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()
  ...

Documentation/driver-api/vfio-mediated-device.rst

@@ -262,10 +262,10 @@ Translation APIs for Mediated Devices
 The following APIs are provided for translating user pfn to host pfn in a VFIO
 driver::
 
-	extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
+	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,
+	int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
 				    int npage);
 
 These functions call back into the back-end IOMMU module by using the pin_pages

drivers/gpu/drm/i915/gvt/gtt.c

@@ -51,7 +51,7 @@ static int preallocated_oos_pages = 8192;
 
 static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn)
 {
-	struct kvm *kvm = vgpu->kvm;
+	struct kvm *kvm = vgpu->vfio_device.kvm;
 	int idx;
 	bool ret;
 
@@ -1185,7 +1185,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 
 	if (!vgpu->attached)
 		return -EINVAL;
-	pfn = gfn_to_pfn(vgpu->kvm, ops->get_pfn(entry));
+	pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
 	return PageTransHuge(pfn_to_page(pfn));

drivers/gpu/drm/i915/gvt/gvt.h

@@ -227,11 +227,7 @@ struct intel_vgpu {
 	struct mutex cache_lock;
 
 	struct notifier_block iommu_notifier;
-	struct notifier_block group_notifier;
-	struct kvm *kvm;
-	struct work_struct release_work;
 	atomic_t released;
-	struct vfio_group *vfio_group;
 
 	struct kvm_page_track_notifier_node track_node;
 #define NR_BKT (1 << 18)
@@ -732,7 +728,7 @@ static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa,
 {
 	if (!vgpu->attached)
 		return -ESRCH;
-	return vfio_dma_rw(vgpu->vfio_group, gpa, buf, len, false);
+	return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false);
 }
 
 /**
@@ -750,7 +746,7 @@ static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu,
 {
 	if (!vgpu->attached)
 		return -ESRCH;
-	return vfio_dma_rw(vgpu->vfio_group, gpa, buf, len, true);
+	return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true);
 }
 
 void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu);

drivers/gpu/drm/i915/gvt/kvmgt.c

@@ -228,8 +228,6 @@ static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt)
 	}
 }
 
-static void intel_vgpu_release_work(struct work_struct *work);
-
 static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 		unsigned long size)
 {
@@ -243,7 +241,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 	for (npage = 0; npage < total_pages; npage++) {
 		unsigned long cur_gfn = gfn + npage;
 
-		ret = vfio_group_unpin_pages(vgpu->vfio_group, &cur_gfn, 1);
+		ret = vfio_unpin_pages(&vgpu->vfio_device, &cur_gfn, 1);
 		drm_WARN_ON(&i915->drm, ret != 1);
 	}
 }
@@ -266,8 +264,8 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 		unsigned long cur_gfn = gfn + npage;
 		unsigned long pfn;
 
-		ret = vfio_group_pin_pages(vgpu->vfio_group, &cur_gfn, 1,
-					   IOMMU_READ | IOMMU_WRITE, &pfn);
+		ret = vfio_pin_pages(&vgpu->vfio_device, &cur_gfn, 1,
+				     IOMMU_READ | IOMMU_WRITE, &pfn);
 		if (ret != 1) {
 			gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n",
 				     cur_gfn, ret);
@@ -761,23 +759,6 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static int intel_vgpu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data)
-{
-	struct intel_vgpu *vgpu =
-		container_of(nb, struct intel_vgpu, group_notifier);
-
-	/* the only action we care about */
-	if (action == VFIO_GROUP_NOTIFY_SET_KVM) {
-		vgpu->kvm = data;
-
-		if (!data)
-			schedule_work(&vgpu->release_work);
-	}
-
-	return NOTIFY_OK;
-}
-
 static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)
 {
 	struct intel_vgpu *itr;
@@ -789,7 +770,7 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)
 		if (!itr->attached)
 			continue;
 
-		if (vgpu->kvm == itr->kvm) {
+		if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) {
 			ret = true;
 			goto out;
 		}
@@ -804,61 +785,44 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
 	unsigned long events;
 	int ret;
-	struct vfio_group *vfio_group;
 
 	vgpu->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier;
-	vgpu->group_notifier.notifier_call = intel_vgpu_group_notifier;
 
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(vfio_dev->dev, VFIO_IOMMU_NOTIFY, &events,
-				&vgpu->iommu_notifier);
+	ret = vfio_register_notifier(vfio_dev, VFIO_IOMMU_NOTIFY, &events,
+				     &vgpu->iommu_notifier);
 	if (ret != 0) {
 		gvt_vgpu_err("vfio_register_notifier for iommu failed: %d\n",
 			ret);
 		goto out;
 	}
 
-	events = VFIO_GROUP_NOTIFY_SET_KVM;
-	ret = vfio_register_notifier(vfio_dev->dev, VFIO_GROUP_NOTIFY, &events,
-				&vgpu->group_notifier);
-	if (ret != 0) {
-		gvt_vgpu_err("vfio_register_notifier for group failed: %d\n",
-			ret);
-		goto undo_iommu;
-	}
-
-	vfio_group =
-		vfio_group_get_external_user_from_dev(vgpu->vfio_device.dev);
-	if (IS_ERR_OR_NULL(vfio_group)) {
-		ret = !vfio_group ? -EFAULT : PTR_ERR(vfio_group);
-		gvt_vgpu_err("vfio_group_get_external_user_from_dev failed\n");
-		goto undo_register;
-	}
-	vgpu->vfio_group = vfio_group;
-
 	ret = -EEXIST;
 	if (vgpu->attached)
-		goto undo_group;
+		goto undo_iommu;
 
 	ret = -ESRCH;
-	if (!vgpu->kvm || vgpu->kvm->mm != current->mm) {
+	if (!vgpu->vfio_device.kvm ||
+	    vgpu->vfio_device.kvm->mm != current->mm) {
 		gvt_vgpu_err("KVM is required to use Intel vGPU\n");
-		goto undo_group;
+		goto undo_iommu;
 	}
 
