IOMMU group
+ * at the moment of initialization.
+ */
+struct tce_container {
+	struct mutex lock;
+	struct iommu_table *tbl;
+	bool enabled;
+};
+
+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;
+
+	if (!current->mm)
+		return -ESRCH; /* process exited */
+
+	if (container->enabled)
+		return -EBUSY;
+
+	/*
+	 * When userspace pages are mapped into the IOMMU, they are effectively
+	 * locked memory, so, theoretically, we need to update the accounting
+	 * of locked pages on each map and unmap.  For powerpc, the map unmap
+	 * paths can be very hot, though, and the accounting would kill
+	 * performance, especially since it would be difficult to impossible
+	 * to handle the accounting in real mode only.
+	 *
+	 * To address that, rather than precisely accounting every page, we
+	 * instead account for a worst case on locked memory when the iommu is
+	 * enabled and disabled.  The worst case upper bound on locked memory
+	 * is the size of the whole iommu window, which is usually relatively
+	 * small (compared to total memory sizes) on POWER hardware.
+	 *
+	 * 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.
+	 */
+	down_write(&current->mm->mmap_sem);
+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> 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 {
+
+		current->mm->locked_vm += npages;
+		container->enabled = true;
+	}
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static void tce_iommu_disable(struct tce_container *container)
+{
+	if (!container->enabled)
+		return;
+
+	container->enabled = false;
+
+	if (!container->tbl || !current->mm)
+		return;
+
+	down_write(&current->mm->mmap_sem);
+	current->mm->locked_vm -= (container->tbl->it_size <<
+			IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	up_write(&current->mm->mmap_sem);
+}
+
+static void *tce_iommu_open(unsigned long arg)
+{
+	struct tce_container *container;
+
+	if (arg != VFIO_SPAPR_TCE_IOMMU) {
+		pr_err("tce_vfio: Wrong IOMMU type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	container = kzalloc(sizeof(*container), GFP_KERNEL);
+	if (!container)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&container->lock);
+
+	return container;
+}
+
+static void tce_iommu_release(void *iommu_data)
+{
+	struct tce_container *container = iommu_data;
+
+	WARN_ON(container->tbl && !container->tbl->it_group);
+	tce_iommu_disable(container);
+
+	if (container->tbl && container->tbl->it_group)
+		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+
+	mutex_destroy(&container->lock);
+
+	kfree(container);
+}
+
+static long tce_iommu_ioctl(void *iommu_data,
+				 unsigned int cmd, unsigned long arg)
+{
+	struct tce_container *container = iommu_data;
+	unsigned long minsz;
+	long ret;
+
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0;
+
+	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
+		struct vfio_iommu_spapr_tce_info info;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
+				dma32_window_size);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT;
+		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT;
+		info.flags = 0;
+
+		if (copy_to_user((void __user *)arg, &info, minsz))
+			return -EFAULT;
+
+		return 0;
+	}
+	case VFIO_IOMMU_MAP_DMA: {
+		struct vfio_iommu_type1_dma_map param;
+		struct iommu_table *tbl = container->tbl;
+		unsigned long tce, i;
+
+		if (!tbl)
+			return -ENXIO;
+
+		BUG_ON(!tbl->it_group);
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
+				VFIO_DMA_MAP_FLAG_WRITE))
+			return -EINVAL;
+
+		if ((param.size & ~IOMMU_PAGE_MASK) ||
+				(param.vaddr & ~IOMMU_PAGE_MASK))
+			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;
+
+		ret = iommu_tce_put_param_check(tbl, param.iova, tce);
+		if (ret)
+			return ret;
+
+		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) {
+			ret = iommu_put_tce_user_mode(tbl,
+					(param.iova >> IOMMU_PAGE_SHIFT) + i,
+					tce);
+			if (ret)
+				break;
+			tce += IOMMU_PAGE_SIZE;
+		}
+		if (ret)
+			iommu_clear_tces_and_put_pages(tbl,
+					param.iova >> IOMMU_PAGE_SHIFT,	i);
+
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_UNMAP_DMA: {
+		struct vfio_iommu_type1_dma_unmap param;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
+				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;
+
+		if (param.size & ~IOMMU_PAGE_MASK)
+			return -EINVAL;
+
+		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
+				param.size >> IOMMU_PAGE_SHIFT);
+		if (ret)
+			return ret;
+
+		ret = iommu_clear_tces_and_put_pages(tbl,
+				param.iova >> IOMMU_PAGE_SHIFT,
+				param.size >> IOMMU_PAGE_SHIFT);
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_ENABLE:
+		mutex_lock(&container->lock);
+		ret = tce_iommu_enable(container);
+		mutex_unlock(&container->lock);
+		return ret;
+
+
+	case VFIO_IOMMU_DISABLE:
+		mutex_lock(&container->lock);
+		tce_iommu_disable(container);
+		mutex_unlock(&container->lock);
+		return 0;
+	}
+
+	return -ENOTTY;
+}
+
+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);
+
+	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));
+		ret = -EBUSY;
+	} else {
+		ret = iommu_take_ownership(tbl);
+		if (!ret)
+			container->tbl = tbl;
+	}
+
+	mutex_unlock(&container->lock);
+
+	return ret;
+}
+
+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);
+
+	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);
+		}
+
+		/* 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);
+	}
+	mutex_unlock(&container->lock);
+}
+
+const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+	.name		= "iommu-vfio-powerpc",
+	.owner		= THIS_MODULE,
+	.open		= tce_iommu_open,
+	.release	= tce_iommu_release,
+	.ioctl		= tce_iommu_ioctl,
+	.attach_group	= tce_iommu_attach_group,
+	.detach_group	= tce_iommu_detach_group,
+};
+
+static int __init tce_iommu_init(void)
+{
+	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
+}
+
+static void __exit tce_iommu_cleanup(void)
+{
+	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
+}
+
+module_init(tce_iommu_init);
+module_exit(tce_iommu_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 6f3fbc4..4fb7a8f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/pci.h>		/* pci_bus_type */
+#include <linux/rbtree.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
@@ -47,19 +48,25 @@ module_param_named(allow_unsafe_interrupts,
 MODULE_PARM_DESC(allow_unsafe_interrupts,
 		 "Enable VFIO IOMMU support for on platforms without interrupt remapping support.");
 
