Merge tag 'vfio-v5.2-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Improve dev_printk() usage (Bjorn Helgaas)

 - Fix issue with blocking in !TASK_RUNNING state while waiting for
   userspace to release devices (Farhan Ali)

 - Fix error path cleanup in nvlink setup (Greg Kurz)

 - mdev-core cleanups and fixes in preparation for more use cases (Parav
   Pandit)

 - Cornelia has volunteered as an official vfio reviewer (Cornelia Huck)

* tag 'vfio-v5.2-rc1' of git://github.com/awilliam/linux-vfio:
  vfio: Add Cornelia Huck as reviewer
  vfio/mdev: Avoid inline get and put parent helpers
  vfio/mdev: Fix aborting mdev child device removal if one fails
  vfio/mdev: Follow correct remove sequence
  vfio/mdev: Avoid masking error code to EBUSY
  vfio/mdev: Drop redundant extern for exported symbols
  vfio/mdev: Removed unused kref
  vfio/mdev: Avoid release parent reference during error path
  vfio-pci/nvlink2: Fix potential VMA leak
  vfio: Fix WARNING "do not call blocking ops when !TASK_RUNNING"
  vfio: Use dev_printk() when possible

9 files changed, 67 insertions, 84 deletions

diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index b96fedc77ee5..1040a4a2dcbc 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -88,7 +88,7 @@ static void mdev_release_parent(struct kref *kref)
 	put_device(dev);
 }
 
-static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
+static struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
 {
 	if (parent)
 		kref_get(&parent->ref);
@@ -96,7 +96,7 @@ static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
 	return parent;
 }
 
-static inline void mdev_put_parent(struct mdev_parent *parent)
+static void mdev_put_parent(struct mdev_parent *parent)
 {
 	if (parent)
 		kref_put(&parent->ref, mdev_release_parent);
@@ -141,7 +141,7 @@ static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
 	 */
 	ret = parent->ops->remove(mdev);
 	if (ret && !force_remove)
-		return -EBUSY;
+		return ret;
 
 	sysfs_remove_groups(&mdev->dev.kobj, parent->ops->mdev_attr_groups);
 	return 0;
@@ -149,10 +149,10 @@ static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
 
 static int mdev_device_remove_cb(struct device *dev, void *data)
 {
-	if (!dev_is_mdev(dev))
-		return 0;
+	if (dev_is_mdev(dev))
+		mdev_device_remove(dev, true);
 
-	return mdev_device_remove(dev, data ? *(bool *)data : true);
+	return 0;
 }
 
 /*
@@ -181,6 +181,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	/* Check for duplicate */
 	parent = __find_parent_device(dev);
 	if (parent) {
+		parent = NULL;
 		ret = -EEXIST;
 		goto add_dev_err;
 	}
@@ -239,7 +240,6 @@ EXPORT_SYMBOL(mdev_register_device);
 void mdev_unregister_device(struct device *dev)
 {
 	struct mdev_parent *parent;
-	bool force_remove = true;
 
 	mutex_lock(&parent_list_lock);
 	parent = __find_parent_device(dev);
@@ -253,8 +253,7 @@ void mdev_unregister_device(struct device *dev)
 	list_del(&parent->next);
 	class_compat_remove_link(mdev_bus_compat_class, dev, NULL);
 
-	device_for_each_child(dev, (void *)&force_remove,
-			      mdev_device_remove_cb);
+	device_for_each_child(dev, NULL, mdev_device_remove_cb);
 
 	parent_remove_sysfs_files(parent);
 
@@ -310,7 +309,6 @@ int mdev_device_create(struct kobject *kobj,
 	mutex_unlock(&mdev_list_lock);
 
 	mdev->parent = parent;
-	kref_init(&mdev->ref);
 
 	mdev->dev.parent  = dev;
 	mdev->dev.bus     = &mdev_bus_type;
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index 379758c52b1b..ddcf9c72bd8a 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -30,7 +30,6 @@ struct mdev_device {
 	struct mdev_parent *parent;
 	guid_t uuid;
 	void *driver_data;
-	struct kref ref;
 	struct list_head next;
 	struct kobject *type_kobj;
 	bool active;
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 5193a0e0ce5a..cbf94b8165ea 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -280,7 +280,7 @@ type_link_failed:
 
 void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type)
 {
+	sysfs_remove_files(&dev->kobj, mdev_device_attrs);
 	sysfs_remove_link(&dev->kobj, "mdev_type");
 	sysfs_remove_link(type->devices_kobj, dev_name(dev));
-	sysfs_remove_files(&dev->kobj, mdev_device_attrs);
 }
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 3fa20e95a6bb..cab71da46f4a 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -12,6 +12,7 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define dev_fmt pr_fmt
 
