Merge tag 'vfio-v4.18-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Bind type1 task tracking to group_leader to facilitate vCPU hotplug
   in QEMU (Alex Williamson)

 - Sample mdev display drivers, including region-based host and guest
   Linux drivers and bochs compatible dmabuf device
   (Gerd Hoffmann)

 - Fix vfio-platform reset module leak (Geert Uytterhoeven)

 - vfio-platform error message consistency (Geert Uytterhoeven)

 - Global checking for mdev uuid collisions rather than per parent
   device (Alex Williamson)

 - Use match_string() helper (Yisheng Xie)

 - vfio-platform PM domain fixes (Geert Uytterhoeven)

 - Fix sample mbochs driver build dependency (Arnd Bergmann)

* tag 'vfio-v4.18-rc1' of git://github.com/awilliam/linux-vfio:
  samples: mbochs: add DMA_SHARED_BUFFER dependency
  vfio: platform: Fix using devices in PM Domains
  vfio: use match_string() helper
  vfio/mdev: Re-order sysfs attribute creation
  vfio/mdev: Check globally for duplicate devices
  vfio: platform: Make printed error messages more consistent
  vfio: platform: Fix reset module leak in error path
  sample: vfio bochs vbe display (host device for bochs-drm)
  sample: vfio mdev display - guest driver
  sample: vfio mdev display - host device
  vfio/type1: Fix task tracking for QEMU vCPU hotplug

6 files changed, 116 insertions, 116 deletions

diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index 126991046eb7..0212f0ee8aea 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -66,34 +66,6 @@ uuid_le mdev_uuid(struct mdev_device *mdev)
 }
 EXPORT_SYMBOL(mdev_uuid);
 
-static int _find_mdev_device(struct device *dev, void *data)
-{
-	struct mdev_device *mdev;
-
-	if (!dev_is_mdev(dev))
-		return 0;
-
-	mdev = to_mdev_device(dev);
-
-	if (uuid_le_cmp(mdev->uuid, *(uuid_le *)data) == 0)
-		return 1;
-
-	return 0;
-}
-
-static bool mdev_device_exist(struct mdev_parent *parent, uuid_le uuid)
-{
-	struct device *dev;
-
-	dev = device_find_child(parent->dev, &uuid, _find_mdev_device);
-	if (dev) {
-		put_device(dev);
-		return true;
-	}
-
-	return false;
-}
-
 /* Should be called holding parent_list_lock */
 static struct mdev_parent *__find_parent_device(struct device *dev)
 {
@@ -221,7 +193,6 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	}
 
 	kref_init(&parent->ref);
-	mutex_init(&parent->lock);
 
 	parent->dev = dev;
 	parent->ops = ops;
@@ -297,6 +268,10 @@ static void mdev_device_release(struct device *dev)
 {
 	struct mdev_device *mdev = to_mdev_device(dev);
 
+	mutex_lock(&mdev_list_lock);
+	list_del(&mdev->next);
+	mutex_unlock(&mdev_list_lock);
+
 	dev_dbg(&mdev->dev, "MDEV: destroying\n");
 	kfree(mdev);
 }
@@ -304,7 +279,7 @@ static void mdev_device_release(struct device *dev)
 int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 {
 	int ret;
-	struct mdev_device *mdev;
+	struct mdev_device *mdev, *tmp;
 	struct mdev_parent *parent;
 	struct mdev_type *type = to_mdev_type(kobj);
 
@@ -312,21 +287,28 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 	if (!parent)
 		return -EINVAL;
 
-	mutex_lock(&parent->lock);
+	mutex_lock(&mdev_list_lock);
 
 	/* Check for duplicate */
-	if (mdev_device_exist(parent, uuid)) {
-		ret = -EEXIST;
-		goto create_err;
+	list_for_each_entry(tmp, &mdev_list, next) {
+		if (!uuid_le_cmp(tmp->uuid, uuid)) {
+			mutex_unlock(&mdev_list_lock);
+			ret = -EEXIST;
+			goto mdev_fail;
+		}
 	}
 