+static bool disable_hugepages;
+module_param_named(disable_hugepages,
+		   disable_hugepages, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(disable_hugepages,
+		 "Disable VFIO IOMMU support for IOMMU hugepages.");
+
 struct vfio_iommu {
 	struct iommu_domain	*domain;
 	struct mutex		lock;
-	struct list_head	dma_list;
+	struct rb_root		dma_list;
 	struct list_head	group_list;
 	bool			cache;
 };
 
 struct vfio_dma {
-	struct list_head	next;
+	struct rb_node		node;
 	dma_addr_t		iova;		/* Device address */
 	unsigned long		vaddr;		/* Process virtual addr */
-	long			npage;		/* Number of pages */
+	size_t			size;		/* Map size (bytes) */
 	int			prot;		/* IOMMU_READ/WRITE */
 };
 
@@ -73,7 +80,48 @@ struct vfio_group {
  * into DMA'ble space using the IOMMU
  */
 
-#define NPAGE_TO_SIZE(npage)	((size_t)(npage) << PAGE_SHIFT)
+static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
+				      dma_addr_t start, size_t size)
+{
+	struct rb_node *node = iommu->dma_list.rb_node;
+
+	while (node) {
+		struct vfio_dma *dma = rb_entry(node, struct vfio_dma, node);
+
+		if (start + size <= dma->iova)
+			node = node->rb_left;
+		else if (start >= dma->iova + dma->size)
+			node = node->rb_right;
+		else
+			return dma;
+	}
+
+	return NULL;
+}
+
+static void vfio_insert_dma(struct vfio_iommu *iommu, struct vfio_dma *new)
+{
+	struct rb_node **link = &iommu->dma_list.rb_node, *parent = NULL;
+	struct vfio_dma *dma;
+
+	while (*link) {
+		parent = *link;
+		dma = rb_entry(parent, struct vfio_dma, node);
+
+		if (new->iova + new->size <= dma->iova)
+			link = &(*link)->rb_left;
+		else
+			link = &(*link)->rb_right;
+	}
+
+	rb_link_node(&new->node, parent, link);
+	rb_insert_color(&new->node, &iommu->dma_list);
+}
+
+static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *old)
+{
+	rb_erase(&old->node, &iommu->dma_list);
+}
 
 struct vwork {
 	struct mm_struct	*mm;
@@ -100,8 +148,8 @@ static void vfio_lock_acct(long npage)
 	struct vwork *vwork;
 	struct mm_struct *mm;
 