 #include <linux/device.h>
 #include <linux/eventfd.h>
@@ -287,12 +288,11 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	pci_save_state(pdev);
 	vdev->pci_saved_state = pci_store_saved_state(pdev);
 	if (!vdev->pci_saved_state)
-		pr_debug("%s: Couldn't store %s saved state\n",
-			 __func__, dev_name(&pdev->dev));
+		pci_dbg(pdev, "%s: Couldn't store saved state\n", __func__);
 
 	if (likely(!nointxmask)) {
 		if (vfio_pci_nointx(pdev)) {
-			dev_info(&pdev->dev, "Masking broken INTx support\n");
+			pci_info(pdev, "Masking broken INTx support\n");
 			vdev->nointx = true;
 			pci_intx(pdev, 0);
 		} else
@@ -336,8 +336,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	    IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
 		ret = vfio_pci_igd_init(vdev);
 		if (ret) {
-			dev_warn(&vdev->pdev->dev,
-				 "Failed to setup Intel IGD regions\n");
+			pci_warn(pdev, "Failed to setup Intel IGD regions\n");
 			goto disable_exit;
 		}
 	}
@@ -346,8 +345,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	    IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
 		ret = vfio_pci_nvdia_v100_nvlink2_init(vdev);
 		if (ret && ret != -ENODEV) {
-			dev_warn(&vdev->pdev->dev,
-				 "Failed to setup NVIDIA NV2 RAM region\n");
+			pci_warn(pdev, "Failed to setup NVIDIA NV2 RAM region\n");
 			goto disable_exit;
 		}
 	}
@@ -356,8 +354,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	    IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
 		ret = vfio_pci_ibm_npu2_init(vdev);
 		if (ret && ret != -ENODEV) {
-			dev_warn(&vdev->pdev->dev,
-					"Failed to setup NVIDIA NV2 ATSD region\n");
+			pci_warn(pdev, "Failed to setup NVIDIA NV2 ATSD region\n");
 			goto disable_exit;
 		}
 	}
@@ -429,8 +426,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	 * is just busy work.
 	 */
 	if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) {
-		pr_info("%s: Couldn't reload %s saved state\n",
-			__func__, dev_name(&pdev->dev));
+		pci_info(pdev, "%s: Couldn't reload saved state\n", __func__);
 
 		if (!vdev->reset_works)
 			goto out;
@@ -1255,17 +1251,18 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 static void vfio_pci_request(void *device_data, unsigned int count)
 {
 	struct vfio_pci_device *vdev = device_data;
+	struct pci_dev *pdev = vdev->pdev;
 
 	mutex_lock(&vdev->igate);
 
 	if (vdev->req_trigger) {
 		if (!(count % 10))
-			dev_notice_ratelimited(&vdev->pdev->dev,
+			pci_notice_ratelimited(pdev,
 				"Relaying device request to user (#%u)\n",
 				count);
 		eventfd_signal(vdev->req_trigger, 1);
 	} else if (count == 0) {
-		dev_warn(&vdev->pdev->dev,
+		pci_warn(pdev,
 			"No device request channel registered, blocked until released by user\n");
 	}
 
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index e82b51114687..52963a904790 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -412,8 +412,7 @@ static void vfio_bar_restore(struct vfio_pci_device *vdev)
 	if (pdev->is_virtfn)
 		return;
 
-	pr_info("%s: %s reset recovery - restoring bars\n",
-		__func__, dev_name(&pdev->dev));
+	pci_info(pdev, "%s: reset recovery - restoring BARs\n", __func__);
 
 	for (i = PCI_BASE_ADDRESS_0; i <= PCI_BASE_ADDRESS_5; i += 4, rbar++)
 		pci_user_write_config_dword(pdev, i, *rbar);
@@ -1298,8 +1297,8 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
 		else
 			return PCI_SATA_SIZEOF_SHORT;
 	default:
-		pr_warn("%s: %s unknown length for pci cap 0x%x@0x%x\n",
-			dev_name(&pdev->dev), __func__, cap, pos);
+		pci_warn(pdev, "%s: unknown length for PCI cap %#x@%#x\n",
+			 __func__, cap, pos);
 	}
 
 	return 0;
@@ -1372,8 +1371,8 @@ static int vfio_ext_cap_len(struct vfio_pci_device *vdev, u16 ecap, u16 epos)
 		}
 		return PCI_TPH_BASE_SIZEOF;
 	default:
-		pr_warn("%s: %s unknown length for pci ecap 0x%x@0x%x\n",
-			dev_name(&pdev->dev), __func__, ecap, epos);
+		pci_warn(pdev, "%s: unknown length for PCI ecap %#x@%#x\n",
+			 __func__, ecap, epos);
 	}
 
 	return 0;
@@ -1474,8 +1473,8 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
 		}
 
 		if (!len) {
-			pr_info("%s: %s hiding cap 0x%x\n",
-				__func__, dev_name(&pdev->dev), cap);
+			pci_info(pdev, "%s: hiding cap %#x@%#x\n", __func__,
+				 cap, pos);
 			*prev = next;
 			pos = next;
 			continue;
@@ -1486,9 +1485,8 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
 			if (likely(map[pos + i] == PCI_CAP_ID_INVALID))
 				continue;
 