+	kvm_get_kvm(vgpu->vfio_device.kvm);
+
 	ret = -EEXIST;
 	if (__kvmgt_vgpu_exist(vgpu))
-		goto undo_group;
+		goto undo_iommu;
 
 	vgpu->attached = true;
-	kvm_get_kvm(vgpu->kvm);
 
 	kvmgt_protect_table_init(vgpu);
 	gvt_cache_init(vgpu);
 
 	vgpu->track_node.track_write = kvmgt_page_track_write;
 	vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
-	kvm_page_track_register_notifier(vgpu->kvm, &vgpu->track_node);
+	kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
+					 &vgpu->track_node);
 
 	debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs,
 			     &vgpu->nr_cache_entries);
@@ -868,17 +832,9 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 	atomic_set(&vgpu->released, 0);
 	return 0;
 
-undo_group:
-	vfio_group_put_external_user(vgpu->vfio_group);
-	vgpu->vfio_group = NULL;
-
-undo_register:
-	vfio_unregister_notifier(vfio_dev->dev, VFIO_GROUP_NOTIFY,
-					&vgpu->group_notifier);
-
 undo_iommu:
-	vfio_unregister_notifier(vfio_dev->dev, VFIO_IOMMU_NOTIFY,
-					&vgpu->iommu_notifier);
+	vfio_unregister_notifier(vfio_dev, VFIO_IOMMU_NOTIFY,
+				 &vgpu->iommu_notifier);
 out:
 	return ret;
 }
@@ -894,8 +850,9 @@ static void intel_vgpu_release_msi_eventfd_ctx(struct intel_vgpu *vgpu)
 	}
 }
 
-static void __intel_vgpu_release(struct intel_vgpu *vgpu)
+static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
 {
+	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
 	struct drm_i915_private *i915 = vgpu->gvt->gt->i915;
 	int ret;
 
@@ -907,41 +864,24 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 
 	intel_gvt_release_vgpu(vgpu);
 
-	ret = vfio_unregister_notifier(vgpu->vfio_device.dev, VFIO_IOMMU_NOTIFY,
-					&vgpu->iommu_notifier);
+	ret = vfio_unregister_notifier(&vgpu->vfio_device, VFIO_IOMMU_NOTIFY,
+				       &vgpu->iommu_notifier);
 	drm_WARN(&i915->drm, ret,
 		 "vfio_unregister_notifier for iommu failed: %d\n", ret);
 
-	ret = vfio_unregister_notifier(vgpu->vfio_device.dev, VFIO_GROUP_NOTIFY,
-					&vgpu->group_notifier);
-	drm_WARN(&i915->drm, ret,
-		 "vfio_unregister_notifier for group failed: %d\n", ret);
-
 	debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
 
-	kvm_page_track_unregister_notifier(vgpu->kvm, &vgpu->track_node);
-	kvm_put_kvm(vgpu->kvm);
+	kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
+					   &vgpu->track_node);
 	kvmgt_protect_table_destroy(vgpu);
 	gvt_cache_destroy(vgpu);
 
 	intel_vgpu_release_msi_eventfd_ctx(vgpu);
-	vfio_group_put_external_user(vgpu->vfio_group);
 
-	vgpu->kvm = NULL;
 	vgpu->attached = false;
-}
-
-static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
-{
-	__intel_vgpu_release(vfio_dev_to_vgpu(vfio_dev));
-}
-
-static void intel_vgpu_release_work(struct work_struct *work)
-{
-	struct intel_vgpu *vgpu =
-		container_of(work, struct intel_vgpu, release_work);
 
-	__intel_vgpu_release(vgpu);
+	if (vgpu->vfio_device.kvm)
+		kvm_put_kvm(vgpu->vfio_device.kvm);
 }
 
 static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
@@ -1690,7 +1630,6 @@ static int intel_vgpu_probe(struct mdev_device *mdev)
 		return PTR_ERR(vgpu);
 	}
 
-	INIT_WORK(&vgpu->release_work, intel_vgpu_release_work);
 	vfio_init_group_dev(&vgpu->vfio_device, &mdev->dev,
 			    &intel_vgpu_dev_ops);
 
@@ -1728,7 +1667,7 @@ static struct mdev_driver intel_vgpu_mdev_driver = {
 
 int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->kvm;
+	struct kvm *kvm = info->vfio_device.kvm;
 	struct kvm_memory_slot *slot;
 	int idx;
 
@@ -1758,7 +1697,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 
 int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->kvm;
+	struct kvm *kvm = info->vfio_device.kvm;
 	struct kvm_memory_slot *slot;
 	int idx;
 

drivers/net/ethernet/mellanox/mlx5/core/sriov.c

@@ -87,6 +87,11 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 enable_vfs_hca:
 	num_msix_count = mlx5_get_default_msix_vec_count(dev, num_vfs);
 	for (vf = 0; vf < num_vfs; vf++) {
+		/* Notify the VF before its enablement to let it set
+		 * some stuff.
+		 */
+		blocking_notifier_call_chain(&sriov->vfs_ctx[vf].notifier,
+					     MLX5_PF_NOTIFY_ENABLE_VF, dev);
 		err = mlx5_core_enable_hca(dev, vf + 1);
 		if (err) {
 			mlx5_core_warn(dev, "failed to enable VF %d (%d)\n", vf, err);
@@ -127,6 +132,11 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf)
 	for (vf = num_vfs - 1; vf >= 0; vf--) {
 		if (!sriov->vfs_ctx[vf].enabled)
 			continue;
+		/* Notify the VF before its disablement to let it clean
+		 * some resources.
+		 */
+		blocking_notifier_call_chain(&sriov->vfs_ctx[vf].notifier,
+					     MLX5_PF_NOTIFY_DISABLE_VF, dev);
 		err = mlx5_core_disable_hca(dev, vf + 1);
 		if (err) {
 			mlx5_core_warn(dev, "failed to disable VF %d\n", vf);
@@ -257,7 +267,7 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
 	struct pci_dev *pdev = dev->pdev;
-	int total_vfs;
+	int total_vfs, i;
 
 	if (!mlx5_core_is_pf(dev))
 		return 0;
@@ -269,6 +279,9 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 	if (!sriov->vfs_ctx)
 		return -ENOMEM;
 
