Merge tag 'vfio-v6.1-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Prune private items from vfio_pci_core.h to a new internal header,
   fix missed function rename, and refactor vfio-pci interrupt defines
   (Jason Gunthorpe)

 - Create consistent naming and handling of ioctls with a function per
   ioctl for vfio-pci and vfio group handling, use proper type args
   where available (Jason Gunthorpe)

 - Implement a set of low power device feature ioctls allowing userspace
   to make use of power states such as D3cold where supported (Abhishek
   Sahu)

 - Remove device counter on vfio groups, which had restricted the page
   pinning interface to singleton groups to account for limitations in
   the type1 IOMMU backend. Document usage as limited to emulated IOMMU
   devices, ie. traditional mdev devices where this restriction is
   consistent (Jason Gunthorpe)

 - Correct function prefix in hisi_acc driver incurred during previous
   refactoring (Shameer Kolothum)

 - Correct typo and remove redundant warning triggers in vfio-fsl driver
   (Christophe JAILLET)

 - Introduce device level DMA dirty tracking uAPI and implementation in
   the mlx5 variant driver (Yishai Hadas & Joao Martins)

 - Move much of the vfio_device life cycle management into vfio core,
   simplifying and avoiding duplication across drivers. This also
   facilitates adding a struct device to vfio_device which begins the
   introduction of device rather than group level user support and fills
   a gap allowing userspace identify devices as vfio capable without
   implicit knowledge of the driver (Kevin Tian & Yi Liu)

 - Split vfio container handling to a separate file, creating a more
   well defined API between the core and container code, masking IOMMU
   backend implementation from the core, allowing for an easier future
   transition to an iommufd based implementation of the same (Jason
   Gunthorpe)

 - Attempt to resolve race accessing the iommu_group for a device
   between vfio releasing DMA ownership and removal of the device from
   the IOMMU driver. Follow-up with support to allow vfio_group to exist
   with NULL iommu_group pointer to support existing userspace use cases
   of holding the group file open (Jason Gunthorpe)

 - Fix error code and hi/lo register manipulation issues in the hisi_acc
   variant driver, along with various code cleanups (Longfang Liu)

 - Fix a prior regression in GVT-g group teardown, resulting in
   unreleased resources (Jason Gunthorpe)

 - A significant cleanup and simplification of the mdev interface,
   consolidating much of the open coded per driver sysfs interface
   support into the mdev core (Christoph Hellwig)

 - Simplification of tracking and locking around vfio_groups that fall
   out from previous refactoring (Jason Gunthorpe)

 - Replace trivial open coded f_ops tests with new helper (Alex
   Williamson)

* tag 'vfio-v6.1-rc1' of https://github.com/awilliam/linux-vfio: (77 commits)
  vfio: More vfio_file_is_group() use cases
  vfio: Make the group FD disassociate from the iommu_group
  vfio: Hold a reference to the iommu_group in kvm for SPAPR
  vfio: Add vfio_file_is_group()
  vfio: Change vfio_group->group_rwsem to a mutex
  vfio: Remove the vfio_group->users and users_comp
  vfio/mdev: add mdev available instance checking to the core
  vfio/mdev: consolidate all the description sysfs into the core code
  vfio/mdev: consolidate all the available_instance sysfs into the core code
  vfio/mdev: consolidate all the name sysfs into the core code
  vfio/mdev: consolidate all the device_api sysfs into the core code
  vfio/mdev: remove mtype_get_parent_dev
  vfio/mdev: remove mdev_parent_dev
  vfio/mdev: unexport mdev_bus_type
  vfio/mdev: remove mdev_from_dev
  vfio/mdev: simplify mdev_type handling
  vfio/mdev: embedd struct mdev_parent in the parent data structure
  vfio/mdev: make mdev.h standalone includable
  drm/i915/gvt: simplify vgpu configuration management
  drm/i915/gvt: fix a memory leak in intel_gvt_init_vgpu_types
  ...

