From: Parav Pandit parav@mellanox.com
mainline inclusion from mainline-5.2 commit 5715c4dd66a315515eedef3fc4cbe1bf4620f009 category: bugfix bugzilla: NA CVE: NA
-------------------------------------------------
In following sequences, child devices created while removing mdev parent device can be left out, or it may lead to race of removing half initialized child mdev devices.
issue-1: -------- cpu-0 cpu-1 ----- ----- mdev_unregister_device() device_for_each_child() mdev_device_remove_cb() mdev_device_remove() create_store() mdev_device_create() [...] device_add() parent_remove_sysfs_files()
/* BUG: device added by cpu-0 * whose parent is getting removed * and it won't process this mdev. */
issue-2: -------- Below crash is observed when user initiated remove is in progress and mdev_unregister_driver() completes parent unregistration.
cpu-0 cpu-1 ----- ----- remove_store() mdev_device_remove() active = false; mdev_unregister_device() parent device removed. [...] parents->ops->remove() /* * BUG: Accessing invalid parent. */
This is similar race like create() racing with mdev_unregister_device().
BUG: unable to handle kernel paging request at ffffffffc0585668 PGD e8f618067 P4D e8f618067 PUD e8f61a067 PMD 85adca067 PTE 0 Oops: 0000 [#1] SMP PTI CPU: 41 PID: 37403 Comm: bash Kdump: loaded Not tainted 5.1.0-rc6-vdevbus+ #6 Hardware name: Supermicro SYS-6028U-TR4+/X10DRU-i+, BIOS 2.0b 08/09/2016 RIP: 0010:mdev_device_remove+0xfa/0x140 [mdev] Call Trace: remove_store+0x71/0x90 [mdev] kernfs_fop_write+0x113/0x1a0 vfs_write+0xad/0x1b0 ksys_write+0x5a/0xe0 do_syscall_64+0x5a/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe
Therefore, mdev core is improved as below to overcome above issues.
Wait for any ongoing mdev create() and remove() to finish before unregistering parent device. This continues to allow multiple create and remove to progress in parallel for different mdev devices as most common case. At the same time guard parent removal while parent is being accessed by create() and remove() callbacks. create()/remove() and unregister_device() are synchronized by the rwsem.
Refactor device removal code to mdev_device_remove_common() to avoid acquiring unreg_sem of the parent.
Fixes: 7b96953bc640 ("vfio: Mediated device Core driver") Signed-off-by: Parav Pandit parav@mellanox.com Reviewed-by: Cornelia Huck cohuck@redhat.com Signed-off-by: Alex Williamson alex.williamson@redhat.com
Conflicts: drivers/vfio/mdev/mdev_core.c The type of uuid is still uuid_le, and it has not been changed to guid_t.
Signed-off-by: Xiaoyang Xu xuxiaoyang2@huawei.com Reviewed-by: Yingtai Xie xieyingtai@huawei.com--- Reviewed-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/vfio/mdev/mdev_core.c | 72 ++++++++++++++++++++++++++++++---------- drivers/vfio/mdev/mdev_private.h | 2 ++ 2 files changed, 56 insertions(+), 18 deletions(-)
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c index 9705a4a..c4a4659 100644 --- a/drivers/vfio/mdev/mdev_core.c +++ b/drivers/vfio/mdev/mdev_core.c @@ -103,11 +103,35 @@ static inline void mdev_put_parent(struct mdev_parent *parent) kref_put(&parent->ref, mdev_release_parent); }
+/* Caller must hold parent unreg_sem read or write lock */ +static void mdev_device_remove_common(struct mdev_device *mdev) +{ + struct mdev_parent *parent; + struct mdev_type *type; + int ret; + + type = to_mdev_type(mdev->type_kobj); + mdev_remove_sysfs_files(&mdev->dev, type); + device_del(&mdev->dev); + parent = mdev->parent; + lockdep_assert_held(&parent->unreg_sem); + ret = parent->ops->remove(mdev); + if (ret) + dev_err(&mdev->dev, "Remove failed: err=%d\n", ret); + + /* Balances with device_initialize() */ + put_device(&mdev->dev); + mdev_put_parent(parent); +} + static int mdev_device_remove_cb(struct device *dev, void *data) { - if (dev_is_mdev(dev)) - mdev_device_remove(dev); + if (dev_is_mdev(dev)) { + struct mdev_device *mdev;