+	for (i = 0; i < total_vfs; i++)
+		BLOCKING_INIT_NOTIFIER_HEAD(&sriov->vfs_ctx[i].notifier);
+
 	return 0;
 }
 
@@ -281,3 +294,53 @@ void mlx5_sriov_cleanup(struct mlx5_core_dev *dev)
 
 	kfree(sriov->vfs_ctx);
 }
+
+/**
+ * mlx5_sriov_blocking_notifier_unregister - Unregister a VF from
+ * a notification block chain.
+ *
+ * @mdev: The mlx5 core device.
+ * @vf_id: The VF id.
+ * @nb: The notifier block to be unregistered.
+ */
+void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev,
+					     int vf_id,
+					     struct notifier_block *nb)
+{
+	struct mlx5_vf_context *vfs_ctx;
+	struct mlx5_core_sriov *sriov;
+
+	sriov = &mdev->priv.sriov;
+	if (WARN_ON(vf_id < 0 || vf_id >= sriov->num_vfs))
+		return;
+
+	vfs_ctx = &sriov->vfs_ctx[vf_id];
+	blocking_notifier_chain_unregister(&vfs_ctx->notifier, nb);
+}
+EXPORT_SYMBOL(mlx5_sriov_blocking_notifier_unregister);
+
+/**
+ * mlx5_sriov_blocking_notifier_register - Register a VF notification
+ * block chain.
+ *
+ * @mdev: The mlx5 core device.
+ * @vf_id: The VF id.
+ * @nb: The notifier block to be called upon the VF events.
+ *
+ * Returns 0 on success or an error code.
+ */
+int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev,
+					  int vf_id,
+					  struct notifier_block *nb)
+{
+	struct mlx5_vf_context *vfs_ctx;
+	struct mlx5_core_sriov *sriov;
+
+	sriov = &mdev->priv.sriov;
+	if (vf_id < 0 || vf_id >= sriov->num_vfs)
+		return -EINVAL;
+
+	vfs_ctx = &sriov->vfs_ctx[vf_id];
+	return blocking_notifier_chain_register(&vfs_ctx->notifier, nb);
+}
+EXPORT_SYMBOL(mlx5_sriov_blocking_notifier_register);

drivers/s390/cio/vfio_ccw_cp.c

@@ -16,6 +16,7 @@
 #include <asm/idals.h>
 
 #include "vfio_ccw_cp.h"
+#include "vfio_ccw_private.h"
 
 struct pfn_array {
 	/* Starting guest physical I/O address. */
@@ -98,17 +99,17 @@ static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len)
  * If the pin request partially succeeds, or fails completely,
  * all pages are left unpinned and a negative error value is returned.
  */
-static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
+static int pfn_array_pin(struct pfn_array *pa, struct vfio_device *vdev)
 {
 	int ret = 0;
 
-	ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
+	ret = vfio_pin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr,
 			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
 
 	if (ret < 0) {
 		goto err_out;
 	} else if (ret > 0 && ret != pa->pa_nr) {
-		vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
+		vfio_unpin_pages(vdev, pa->pa_iova_pfn, ret);
 		ret = -EINVAL;
 		goto err_out;
 	}
@@ -122,11 +123,11 @@ static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
 }
 
 /* Unpin the pages before releasing the memory. */
-static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
+static void pfn_array_unpin_free(struct pfn_array *pa, struct vfio_device *vdev)
 {
 	/* Only unpin if any pages were pinned to begin with */
 	if (pa->pa_nr)
-		vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
+		vfio_unpin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr);
 	pa->pa_nr = 0;
 	kfree(pa->pa_iova_pfn);
 }
@@ -190,8 +191,7 @@ static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
  * Within the domain (@mdev), copy @n bytes from a guest physical
  * address (@iova) to a host physical address (@to).
  */
-static long copy_from_iova(struct device *mdev,
-			   void *to, u64 iova,
+static long copy_from_iova(struct vfio_device *vdev, void *to, u64 iova,
 			   unsigned long n)
 {
 	struct pfn_array pa = {0};
@@ -203,9 +203,9 @@ static long copy_from_iova(struct device *mdev,
 	if (ret < 0)
 		return ret;
 
-	ret = pfn_array_pin(&pa, mdev);
+	ret = pfn_array_pin(&pa, vdev);
 	if (ret < 0) {
-		pfn_array_unpin_free(&pa, mdev);
+		pfn_array_unpin_free(&pa, vdev);
 		return ret;
 	}
 
@@ -226,7 +226,7 @@ static long copy_from_iova(struct device *mdev,
 			break;
 	}
 
-	pfn_array_unpin_free(&pa, mdev);
+	pfn_array_unpin_free(&pa, vdev);
 
 	return l;
 }
@@ -423,11 +423,13 @@ static int ccwchain_loop_tic(struct ccwchain *chain,
 
 static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	struct ccwchain *chain;
 	int len, ret;
 
 	/* Copy 2K (the most we support today) of possible CCWs */
-	len = copy_from_iova(cp->mdev, cp->guest_cp, cda,
+	len = copy_from_iova(vdev, cp->guest_cp, cda,
 			     CCWCHAIN_LEN_MAX * sizeof(struct ccw1));
 	if (len)
 		return len;
@@ -508,6 +510,8 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 				 int idx,
 				 struct channel_program *cp)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	struct ccw1 *ccw;
 	struct pfn_array *pa;
 	u64 iova;
@@ -526,7 +530,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	if (ccw_is_idal(ccw)) {
 		/* Read first IDAW to see if it's 4K-aligned or not. */
 		/* All subsequent IDAws will be 4K-aligned. */
-		ret = copy_from_iova(cp->mdev, &iova, ccw->cda, sizeof(iova));
+		ret = copy_from_iova(vdev, &iova, ccw->cda, sizeof(iova));
 		if (ret)
 			return ret;
 	} else {
@@ -555,7 +559,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 
 	if (ccw_is_idal(ccw)) {
 		/* Copy guest IDAL into host IDAL */
-		ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idal_len);
+		ret = copy_from_iova(vdev, idaws, ccw->cda, idal_len);
 		if (ret)
 			goto out_unpin;
 