4 files changed, 126 insertions, 183 deletions

diff --git a/include/linux/iova_bitmap.h b/include/linux/iova_bitmap.h
new file mode 100644
index 000000000000..c006cf0a25f3
--- /dev/null
+++ b/include/linux/iova_bitmap.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022, Oracle and/or its affiliates.
+ * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+#ifndef _IOVA_BITMAP_H_
+#define _IOVA_BITMAP_H_
+
+#include <linux/types.h>
+
+struct iova_bitmap;
+
+typedef int (*iova_bitmap_fn_t)(struct iova_bitmap *bitmap,
+				unsigned long iova, size_t length,
+				void *opaque);
+
+struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length,
+				      unsigned long page_size,
+				      u64 __user *data);
+void iova_bitmap_free(struct iova_bitmap *bitmap);
+int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque,
+			 iova_bitmap_fn_t fn);
+void iova_bitmap_set(struct iova_bitmap *bitmap,
+		     unsigned long iova, size_t length);
+
+#endif
diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index 47ad3b104d9e..139d05b26f82 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -10,6 +10,9 @@
 #ifndef MDEV_H
 #define MDEV_H
 
+#include <linux/device.h>
+#include <linux/uuid.h>
+
 struct mdev_type;
 
 struct mdev_device {
@@ -20,67 +23,67 @@ struct mdev_device {
 	bool active;
 };
 
-static inline struct mdev_device *to_mdev_device(struct device *dev)
-{
-	return container_of(dev, struct mdev_device, dev);
-}
+struct mdev_type {
+	/* set by the driver before calling mdev_register parent: */
+	const char *sysfs_name;
+	const char *pretty_name;
 
-unsigned int mdev_get_type_group_id(struct mdev_device *mdev);
-unsigned int mtype_get_type_group_id(struct mdev_type *mtype);
-struct device *mtype_get_parent_dev(struct mdev_type *mtype);
+	/* set by the core, can be used drivers */
+	struct mdev_parent *parent;
 
-/* interface for exporting mdev supported type attributes */
-struct mdev_type_attribute {
-	struct attribute attr;
-	ssize_t (*show)(struct mdev_type *mtype,
-			struct mdev_type_attribute *attr, char *buf);
-	ssize_t (*store)(struct mdev_type *mtype,
-			 struct mdev_type_attribute *attr, const char *buf,
-			 size_t count);
+	/* internal only */
+	struct kobject kobj;
+	struct kobject *devices_kobj;
 };
 
-#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)
+/* embedded into the struct device that the mdev devices hang off */
+struct mdev_parent {
+	struct device *dev;
+	struct mdev_driver *mdev_driver;
+	struct kset *mdev_types_kset;
+	/* Synchronize device creation/removal with parent unregistration */
+	struct rw_semaphore unreg_sem;
+	struct mdev_type **types;
+	unsigned int nr_types;
+	atomic_t available_instances;
+};
+
+static inline struct mdev_device *to_mdev_device(struct device *dev)
+{
+	return container_of(dev, struct mdev_device, dev);
+}
 
 /**
  * struct mdev_driver - Mediated device driver
+ * @device_api: string to return for the device_api sysfs
+ * @max_instances: maximum number of instances supported (optional)
  * @probe: called when new device created
  * @remove: called when device removed
- * @supported_type_groups: Attributes to define supported types. It is mandatory
- *			to provide supported types.
+ * @get_available: Return the max number of instances that can be created
+ * @show_description: Print a description of the mtype
  * @driver: device driver structure
- *
  **/
 struct mdev_driver {
+	const char *device_api;
+	unsigned int max_instances;
 	int (*probe)(struct mdev_device *dev);
 	void (*remove)(struct mdev_device *dev);
-	struct attribute_group **supported_type_groups;
+	unsigned int (*get_available)(struct mdev_type *mtype);
+	ssize_t (*show_description)(struct mdev_type *mtype, char *buf);
 	struct device_driver driver;
 };
 