-	if (!current->mm)
-		return; /* process exited */
+	if (!current->mm || !npage)
+		return; /* process exited or nothing to do */
 
 	if (down_write_trylock(&current->mm->mmap_sem)) {
 		current->mm->locked_vm += npage;
@@ -173,33 +221,6 @@ static int put_pfn(unsigned long pfn, int prot)
 	return 0;
 }
 
-/* Unmap DMA region */
-static long __vfio_dma_do_unmap(struct vfio_iommu *iommu, dma_addr_t iova,
-			     long npage, int prot)
-{
-	long i, unlocked = 0;
-
-	for (i = 0; i < npage; i++, iova += PAGE_SIZE) {
-		unsigned long pfn;
-
-		pfn = iommu_iova_to_phys(iommu->domain, iova) >> PAGE_SHIFT;
-		if (pfn) {
-			iommu_unmap(iommu->domain, iova, PAGE_SIZE);
-			unlocked += put_pfn(pfn, prot);
-		}
-	}
-	return unlocked;
-}
-
-static void vfio_dma_unmap(struct vfio_iommu *iommu, dma_addr_t iova,
-			   long npage, int prot)
-{
-	long unlocked;
-
-	unlocked = __vfio_dma_do_unmap(iommu, iova, npage, prot);
-	vfio_lock_acct(-unlocked);
-}
-
 static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
 {
 	struct page *page[1];
@@ -226,198 +247,308 @@ static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
 	return ret;
 }
 
-/* Map DMA region */
-static int __vfio_dma_map(struct vfio_iommu *iommu, dma_addr_t iova,
-			  unsigned long vaddr, long npage, int prot)
+/*
+ * Attempt to pin pages.  We really don't want to track all the pfns and
+ * the iommu can only map chunks of consecutive pfns anyway, so get the
+ * first page and all consecutive pages with the same locking.
+ */
+static long vfio_pin_pages(unsigned long vaddr, long npage,
+			   int prot, unsigned long *pfn_base)
 {
-	dma_addr_t start = iova;
-	long i, locked = 0;
-	int ret;
+	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	bool lock_cap = capable(CAP_IPC_LOCK);
+	long ret, i;
 
-	/* Verify that pages are not already mapped */
-	for (i = 0; i < npage; i++, iova += PAGE_SIZE)
-		if (iommu_iova_to_phys(iommu->domain, iova))
-			return -EBUSY;
+	if (!current->mm)
+		return -ENODEV;
 
-	iova = start;
+	ret = vaddr_get_pfn(vaddr, prot, pfn_base);
+	if (ret)
+		return ret;
 
-	if (iommu->cache)
-		prot |= IOMMU_CACHE;
+	if (is_invalid_reserved_pfn(*pfn_base))
+		return 1;
 
-	/*
-	 * XXX We break mappings into pages and use get_user_pages_fast to
-	 * pin the pages in memory.  It's been suggested that mlock might
-	 * provide a more efficient mechanism, but nothing prevents the
-	 * user from munlocking the pages, which could then allow the user
-	 * access to random host memory.  We also have no guarantee from the
-	 * IOMMU API that the iommu driver can unmap sub-pages of previous
-	 * mappings.  This means we might lose an entire range if a single
-	 * page within it is unmapped.  Single page mappings are inefficient,
-	 * but provide the most flexibility for now.
-	 */
-	for (i = 0; i < npage; i++, iova += PAGE_SIZE, vaddr += PAGE_SIZE) {
+	if (!lock_cap && current->mm->locked_vm + 1 > limit) {
+		put_pfn(*pfn_base, prot);
+		pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
+			limit << PAGE_SHIFT);
+		return -ENOMEM;
+	}
+
+	if (unlikely(disable_hugepages)) {
+		vfio_lock_acct(1);
+		return 1;
+	}
+
+	/* Lock all the consecutive pages from pfn_base */
+	for (i = 1, vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) {
 		unsigned long pfn = 0;
 
 		ret = vaddr_get_pfn(vaddr, prot, &pfn);
-		if (ret) {
-			__vfio_dma_do_unmap(iommu, start, i, prot);
-			return ret;
-		}
+		if (ret)
+			break;
 