 	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
 	if (!mdev) {
+		mutex_unlock(&mdev_list_lock);
 		ret = -ENOMEM;
-		goto create_err;
+		goto mdev_fail;
 	}
 
 	memcpy(&mdev->uuid, &uuid, sizeof(uuid_le));
+	list_add(&mdev->next, &mdev_list);
+	mutex_unlock(&mdev_list_lock);
+
 	mdev->parent = parent;
 	kref_init(&mdev->ref);
 
@@ -338,35 +320,28 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 	ret = device_register(&mdev->dev);
 	if (ret) {
 		put_device(&mdev->dev);
-		goto create_err;
+		goto mdev_fail;
 	}
 
 	ret = mdev_device_create_ops(kobj, mdev);
 	if (ret)
-		goto create_failed;
+		goto create_fail;
 
 	ret = mdev_create_sysfs_files(&mdev->dev, type);
 	if (ret) {
 		mdev_device_remove_ops(mdev, true);
-		goto create_failed;
+		goto create_fail;
 	}
 
 	mdev->type_kobj = kobj;
+	mdev->active = true;
 	dev_dbg(&mdev->dev, "MDEV: created\n");
 
-	mutex_unlock(&parent->lock);
-
-	mutex_lock(&mdev_list_lock);
-	list_add(&mdev->next, &mdev_list);
-	mutex_unlock(&mdev_list_lock);
-
-	return ret;
+	return 0;
 
-create_failed:
+create_fail:
 	device_unregister(&mdev->dev);
-
-create_err:
-	mutex_unlock(&parent->lock);
+mdev_fail:
 	mdev_put_parent(parent);
 	return ret;
 }
@@ -377,44 +352,39 @@ int mdev_device_remove(struct device *dev, bool force_remove)
 	struct mdev_parent *parent;
 	struct mdev_type *type;
 	int ret;
-	bool found = false;
 
 	mdev = to_mdev_device(dev);
 
 	mutex_lock(&mdev_list_lock);
 	list_for_each_entry(tmp, &mdev_list, next) {
-		if (tmp == mdev) {
-			found = true;
+		if (tmp == mdev)
 			break;
-		}
 	}
 
-	if (found)
-		list_del(&mdev->next);
+	if (tmp != mdev) {
+		mutex_unlock(&mdev_list_lock);
+		return -ENODEV;
+	}
 
-	mutex_unlock(&mdev_list_lock);
+	if (!mdev->active) {
+		mutex_unlock(&mdev_list_lock);
+		return -EAGAIN;
+	}
 
-	if (!found)
-		return -ENODEV;
+	mdev->active = false;
+	mutex_unlock(&mdev_list_lock);
 
 	type = to_mdev_type(mdev->type_kobj);
 	parent = mdev->parent;
-	mutex_lock(&parent->lock);
 
 	ret = mdev_device_remove_ops(mdev, force_remove);
 	if (ret) {
-		mutex_unlock(&parent->lock);
-
-		mutex_lock(&mdev_list_lock);
-		list_add(&mdev->next, &mdev_list);
-		mutex_unlock(&mdev_list_lock);
-
+		mdev->active = true;
 		return ret;
 	}
 
 	mdev_remove_sysfs_files(dev, type);
 	device_unregister(dev);
-	mutex_unlock(&parent->lock);
 	mdev_put_parent(parent);
 
 	return 0;
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index a9cefd70a705..b5819b7d7ef7 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -20,7 +20,6 @@ struct mdev_parent {
 	struct device *dev;
 	const struct mdev_parent_ops *ops;
 	struct kref ref;
-	struct mutex lock;
 	struct list_head next;
 	struct kset *mdev_types_kset;
 	struct list_head type_list;
@@ -34,6 +33,7 @@ struct mdev_device {
 	struct kref ref;
 	struct list_head next;
 	struct kobject *type_kobj;
+	bool active;
 };
 
 #define to_mdev_device(dev)	container_of(dev, struct mdev_device, dev)
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 802df210929b..249472f05509 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -257,24 +257,24 @@ int  mdev_create_sysfs_files(struct device *dev, struct mdev_type *type)
 {
 	int ret;
 