-			pr_warn("%s: %s pci config conflict @0x%x, was cap 0x%x now cap 0x%x\n",
-				__func__, dev_name(&pdev->dev),
-				pos + i, map[pos + i], cap);
+			pci_warn(pdev, "%s: PCI config conflict @%#x, was cap %#x now cap %#x\n",
+				 __func__, pos + i, map[pos + i], cap);
 		}
 
 		BUILD_BUG_ON(PCI_CAP_ID_MAX >= PCI_CAP_ID_INVALID_VIRT);
@@ -1549,8 +1547,8 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
 		}
 
 		if (!len) {
-			pr_info("%s: %s hiding ecap 0x%x@0x%x\n",
-				__func__, dev_name(&pdev->dev), ecap, epos);
+			pci_info(pdev, "%s: hiding ecap %#x@%#x\n",
+				 __func__, ecap, epos);
 
 			/* If not the first in the chain, we can skip over it */
 			if (prev) {
@@ -1572,9 +1570,8 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
 			if (likely(map[epos + i] == PCI_CAP_ID_INVALID))
 				continue;
 
-			pr_warn("%s: %s pci config conflict @0x%x, was ecap 0x%x now ecap 0x%x\n",
-				__func__, dev_name(&pdev->dev),
-				epos + i, map[epos + i], ecap);
+			pci_warn(pdev, "%s: PCI config conflict @%#x, was ecap %#x now ecap %#x\n",
+				 __func__, epos + i, map[epos + i], ecap);
 		}
 
 		/*
diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c
index 32f695ffe128..50fe3c4f7feb 100644
--- a/drivers/vfio/pci/vfio_pci_nvlink2.c
+++ b/drivers/vfio/pci/vfio_pci_nvlink2.c
@@ -472,6 +472,8 @@ int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev)
 	return 0;
 
 free_exit:
+	if (data->base)
+		memunmap(data->base);
 	kfree(data);
 
 	return ret;
diff --git a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
index 3ddb2704221d..fe95964bc3be 100644
--- a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
+++ b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
@@ -89,7 +89,8 @@ static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
 	} while ((pcs_value & MDIO_CTRL1_RESET) && --count);
 
 	if (pcs_value & MDIO_CTRL1_RESET)
-		pr_warn("%s XGBE PHY reset timeout\n", __func__);
+		dev_warn(vdev->device, "%s: XGBE PHY reset timeout\n",
+			 __func__);
 
 	/* disable auto-negotiation */
 	value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1);
@@ -114,7 +115,7 @@ static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
 		usleep_range(500, 600);
 
 	if (!count)
-		pr_warn("%s MAC SW reset failed\n", __func__);
+		dev_warn(vdev->device, "%s: MAC SW reset failed\n", __func__);
 
 	return 0;
 }
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index c0cd824be2b7..2a45b36bcf58 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -12,6 +12,8 @@
  * GNU General Public License for more details.
  */
 
+#define dev_fmt(fmt)	"VFIO: " fmt
+
 #include <linux/device.h>
 #include <linux/acpi.h>
 #include <linux/iommu.h>
@@ -63,7 +65,7 @@ static int vfio_platform_acpi_probe(struct vfio_platform_device *vdev,
 
 	adev = ACPI_COMPANION(dev);
 	if (!adev) {
-		pr_err("VFIO: ACPI companion device not found for %s\n",
+		dev_err(dev, "ACPI companion device not found for %s\n",
 			vdev->name);
 		return -ENODEV;
 	}
@@ -638,7 +640,7 @@ static int vfio_platform_of_probe(struct vfio_platform_device *vdev,
 	ret = device_property_read_string(dev, "compatible",
 					  &vdev->compat);
 	if (ret)
-		pr_err("VFIO: Cannot retrieve compat for %s\n", vdev->name);
+		dev_err(dev, "Cannot retrieve compat for %s\n", vdev->name);
 
 	return ret;
 }
@@ -680,14 +682,14 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev,
 
 	ret = vfio_platform_get_reset(vdev);
 	if (ret && vdev->reset_required) {
-		pr_err("VFIO: No reset function found for device %s\n",
-		       vdev->name);
+		dev_err(dev, "No reset function found for device %s\n",
+			vdev->name);
 		return ret;
 	}
 
 	group = vfio_iommu_group_get(dev);
 	if (!group) {
-		pr_err("VFIO: No IOMMU group for device %s\n", vdev->name);
+		dev_err(dev, "No IOMMU group for device %s\n", vdev->name);
 		ret = -EINVAL;
 		goto put_reset;
 	}
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index a3030cdf3c18..82fcf07fa9ea 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -34,6 +34,7 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 
 #define DRIVER_VERSION	"0.3"
 #define DRIVER_AUTHOR	"Alex Williamson <alex.williamson@redhat.com>"
@@ -704,8 +705,8 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
 		return 0;
 