-		/*
-		 * Only add actual locked pages to accounting
-		 * XXX We're effectively marking a page locked for every
-		 * IOVA page even though it's possible the user could be
-		 * backing multiple IOVAs with the same vaddr.  This over-
-		 * penalizes the user process, but we currently have no
-		 * easy way to do this properly.
-		 */
-		if (!is_invalid_reserved_pfn(pfn))
-			locked++;
+		if (pfn != *pfn_base + i || is_invalid_reserved_pfn(pfn)) {
+			put_pfn(pfn, prot);
+			break;
+		}
 
-		ret = iommu_map(iommu->domain, iova,
-				(phys_addr_t)pfn << PAGE_SHIFT,
-				PAGE_SIZE, prot);
-		if (ret) {
-			/* Back out mappings on error */
+		if (!lock_cap && current->mm->locked_vm + i + 1 > limit) {
 			put_pfn(pfn, prot);
-			__vfio_dma_do_unmap(iommu, start, i, prot);
-			return ret;
+			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
+				__func__, limit << PAGE_SHIFT);
+			break;
 		}
 	}
-	vfio_lock_acct(locked);
-	return 0;
+
+	vfio_lock_acct(i);
+
+	return i;
 }
 
-static inline bool ranges_overlap(dma_addr_t start1, size_t size1,
-				  dma_addr_t start2, size_t size2)
+static long vfio_unpin_pages(unsigned long pfn, long npage,
+			     int prot, bool do_accounting)
 {
-	if (start1 < start2)
-		return (start2 - start1 < size1);
-	else if (start2 < start1)
-		return (start1 - start2 < size2);
-	return (size1 > 0 && size2 > 0);
+	unsigned long unlocked = 0;
+	long i;
+
+	for (i = 0; i < npage; i++)
+		unlocked += put_pfn(pfn++, prot);
+
+	if (do_accounting)
+		vfio_lock_acct(-unlocked);
+
+	return unlocked;
 }
 
-static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
-						dma_addr_t start, size_t size)
+static int vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
+			    dma_addr_t iova, size_t *size)
 {
-	struct vfio_dma *dma;
+	dma_addr_t start = iova, end = iova + *size;
+	long unlocked = 0;
 
-	list_for_each_entry(dma, &iommu->dma_list, next) {
-		if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage),
-				   start, size))
-			return dma;
+	while (iova < end) {
+		size_t unmapped;
+		phys_addr_t phys;
+
+		/*
+		 * We use the IOMMU to track the physical address.  This
+		 * saves us from having a lot more entries in our mapping
+		 * tree.  The downside is that we don't track the size
+		 * used to do the mapping.  We request unmap of a single
+		 * page, but expect IOMMUs that support large pages to
+		 * unmap a larger chunk.
+		 */
+		phys = iommu_iova_to_phys(iommu->domain, iova);
+		if (WARN_ON(!phys)) {
+			iova += PAGE_SIZE;
+			continue;
+		}
+
+		unmapped = iommu_unmap(iommu->domain, iova, PAGE_SIZE);
+		if (!unmapped)
+			break;
+
+		unlocked += vfio_unpin_pages(phys >> PAGE_SHIFT,
+					     unmapped >> PAGE_SHIFT,
+					     dma->prot, false);
+		iova += unmapped;
 	}
-	return NULL;
+
+	vfio_lock_acct(-unlocked);
+
+	*size = iova - start;
+
+	return 0;
 }
 