-	ret = sysfs_create_files(&dev->kobj, mdev_device_attrs);
-	if (ret)
-		return ret;
-
 	ret = sysfs_create_link(type->devices_kobj, &dev->kobj, dev_name(dev));
 	if (ret)
-		goto device_link_failed;
+		return ret;
 
 	ret = sysfs_create_link(&dev->kobj, &type->kobj, "mdev_type");
 	if (ret)
 		goto type_link_failed;
 
+	ret = sysfs_create_files(&dev->kobj, mdev_device_attrs);
+	if (ret)
+		goto create_files_failed;
+
 	return ret;
 
+create_files_failed:
+	sysfs_remove_link(&dev->kobj, "mdev_type");
 type_link_failed:
 	sysfs_remove_link(type->devices_kobj, dev_name(dev));
-device_link_failed:
-	sysfs_remove_files(&dev->kobj, mdev_device_attrs);
 	return ret;
 }
 
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index 4c27f4be3c3d..c0cd824be2b7 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -17,6 +17,7 @@
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
@@ -239,6 +240,7 @@ static void vfio_platform_release(void *device_data)
 				 ret, extra_dbg ? extra_dbg : "");
 			WARN_ON(1);
 		}
+		pm_runtime_put(vdev->device);
 		vfio_platform_regions_cleanup(vdev);
 		vfio_platform_irq_cleanup(vdev);
 	}
@@ -269,6 +271,10 @@ static int vfio_platform_open(void *device_data)
 		if (ret)
 			goto err_irq;
 
+		ret = pm_runtime_get_sync(vdev->device);
+		if (ret < 0)
+			goto err_pm;
+
 		ret = vfio_platform_call_reset(vdev, &extra_dbg);
 		if (ret && vdev->reset_required) {
 			dev_warn(vdev->device, "reset driver is required and reset call failed in open (%d) %s\n",
@@ -283,6 +289,8 @@ static int vfio_platform_open(void *device_data)
 	return 0;
 
 err_rst:
+	pm_runtime_put(vdev->device);
+err_pm:
 	vfio_platform_irq_cleanup(vdev);
 err_irq:
 	vfio_platform_regions_cleanup(vdev);
@@ -630,8 +638,7 @@ 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);
+		pr_err("VFIO: Cannot retrieve compat for %s\n", vdev->name);
 
 	return ret;
 }
@@ -673,7 +680,7 @@ 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",
+		pr_err("VFIO: No reset function found for device %s\n",
 		       vdev->name);
 		return ret;
 	}
@@ -681,18 +688,24 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev,
 	group = vfio_iommu_group_get(dev);
 	if (!group) {
 		pr_err("VFIO: No IOMMU group for device %s\n", vdev->name);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_reset;
 	}
 
 	ret = vfio_add_group_dev(dev, &vfio_platform_ops, vdev);
-	if (ret) {
-		vfio_iommu_group_put(group, dev);
-		return ret;
-	}
+	if (ret)
+		goto put_iommu;
 
 	mutex_init(&vdev->igate);
 
+	pm_runtime_enable(vdev->device);
 	return 0;
+
+put_iommu:
+	vfio_iommu_group_put(group, dev);
+put_reset:
+	vfio_platform_put_reset(vdev);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(vfio_platform_probe_common);
 
@@ -703,6 +716,7 @@ struct vfio_platform_device *vfio_platform_remove_common(struct device *dev)
 	vdev = vfio_del_group_dev(dev);
 
 	if (vdev) {
+		pm_runtime_disable(vdev->device);
 		vfio_platform_put_reset(vdev);
 		vfio_iommu_group_put(dev->iommu_group, dev);
 	}
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 721f97f8dac1..64833879f75d 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -630,8 +630,6 @@ static const char * const vfio_driver_whitelist[] = { "pci-stub" };
 
 static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
 {
-	int i;
-
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
 
@@ -639,12 +637,9 @@ static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv)
 			return true;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(vfio_driver_whitelist); i++) {
-		if (!strcmp(drv->name, vfio_driver_whitelist[i]))
-			return true;
-	}
-
-	return false;
+	return match_string(vfio_driver_whitelist,
+			    ARRAY_SIZE(vfio_driver_whitelist),
+			    drv->name) >= 0;
 }
 