-extern struct bus_type mdev_bus_type;
-
-int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver);
-void mdev_unregister_device(struct device *dev);
+int mdev_register_parent(struct mdev_parent *parent, struct device *dev,
+		struct mdev_driver *mdev_driver, struct mdev_type **types,
+		unsigned int nr_types);
+void mdev_unregister_parent(struct mdev_parent *parent);
 
 int mdev_register_driver(struct mdev_driver *drv);
 void mdev_unregister_driver(struct mdev_driver *drv);
 
-struct device *mdev_parent_dev(struct mdev_device *mdev);
 static inline struct device *mdev_dev(struct mdev_device *mdev)
 {
 	return &mdev->dev;
 }
-static inline struct mdev_device *mdev_from_dev(struct device *dev)
-{
-	return dev->bus == &mdev_bus_type ? to_mdev_device(dev) : NULL;
-}
 
 #endif /* MDEV_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index e05ddc6fe6a5..e7cebeb875dd 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -14,6 +14,7 @@
 #include <linux/workqueue.h>
 #include <linux/poll.h>
 #include <uapi/linux/vfio.h>
+#include <linux/iova_bitmap.h>
 
 struct kvm;
 
@@ -33,10 +34,11 @@ struct vfio_device {
 	struct device *dev;
 	const struct vfio_device_ops *ops;
 	/*
-	 * mig_ops is a static property of the vfio_device which must be set
-	 * prior to registering the vfio_device.
+	 * mig_ops/log_ops is a static property of the vfio_device which must
+	 * be set prior to registering the vfio_device.
 	 */
 	const struct vfio_migration_ops *mig_ops;
+	const struct vfio_log_ops *log_ops;
 	struct vfio_group *group;
 	struct vfio_device_set *dev_set;
 	struct list_head dev_set_list;
@@ -45,7 +47,9 @@ struct vfio_device {
 	struct kvm *kvm;
 
 	/* Members below here are private, not for driver use */
-	refcount_t refcount;
+	unsigned int index;
+	struct device device;	/* device.kref covers object life circle */
+	refcount_t refcount;	/* user count on registered device*/
 	unsigned int open_count;
 	struct completion comp;
 	struct list_head group_next;
@@ -55,6 +59,8 @@ struct vfio_device {
 /**
  * struct vfio_device_ops - VFIO bus driver device callbacks
  *
+ * @init: initialize private fields in device structure
+ * @release: Reclaim private fields in device structure
  * @open_device: Called when the first file descriptor is opened for this device
  * @close_device: Opposite of open_device
  * @read: Perform read(2) on device file descriptor
@@ -72,6 +78,8 @@ struct vfio_device {
  */
 struct vfio_device_ops {
 	char	*name;
+	int	(*init)(struct vfio_device *vdev);
+	void	(*release)(struct vfio_device *vdev);
 	int	(*open_device)(struct vfio_device *vdev);
 	void	(*close_device)(struct vfio_device *vdev);
 	ssize_t	(*read)(struct vfio_device *vdev, char __user *buf,
@@ -109,6 +117,28 @@ struct vfio_migration_ops {
 };
 
 /**
+ * @log_start: Optional callback to ask the device start DMA logging.
+ * @log_stop: Optional callback to ask the device stop DMA logging.
+ * @log_read_and_clear: Optional callback to ask the device read
+ *         and clear the dirty DMAs in some given range.
+ *
+ * The vfio core implementation of the DEVICE_FEATURE_DMA_LOGGING_ set
+ * of features does not track logging state relative to the device,
+ * therefore the device implementation of vfio_log_ops must handle
+ * arbitrary user requests. This includes rejecting subsequent calls
+ * to log_start without an intervening log_stop, as well as graceful
+ * handling of log_stop and log_read_and_clear from invalid states.
+ */
+struct vfio_log_ops {
+	int (*log_start)(struct vfio_device *device,
+		struct rb_root_cached *ranges, u32 nnodes, u64 *page_size);
+	int (*log_stop)(struct vfio_device *device);
+	int (*log_read_and_clear)(struct vfio_device *device,
+		unsigned long iova, unsigned long length,
+		struct iova_bitmap *dirty);
+};
+
+/**
  * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl
  * @flags: Arg from the device_feature op
  * @argsz: Arg from the device_feature op
@@ -137,9 +167,23 @@ static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops,
 	return 1;
 }
 