-static long vfio_remove_dma_overlap(struct vfio_iommu *iommu, dma_addr_t start,
-				    size_t size, struct vfio_dma *dma)
+static int vfio_remove_dma_overlap(struct vfio_iommu *iommu, dma_addr_t start,
+				   size_t *size, struct vfio_dma *dma)
 {
+	size_t offset, overlap, tmp;
 	struct vfio_dma *split;
-	long npage_lo, npage_hi;
-
-	/* Existing dma region is completely covered, unmap all */
-	if (start <= dma->iova &&
-	    start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) {
-		vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot);
-		list_del(&dma->next);
-		npage_lo = dma->npage;
+	int ret;
+
+	if (!*size)
+		return 0;
+
+	/*
+	 * Existing dma region is completely covered, unmap all.  This is
+	 * the likely case since userspace tends to map and unmap buffers
+	 * in one shot rather than multiple mappings within a buffer.
+	 */
+	if (likely(start <= dma->iova &&
+		   start + *size >= dma->iova + dma->size)) {
+		*size = dma->size;
+		ret = vfio_unmap_unpin(iommu, dma, dma->iova, size);
+		if (ret)
+			return ret;
+
+		/*
+		 * Did we remove more than we have?  Should never happen
+		 * since a vfio_dma is contiguous in iova and vaddr.
+		 */
+		WARN_ON(*size != dma->size);
+
+		vfio_remove_dma(iommu, dma);
 		kfree(dma);
-		return npage_lo;
+		return 0;
 	}
 
 	/* Overlap low address of existing range */
 	if (start <= dma->iova) {
-		size_t overlap;
+		overlap = start + *size - dma->iova;
+		ret = vfio_unmap_unpin(iommu, dma, dma->iova, &overlap);
+		if (ret)
+			return ret;
 
-		overlap = start + size - dma->iova;
-		npage_lo = overlap >> PAGE_SHIFT;
+		vfio_remove_dma(iommu, dma);
 
-		vfio_dma_unmap(iommu, dma->iova, npage_lo, dma->prot);
-		dma->iova += overlap;
-		dma->vaddr += overlap;
-		dma->npage -= npage_lo;
-		return npage_lo;
+		/*
+		 * Check, we may have removed to whole vfio_dma.  If not
+		 * fixup and re-insert.
+		 */
+		if (overlap < dma->size) {
+			dma->iova += overlap;
+			dma->vaddr += overlap;
+			dma->size -= overlap;
+			vfio_insert_dma(iommu, dma);
+		} else
+			kfree(dma);
+
+		*size = overlap;
+		return 0;
 	}
 
 	/* Overlap high address of existing range */
-	if (start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) {
-		size_t overlap;
+	if (start + *size >= dma->iova + dma->size) {
+		offset = start - dma->iova;
+		overlap = dma->size - offset;
 
-		overlap = dma->iova + NPAGE_TO_SIZE(dma->npage) - start;
-		npage_hi = overlap >> PAGE_SHIFT;
+		ret = vfio_unmap_unpin(iommu, dma, start, &overlap);
+		if (ret)
+			return ret;
 
-		vfio_dma_unmap(iommu, start, npage_hi, dma->prot);
-		dma->npage -= npage_hi;
-		return npage_hi;
+		dma->size -= overlap;
+		*size = overlap;
+		return 0;
 	}
 
 	/* Split existing */
-	npage_lo = (start - dma->iova) >> PAGE_SHIFT;
-	npage_hi = dma->npage - (size >> PAGE_SHIFT) - npage_lo;
 
-	split = kzalloc(sizeof *split, GFP_KERNEL);
+	/*
+	 * Allocate our tracking structure early even though it may not
+	 * be used.  An Allocation failure later loses track of pages and
+	 * is more difficult to unwind.
+	 */
+	split = kzalloc(sizeof(*split), GFP_KERNEL);
 	if (!split)
 		return -ENOMEM;
 
-	vfio_dma_unmap(iommu, start, size >> PAGE_SHIFT, dma->prot);
+	offset = start - dma->iova;
 
-	dma->npage = npage_lo;
+	ret = vfio_unmap_unpin(iommu, dma, start, size);
+	if (ret || !*size) {
+		kfree(split);
+		return ret;
+	}
+
+	tmp = dma->size;
 
