Merge tag 'vfio-v6.0-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Cleanup use of extern in function prototypes (Alex Williamson)

 - Simplify bus_type usage and convert to device IOMMU interfaces (Robin
   Murphy)

 - Check missed return value and fix comment typos (Bo Liu)

 - Split migration ops from device ops and fix races in mlx5 migration
   support (Yishai Hadas)

 - Fix missed return value check in noiommu support (Liam Ni)

 - Hardening to clear buffer pointer to avoid use-after-free (Schspa
   Shi)

 - Remove requirement that only the same mm can unmap a previously
   mapped range (Li Zhe)

 - Adjust semaphore release vs device open counter (Yi Liu)

 - Remove unused arg from SPAPR support code (Deming Wang)

 - Rework vfio-ccw driver to better fit new mdev framework (Eric Farman,
   Michael Kawano)

 - Replace DMA unmap notifier with callbacks (Jason Gunthorpe)

 - Clarify SPAPR support comment relative to iommu_ops (Alexey
   Kardashevskiy)

 - Revise page pinning API towards compatibility with future iommufd
   support (Nicolin Chen)

 - Resolve issues in vfio-ccw, including use of DMA unmap callback (Eric
   Farman)

* tag 'vfio-v6.0-rc1' of https://github.com/awilliam/linux-vfio: (40 commits)
  vfio/pci: fix the wrong word
  vfio/ccw: Check return code from subchannel quiesce
  vfio/ccw: Remove FSM Close from remove handlers
  vfio/ccw: Add length to DMA_UNMAP checks
  vfio: Replace phys_pfn with pages for vfio_pin_pages()
  vfio/ccw: Add kmap_local_page() for memcpy
  vfio: Rename user_iova of vfio_dma_rw()
  vfio/ccw: Change pa_pfn list to pa_iova list
  vfio/ap: Change saved_pfn to saved_iova
  vfio: Pass in starting IOVA to vfio_pin/unpin_pages API
  vfio/ccw: Only pass in contiguous pages
  vfio/ap: Pass in physical address of ind to ap_aqic()
  drm/i915/gvt: Replace roundup with DIV_ROUND_UP
  vfio: Make vfio_unpin_pages() return void
  vfio/spapr_tce: Fix the comment
  vfio: Replace the iommu notifier with a device list
  vfio: Replace the DMA unmapping notifier with a callback
  vfio/ccw: Move FSM open/close to MDEV open/close
  vfio/ccw: Refactor vfio_ccw_mdev_reset
  vfio/ccw: Create a CLOSE FSM event
  ...

3 files changed, 82 insertions, 94 deletions

diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index bb539794f54a..47ad3b104d9e 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -65,11 +65,6 @@ struct mdev_driver {
 	struct device_driver driver;
 };
 
-static inline const guid_t *mdev_uuid(struct mdev_device *mdev)
-{
-	return &mdev->uuid;
-}
-
 extern struct bus_type mdev_bus_type;
 
 int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index aa888cc51757..e05ddc6fe6a5 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -32,6 +32,11 @@ struct vfio_device_set {
 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.
+	 */
+	const struct vfio_migration_ops *mig_ops;
 	struct vfio_group *group;
 	struct vfio_device_set *dev_set;
 	struct list_head dev_set_list;
@@ -44,6 +49,7 @@ struct vfio_device {
 	unsigned int open_count;
 	struct completion comp;
 	struct list_head group_next;
+	struct list_head iommu_entry;
 };
 
 /**
@@ -60,17 +66,9 @@ struct vfio_device {
  * @match: Optional device name match callback (return: 0 for no-match, >0 for
  *         match, -errno for abort (ex. match with insufficient or incorrect
  *         additional args)
+ * @dma_unmap: Called when userspace unmaps IOVA from the container
+ *             this device is attached to.
  * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl
- * @migration_set_state: Optional callback to change the migration state for
- *         devices that support migration. It's mandatory for
- *         VFIO_DEVICE_FEATURE_MIGRATION migration support.
- *         The returned FD is used for data transfer according to the FSM
- *         definition. The driver is responsible to ensure that FD reaches end
- *         of stream or error whenever the migration FSM leaves a data transfer
- *         state or before close_device() returns.
- * @migration_get_state: Optional callback to get the migration state for
- *         devices that support migration. It's mandatory for
- *         VFIO_DEVICE_FEATURE_MIGRATION migration support.
  */
 struct vfio_device_ops {
 	char	*name;
@@ -85,8 +83,24 @@ struct vfio_device_ops {
 	int	(*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma);
 	void	(*request)(struct vfio_device *vdev, unsigned int count);
 	int	(*match)(struct vfio_device *vdev, char *buf);
+	void	(*dma_unmap)(struct vfio_device *vdev, u64 iova, u64 length);
 	int	(*device_feature)(struct vfio_device *device, u32 flags,
 				  void __user *arg, size_t argsz);
+};
+
+/**
+ * @migration_set_state: Optional callback to change the migration state for
+ *         devices that support migration. It's mandatory for
+ *         VFIO_DEVICE_FEATURE_MIGRATION migration support.
+ *         The returned FD is used for data transfer according to the FSM
+ *         definition. The driver is responsible to ensure that FD reaches end
+ *         of stream or error whenever the migration FSM leaves a data transfer
+ *         state or before close_device() returns.
+ * @migration_get_state: Optional callback to get the migration state for
+ *         devices that support migration. It's mandatory for
+ *         VFIO_DEVICE_FEATURE_MIGRATION migration support.
+ */
+struct vfio_migration_ops {
 	struct file *(*migration_set_state)(
 		struct vfio_device *device,
 		enum vfio_device_mig_state new_state);
@@ -140,36 +154,18 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 /*
  * External user API
  */
-extern struct iommu_group *vfio_file_iommu_group(struct file *file);
-extern bool vfio_file_enforced_coherent(struct file *file);
-extern void vfio_file_set_kvm(struct file *file, struct kvm *kvm);
-extern bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
+struct iommu_group *vfio_file_iommu_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);
 