 /*
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 3c082451ab1a..2c75b33db4ac 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -83,6 +83,7 @@ struct vfio_dma {
 	size_t			size;		/* Map size (bytes) */
 	int			prot;		/* IOMMU_READ/WRITE */
 	bool			iommu_mapped;
+	bool			lock_cap;	/* capable(CAP_IPC_LOCK) */
 	struct task_struct	*task;
 	struct rb_root		pfn_list;	/* Ex-user pinned pfn list */
 };
@@ -253,29 +254,25 @@ static int vfio_iova_put_vfio_pfn(struct vfio_dma *dma, struct vfio_pfn *vpfn)
 	return ret;
 }
 
-static int vfio_lock_acct(struct task_struct *task, long npage, bool *lock_cap)
+static int vfio_lock_acct(struct vfio_dma *dma, long npage, bool async)
 {
 	struct mm_struct *mm;
-	bool is_current;
 	int ret;
 
 	if (!npage)
 		return 0;
 
-	is_current = (task->mm == current->mm);
-
-	mm = is_current ? task->mm : get_task_mm(task);
+	mm = async ? get_task_mm(dma->task) : dma->task->mm;
 	if (!mm)
 		return -ESRCH; /* process exited */
 
 	ret = down_write_killable(&mm->mmap_sem);
 	if (!ret) {
 		if (npage > 0) {
-			if (lock_cap ? !*lock_cap :
-			    !has_capability(task, CAP_IPC_LOCK)) {
+			if (!dma->lock_cap) {
 				unsigned long limit;
 
-				limit = task_rlimit(task,
+				limit = task_rlimit(dma->task,
 						RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
 				if (mm->locked_vm + npage > limit)
@@ -289,7 +286,7 @@ static int vfio_lock_acct(struct task_struct *task, long npage, bool *lock_cap)
 		up_write(&mm->mmap_sem);
 	}
 
-	if (!is_current)
+	if (async)
 		mmput(mm);
 
 	return ret;
@@ -400,7 +397,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
  */
 static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 				  long npage, unsigned long *pfn_base,
-				  bool lock_cap, unsigned long limit)
+				  unsigned long limit)
 {
 	unsigned long pfn = 0;
 	long ret, pinned = 0, lock_acct = 0;
@@ -423,7 +420,7 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 	 * pages are already counted against the user.
 	 */
 	if (!rsvd && !vfio_find_vpfn(dma, iova)) {
-		if (!lock_cap && current->mm->locked_vm + 1 > limit) {
+		if (!dma->lock_cap && current->mm->locked_vm + 1 > limit) {
 			put_pfn(*pfn_base, dma->prot);
 			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
 					limit << PAGE_SHIFT);
@@ -449,7 +446,7 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 		}
 
 		if (!rsvd && !vfio_find_vpfn(dma, iova)) {
-			if (!lock_cap &&
+			if (!dma->lock_cap &&
 			    current->mm->locked_vm + lock_acct + 1 > limit) {
 				put_pfn(pfn, dma->prot);
 				pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
@@ -462,7 +459,7 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 	}
 
 out:
-	ret = vfio_lock_acct(current, lock_acct, &lock_cap);
+	ret = vfio_lock_acct(dma, lock_acct, false);
 
 unpin_out:
 	if (ret) {
@@ -493,7 +490,7 @@ static long vfio_unpin_pages_remote(struct vfio_dma *dma, dma_addr_t iova,
 	}
 
 	if (do_accounting)
-		vfio_lock_acct(dma->task, locked - unlocked, NULL);
+		vfio_lock_acct(dma, locked - unlocked, true);
 
 	return unlocked;
 }
@@ -510,7 +507,7 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr,
 
 	ret = vaddr_get_pfn(mm, vaddr, dma->prot, pfn_base);
 	if (!ret && do_accounting && !is_invalid_reserved_pfn(*pfn_base)) {
-		ret = vfio_lock_acct(dma->task, 1, NULL);
+		ret = vfio_lock_acct(dma, 1, true);
 		if (ret) {
 			put_pfn(*pfn_base, dma->prot);
 			if (ret == -ENOMEM)
@@ -537,7 +534,7 @@ static int vfio_unpin_page_external(struct vfio_dma *dma, dma_addr_t iova,
 	unlocked = vfio_iova_put_vfio_pfn(dma, vpfn);
 