@@ -574,7 +578,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	}
 
 	if (ccw_does_data_transfer(ccw)) {
-		ret = pfn_array_pin(pa, cp->mdev);
+		ret = pfn_array_pin(pa, vdev);
 		if (ret < 0)
 			goto out_unpin;
 	} else {
@@ -590,7 +594,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	return 0;
 
 out_unpin:
-	pfn_array_unpin_free(pa, cp->mdev);
+	pfn_array_unpin_free(pa, vdev);
 out_free_idaws:
 	kfree(idaws);
 out_init:
@@ -632,8 +636,10 @@ static int ccwchain_fetch_one(struct ccwchain *chain,
  * Returns:
  *   %0 on success and a negative error value on failure.
  */
-int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
+int cp_init(struct channel_program *cp, union orb *orb)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	/* custom ratelimit used to avoid flood during guest IPL */
 	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 1);
 	int ret;
@@ -650,11 +656,12 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
 	 * the problem if something does break.
 	 */
 	if (!orb->cmd.pfch && __ratelimit(&ratelimit_state))
-		dev_warn(mdev, "Prefetching channel program even though prefetch not specified in ORB");
+		dev_warn(
+			vdev->dev,
+			"Prefetching channel program even though prefetch not specified in ORB");
 
 	INIT_LIST_HEAD(&cp->ccwchain_list);
 	memcpy(&cp->orb, orb, sizeof(*orb));
-	cp->mdev = mdev;
 
 	/* Build a ccwchain for the first CCW segment */
 	ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
@@ -682,6 +689,8 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
  */
 void cp_free(struct channel_program *cp)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	struct ccwchain *chain, *temp;
 	int i;
 
@@ -691,7 +700,7 @@ void cp_free(struct channel_program *cp)
 	cp->initialized = false;
 	list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++) {
-			pfn_array_unpin_free(chain->ch_pa + i, cp->mdev);
+			pfn_array_unpin_free(chain->ch_pa + i, vdev);
 			ccwchain_cda_free(chain, i);
 		}
 		ccwchain_free(chain);

drivers/s390/cio/vfio_ccw_cp.h

@@ -37,13 +37,11 @@
 struct channel_program {
 	struct list_head ccwchain_list;
 	union orb orb;
-	struct device *mdev;
 	bool initialized;
 	struct ccw1 *guest_cp;
 };
 
-extern int cp_init(struct channel_program *cp, struct device *mdev,
-		   union orb *orb);
+extern int cp_init(struct channel_program *cp, union orb *orb);
 extern void cp_free(struct channel_program *cp);
 extern int cp_prefetch(struct channel_program *cp);
 extern union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm);

drivers/s390/cio/vfio_ccw_fsm.c

@@ -262,8 +262,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 			errstr = "transport mode";
 			goto err_out;
 		}
-		io_region->ret_code = cp_init(&private->cp, mdev_dev(mdev),
-					      orb);
+		io_region->ret_code = cp_init(&private->cp, orb);
 		if (io_region->ret_code) {
 			VFIO_CCW_MSG_EVENT(2,
 					   "%pUl (%x.%x.%04x): cp_init=%d\n",

drivers/s390/cio/vfio_ccw_ops.c

@@ -183,7 +183,7 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 
 	private->nb.notifier_call = vfio_ccw_mdev_notifier;
 
-	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
+	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY,
 				     &events, &private->nb);
 	if (ret)
 		return ret;
@@ -204,8 +204,7 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 
 out_unregister:
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
-				 &private->nb);
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 	return ret;
 }
 
@@ -223,7 +222,7 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 
 	cp_free(&private->cp);
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY, &private->nb);
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 }
 
 static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,

drivers/s390/crypto/vfio_ap_ops.c

@@ -124,8 +124,7 @@ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q)
 		q->saved_isc = VFIO_AP_ISC_INVALID;
 	}
 	if (q->saved_pfn && !WARN_ON(!q->matrix_mdev)) {
-		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev),
-				 &q->saved_pfn, 1);
+		vfio_unpin_pages(&q->matrix_mdev->vdev, &q->saved_pfn, 1);
 		q->saved_pfn = 0;
 	}
 }
@@ -258,7 +257,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		return status;
 	}
 
-	ret = vfio_pin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1,
+	ret = vfio_pin_pages(&q->matrix_mdev->vdev, &g_pfn, 1,
 			     IOMMU_READ | IOMMU_WRITE, &h_pfn);
 	switch (ret) {
 	case 1:
@@ -301,7 +300,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		break;
 	case AP_RESPONSE_OTHERWISE_CHANGED:
 		/* We could not modify IRQ setings: clear new configuration */
-		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1);
+		vfio_unpin_pages(&q->matrix_mdev->vdev, &g_pfn, 1);
 		kvm_s390_gisc_unregister(kvm, isc);
 		break;
 	default:
@@ -1250,7 +1249,7 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
 		struct vfio_iommu_type1_dma_unmap *unmap = data;
 		unsigned long g_pfn = unmap->iova >> PAGE_SHIFT;
 
-		vfio_unpin_pages(mdev_dev(matrix_mdev->mdev), &g_pfn, 1);
+		vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1);
 		return NOTIFY_OK;
 	}
 
@@ -1285,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 	}
 }
 
-static int vfio_ap_mdev_group_notifier(struct notifier_block *nb,
-				       unsigned long action, void *data)
-{
-	int notify_rc = NOTIFY_OK;
-	struct ap_matrix_mdev *matrix_mdev;
-
-	if (action != VFIO_GROUP_NOTIFY_SET_KVM)
-		return NOTIFY_OK;
-
-	matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);
-
-	if (!data)
-		vfio_ap_mdev_unset_kvm(matrix_mdev);
-	else if (vfio_ap_mdev_set_kvm(matrix_mdev, data))
-		notify_rc = NOTIFY_DONE;
-
-	return notify_rc;
-}
-
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn)
 {
 	struct device *dev;
@@ -1403,25 +1383,23 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)
 	unsigned long events;
 	int ret;
 
