Merge tag 'vfio-v5.19-rc1' of https://github.com/awilliam/linux-vfio

Pull vfio updates from Alex Williamson:

 - Improvements to mlx5 vfio-pci variant driver, including support for
   parallel migration per PF (Yishai Hadas)

 - Remove redundant iommu_present() check (Robin Murphy)

 - Ongoing refactoring to consolidate the VFIO driver facing API to use
   vfio_device (Jason Gunthorpe)

 - Use drvdata to store vfio_device among all vfio-pci and variant
   drivers (Jason Gunthorpe)

 - Remove redundant code now that IOMMU core manages group DMA ownership
   (Jason Gunthorpe)

 - Remove vfio_group from external API handling struct file ownership
   (Jason Gunthorpe)

 - Correct typo in uapi comments (Thomas Huth)

 - Fix coccicheck detected deadlock (Wan Jiabing)

 - Use rwsem to remove races and simplify code around container and kvm
   association to groups (Jason Gunthorpe)

 - Harden access to devices in low power states and use runtime PM to
   enable d3cold support for unused devices (Abhishek Sahu)

 - Fix dma_owner handling of fake IOMMU groups (Jason Gunthorpe)

 - Set driver_managed_dma on vfio-pci variant drivers (Jason Gunthorpe)

 - Pass KVM pointer directly rather than via notifier (Matthew Rosato)

* tag 'vfio-v5.19-rc1' of https://github.com/awilliam/linux-vfio: (38 commits)
  vfio: remove VFIO_GROUP_NOTIFY_SET_KVM
  vfio/pci: Add driver_managed_dma to the new vfio_pci drivers
  vfio: Do not manipulate iommu dma_owner for fake iommu groups
  vfio/pci: Move the unused device into low power state with runtime PM
  vfio/pci: Virtualize PME related registers bits and initialize to zero
  vfio/pci: Change the PF power state to D0 before enabling VFs
  vfio/pci: Invalidate mmaps and block the access in D3hot power state
  vfio: Change struct vfio_group::container_users to a non-atomic int
  vfio: Simplify the life cycle of the group FD
  vfio: Fully lock struct vfio_group::container
  vfio: Split up vfio_group_get_device_fd()
  vfio: Change struct vfio_group::opened from an atomic to bool
  vfio: Add missing locking for struct vfio_group::kvm
  kvm/vfio: Fix potential deadlock problem in vfio
  include/uapi/linux/vfio.h: Fix trivial typo - _IORW should be _IOWR instead
  vfio/pci: Use the struct file as the handle not the vfio_group
  kvm/vfio: Remove vfio_group from kvm
  vfio: Change vfio_group_set_kvm() to vfio_file_set_kvm()
  vfio: Change vfio_external_check_extension() to vfio_file_enforced_coherent()
  vfio: Remove vfio_external_group_match_file()
  ...

4 files changed, 29 insertions, 34 deletions

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index b064bc278f52..5040cd774c5a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -447,6 +447,11 @@ struct mlx5_qp_table {
 	struct radix_tree_root	tree;
 };
 
+enum {
+	MLX5_PF_NOTIFY_DISABLE_VF,
+	MLX5_PF_NOTIFY_ENABLE_VF,
+};
+
 struct mlx5_vf_context {
 	int	enabled;
 	u64	port_guid;
@@ -457,6 +462,7 @@ struct mlx5_vf_context {
 	u8	port_guid_valid:1;
 	u8	node_guid_valid:1;
 	enum port_state_policy	policy;
+	struct blocking_notifier_head notifier;
 };
 
 struct mlx5_core_sriov {
@@ -1162,6 +1168,12 @@ int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type
 struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev);
 void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev);
 
+int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev,
+					  int vf_id,
+					  struct notifier_block *nb);
+void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev,
+					     int vf_id,
+					     struct notifier_block *nb);
 #ifdef CONFIG_MLX5_CORE_IPOIB
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  struct ib_device *ibdev,
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 66dda06ec42d..aa888cc51757 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -15,6 +15,8 @@
 #include <linux/poll.h>
 #include <uapi/linux/vfio.h>
 
+struct kvm;
+
 /*
  * VFIO devices can be placed in a set, this allows all devices to share this
  * structure and the VFIO core will provide a lock that is held around
@@ -34,6 +36,8 @@ struct vfio_device {
 	struct vfio_device_set *dev_set;
 	struct list_head dev_set_list;
 	unsigned int migration_flags;
+	/* Driver must reference the kvm during open_device or never touch it */
+	struct kvm *kvm;
 
 	/* Members below here are private, not for driver use */
 	refcount_t refcount;
@@ -125,8 +129,6 @@ void vfio_uninit_group_dev(struct vfio_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);
-extern struct vfio_device *vfio_device_get_from_dev(struct device *dev);
-extern void vfio_device_put(struct vfio_device *device);
 
 int vfio_assign_device_set(struct vfio_device *device, void *set_id);
 
@@ -138,56 +140,36 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 /*
  * 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 struct vfio_group *vfio_group_get_external_user_from_dev(struct device
-								*dev);
-extern bool vfio_external_group_match_file(struct vfio_group *group,
-					   struct file *filep);
-extern int vfio_external_user_iommu_id(struct vfio_group *group);
-extern long vfio_external_check_extension(struct vfio_group *group,
-					  unsigned long arg);
+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);
 
 #define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
 
-extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
+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 device *dev, unsigned long *user_pfn,
+extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
 			    int npage);
-
-extern int vfio_group_pin_pages(struct vfio_group *group,
-				unsigned long *user_iova_pfn, int npage,
-				int prot, unsigned long *phys_pfn);
-extern int vfio_group_unpin_pages(struct vfio_group *group,
-				  unsigned long *user_iova_pfn, int npage);
-
-extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
+extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,
 		       void *data, size_t len, bool write);
 
-extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group);
-
 /* 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,
+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 device *dev,
+extern int vfio_unregister_notifier(struct vfio_device *device,
 				    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
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 48f2dd3c568c..23c176d4b073 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -227,8 +227,9 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *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);
-int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn);
 extern const struct pci_error_handlers vfio_pci_core_err_handlers;
+int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
+				  int nr_virtfn);
 long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
 		unsigned long arg);
 int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags,
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index fea86061b44e..733a1cddde30 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -643,7 +643,7 @@ enum {
 };
 
 /**
- * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12,
+ * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12,
  *					      struct vfio_pci_hot_reset_info)
  *
  * Return: 0 on success, -errno on failure:
@@ -770,7 +770,7 @@ struct vfio_device_ioeventfd {
 #define VFIO_DEVICE_IOEVENTFD		_IO(VFIO_TYPE, VFIO_BASE + 16)
 
 /**
- * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17,
+ * VFIO_DEVICE_FEATURE - _IOWR(VFIO_TYPE, VFIO_BASE + 17,
  *			       struct vfio_device_feature)
  *
  * Get, set, or probe feature data of the device.  The feature is selected