 	/* TODO Prevent device auto probing */
-	WARN(1, "Device %s added to live group %d!\n", dev_name(dev),
-	     iommu_group_id(group->iommu_group));
+	dev_WARN(dev, "Device added to live group %d!\n",
+		 iommu_group_id(group->iommu_group));
 
 	return 0;
 }
@@ -748,25 +749,22 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 		 */
 		break;
 	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
-		pr_debug("%s: Device %s, group %d binding to driver\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group));
+		dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
+			iommu_group_id(group->iommu_group));
 		break;
 	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
-		pr_debug("%s: Device %s, group %d bound to driver %s\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group), dev->driver->name);
+		dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
+			iommu_group_id(group->iommu_group), dev->driver->name);
 		BUG_ON(vfio_group_nb_verify(group, dev));
 		break;
 	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
-		pr_debug("%s: Device %s, group %d unbinding from driver %s\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group), dev->driver->name);
+		dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
+			__func__, iommu_group_id(group->iommu_group),
+			dev->driver->name);
 		break;
 	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
-		pr_debug("%s: Device %s, group %d unbound from driver\n",
-			 __func__, dev_name(dev),
-			 iommu_group_id(group->iommu_group));
+		dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
+			iommu_group_id(group->iommu_group));
 		/*
 		 * XXX An unbound device in a live group is ok, but we'd
 		 * really like to avoid the above BUG_ON by preventing other
@@ -830,8 +828,8 @@ int vfio_add_group_dev(struct device *dev,
 
 	device = vfio_group_get_device(group, dev);
 	if (device) {
-		WARN(1, "Device %s already exists on group %d\n",
-		     dev_name(dev), iommu_group_id(iommu_group));
+		dev_WARN(dev, "Device already exists on group %d\n",
+			 iommu_group_id(iommu_group));
 		vfio_device_put(device);
 		vfio_group_put(group);
 		return -EBUSY;
@@ -904,30 +902,17 @@ void *vfio_device_data(struct vfio_device *device)
 }
 EXPORT_SYMBOL_GPL(vfio_device_data);
 
-/* Given a referenced group, check if it contains the device */
-static bool vfio_dev_present(struct vfio_group *group, struct device *dev)
-{
-	struct vfio_device *device;
-
-	device = vfio_group_get_device(group, dev);
-	if (!device)
-		return false;
-
-	vfio_device_put(device);
-	return true;
-}
-
 /*
  * Decrement the device reference count and wait for the device to be
  * removed.  Open file descriptors for the device... */
 void *vfio_del_group_dev(struct device *dev)
 {
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct vfio_device *device = dev_get_drvdata(dev);
 	struct vfio_group *group = device->group;
 	void *device_data = device->device_data;
 	struct vfio_unbound_dev *unbound;
 	unsigned int i = 0;
-	long ret;
 	bool interrupted = false;
 
 	/*
@@ -964,6 +949,8 @@ void *vfio_del_group_dev(struct device *dev)
 	 * interval with counter to allow the driver to take escalating
 	 * measures to release the device if it has the ability to do so.
 	 */
+	add_wait_queue(&vfio.release_q, &wait);
+
 	do {
 		device = vfio_group_get_device(group, dev);
 		if (!device)
@@ -975,12 +962,10 @@ void *vfio_del_group_dev(struct device *dev)
 		vfio_device_put(device);
 
 		if (interrupted) {
-			ret = wait_event_timeout(vfio.release_q,
-					!vfio_dev_present(group, dev), HZ * 10);
+			wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
 		} else {
-			ret = wait_event_interruptible_timeout(vfio.release_q,
-					!vfio_dev_present(group, dev), HZ * 10);
-			if (ret == -ERESTARTSYS) {
+			wait_woken(&wait, TASK_INTERRUPTIBLE, HZ * 10);
+			if (signal_pending(current)) {
 				interrupted = true;
 				dev_warn(dev,
 					 "Device is currently in use, task"
@@ -989,8 +974,10 @@ void *vfio_del_group_dev(struct device *dev)
 					 current->comm, task_pid_nr(current));
 			}
 		}
-	} while (ret <= 0);
 
+	} while (1);
+
+	remove_wait_queue(&vfio.release_q, &wait);
 	/*
 	 * In order to support multiple devices per group, devices can be
 	 * plucked from the group while other devices in the group are still