-	matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier;
-	events = VFIO_GROUP_NOTIFY_SET_KVM;
+	if (!vdev->kvm)
+		return -EINVAL;
 
-	ret = vfio_register_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
-				     &events, &matrix_mdev->group_notifier);
+	ret = vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm);
 	if (ret)
 		return ret;
 
 	matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier;
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
-				     &events, &matrix_mdev->iommu_notifier);
+	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events,
+				     &matrix_mdev->iommu_notifier);
 	if (ret)
-		goto out_unregister_group;
+		goto err_kvm;
 	return 0;
 
-out_unregister_group:
-	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
-				 &matrix_mdev->group_notifier);
+err_kvm:
+	vfio_ap_mdev_unset_kvm(matrix_mdev);
 	return ret;
 }
 
@@ -1430,10 +1408,8 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)
 	struct ap_matrix_mdev *matrix_mdev =
 		container_of(vdev, struct ap_matrix_mdev, vdev);
 
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY,
 				 &matrix_mdev->iommu_notifier);
-	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
-				 &matrix_mdev->group_notifier);
 	vfio_ap_mdev_unset_kvm(matrix_mdev);
 }
 

drivers/s390/crypto/vfio_ap_private.h

@@ -81,8 +81,6 @@ struct ap_matrix {
  * @node:	allows the ap_matrix_mdev struct to be added to a list
  * @matrix:	the adapters, usage domains and control domains assigned to the
  *		mediated matrix device.
- * @group_notifier: notifier block used for specifying callback function for
- *		    handling the VFIO_GROUP_NOTIFY_SET_KVM event
  * @iommu_notifier: notifier block used for specifying callback function for
  *		    handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even
  * @kvm:	the struct holding guest's state
@@ -94,7 +92,6 @@ struct ap_matrix_mdev {
 	struct vfio_device vdev;
 	struct list_head node;
 	struct ap_matrix matrix;
-	struct notifier_block group_notifier;
 	struct notifier_block iommu_notifier;
 	struct kvm *kvm;
 	crypto_hook pqap_hook;

drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c

@@ -337,6 +337,14 @@ static int vf_qm_cache_wb(struct hisi_qm *qm)
 	return 0;
 }
 
+static struct hisi_acc_vf_core_device *hssi_acc_drvdata(struct pci_dev *pdev)
+{
+	struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev);
+
+	return container_of(core_device, struct hisi_acc_vf_core_device,
+			    core_device);
+}
+
 static void vf_qm_fun_reset(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 			    struct hisi_qm *qm)
 {
@@ -962,7 +970,7 @@ hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
 
 static void hisi_acc_vf_pci_aer_reset_done(struct pci_dev *pdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = dev_get_drvdata(&pdev->dev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hssi_acc_drvdata(pdev);
 
 	if (hisi_acc_vdev->core_device.vdev.migration_flags !=
 				VFIO_MIGRATION_STOP_COPY)
@@ -1274,11 +1282,10 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
 					  &hisi_acc_vfio_pci_ops);
 	}
 
+	dev_set_drvdata(&pdev->dev, &hisi_acc_vdev->core_device);
 	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
 	if (ret)
 		goto out_free;
-
-	dev_set_drvdata(&pdev->dev, hisi_acc_vdev);
 	return 0;
 
 out_free:
@@ -1289,7 +1296,7 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
 
 static void hisi_acc_vfio_pci_remove(struct pci_dev *pdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = dev_get_drvdata(&pdev->dev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hssi_acc_drvdata(pdev);
 
 	vfio_pci_core_unregister_device(&hisi_acc_vdev->core_device);
 	vfio_pci_core_uninit_device(&hisi_acc_vdev->core_device);
@@ -1316,6 +1323,7 @@ static struct pci_driver hisi_acc_vfio_pci_driver = {
 	.probe = hisi_acc_vfio_pci_probe,
 	.remove = hisi_acc_vfio_pci_remove,
 	.err_handler = &hisi_acc_vf_err_handlers,
+	.driver_managed_dma = true,
 };
 
 module_pci_driver(hisi_acc_vfio_pci_driver);

drivers/vfio/pci/mlx5/cmd.h

@@ -7,12 +7,23 @@
 #define MLX5_VFIO_CMD_H
 
 #include <linux/kernel.h>
+#include <linux/vfio_pci_core.h>
 #include <linux/mlx5/driver.h>
 
+struct mlx5vf_async_data {
+	struct mlx5_async_work cb_work;
+	struct work_struct work;
+	int status;
+	u32 pdn;
+	u32 mkey;
+	void *out;
+};
+
 struct mlx5_vf_migration_file {
 	struct file *filp;
 	struct mutex lock;
-	bool disabled;
+	u8 disabled:1;
+	u8 is_err:1;
 
 	struct sg_append_table table;
 	size_t total_length;
@@ -22,15 +33,42 @@ struct mlx5_vf_migration_file {
 	struct scatterlist *last_offset_sg;
 	unsigned int sg_last_entry;
 	unsigned long last_offset;
+	struct mlx5vf_pci_core_device *mvdev;
+	wait_queue_head_t poll_wait;
+	struct mlx5_async_ctx async_ctx;
+	struct mlx5vf_async_data async_data;
+};
+
+struct mlx5vf_pci_core_device {
+	struct vfio_pci_core_device core_device;
+	int vf_id;
+	u16 vhca_id;
+	u8 migrate_cap:1;
+	u8 deferred_reset:1;
+	u8 mdev_detach:1;
+	/* protect migration state */
+	struct mutex state_mutex;
+	enum vfio_device_mig_state mig_state;
+	/* protect the reset_done flow */
+	spinlock_t reset_lock;
+	struct mlx5_vf_migration_file *resuming_migf;
+	struct mlx5_vf_migration_file *saving_migf;
+	struct workqueue_struct *cb_wq;
+	struct notifier_block nb;
+	struct mlx5_core_dev *mdev;
 };
 
