vhost: Fix crash during early vhost_transport_send_pkt calls

If userspace does VHOST_VSOCK_SET_GUEST_CID before VHOST_SET_OWNER we
can race where:
1. thread0 calls vhost_transport_send_pkt -> vhost_work_queue
2. thread1 does VHOST_SET_OWNER which calls vhost_worker_create.
3. vhost_worker_create will set the dev->worker pointer before setting
the worker->vtsk pointer.
4. thread0's vhost_work_queue will see the dev->worker pointer is
set and try to call vhost_task_wake using not yet set worker->vtsk
pointer.
5. We then crash since vtsk is NULL.

Before commit 6e890c5d50 ("vhost: use vhost_tasks for worker
threads"), we only had the worker pointer so we could just check it to
see if VHOST_SET_OWNER has been done. After that commit we have the
vhost_worker and vhost_task pointer, so we can now hit the bug above.

This patch embeds the vhost_worker in the vhost_dev and moves the work
list initialization back to vhost_dev_init, so we can just check the
worker.vtsk pointer to check if VHOST_SET_OWNER has been done like
before.

Fixes: 6e890c5d50 ("vhost: use vhost_tasks for worker threads")
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Message-Id: <20230607192338.6041-2-michael.christie@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reported-by: syzbot+d0d442c22fa8db45ff0e@syzkaller.appspotmail.com
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
This commit is contained in:
Mike Christie 2023-06-07 14:23:37 -05:00 committed by Michael S. Tsirkin
parent 1f5d2e3bab
commit a284f09eff
2 changed files with 18 additions and 34 deletions

View File

@ -235,7 +235,7 @@ void vhost_dev_flush(struct vhost_dev *dev)
{
struct vhost_flush_struct flush;
if (dev->worker) {
if (dev->worker.vtsk) {
init_completion(&flush.wait_event);
vhost_work_init(&flush.work, vhost_flush_work);
@ -247,7 +247,7 @@ EXPORT_SYMBOL_GPL(vhost_dev_flush);
void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
{
if (!dev->worker)
if (!dev->worker.vtsk)
return;
if (!test_and_set_bit(VHOST_WORK_QUEUED, &work->flags)) {
@ -255,8 +255,8 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
* sure it was not in the list.
* test_and_set_bit() implies a memory barrier.
*/
llist_add(&work->node, &dev->worker->work_list);
vhost_task_wake(dev->worker->vtsk);
llist_add(&work->node, &dev->worker.work_list);
vhost_task_wake(dev->worker.vtsk);
}
}
EXPORT_SYMBOL_GPL(vhost_work_queue);
@ -264,7 +264,7 @@ EXPORT_SYMBOL_GPL(vhost_work_queue);
/* A lockless hint for busy polling code to exit the loop */
bool vhost_has_work(struct vhost_dev *dev)
{
return dev->worker && !llist_empty(&dev->worker->work_list);
return !llist_empty(&dev->worker.work_list);
}
EXPORT_SYMBOL_GPL(vhost_has_work);
@ -456,7 +456,8 @@ void vhost_dev_init(struct vhost_dev *dev,
dev->umem = NULL;
dev->iotlb = NULL;
dev->mm = NULL;
dev->worker = NULL;
memset(&dev->worker, 0, sizeof(dev->worker));
init_llist_head(&dev->worker.work_list);
dev->iov_limit = iov_limit;
dev->weight = weight;
dev->byte_weight = byte_weight;
@ -530,47 +531,30 @@ static void vhost_detach_mm(struct vhost_dev *dev)
static void vhost_worker_free(struct vhost_dev *dev)
{
struct vhost_worker *worker = dev->worker;
if (!worker)
if (!dev->worker.vtsk)
return;
dev->worker = NULL;
WARN_ON(!llist_empty(&worker->work_list));
vhost_task_stop(worker->vtsk);
kfree(worker);
WARN_ON(!llist_empty(&dev->worker.work_list));
vhost_task_stop(dev->worker.vtsk);
dev->worker.kcov_handle = 0;
dev->worker.vtsk = NULL;
}
static int vhost_worker_create(struct vhost_dev *dev)
{
struct vhost_worker *worker;
struct vhost_task *vtsk;
char name[TASK_COMM_LEN];
int ret;
worker = kzalloc(sizeof(*worker), GFP_KERNEL_ACCOUNT);
if (!worker)
return -ENOMEM;
dev->worker = worker;
worker->kcov_handle = kcov_common_handle();
init_llist_head(&worker->work_list);
snprintf(name, sizeof(name), "vhost-%d", current->pid);
vtsk = vhost_task_create(vhost_worker, worker, name);
if (!vtsk) {
ret = -ENOMEM;
goto free_worker;
}
vtsk = vhost_task_create(vhost_worker, &dev->worker, name);
if (!vtsk)
return -ENOMEM;
worker->vtsk = vtsk;
dev->worker.kcov_handle = kcov_common_handle();
dev->worker.vtsk = vtsk;
vhost_task_start(vtsk);
return 0;
free_worker:
kfree(worker);
dev->worker = NULL;
return ret;
}
/* Caller should have device mutex */

View File

@ -154,7 +154,7 @@ struct vhost_dev {
struct vhost_virtqueue **vqs;
int nvqs;
struct eventfd_ctx *log_ctx;
struct vhost_worker *worker;
struct vhost_worker worker;
struct vhost_iotlb *umem;
struct vhost_iotlb *iotlb;
spinlock_t iotlb_lock;