-	split->npage = npage_hi;
-	split->iova = start + size;
-	split->vaddr = dma->vaddr + NPAGE_TO_SIZE(npage_lo) + size;
-	split->prot = dma->prot;
-	list_add(&split->next, &iommu->dma_list);
-	return size >> PAGE_SHIFT;
+	/* Resize the lower vfio_dma in place, before the below insert */
+	dma->size = offset;
+
+	/* Insert new for remainder, assuming it didn't all get unmapped */
+	if (likely(offset + *size < tmp)) {
+		split->size = tmp - offset - *size;
+		split->iova = dma->iova + offset + *size;
+		split->vaddr = dma->vaddr + offset + *size;
+		split->prot = dma->prot;
+		vfio_insert_dma(iommu, split);
+	} else
+		kfree(split);
+
+	return 0;
 }
 
 static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 			     struct vfio_iommu_type1_dma_unmap *unmap)
 {
-	long ret = 0, npage = unmap->size >> PAGE_SHIFT;
-	struct vfio_dma *dma, *tmp;
 	uint64_t mask;
+	struct vfio_dma *dma;
+	size_t unmapped = 0, size;
+	int ret = 0;
 
 	mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1;
 
 	if (unmap->iova & mask)
 		return -EINVAL;
-	if (unmap->size & mask)
+	if (!unmap->size || unmap->size & mask)
 		return -EINVAL;
 
-	/* XXX We still break these down into PAGE_SIZE */
 	WARN_ON(mask & PAGE_MASK);
 
 	mutex_lock(&iommu->lock);
 
-	list_for_each_entry_safe(dma, tmp, &iommu->dma_list, next) {
-		if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage),
-				   unmap->iova, unmap->size)) {
-			ret = vfio_remove_dma_overlap(iommu, unmap->iova,
-						      unmap->size, dma);
-			if (ret > 0)
-				npage -= ret;
-			if (ret < 0 || npage == 0)
-				break;
-		}
+	while ((dma = vfio_find_dma(iommu, unmap->iova, unmap->size))) {
+		size = unmap->size;
+		ret = vfio_remove_dma_overlap(iommu, unmap->iova, &size, dma);
+		if (ret || !size)
+			break;
+		unmapped += size;
 	}
+
 	mutex_unlock(&iommu->lock);
-	return ret > 0 ? 0 : (int)ret;
+
+	/*
+	 * We may unmap more than requested, update the unmap struct so
+	 * userspace can know.
+	 */
+	unmap->size = unmapped;
+
+	return ret;
+}
+
+/*
+ * Turns out AMD IOMMU has a page table bug where it won't map large pages
+ * to a region that previously mapped smaller pages.  This should be fixed
+ * soon, so this is just a temporary workaround to break mappings down into
+ * PAGE_SIZE.  Better to map smaller pages than nothing.
+ */
+static int map_try_harder(struct vfio_iommu *iommu, dma_addr_t iova,
+			  unsigned long pfn, long npage, int prot)
+{
+	long i;
+	int ret;
+
+	for (i = 0; i < npage; i++, pfn++, iova += PAGE_SIZE) {
+		ret = iommu_map(iommu->domain, iova,
+				(phys_addr_t)pfn << PAGE_SHIFT,
+				PAGE_SIZE, prot);
+		if (ret)
+			break;
+	}
+
+	for (; i < npage && i > 0; i--, iova -= PAGE_SIZE)
+		iommu_unmap(iommu->domain, iova, PAGE_SIZE);
+
+	return ret;
 }
 
 static int vfio_dma_do_map(struct vfio_iommu *iommu,
 			   struct vfio_iommu_type1_dma_map *map)
 {
-	struct vfio_dma *dma, *pdma = NULL;
-	dma_addr_t iova = map->iova;
-	unsigned long locked, lock_limit, vaddr = map->vaddr;
+	dma_addr_t end, iova;
+	unsigned long vaddr = map->vaddr;
 	size_t size = map->size;
+	long npage;
 	int ret = 0, prot = 0;
 	uint64_t mask;
-	long npage;
+	struct vfio_dma *dma = NULL;
+	unsigned long pfn;
+
+	end = map->iova + map->size;
 
 	mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1;
 
@@ -430,104 +561,144 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 	if (!prot)
 		return -EINVAL; /* No READ/WRITE? */
 
+	if (iommu->cache)
+		prot |= IOMMU_CACHE;
+
 	if (vaddr & mask)
 		return -EINVAL;
-	if (iova & mask)
+	if (map->iova & mask)
 		return -EINVAL;
-	if (size & mask)
+	if (!map->size || map->size & mask)
 		return -EINVAL;
 