-int mlx5vf_cmd_suspend_vhca(struct pci_dev *pdev, u16 vhca_id, u16 op_mod);
-int mlx5vf_cmd_resume_vhca(struct pci_dev *pdev, u16 vhca_id, u16 op_mod);
-int mlx5vf_cmd_query_vhca_migration_state(struct pci_dev *pdev, u16 vhca_id,
+int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
+int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
+int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
 					  size_t *state_size);
-int mlx5vf_cmd_get_vhca_id(struct pci_dev *pdev, u16 function_id, u16 *vhca_id);
-int mlx5vf_cmd_save_vhca_state(struct pci_dev *pdev, u16 vhca_id,
+void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev);
+void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev);
+int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 			       struct mlx5_vf_migration_file *migf);
-int mlx5vf_cmd_load_vhca_state(struct pci_dev *pdev, u16 vhca_id,
+int mlx5vf_cmd_load_vhca_state(struct mlx5vf_pci_core_device *mvdev,
 			       struct mlx5_vf_migration_file *migf);
+void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev);
+void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev);
+void mlx5vf_mig_file_cleanup_cb(struct work_struct *_work);
 #endif /* MLX5_VFIO_CMD_H */

drivers/vfio/pci/mlx5/main.c

@@ -17,7 +17,6 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/sched/mm.h>
-#include <linux/vfio_pci_core.h>
 #include <linux/anon_inodes.h>
 
 #include "cmd.h"
@@ -25,19 +24,13 @@
 /* Arbitrary to prevent userspace from consuming endless memory */
 #define MAX_MIGRATION_SIZE (512*1024*1024)
 
-struct mlx5vf_pci_core_device {
-	struct vfio_pci_core_device core_device;
-	u16 vhca_id;
-	u8 migrate_cap:1;
-	u8 deferred_reset:1;
-	/* protect migration state */
-	struct mutex state_mutex;
-	enum vfio_device_mig_state mig_state;
-	/* protect the reset_done flow */
-	spinlock_t reset_lock;
-	struct mlx5_vf_migration_file *resuming_migf;
-	struct mlx5_vf_migration_file *saving_migf;
-};
+static struct mlx5vf_pci_core_device *mlx5vf_drvdata(struct pci_dev *pdev)
+{
+	struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev);
+
+	return container_of(core_device, struct mlx5vf_pci_core_device,
+			    core_device);
+}
 
 static struct page *
 mlx5vf_get_migration_page(struct mlx5_vf_migration_file *migf,
@@ -149,12 +142,22 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
 		return -ESPIPE;
 	pos = &filp->f_pos;
 
+	if (!(filp->f_flags & O_NONBLOCK)) {
+		if (wait_event_interruptible(migf->poll_wait,
+			     READ_ONCE(migf->total_length) || migf->is_err))
+			return -ERESTARTSYS;
+	}
+
 	mutex_lock(&migf->lock);
+	if ((filp->f_flags & O_NONBLOCK) && !READ_ONCE(migf->total_length)) {
+		done = -EAGAIN;
+		goto out_unlock;
+	}
 	if (*pos > migf->total_length) {
 		done = -EINVAL;
 		goto out_unlock;
 	}
-	if (migf->disabled) {
+	if (migf->disabled || migf->is_err) {
 		done = -ENODEV;
 		goto out_unlock;
 	}
@@ -194,9 +197,28 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
 	return done;
 }
 
+static __poll_t mlx5vf_save_poll(struct file *filp,
+				 struct poll_table_struct *wait)
+{
+	struct mlx5_vf_migration_file *migf = filp->private_data;
+	__poll_t pollflags = 0;
+
+	poll_wait(filp, &migf->poll_wait, wait);
+
+	mutex_lock(&migf->lock);
+	if (migf->disabled || migf->is_err)
+		pollflags = EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+	else if (READ_ONCE(migf->total_length))
+		pollflags = EPOLLIN | EPOLLRDNORM;
+	mutex_unlock(&migf->lock);
+
+	return pollflags;
+}
+
 static const struct file_operations mlx5vf_save_fops = {
 	.owner = THIS_MODULE,
 	.read = mlx5vf_save_read,
+	.poll = mlx5vf_save_poll,
 	.release = mlx5vf_release_file,
 	.llseek = no_llseek,
 };
@@ -222,9 +244,11 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
 
 	stream_open(migf->filp->f_inode, migf->filp);
 	mutex_init(&migf->lock);
-
-	ret = mlx5vf_cmd_query_vhca_migration_state(
-		mvdev->core_device.pdev, mvdev->vhca_id, &migf->total_length);
+	init_waitqueue_head(&migf->poll_wait);
+	mlx5_cmd_init_async_ctx(mvdev->mdev, &migf->async_ctx);
+	INIT_WORK(&migf->async_data.work, mlx5vf_mig_file_cleanup_cb);
+	ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
+						    &migf->total_length);
 	if (ret)
 		goto out_free;
 
@@ -233,8 +257,8 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
 	if (ret)
 		goto out_free;
 
-	ret = mlx5vf_cmd_save_vhca_state(mvdev->core_device.pdev,
-					 mvdev->vhca_id, migf);
+	migf->mvdev = mvdev;
+	ret = mlx5vf_cmd_save_vhca_state(mvdev, migf);
 	if (ret)
 		goto out_free;
 	return migf;
@@ -339,7 +363,7 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
 	return migf;
 }
 
