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()
  ...

Author: torvalds

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);