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
  ...

6 files changed, 40 insertions, 11 deletions

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 4def43f5f7b6..ea762e28c1cc 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -1185,7 +1185,7 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 	if (ret)
 		return ret;
 
-	if (core_vdev->ops->migration_set_state) {
+	if (core_vdev->mig_ops) {
 		ret = hisi_acc_vf_qm_init(hisi_acc_vdev);
 		if (ret) {
 			vfio_pci_core_disable(vdev);
@@ -1208,6 +1208,11 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 	vfio_pci_core_close_device(core_vdev);
 }
 
+static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = {
+	.migration_set_state = hisi_acc_vfio_pci_set_device_state,
+	.migration_get_state = hisi_acc_vfio_pci_get_device_state,
+};
+
 static const struct vfio_device_ops hisi_acc_vfio_pci_migrn_ops = {
 	.name = "hisi-acc-vfio-pci-migration",
 	.open_device = hisi_acc_vfio_pci_open_device,
@@ -1219,8 +1224,6 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_migrn_ops = {
 	.mmap = hisi_acc_vfio_pci_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
-	.migration_set_state = hisi_acc_vfio_pci_set_device_state,
-	.migration_get_state = hisi_acc_vfio_pci_get_device_state,
 };
 
 static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
@@ -1272,6 +1275,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
 		if (!ret) {
 			vfio_pci_core_init_device(&hisi_acc_vdev->core_device, pdev,
 						  &hisi_acc_vfio_pci_migrn_ops);
+			hisi_acc_vdev->core_device.vdev.mig_ops =
+					&hisi_acc_vfio_pci_migrn_state_ops;
 		} else {
 			pci_warn(pdev, "migration support failed, continue with generic interface\n");
 			vfio_pci_core_init_device(&hisi_acc_vdev->core_device, pdev,
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index 9b9f33ca270a..dd5d7bfe0a49 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -88,6 +88,16 @@ static int mlx5fv_vf_event(struct notifier_block *nb,
 	return 0;
 }
 
+void mlx5vf_cmd_close_migratable(struct mlx5vf_pci_core_device *mvdev)
+{
+	if (!mvdev->migrate_cap)
+		return;
+
+	mutex_lock(&mvdev->state_mutex);
+	mlx5vf_disable_fds(mvdev);
+	mlx5vf_state_mutex_unlock(mvdev);
+}
+
 void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev)
 {
 	if (!mvdev->migrate_cap)
@@ -98,7 +108,8 @@ void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev)
 	destroy_workqueue(mvdev->cb_wq);
 }
 
-void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev)
+void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev,
+			       const struct vfio_migration_ops *mig_ops)
 {
 	struct pci_dev *pdev = mvdev->core_device.pdev;
 	int ret;
@@ -139,6 +150,7 @@ void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev)
 	mvdev->core_device.vdev.migration_flags =
 		VFIO_MIGRATION_STOP_COPY |
 		VFIO_MIGRATION_P2P;
+	mvdev->core_device.vdev.mig_ops = mig_ops;
 
 end:
 	mlx5_vf_put_core_dev(mvdev->mdev);
diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index 6c3112fdd8b1..8208f4701a90 100644
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -62,8 +62,10 @@ 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);
-void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev);
+void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev,
+			       const struct vfio_migration_ops *mig_ops);
 void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev);
+void mlx5vf_cmd_close_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 mlx5vf_pci_core_device *mvdev,
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 0558d0649ddb..a9b63d15c5d3 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -570,10 +570,15 @@ static void mlx5vf_pci_close_device(struct vfio_device *core_vdev)
 	struct mlx5vf_pci_core_device *mvdev = container_of(
 		core_vdev, struct mlx5vf_pci_core_device, core_device.vdev);
 
-	mlx5vf_disable_fds(mvdev);
+	mlx5vf_cmd_close_migratable(mvdev);
 	vfio_pci_core_close_device(core_vdev);
 }
 
+static const struct vfio_migration_ops mlx5vf_pci_mig_ops = {
+	.migration_set_state = mlx5vf_pci_set_device_state,
+	.migration_get_state = mlx5vf_pci_get_device_state,
+};
+
 static const struct vfio_device_ops mlx5vf_pci_ops = {
 	.name = "mlx5-vfio-pci",
 	.open_device = mlx5vf_pci_open_device,
@@ -585,8 +590,6 @@ static const struct vfio_device_ops mlx5vf_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
-	.migration_set_state = mlx5vf_pci_set_device_state,
-	.migration_get_state = mlx5vf_pci_get_device_state,
 };
 
 static int mlx5vf_pci_probe(struct pci_dev *pdev,
@@ -599,7 +602,7 @@ 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);
-	mlx5vf_cmd_set_migratable(mvdev);
+	mlx5vf_cmd_set_migratable(mvdev, &mlx5vf_pci_mig_ops);
 	dev_set_drvdata(&pdev->dev, &mvdev->core_device);
 	ret = vfio_pci_core_register_device(&mvdev->core_device);
 	if (ret)
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 9343f597182d..442d3ba4122b 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -222,7 +222,7 @@ static int vfio_default_config_write(struct vfio_pci_core_device *vdev, int pos,
 		memcpy(vdev->vconfig + pos, &virt_val, count);
 	}
 
-	/* Non-virtualzed and writable bits go to hardware */
+	/* Non-virtualized and writable bits go to hardware */
 	if (write & ~virt) {
 		struct pci_dev *pdev = vdev->pdev;
 		__le32 phys_val = 0;
@@ -1728,7 +1728,7 @@ int vfio_config_init(struct vfio_pci_core_device *vdev)
 	/*
 	 * Config space, caps and ecaps are all dword aligned, so we could
 	 * use one byte per dword to record the type.  However, there are
-	 * no requiremenst on the length of a capability, so the gap between
+	 * no requirements on the length of a capability, so the gap between
 	 * capabilities needs byte granularity.
 	 */
 	map = kmalloc(pdev->cfg_size, GFP_KERNEL);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 0d8d4cdfb2f0..c8d3b0450fb3 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1868,6 +1868,13 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
 	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
+	if (vdev->vdev.mig_ops) {
+		if (!(vdev->vdev.mig_ops->migration_get_state &&
+		      vdev->vdev.mig_ops->migration_set_state) ||
+		    !(vdev->vdev.migration_flags & VFIO_MIGRATION_STOP_COPY))
+			return -EINVAL;
+	}
+
 	/*
 	 * Prevent binding to PFs with VFs enabled, the VFs might be in use
 	 * by the host or other users.  We cannot capture the VFs if they