 #define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
 
-extern int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn,
-			  int npage, int prot, unsigned long *phys_pfn);
-extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
-			    int npage);
-extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,
-		       void *data, size_t len, bool write);
-
-/* each type has independent events */
-enum vfio_notify_type {
-	VFIO_IOMMU_NOTIFY = 0,
-};
-
-/* events for VFIO_IOMMU_NOTIFY */
-#define VFIO_IOMMU_NOTIFY_DMA_UNMAP	BIT(0)
-
-extern int vfio_register_notifier(struct vfio_device *device,
-				  enum vfio_notify_type type,
-				  unsigned long *required_events,
-				  struct notifier_block *nb);
-extern int vfio_unregister_notifier(struct vfio_device *device,
-				    enum vfio_notify_type type,
-				    struct notifier_block *nb);
-
+int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
+		   int npage, int prot, struct page **pages);
+void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage);
+int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova,
+		void *data, size_t len, bool write);
 
 /*
  * Sub-module helpers
@@ -178,25 +174,24 @@ struct vfio_info_cap {
 	struct vfio_info_cap_header *buf;
 	size_t size;
 };
-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);
+struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps,
+					       size_t size, u16 id,
+					       u16 version);
+void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset);
 
-extern int vfio_info_add_capability(struct vfio_info_cap *caps,
-				    struct vfio_info_cap_header *cap,
-				    size_t size);
+int vfio_info_add_capability(struct vfio_info_cap *caps,
+			     struct vfio_info_cap_header *cap, size_t size);
 
-extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr,
-					      int num_irqs, int max_irq_type,
-					      size_t *data_size);
+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;
 #if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH)
-extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev);
-extern void vfio_spapr_pci_eeh_release(struct pci_dev *pdev);
-extern long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
-				       unsigned int cmd,
-				       unsigned long arg);
+void vfio_spapr_pci_eeh_open(struct pci_dev *pdev);
+void vfio_spapr_pci_eeh_release(struct pci_dev *pdev);
+long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, unsigned int cmd,
+				unsigned long arg);
 #else
 static inline void vfio_spapr_pci_eeh_open(struct pci_dev *pdev)
 {
@@ -230,10 +225,9 @@ struct virqfd {
 	struct virqfd		**pvirqfd;
 };
 
-extern int vfio_virqfd_enable(void *opaque,
-			      int (*handler)(void *, void *),
-			      void (*thread)(void *, void *),
-			      void *data, struct virqfd **pvirqfd, int fd);
-extern void vfio_virqfd_disable(struct virqfd **pvirqfd);
+int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *),
+		       void (*thread)(void *, void *), void *data,
+		       struct virqfd **pvirqfd, int fd);
+void vfio_virqfd_disable(struct virqfd **pvirqfd);
 
 #endif /* VFIO_H */
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index d5d9e17f0156..5579ece4347b 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -147,23 +147,23 @@ struct vfio_pci_core_device {
 #define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev)))
 #define irq_is(vdev, type) (vdev->irq_type == type)
 
-extern void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev);
-extern void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev);
+void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev);
+void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev);
 
-extern int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev,
-				   uint32_t flags, unsigned index,
-				   unsigned start, unsigned count, void *data);
+int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev,
+			    uint32_t flags, unsigned index,
+			    unsigned start, unsigned count, void *data);
 
-extern 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_config_rw(struct vfio_pci_core_device *vdev,
+			   char __user *buf, size_t count,
+			   loff_t *ppos, bool iswrite);
 
-extern ssize_t vfio_pci_bar_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
-extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,
-			       size_t count, loff_t *ppos, bool iswrite);
+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,
@@ -173,32 +173,31 @@ static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev,
 }
 #endif
 
-extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
-			       uint64_t data, int count, int fd);
+long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
+			uint64_t data, int count, int fd);
 
-extern int vfio_pci_init_perm_bits(void);
-extern void vfio_pci_uninit_perm_bits(void);
+int vfio_pci_init_perm_bits(void);
+void vfio_pci_uninit_perm_bits(void);
 
-extern int vfio_config_init(struct vfio_pci_core_device *vdev);
-extern void vfio_config_free(struct vfio_pci_core_device *vdev);
+int vfio_config_init(struct vfio_pci_core_device *vdev);
+void vfio_config_free(struct vfio_pci_core_device *vdev);
 
-extern 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_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);
 
-extern int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev,
-				    pci_power_t state);
+int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev,
+			     pci_power_t state);
 
-extern bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev);
-extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device
-						    *vdev);
-extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev);
-extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev,
-					       u16 cmd);
+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
-extern int vfio_pci_igd_init(struct vfio_pci_core_device *vdev);
+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)
 {
@@ -207,8 +206,8 @@ static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev)
 #endif
 
 #ifdef CONFIG_VFIO_PCI_ZDEV_KVM
-extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
-				       struct vfio_info_cap *caps);
+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