Merge tag 'vfio-v4.10-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - VFIO updates for v4.10 primarily include a new Mediated Device
   interface, which essentially allows software defined devices to be
   exposed to users through VFIO. The host vendor driver providing this
   virtual device polices, or mediates user access to the device.

   These devices often incorporate portions of real devices, for
   instance the primary initial users of this interface expose vGPUs
   which allow the user to map mediated devices, or mdevs, to a portion
   of a physical GPU. QEMU composes these mdevs into PCI representations
   using the existing VFIO user API. This enables both Intel KVM-GT
   support, which is also expected to arrive into Linux mainline during
   the v4.10 merge window, as well as NVIDIA vGPU, and also Channel I/O
   devices (aka CCW devices) for s390 virtualization support. (Kirti
   Wankhede, Neo Jia)

 - Drop unnecessary uses of pcibios_err_to_errno() (Cao Jin)

 - Fixes to VFIO capability chain handling (Eric Auger)

 - Error handling fixes for fallout from mdev (Christophe JAILLET)

 - Notifiers to expose struct kvm to mdev vendor drivers (Jike Song)

 - type1 IOMMU model search fixes (Kirti Wankhede, Neo Jia)

* tag 'vfio-v4.10-rc1' of git://github.com/awilliam/linux-vfio: (30 commits)
  vfio iommu type1: Fix size argument to vfio_find_dma() in pin_pages/unpin_pages
  vfio iommu type1: Fix size argument to vfio_find_dma() during DMA UNMAP.
  vfio iommu type1: WARN_ON if notifier block is not unregistered
  kvm: set/clear kvm to/from vfio_group when group add/delete
  vfio: support notifier chain in vfio_group
  vfio: vfio_register_notifier: classify iommu notifier
  vfio: Fix handling of error returned by 'vfio_group_get_from_dev()'
  vfio: fix vfio_info_cap_add/shift
  vfio/pci: Drop unnecessary pcibios_err_to_errno()
  MAINTAINERS: Add entry VFIO based Mediated device drivers
  docs: Sample driver to demonstrate how to use Mediated device framework.
  docs: Sysfs ABI for mediated device framework
  docs: Add Documentation for Mediated devices
  vfio: Define device_api strings
  vfio_platform: Updated to use vfio_set_irqs_validate_and_prepare()
  vfio_pci: Updated to use vfio_set_irqs_validate_and_prepare()
  vfio: Introduce vfio_set_irqs_validate_and_prepare()
  vfio_pci: Update vfio_pci to use vfio_info_add_capability()
  vfio: Introduce common function to add capabilities
  vfio iommu: Add blocking notifier to notify DMA_UNMAP
  ...