-static void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
+void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
 {
 	if (mvdev->resuming_migf) {
 		mlx5vf_disable_fd(mvdev->resuming_migf);
@@ -347,6 +371,8 @@ static void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
 		mvdev->resuming_migf = NULL;
 	}
 	if (mvdev->saving_migf) {
+		mlx5_cmd_cleanup_async_ctx(&mvdev->saving_migf->async_ctx);
+		cancel_work_sync(&mvdev->saving_migf->async_data.work);
 		mlx5vf_disable_fd(mvdev->saving_migf);
 		fput(mvdev->saving_migf->filp);
 		mvdev->saving_migf = NULL;
@@ -361,8 +387,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
 	int ret;
 
 	if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_STOP) {
-		ret = mlx5vf_cmd_suspend_vhca(
-			mvdev->core_device.pdev, mvdev->vhca_id,
+		ret = mlx5vf_cmd_suspend_vhca(mvdev,
 			MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER);
 		if (ret)
 			return ERR_PTR(ret);
@@ -370,8 +395,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
 	}
 
 	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
-		ret = mlx5vf_cmd_resume_vhca(
-			mvdev->core_device.pdev, mvdev->vhca_id,
+		ret = mlx5vf_cmd_resume_vhca(mvdev,
 			MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_RESPONDER);
 		if (ret)
 			return ERR_PTR(ret);
@@ -379,8 +403,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
 	}
 
 	if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
-		ret = mlx5vf_cmd_suspend_vhca(
-			mvdev->core_device.pdev, mvdev->vhca_id,
+		ret = mlx5vf_cmd_suspend_vhca(mvdev,
 			MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR);
 		if (ret)
 			return ERR_PTR(ret);
@@ -388,8 +411,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
 	}
 
 	if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
-		ret = mlx5vf_cmd_resume_vhca(
-			mvdev->core_device.pdev, mvdev->vhca_id,
+		ret = mlx5vf_cmd_resume_vhca(mvdev,
 			MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR);
 		if (ret)
 			return ERR_PTR(ret);
@@ -424,8 +446,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
 	}
 
 	if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
-		ret = mlx5vf_cmd_load_vhca_state(mvdev->core_device.pdev,
-						 mvdev->vhca_id,
+		ret = mlx5vf_cmd_load_vhca_state(mvdev,
 						 mvdev->resuming_migf);
 		if (ret)
 			return ERR_PTR(ret);
@@ -444,7 +465,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
  * This function is called in all state_mutex unlock cases to
  * handle a 'deferred_reset' if exists.
  */
-static void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
+void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
 {
 again:
 	spin_lock(&mvdev->reset_lock);
@@ -505,7 +526,7 @@ static int mlx5vf_pci_get_device_state(struct vfio_device *vdev,
 
 static void mlx5vf_pci_aer_reset_done(struct pci_dev *pdev)
 {
-	struct mlx5vf_pci_core_device *mvdev = dev_get_drvdata(&pdev->dev);
+	struct mlx5vf_pci_core_device *mvdev = mlx5vf_drvdata(pdev);
 
 	if (!mvdev->migrate_cap)
 		return;
@@ -532,34 +553,16 @@ static int mlx5vf_pci_open_device(struct vfio_device *core_vdev)
 	struct mlx5vf_pci_core_device *mvdev = container_of(
 		core_vdev, struct mlx5vf_pci_core_device, core_device.vdev);
 	struct vfio_pci_core_device *vdev = &mvdev->core_device;
-	int vf_id;
 	int ret;
 
 	ret = vfio_pci_core_enable(vdev);
 	if (ret)
 		return ret;
 
-	if (!mvdev->migrate_cap) {
-		vfio_pci_core_finish_enable(vdev);
-		return 0;
-	}
-
-	vf_id = pci_iov_vf_id(vdev->pdev);
-	if (vf_id < 0) {
-		ret = vf_id;
-		goto out_disable;
-	}
-
-	ret = mlx5vf_cmd_get_vhca_id(vdev->pdev, vf_id + 1, &mvdev->vhca_id);
-	if (ret)
-		goto out_disable;
-
-	mvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+	if (mvdev->migrate_cap)
+		mvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
 	vfio_pci_core_finish_enable(vdev);
 	return 0;
-out_disable:
-	vfio_pci_core_disable(vdev);
-	return ret;
 }
 
 static void mlx5vf_pci_close_device(struct vfio_device *core_vdev)
@@ -596,32 +599,15 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
 	if (!mvdev)
 		return -ENOMEM;
 	vfio_pci_core_init_device(&mvdev->core_device, pdev, &mlx5vf_pci_ops);
-
-	if (pdev->is_virtfn) {
-		struct mlx5_core_dev *mdev =
-			mlx5_vf_get_core_dev(pdev);
-
-		if (mdev) {
-			if (MLX5_CAP_GEN(mdev, migration)) {
-				mvdev->migrate_cap = 1;
-				mvdev->core_device.vdev.migration_flags =
-					VFIO_MIGRATION_STOP_COPY |
-					VFIO_MIGRATION_P2P;
-				mutex_init(&mvdev->state_mutex);
-				spin_lock_init(&mvdev->reset_lock);
-			}
-			mlx5_vf_put_core_dev(mdev);
-		}
-	}
-
+	mlx5vf_cmd_set_migratable(mvdev);
+	dev_set_drvdata(&pdev->dev, &mvdev->core_device);
 	ret = vfio_pci_core_register_device(&mvdev->core_device);
 	if (ret)
 		goto out_free;
-
-	dev_set_drvdata(&pdev->dev, mvdev);
 	return 0;
 
 out_free:
+	mlx5vf_cmd_remove_migratable(mvdev);
 	vfio_pci_core_uninit_device(&mvdev->core_device);
 	kfree(mvdev);
 	return ret;
@@ -629,9 +615,10 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
 
 static void mlx5vf_pci_remove(struct pci_dev *pdev)
 {
-	struct mlx5vf_pci_core_device *mvdev = dev_get_drvdata(&pdev->dev);
+	struct mlx5vf_pci_core_device *mvdev = mlx5vf_drvdata(pdev);
 
 	vfio_pci_core_unregister_device(&mvdev->core_device);
+	mlx5vf_cmd_remove_migratable(mvdev);
 	vfio_pci_core_uninit_device(&mvdev->core_device);
 	kfree(mvdev);
 }
@@ -654,6 +641,7 @@ static struct pci_driver mlx5vf_pci_driver = {
 	.probe = mlx5vf_pci_probe,
 	.remove = mlx5vf_pci_remove,
 	.err_handler = &mlx5vf_err_handlers,
+	.driver_managed_dma = true,
 };
 
 static void __exit mlx5vf_pci_cleanup(void)

drivers/vfio/pci/vfio_pci.c

@@ -151,10 +151,10 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 	vfio_pci_core_init_device(vdev, pdev, &vfio_pci_ops);
 