-	/* XXX We still break these down into PAGE_SIZE */
 	WARN_ON(mask & PAGE_MASK);
 
 	/* Don't allow IOVA wrap */
-	if (iova + size && iova + size < iova)
+	if (end && end < map->iova)
 		return -EINVAL;
 
 	/* Don't allow virtual address wrap */
-	if (vaddr + size && vaddr + size < vaddr)
-		return -EINVAL;
-
-	npage = size >> PAGE_SHIFT;
-	if (!npage)
+	if (vaddr + map->size && vaddr + map->size < vaddr)
 		return -EINVAL;
 
 	mutex_lock(&iommu->lock);
 
-	if (vfio_find_dma(iommu, iova, size)) {
-		ret = -EBUSY;
-		goto out_lock;
+	if (vfio_find_dma(iommu, map->iova, map->size)) {
+		mutex_unlock(&iommu->lock);
+		return -EEXIST;
 	}
 
-	/* account for locked pages */
-	locked = current->mm->locked_vm + npage;
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
-		pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
-			__func__, rlimit(RLIMIT_MEMLOCK));
-		ret = -ENOMEM;
-		goto out_lock;
-	}
+	for (iova = map->iova; iova < end; iova += size, vaddr += size) {
+		long i;
 
-	ret = __vfio_dma_map(iommu, iova, vaddr, npage, prot);
-	if (ret)
-		goto out_lock;
-
-	/* Check if we abut a region below - nothing below 0 */
-	if (iova) {
-		dma = vfio_find_dma(iommu, iova - 1, 1);
-		if (dma && dma->prot == prot &&
-		    dma->vaddr + NPAGE_TO_SIZE(dma->npage) == vaddr) {
+		/* Pin a contiguous chunk of memory */
+		npage = vfio_pin_pages(vaddr, (end - iova) >> PAGE_SHIFT,
+				       prot, &pfn);
+		if (npage <= 0) {
+			WARN_ON(!npage);
+			ret = (int)npage;
+			goto out;
+		}
 
-			dma->npage += npage;
-			iova = dma->iova;
-			vaddr = dma->vaddr;
-			npage = dma->npage;
-			size = NPAGE_TO_SIZE(npage);
+		/* Verify pages are not already mapped */
+		for (i = 0; i < npage; i++) {
+			if (iommu_iova_to_phys(iommu->domain,
+					       iova + (i << PAGE_SHIFT))) {
+				ret = -EBUSY;
+				goto out_unpin;
+			}
+		}
 
-			pdma = dma;
+		ret = iommu_map(iommu->domain, iova,
+				(phys_addr_t)pfn << PAGE_SHIFT,
+				npage << PAGE_SHIFT, prot);
+		if (ret) {
+			if (ret != -EBUSY ||
+			    map_try_harder(iommu, iova, pfn, npage, prot)) {
+				goto out_unpin;
+			}
 		}
-	}
 
-	/* Check if we abut a region above - nothing above ~0 + 1 */
-	if (iova + size) {
-		dma = vfio_find_dma(iommu, iova + size, 1);
-		if (dma && dma->prot == prot &&
-		    dma->vaddr == vaddr + size) {
+		size = npage << PAGE_SHIFT;
 
-			dma->npage += npage;
-			dma->iova = iova;
-			dma->vaddr = vaddr;
+		/*
+		 * Check if we abut a region below - nothing below 0.
+		 * This is the most likely case when mapping chunks of
+		 * physically contiguous regions within a virtual address
+		 * range.  Update the abutting entry in place since iova
+		 * doesn't change.
+		 */
+		if (likely(iova)) {
+			struct vfio_dma *tmp;
+			tmp = vfio_find_dma(iommu, iova - 1, 1);
+			if (tmp && tmp->prot == prot &&
+			    tmp->vaddr + tmp->size == vaddr) {
+				tmp->size += size;
+				iova = tmp->iova;
+				size = tmp->size;
+				vaddr = tmp->vaddr;
+				dma = tmp;
+			}
+		}
 