+ mdev = to_mdev_device(dev); + mdev_device_remove_common(mdev); + } return 0; }
@@ -149,6 +173,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops) }
kref_init(&parent->ref); + init_rwsem(&parent->unreg_sem);
parent->dev = dev; parent->ops = ops; @@ -207,21 +232,23 @@ void mdev_unregister_device(struct device *dev) dev_info(dev, "MDEV: Unregistering\n");
list_del(&parent->next); + mutex_unlock(&parent_list_lock); + + down_write(&parent->unreg_sem); + class_compat_remove_link(mdev_bus_compat_class, dev, NULL);
device_for_each_child(dev, NULL, mdev_device_remove_cb);
parent_remove_sysfs_files(parent); + up_write(&parent->unreg_sem);
- mutex_unlock(&parent_list_lock); mdev_put_parent(parent); } EXPORT_SYMBOL(mdev_unregister_device);
-static void mdev_device_release(struct device *dev) +static void mdev_device_free(struct mdev_device *mdev) { - struct mdev_device *mdev = to_mdev_device(dev); - mutex_lock(&mdev_list_lock); list_del(&mdev->next); mutex_unlock(&mdev_list_lock); @@ -230,6 +257,13 @@ static void mdev_device_release(struct device *dev) kfree(mdev); }
+static void mdev_device_release(struct device *dev) +{ + struct mdev_device *mdev = to_mdev_device(dev); + + mdev_device_free(mdev); +} + int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid) { int ret; @@ -266,6 +300,13 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid) mdev->parent = parent; kref_init(&mdev->ref);
+ /* Check if parent unregistration has started */ + if (!down_read_trylock(&parent->unreg_sem)) { + mdev_device_free(mdev); + ret = -ENODEV; + goto mdev_fail; + } + device_initialize(&mdev->dev); mdev->dev.parent = dev; mdev->dev.bus = &mdev_bus_type; @@ -288,6 +329,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
mdev->active = true; dev_dbg(&mdev->dev, "MDEV: created\n"); + up_read(&parent->unreg_sem);
return 0;
@@ -296,6 +338,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid) add_fail: parent->ops->remove(mdev); ops_create_fail: + up_read(&parent->unreg_sem); put_device(&mdev->dev); mdev_fail: mdev_put_parent(parent); @@ -306,8 +349,6 @@ int mdev_device_remove(struct device *dev) { struct mdev_device *mdev, *tmp; struct mdev_parent *parent; - struct mdev_type *type; - int ret;
mdev = to_mdev_device(dev);
@@ -330,18 +371,13 @@ int mdev_device_remove(struct device *dev) mdev->active = false; mutex_unlock(&mdev_list_lock);
- type = to_mdev_type(mdev->type_kobj); - mdev_remove_sysfs_files(dev, type); - device_del(&mdev->dev); parent = mdev->parent; - ret = parent->ops->remove(mdev); - if (ret) - dev_err(&mdev->dev, "Remove failed: err=%d\n", ret); - - /* Balances with device_initialize() */ - put_device(&mdev->dev); - mdev_put_parent(parent); + /* Check if parent unregistration has started */ + if (!down_read_trylock(&parent->unreg_sem)) + return -ENODEV;
+ mdev_device_remove_common(mdev); + up_read(&parent->unreg_sem); return 0; }
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h index 9c65d8e..9e9c860 100644 --- a/drivers/vfio/mdev/mdev_private.h +++ b/drivers/vfio/mdev/mdev_private.h @@ -23,6 +23,8 @@ struct mdev_parent { struct list_head next; struct kset *mdev_types_kset; struct list_head type_list; + /* Synchronize device creation/removal with parent unregistration */ + struct rw_semaphore unreg_sem; };
struct mdev_device {