Merge tag 'vfio-v3.12-rc0' of git://github.com/awilliam/linux-vfio

Pull VFIO update from Alex Williamson:
 "VFIO updates include safer default file flags for VFIO device fds, an
  external user interface exported to allow other modules to hold
  references to VFIO groups, a fix to test for extended config space on
  PCIe and PCI-x, and new hot reset interfaces for PCI devices which
  allows the user to do PCI bus/slot resets when all of the devices
  affected by the reset are owned by the user.

  For this last feature, the PCI bus reset interface, I depend on
  changes already merged from Bjorn's PCI pull request.  I therefore
  merged my tree up to commit cb3e4330, which I think was the correct
  action, but as Stephen Rothwell noted, I failed to provide a commit
  message indicating why the merge was required.  Sorry for that.
  Thanks, Alex"

* tag 'vfio-v3.12-rc0' of git://github.com/awilliam/linux-vfio:
  vfio: fix documentation
  vfio-pci: PCI hot reset interface
  vfio-pci: Test for extended config space
  vfio-pci: Use fdget() rather than eventfd_fget()
  vfio: Add O_CLOEXEC flag to vfio device fd
  vfio: use get_unused_fd_flags(0) instead of get_unused_fd()
  vfio: add external user support

Documentation/vfio.txt

@@ -167,8 +167,8 @@ group and can access them as follows:
 	int container, group, device, i;
 	struct vfio_group_status group_status =
 					{ .argsz = sizeof(group_status) };
-	struct vfio_iommu_x86_info iommu_info = { .argsz = sizeof(iommu_info) };
-	struct vfio_iommu_x86_dma_map dma_map = { .argsz = sizeof(dma_map) };
+	struct vfio_iommu_type1_info iommu_info = { .argsz = sizeof(iommu_info) };
+	struct vfio_iommu_type1_dma_map dma_map = { .argsz = sizeof(dma_map) };
 	struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
 
 	/* Create a new container */
@@ -193,7 +193,7 @@ group and can access them as follows:
 	ioctl(group, VFIO_GROUP_SET_CONTAINER, &container);
 
 	/* Enable the IOMMU model we want */
-	ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU)
+	ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU);
 
 	/* Get addition IOMMU info */
 	ioctl(container, VFIO_IOMMU_GET_INFO, &iommu_info);
@@ -229,7 +229,7 @@ group and can access them as follows:
 
 		irq.index = i;
 
-		ioctl(device, VFIO_DEVICE_GET_IRQ_INFO, &reg);
+		ioctl(device, VFIO_DEVICE_GET_IRQ_INFO, &irq);
 
 		/* Setup IRQs... eventfds, VFIO_DEVICE_SET_IRQS */
 	}

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>
@@ -227,6 +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)
 {
@@ -407,10 +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;
 }
 

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

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;

drivers/vfio/vfio.c

@@ -1109,7 +1109,7 @@ 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;
@@ -1352,6 +1352,68 @@ static const struct file_operations vfio_device_fops = {
 	.mmap		= vfio_device_fops_mmap,
 };
 
+/**
+ * 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
  */

include/linux/vfio.h

@@ -90,4 +90,11 @@ extern void vfio_unregister_iommu_driver(
 	TYPE tmp;						\
 	offsetof(TYPE, MEMBER) + sizeof(tmp.MEMBER); })		\
 
+/*
+ * External user API
+ */
+extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
+extern void vfio_group_put_external_user(struct vfio_group *group);
+extern int vfio_external_user_iommu_id(struct vfio_group *group);
+
 #endif /* VFIO_H */

include/uapi/linux/vfio.h

@@ -324,6 +324,44 @@ enum {
 	VFIO_PCI_NUM_IRQS
 };
 
+/**
+ * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12,
+ *					      struct vfio_pci_hot_reset_info)
+ *
+ * Return: 0 on success, -errno on failure:
+ *	-enospc = insufficient buffer, -enodev = unsupported for device.
+ */
+struct vfio_pci_dependent_device {
+	__u32	group_id;
+	__u16	segment;
+	__u8	bus;
+	__u8	devfn; /* Use PCI_SLOT/PCI_FUNC */
+};
+
+struct vfio_pci_hot_reset_info {
+	__u32	argsz;
+	__u32	flags;
+	__u32	count;
+	struct vfio_pci_dependent_device	devices[];
+};
+
+#define VFIO_DEVICE_GET_PCI_HOT_RESET_INFO	_IO(VFIO_TYPE, VFIO_BASE + 12)
+
+/**
+ * VFIO_DEVICE_PCI_HOT_RESET - _IOW(VFIO_TYPE, VFIO_BASE + 13,
+ *				    struct vfio_pci_hot_reset)
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_pci_hot_reset {
+	__u32	argsz;
+	__u32	flags;
+	__u32	count;
+	__s32	group_fds[];
+};
+
+#define VFIO_DEVICE_PCI_HOT_RESET	_IO(VFIO_TYPE, VFIO_BASE + 13)
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**