-void vfio_init_group_dev(struct vfio_device *device, struct device *dev,
-			 const struct vfio_device_ops *ops);
-void vfio_uninit_group_dev(struct vfio_device *device);
+struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev,
+				       const struct vfio_device_ops *ops);
+#define vfio_alloc_device(dev_struct, member, dev, ops)				\
+	container_of(_vfio_alloc_device(sizeof(struct dev_struct) +		\
+					BUILD_BUG_ON_ZERO(offsetof(		\
+						struct dev_struct, member)),	\
+					dev, ops),				\
+		     struct dev_struct, member)
+
+int vfio_init_device(struct vfio_device *device, struct device *dev,
+		     const struct vfio_device_ops *ops);
+void vfio_free_device(struct vfio_device *device);
+static inline void vfio_put_device(struct vfio_device *device)
+{
+	put_device(&device->device);
+}
+
 int vfio_register_group_dev(struct vfio_device *device);
 int vfio_register_emulated_iommu_dev(struct vfio_device *device);
 void vfio_unregister_group_dev(struct vfio_device *device);
@@ -155,6 +199,7 @@ int vfio_mig_get_next_state(struct vfio_device *device,
  * External user API
  */
 struct iommu_group *vfio_file_iommu_group(struct file *file);
+bool vfio_file_is_group(struct file *file);
 bool vfio_file_enforced_coherent(struct file *file);
 void vfio_file_set_kvm(struct file *file, struct kvm *kvm);
 bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 5579ece4347b..367fd79226a3 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -20,39 +20,10 @@
 #define VFIO_PCI_CORE_H
 
 #define VFIO_PCI_OFFSET_SHIFT   40
-
 #define VFIO_PCI_OFFSET_TO_INDEX(off)	(off >> VFIO_PCI_OFFSET_SHIFT)
 #define VFIO_PCI_INDEX_TO_OFFSET(index)	((u64)(index) << VFIO_PCI_OFFSET_SHIFT)
 #define VFIO_PCI_OFFSET_MASK	(((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1)
 
-/* Special capability IDs predefined access */
-#define PCI_CAP_ID_INVALID		0xFF	/* default raw access */
-#define PCI_CAP_ID_INVALID_VIRT		0xFE	/* default virt access */
-
-/* Cap maximum number of ioeventfds per device (arbitrary) */
-#define VFIO_PCI_IOEVENTFD_MAX		1000
-
-struct vfio_pci_ioeventfd {
-	struct list_head	next;
-	struct vfio_pci_core_device	*vdev;
-	struct virqfd		*virqfd;
-	void __iomem		*addr;
-	uint64_t		data;
-	loff_t			pos;
-	int			bar;
-	int			count;
-	bool			test_mem;
-};
-
-struct vfio_pci_irq_ctx {
-	struct eventfd_ctx	*trigger;
-	struct virqfd		*unmask;
-	struct virqfd		*mask;
-	char			*name;
-	bool			masked;
-	struct irq_bypass_producer	producer;
-};
-
 struct vfio_pci_core_device;
 struct vfio_pci_region;
 
@@ -78,23 +49,6 @@ struct vfio_pci_region {
 	u32				flags;
 };
 