3 files changed, 225 insertions, 1 deletions

diff --git a/include/linux/mdev.h b/include/linux/mdev.h
new file mode 100644
index 000000000000..ec819e9a115a
--- /dev/null
+++ b/include/linux/mdev.h
@@ -0,0 +1,168 @@
+/*
+ * Mediated device definition
+ *
+ * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
+ *     Author: Neo Jia <cjia@nvidia.com>
+ *             Kirti Wankhede <kwankhede@nvidia.com>
+ *
+ * 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.
+ */
+
+#ifndef MDEV_H
+#define MDEV_H
+
+/* Parent device */
+struct parent_device {
+	struct device		*dev;
+	const struct parent_ops	*ops;
+
+	/* internal */
+	struct kref		ref;
+	struct mutex		lock;
+	struct list_head	next;
+	struct kset		*mdev_types_kset;
+	struct list_head	type_list;
+};
+
+/* Mediated device */
+struct mdev_device {
+	struct device		dev;
+	struct parent_device	*parent;
+	uuid_le			uuid;
+	void			*driver_data;
+
+	/* internal */
+	struct kref		ref;
+	struct list_head	next;
+	struct kobject		*type_kobj;
+};
+
+/**
+ * struct parent_ops - Structure to be registered for each parent device to
+ * register the device to mdev module.
+ *
+ * @owner:		The module owner.
+ * @dev_attr_groups:	Attributes of the parent device.
+ * @mdev_attr_groups:	Attributes of the mediated device.
+ * @supported_type_groups: Attributes to define supported types. It is mandatory
+ *			to provide supported types.
+ * @create:		Called to allocate basic resources in parent device's
+ *			driver for a particular mediated device. It is
+ *			mandatory to provide create ops.
+ *			@kobj: kobject of type for which 'create' is called.
+ *			@mdev: mdev_device structure on of mediated device
+ *			      that is being created
+ *			Returns integer: success (0) or error (< 0)
+ * @remove:		Called to free resources in parent device's driver for a
+ *			a mediated device. It is mandatory to provide 'remove'
+ *			ops.
+ *			@mdev: mdev_device device structure which is being
+ *			       destroyed
+ *			Returns integer: success (0) or error (< 0)
+ * @open:		Open mediated device.
+ *			@mdev: mediated device.
+ *			Returns integer: success (0) or error (< 0)
+ * @release:		release mediated device
+ *			@mdev: mediated device.
+ * @read:		Read emulation callback
+ *			@mdev: mediated device structure
+ *			@buf: read buffer
+ *			@count: number of bytes to read
+ *			@ppos: address.
+ *			Retuns number on bytes read on success or error.
+ * @write:		Write emulation callback
+ *			@mdev: mediated device structure
+ *			@buf: write buffer
+ *			@count: number of bytes to be written
+ *			@ppos: address.
+ *			Retuns number on bytes written on success or error.
+ * @ioctl:		IOCTL callback
+ *			@mdev: mediated device structure
+ *			@cmd: ioctl command
+ *			@arg: arguments to ioctl
+ * @mmap:		mmap callback
+ *			@mdev: mediated device structure
+ *			@vma: vma structure
+ * Parent device that support mediated device should be registered with mdev
+ * module with parent_ops structure.
+ **/
+
+struct parent_ops {
+	struct module   *owner;
+	const struct attribute_group **dev_attr_groups;
+	const struct attribute_group **mdev_attr_groups;
+	struct attribute_group **supported_type_groups;
+
+	int     (*create)(struct kobject *kobj, struct mdev_device *mdev);
+	int     (*remove)(struct mdev_device *mdev);
+	int     (*open)(struct mdev_device *mdev);
+	void    (*release)(struct mdev_device *mdev);
+	ssize_t (*read)(struct mdev_device *mdev, char __user *buf,
+			size_t count, loff_t *ppos);
+	ssize_t (*write)(struct mdev_device *mdev, const char __user *buf,
+			 size_t count, loff_t *ppos);
+	ssize_t (*ioctl)(struct mdev_device *mdev, unsigned int cmd,
+			 unsigned long arg);
+	int	(*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma);
+};
+
+/* interface for exporting mdev supported type attributes */
+struct mdev_type_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct kobject *kobj, struct device *dev, char *buf);
+	ssize_t (*store)(struct kobject *kobj, struct device *dev,
+			 const char *buf, size_t count);
+};
+
+#define MDEV_TYPE_ATTR(_name, _mode, _show, _store)		\
+struct mdev_type_attribute mdev_type_attr_##_name =		\
+	__ATTR(_name, _mode, _show, _store)
+#define MDEV_TYPE_ATTR_RW(_name) \
+	struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RW(_name)
+#define MDEV_TYPE_ATTR_RO(_name) \
+	struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RO(_name)
+#define MDEV_TYPE_ATTR_WO(_name) \
+	struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_WO(_name)
+
+/**
+ * struct mdev_driver - Mediated device driver
+ * @name: driver name
+ * @probe: called when new device created
+ * @remove: called when device removed
+ * @driver: device driver structure
+ *
+ **/
+struct mdev_driver {
+	const char *name;
+	int  (*probe)(struct device *dev);
+	void (*remove)(struct device *dev);
+	struct device_driver driver;
+};
+
+#define to_mdev_driver(drv)	container_of(drv, struct mdev_driver, driver)
+#define to_mdev_device(dev)	container_of(dev, struct mdev_device, dev)
+
+static inline void *mdev_get_drvdata(struct mdev_device *mdev)
+{
+	return mdev->driver_data;
+}
+
+static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data)
+{
+	mdev->driver_data = data;
+}
+
+extern struct bus_type mdev_bus_type;
+
+#define dev_is_mdev(d) ((d)->bus == &mdev_bus_type)
+
+extern int  mdev_register_device(struct device *dev,
+				 const struct parent_ops *ops);
+extern void mdev_unregister_device(struct device *dev);
+
+extern int  mdev_register_driver(struct mdev_driver *drv, struct module *owner);
+extern void mdev_unregister_driver(struct mdev_driver *drv);
+
+#endif /* MDEV_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 0ecae0b1cd34..edf9b2cad277 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -75,7 +75,16 @@ struct vfio_iommu_driver_ops {
 					struct iommu_group *group);
 	void		(*detach_group)(void *iommu_data,
 					struct iommu_group *group);
-
+	int		(*pin_pages)(void *iommu_data, unsigned long *user_pfn,
+				     int npage, int prot,
+				     unsigned long *phys_pfn);
+	int		(*unpin_pages)(void *iommu_data,
+				       unsigned long *user_pfn, int npage);
+	int		(*register_notifier)(void *iommu_data,
+					     unsigned long *events,
+					     struct notifier_block *nb);
+	int		(*unregister_notifier)(void *iommu_data,
+					       struct notifier_block *nb);
 };
 
 extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -92,6 +101,36 @@ extern int vfio_external_user_iommu_id(struct vfio_group *group);
 extern long vfio_external_check_extension(struct vfio_group *group,
 					  unsigned long arg);
 
+#define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
+
+extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
+			  int npage, int prot, unsigned long *phys_pfn);
+extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
+			    int npage);
+
+/* each type has independent events */
+enum vfio_notify_type {
+	VFIO_IOMMU_NOTIFY = 0,
+	VFIO_GROUP_NOTIFY = 1,
+};
+
+/* events for VFIO_IOMMU_NOTIFY */
+#define VFIO_IOMMU_NOTIFY_DMA_UNMAP	BIT(0)
+
+/* events for VFIO_GROUP_NOTIFY */
+#define VFIO_GROUP_NOTIFY_SET_KVM	BIT(0)
+
+extern int vfio_register_notifier(struct device *dev,
+				  enum vfio_notify_type type,
+				  unsigned long *required_events,
+				  struct notifier_block *nb);
+extern int vfio_unregister_notifier(struct device *dev,
+				    enum vfio_notify_type type,
+				    struct notifier_block *nb);
+
+struct kvm;
+extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm);
+
 /*
  * Sub-module helpers
  */
@@ -103,6 +142,13 @@ extern struct vfio_info_cap_header *vfio_info_cap_add(
 		struct vfio_info_cap *caps, size_t size, u16 id, u16 version);
 extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset);
 
+extern int vfio_info_add_capability(struct vfio_info_cap *caps,
+				    int cap_type_id, void *cap_type);
+
+extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr,
+					      int num_irqs, int max_irq_type,
+					      size_t *data_size);
+
 struct pci_dev;
 #ifdef CONFIG_EEH
 extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev);
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 255a2113f53c..519eff362c1c 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -203,6 +203,16 @@ struct vfio_device_info {
 };
 #define VFIO_DEVICE_GET_INFO		_IO(VFIO_TYPE, VFIO_BASE + 7)
 
+/*
+ * Vendor driver using Mediated device framework should provide device_api
+ * attribute in supported type attribute groups. Device API string should be one
+ * of the following corresponding to device flags in vfio_device_info structure.
+ */
+
+#define VFIO_DEVICE_API_PCI_STRING		"vfio-pci"
+#define VFIO_DEVICE_API_PLATFORM_STRING		"vfio-platform"
+#define VFIO_DEVICE_API_AMBA_STRING		"vfio-amba"
+
 /**
  * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
  *				       struct vfio_region_info)