-			/*
-			 * If merged above and below, remove previously
-			 * merged entry.  New entry covers it.
-			 */
-			if (pdma) {
-				list_del(&pdma->next);
-				kfree(pdma);
+		/*
+		 * Check if we abut a region above - nothing above ~0 + 1.
+		 * If we abut above and below, remove and free.  If only
+		 * abut above, remove, modify, reinsert.
+		 */
+		if (likely(iova + size)) {
+			struct vfio_dma *tmp;
+			tmp = vfio_find_dma(iommu, iova + size, 1);
+			if (tmp && tmp->prot == prot &&
+			    tmp->vaddr == vaddr + size) {
+				vfio_remove_dma(iommu, tmp);
+				if (dma) {
+					dma->size += tmp->size;
+					kfree(tmp);
+				} else {
+					size += tmp->size;
+					tmp->size = size;
+					tmp->iova = iova;
+					tmp->vaddr = vaddr;
+					vfio_insert_dma(iommu, tmp);
+					dma = tmp;
+				}
 			}
-			pdma = dma;
 		}
-	}
 
-	/* Isolated, new region */
-	if (!pdma) {
-		dma = kzalloc(sizeof *dma, GFP_KERNEL);
 		if (!dma) {
-			ret = -ENOMEM;
-			vfio_dma_unmap(iommu, iova, npage, prot);
-			goto out_lock;
+			dma = kzalloc(sizeof(*dma), GFP_KERNEL);
+			if (!dma) {
+				iommu_unmap(iommu->domain, iova, size);
+				ret = -ENOMEM;
+				goto out_unpin;
+			}
+
+			dma->size = size;
+			dma->iova = iova;
+			dma->vaddr = vaddr;
+			dma->prot = prot;
+			vfio_insert_dma(iommu, dma);
 		}
+	}
+
+	WARN_ON(ret);
+	mutex_unlock(&iommu->lock);
+	return ret;
+
+out_unpin:
+	vfio_unpin_pages(pfn, npage, prot, true);
 
-		dma->npage = npage;
-		dma->iova = iova;
-		dma->vaddr = vaddr;
-		dma->prot = prot;
-		list_add(&dma->next, &iommu->dma_list);
+out:
+	iova = map->iova;
+	size = map->size;
+	while ((dma = vfio_find_dma(iommu, iova, size))) {
+		int r = vfio_remove_dma_overlap(iommu, iova,
+						&size, dma);
+		if (WARN_ON(r || !size))
+			break;
 	}
 
-out_lock:
 	mutex_unlock(&iommu->lock);
 	return ret;
 }
@@ -606,7 +777,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&iommu->group_list);
-	INIT_LIST_HEAD(&iommu->dma_list);
+	iommu->dma_list = RB_ROOT;
 	mutex_init(&iommu->lock);
 
 	/*
@@ -640,7 +811,7 @@ static void vfio_iommu_type1_release(void *iommu_data)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_group *group, *group_tmp;
-	struct vfio_dma *dma, *dma_tmp;
+	struct rb_node *node;
 
 	list_for_each_entry_safe(group, group_tmp, &iommu->group_list, next) {
 		iommu_detach_group(iommu->domain, group->iommu_group);
@@ -648,10 +819,12 @@ static void vfio_iommu_type1_release(void *iommu_data)
 		kfree(group);
 	}
 
-	list_for_each_entry_safe(dma, dma_tmp, &iommu->dma_list, next) {
-		vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot);
-		list_del(&dma->next);
-		kfree(dma);
+	while ((node = rb_first(&iommu->dma_list))) {
+		struct vfio_dma *dma = rb_entry(node, struct vfio_dma, node);
+		size_t size = dma->size;
+		vfio_remove_dma_overlap(iommu, dma->iova, &size, dma);
+		if (WARN_ON(!size))
+			break;
 	}
 
 	iommu_domain_free(iommu->domain);
@@ -706,6 +879,7 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 
 	} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
 		struct vfio_iommu_type1_dma_unmap unmap;
+		long ret;
 
 		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
 
@@ -715,7 +889,11 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		if (unmap.argsz < minsz || unmap.flags)
 			return -EINVAL;
 
-		return vfio_dma_do_unmap(iommu, &unmap);
+		ret = vfio_dma_do_unmap(iommu, &unmap);
+		if (ret)
+			return ret;
+
+		return copy_to_user((void __user *)arg, &unmap, minsz);
 	}
 
 	return -ENOTTY;