 	if (do_accounting)
-		vfio_lock_acct(dma->task, -unlocked, NULL);
+		vfio_lock_acct(dma, -unlocked, true);
 
 	return unlocked;
 }
@@ -829,7 +826,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
 		unlocked += vfio_sync_unpin(dma, domain, &unmapped_region_list);
 
 	if (do_accounting) {
-		vfio_lock_acct(dma->task, -unlocked, NULL);
+		vfio_lock_acct(dma, -unlocked, true);
 		return 0;
 	}
 	return unlocked;
@@ -1044,14 +1041,12 @@ static int vfio_pin_map_dma(struct vfio_iommu *iommu, struct vfio_dma *dma,
 	size_t size = map_size;
 	long npage;
 	unsigned long pfn, limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	bool lock_cap = capable(CAP_IPC_LOCK);
 	int ret = 0;
 
 	while (size) {
 		/* Pin a contiguous chunk of memory */
 		npage = vfio_pin_pages_remote(dma, vaddr + dma->size,
-					      size >> PAGE_SHIFT, &pfn,
-					      lock_cap, limit);
+					      size >> PAGE_SHIFT, &pfn, limit);
 		if (npage <= 0) {
 			WARN_ON(!npage);
 			ret = (int)npage;
@@ -1126,8 +1121,36 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 	dma->iova = iova;
 	dma->vaddr = vaddr;
 	dma->prot = prot;
-	get_task_struct(current);
-	dma->task = current;
+
+	/*
+	 * We need to be able to both add to a task's locked memory and test
+	 * against the locked memory limit and we need to be able to do both
+	 * outside of this call path as pinning can be asynchronous via the
+	 * external interfaces for mdev devices.  RLIMIT_MEMLOCK requires a
+	 * task_struct and VM locked pages requires an mm_struct, however
+	 * holding an indefinite mm reference is not recommended, therefore we
+	 * only hold a reference to a task.  We could hold a reference to
+	 * current, however QEMU uses this call path through vCPU threads,
+	 * which can be killed resulting in a NULL mm and failure in the unmap
+	 * path when called via a different thread.  Avoid this problem by
+	 * using the group_leader as threads within the same group require
+	 * both CLONE_THREAD and CLONE_VM and will therefore use the same
+	 * mm_struct.
+	 *
+	 * Previously we also used the task for testing CAP_IPC_LOCK at the
+	 * time of pinning and accounting, however has_capability() makes use
+	 * of real_cred, a copy-on-write field, so we can't guarantee that it
+	 * matches group_leader, or in fact that it might not change by the
+	 * time it's evaluated.  If a process were to call MAP_DMA with
+	 * CAP_IPC_LOCK but later drop it, it doesn't make sense that they
+	 * possibly see different results for an iommu_mapped vfio_dma vs
+	 * externally mapped.  Therefore track CAP_IPC_LOCK in vfio_dma at the
+	 * time of calling MAP_DMA.
+	 */
+	get_task_struct(current->group_leader);
+	dma->task = current->group_leader;
+	dma->lock_cap = capable(CAP_IPC_LOCK);
+
 	dma->pfn_list = RB_ROOT;
 
 	/* Insert zero-sized and grow as we map chunks of it */
@@ -1162,7 +1185,6 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 	struct vfio_domain *d;
 	struct rb_node *n;
 	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	bool lock_cap = capable(CAP_IPC_LOCK);
 	int ret;
 
 	/* Arbitrarily pick the first domain in the list for lookups */
@@ -1209,8 +1231,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 
 				npage = vfio_pin_pages_remote(dma, vaddr,
 							      n >> PAGE_SHIFT,
-							      &pfn, lock_cap,
-							      limit);
+							      &pfn, limit);
 				if (npage <= 0) {
 					WARN_ON(!npage);
 					ret = (int)npage;
@@ -1487,7 +1508,7 @@ static void vfio_iommu_unmap_unpin_reaccount(struct vfio_iommu *iommu)
 			if (!is_invalid_reserved_pfn(vpfn->pfn))
 				locked++;
 		}
-		vfio_lock_acct(dma->task, locked - unlocked, NULL);
+		vfio_lock_acct(dma, locked - unlocked, true);
 	}
 }