+	dev_set_drvdata(&pdev->dev, vdev);
 	ret = vfio_pci_core_register_device(vdev);
 	if (ret)
 		goto out_free;
-	dev_set_drvdata(&pdev->dev, vdev);
 	return 0;
 
 out_free:
@@ -174,10 +174,12 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 
 static int vfio_pci_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
 {
+	struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev);
+
 	if (!enable_sriov)
 		return -ENOENT;
 
-	return vfio_pci_core_sriov_configure(pdev, nr_virtfn);
+	return vfio_pci_core_sriov_configure(vdev, nr_virtfn);
 }
 
 static const struct pci_device_id vfio_pci_table[] = {

drivers/vfio/pci/vfio_pci_config.c

@@ -402,11 +402,14 @@ bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev)
 	u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
 
 	/*
+	 * Memory region cannot be accessed if device power state is D3.
+	 *
 	 * SR-IOV VF memory enable is handled by the MSE bit in the
 	 * PF SR-IOV capability, there's therefore no need to trigger
 	 * faults based on the virtual value.
 	 */
-	return pdev->no_command_memory || (cmd & PCI_COMMAND_MEMORY);
+	return pdev->current_state < PCI_D3hot &&
+	       (pdev->no_command_memory || (cmd & PCI_COMMAND_MEMORY));
 }
 
 /*
@@ -692,6 +695,22 @@ static int __init init_pci_cap_basic_perm(struct perm_bits *perm)
 	return 0;
 }
 
+/*
+ * It takes all the required locks to protect the access of power related
+ * variables and then invokes vfio_pci_set_power_state().
+ */
+static void vfio_lock_and_set_power_state(struct vfio_pci_core_device *vdev,
+					  pci_power_t state)
+{
+	if (state >= PCI_D3hot)
+		vfio_pci_zap_and_down_write_memory_lock(vdev);
+	else
+		down_write(&vdev->memory_lock);
+
+	vfio_pci_set_power_state(vdev, state);
+	up_write(&vdev->memory_lock);
+}
+
 static int vfio_pm_config_write(struct vfio_pci_core_device *vdev, int pos,
 				int count, struct perm_bits *perm,
 				int offset, __le32 val)
@@ -718,7 +737,7 @@ static int vfio_pm_config_write(struct vfio_pci_core_device *vdev, int pos,
 			break;
 		}
 
-		vfio_pci_set_power_state(vdev, state);
+		vfio_lock_and_set_power_state(vdev, state);
 	}
 
 	return count;
@@ -738,12 +757,29 @@ static int __init init_pci_cap_pm_perm(struct perm_bits *perm)
 	 */
 	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
 
+	/*
+	 * The guests can't process PME events. If any PME event will be
+	 * generated, then it will be mostly handled in the host and the
+	 * host will clear the PME_STATUS. So virtualize PME_Support bits.
+	 * The vconfig bits will be cleared during device capability
+	 * initialization.
+	 */
+	p_setw(perm, PCI_PM_PMC, PCI_PM_CAP_PME_MASK, NO_WRITE);
+
 	/*
 	 * Power management is defined *per function*, so we can let
 	 * the user change power state, but we trap and initiate the
 	 * change ourselves, so the state bits are read-only.
+	 *
+	 * The guest can't process PME from D3cold so virtualize PME_Status
+	 * and PME_En bits. The vconfig bits will be cleared during device
+	 * capability initialization.
 	 */
-	p_setd(perm, PCI_PM_CTRL, NO_VIRT, ~PCI_PM_CTRL_STATE_MASK);
+	p_setd(perm, PCI_PM_CTRL,
+	       PCI_PM_CTRL_PME_ENABLE | PCI_PM_CTRL_PME_STATUS,
+	       ~(PCI_PM_CTRL_PME_ENABLE | PCI_PM_CTRL_PME_STATUS |
+		 PCI_PM_CTRL_STATE_MASK));
+
 	return 0;
 }
 
@@ -1412,6 +1448,17 @@ static int vfio_ext_cap_len(struct vfio_pci_core_device *vdev, u16 ecap, u16 epo
 	return 0;
 }
 
+static void vfio_update_pm_vconfig_bytes(struct vfio_pci_core_device *vdev,
+					 int offset)
+{
+	__le16 *pmc = (__le16 *)&vdev->vconfig[offset + PCI_PM_PMC];
+	__le16 *ctrl = (__le16 *)&vdev->vconfig[offset + PCI_PM_CTRL];
+
+	/* Clear vconfig PME_Support, PME_Status, and PME_En bits */
+	*pmc &= ~cpu_to_le16(PCI_PM_CAP_PME_MASK);
+	*ctrl &= ~cpu_to_le16(PCI_PM_CTRL_PME_ENABLE | PCI_PM_CTRL_PME_STATUS);
+}
+
 static int vfio_fill_vconfig_bytes(struct vfio_pci_core_device *vdev,
 				   int offset, int size)
 {
@@ -1535,6 +1582,9 @@ static int vfio_cap_init(struct vfio_pci_core_device *vdev)
 		if (ret)
 			return ret;
 
+		if (cap == PCI_CAP_ID_PM)
+			vfio_update_pm_vconfig_bytes(vdev, pos);
+
 		prev = &vdev->vconfig[pos + PCI_CAP_LIST_NEXT];
 		pos = next;
 		caps++;

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,

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

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,

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