4.17-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alex Williamson alex.williamson@redhat.com
[ Upstream commit 002fe996f67f4f46d8917b14cfb6e4313c20685a ]
When we create an mdev device, we check for duplicates against the parent device and return -EEXIST if found, but the mdev device namespace is global since we'll link all devices from the bus. We do catch this later in sysfs_do_create_link_sd() to return -EEXIST, but with it comes a kernel warning and stack trace for trying to create duplicate sysfs links, which makes it an undesirable response.
Therefore we should really be looking for duplicates across all mdev parent devices, or as implemented here, against our mdev device list. Using mdev_list to prevent duplicates means that we can remove mdev_parent.lock, but in order not to serialize mdev device creation and removal globally, we add mdev_device.active which allows UUIDs to be reserved such that we can drop the mdev_list_lock before the mdev device is fully in place.
Two behavioral notes; first, mdev_parent.lock had the side-effect of serializing mdev create and remove ops per parent device. This was an implementation detail, not an intentional guarantee provided to the mdev vendor drivers. Vendor drivers can trivially provide this serialization internally if necessary. Second, review comments note the new -EAGAIN behavior when the device, and in particular the remove attribute, becomes visible in sysfs. If a remove is triggered prior to completion of mdev_device_create() the user will see a -EAGAIN error. While the errno is different, receiving an error during this period is not, the previous implementation returned -ENODEV for the same condition. Furthermore, the consistency to the user is improved in the case where mdev_device_remove_ops() returns error. Previously concurrent calls to mdev_device_remove() could see the device disappear with -ENODEV and return in the case of error. Now a user would see -EAGAIN while the device is in this transitory state.
Reviewed-by: Kirti Wankhede kwankhede@nvidia.com Reviewed-by: Cornelia Huck cohuck@redhat.com Acked-by: Halil Pasic pasic@linux.ibm.com Acked-by: Zhenyu Wang zhenyuw@linux.intel.com Signed-off-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/vfio-mediated-device.txt | 5 + drivers/vfio/mdev/mdev_core.c | 102 +++++++++++---------------------- drivers/vfio/mdev/mdev_private.h | 2 3 files changed, 42 insertions(+), 67 deletions(-)
--- a/Documentation/vfio-mediated-device.txt +++ b/Documentation/vfio-mediated-device.txt @@ -145,6 +145,11 @@ The functions in the mdev_parent_ops str * create: allocate basic resources in a driver for a mediated device * remove: free resources in a driver when a mediated device is destroyed
+(Note that mdev-core provides no implicit serialization of create/remove +callbacks per mdev parent device, per mdev type, or any other categorization. +Vendor drivers are expected to be fully asynchronous in this respect or +provide their own internal resource protection.) + The callbacks in the mdev_parent_ops structure are as follows:
* open: open callback of mediated device --- 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 *md } 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 * }
kref_init(&parent->ref); - mutex_init(&parent->lock);
parent->dev = dev; parent->ops = ops; @@ -297,6 +268,10 @@ static void mdev_device_release(struct d { 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 d 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 *k 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 *k 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 *de 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; --- 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)