-struct vfio_pci_dummy_resource {
-	struct resource		resource;
-	int			index;
-	struct list_head	res_next;
-};
-
-struct vfio_pci_vf_token {
-	struct mutex		lock;
-	uuid_t			uuid;
-	int			users;
-};
-
-struct vfio_pci_mmap_vma {
-	struct vm_area_struct	*vma;
-	struct list_head	vma_next;
-};
-
 struct vfio_pci_core_device {
 	struct vfio_device	vdev;
 	struct pci_dev		*pdev;
@@ -124,11 +78,14 @@ struct vfio_pci_core_device {
 	bool			needs_reset;
 	bool			nointx;
 	bool			needs_pm_restore;
+	bool			pm_intx_masked;
+	bool			pm_runtime_engaged;
 	struct pci_saved_state	*pci_saved_state;
 	struct pci_saved_state	*pm_save;
 	int			ioeventfds_nr;
 	struct eventfd_ctx	*err_trigger;
 	struct eventfd_ctx	*req_trigger;
+	struct eventfd_ctx	*pm_wake_eventfd_ctx;
 	struct list_head	dummy_resources_list;
 	struct mutex		ioeventfds_lock;
 	struct list_head	ioeventfds_list;
@@ -141,100 +98,17 @@ struct vfio_pci_core_device {
 	struct rw_semaphore	memory_lock;
 };
 
-#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
-#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX)
-#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX)
-#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev)))
-#define irq_is(vdev, type) (vdev->irq_type == type)
-
-void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev);
-void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev);
-
-int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev,
-			    uint32_t flags, unsigned index,
-			    unsigned start, unsigned count, void *data);
-
-ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev,
-			   char __user *buf, size_t count,
-			   loff_t *ppos, bool iswrite);
-
-ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
-			size_t count, loff_t *ppos, bool iswrite);
-
-#ifdef CONFIG_VFIO_PCI_VGA
-ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,
-			size_t count, loff_t *ppos, bool iswrite);
-#else
-static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev,
-				      char __user *buf, size_t count,
-				      loff_t *ppos, bool iswrite)
-{
-	return -EINVAL;
-}
-#endif
-
-long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
-			uint64_t data, int count, int fd);
-
-int vfio_pci_init_perm_bits(void);
-void vfio_pci_uninit_perm_bits(void);
-
-int vfio_config_init(struct vfio_pci_core_device *vdev);
-void vfio_config_free(struct vfio_pci_core_device *vdev);
-
-int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev,
-				 unsigned int type, unsigned int subtype,
-				 const struct vfio_pci_regops *ops,
-				 size_t size, u32 flags, void *data);
-
-int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev,
-			     pci_power_t state);
-
-bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev);
-void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev);
-u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev);
-void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev,
-					u16 cmd);
-
-#ifdef CONFIG_VFIO_PCI_IGD
-int vfio_pci_igd_init(struct vfio_pci_core_device *vdev);
-#else
-static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev)
-{
-	return -ENODEV;
-}
-#endif
-
-#ifdef CONFIG_VFIO_PCI_ZDEV_KVM
-int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
-				struct vfio_info_cap *caps);
-int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev);
-void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev);
-#else
-static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
-					      struct vfio_info_cap *caps)
-{
-	return -ENODEV;
-}
-
-static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
-{
-	return 0;
-}
-
-static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
-{}
-#endif
-
 /* Will be exported for vfio pci drivers usage */
+int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev,
+				      unsigned int type, unsigned int subtype,
+				      const struct vfio_pci_regops *ops,
+				      size_t size, u32 flags, void *data);
 void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga,
 			      bool is_disable_idle_d3);
 void vfio_pci_core_close_device(struct vfio_device *core_vdev);
-void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev,
-			       struct pci_dev *pdev,
-			       const struct vfio_device_ops *vfio_pci_ops);
+int vfio_pci_core_init_dev(struct vfio_device *core_vdev);
+void vfio_pci_core_release_dev(struct vfio_device *core_vdev);
 int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev);
-void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev);
 extern const struct pci_error_handlers vfio_pci_core_err_handlers;
 int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
@@ -256,9 +130,4 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state);
 
-static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
-{
-	return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA;
-}
-
 #endif /* VFIO_PCI_CORE_H */