vdpa_sim: add support for user VA

The new "use_va" module parameter (default: true) is used in
vdpa_alloc_device() to inform the vDPA framework that the device
supports VA.

vringh is initialized to use VA only when "use_va" is true and the
user's mm has been bound. So, only when the bus supports user VA
(e.g. vhost-vdpa).

vdpasim_mm_work_fn work is used to serialize the binding to a new
address space when the .bind_mm callback is invoked, and unbinding
when the .unbind_mm callback is invoked.

Call mmget_not_zero()/kthread_use_mm() inside the worker function
to pin the address space only as long as needed, following the
documentation of mmget() in include/linux/sched/mm.h:

  * Never use this function to pin this address space for an
  * unbounded/indefinite amount of time.

Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20230404131734.45943-1-sgarzare@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

2 files changed, 90 insertions, 8 deletions

diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 2b2e439a66f7..2c706bb18897 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -35,10 +35,44 @@ module_param(max_iotlb_entries, int, 0444);
 MODULE_PARM_DESC(max_iotlb_entries,
 		 "Maximum number of iotlb entries for each address space. 0 means unlimited. (default: 2048)");
 
+static bool use_va = true;
+module_param(use_va, bool, 0444);
+MODULE_PARM_DESC(use_va, "Enable/disable the device's ability to use VA");
+
 #define VDPASIM_QUEUE_ALIGN PAGE_SIZE
 #define VDPASIM_QUEUE_MAX 256
 #define VDPASIM_VENDOR_ID 0
 
+struct vdpasim_mm_work {
+	struct kthread_work work;
+	struct vdpasim *vdpasim;
+	struct mm_struct *mm_to_bind;
+	int ret;
+};
+
+static void vdpasim_mm_work_fn(struct kthread_work *work)
+{
+	struct vdpasim_mm_work *mm_work =
+		container_of(work, struct vdpasim_mm_work, work);
+	struct vdpasim *vdpasim = mm_work->vdpasim;
+
+	mm_work->ret = 0;
+
+	//TODO: should we attach the cgroup of the mm owner?
+	vdpasim->mm_bound = mm_work->mm_to_bind;
+}
+
+static void vdpasim_worker_change_mm_sync(struct vdpasim *vdpasim,
+					  struct vdpasim_mm_work *mm_work)
+{
+	struct kthread_work *work = &mm_work->work;
+
+	kthread_init_work(work, vdpasim_mm_work_fn);
+	kthread_queue_work(vdpasim->worker, work);
+
+	kthread_flush_work(work);
+}
+
 static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa)
 {
 	return container_of(vdpa, struct vdpasim, vdpa);
@@ -59,13 +93,20 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
 {
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 	uint16_t last_avail_idx = vq->vring.last_avail_idx;
-
-	vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, true,
-			  (struct vring_desc *)(uintptr_t)vq->desc_addr,
-			  (struct vring_avail *)
-			  (uintptr_t)vq->driver_addr,
-			  (struct vring_used *)
-			  (uintptr_t)vq->device_addr);
+	struct vring_desc *desc = (struct vring_desc *)
+				  (uintptr_t)vq->desc_addr;
+	struct vring_avail *avail = (struct vring_avail *)
+				    (uintptr_t)vq->driver_addr;
+	struct vring_used *used = (struct vring_used *)
+				  (uintptr_t)vq->device_addr;
+
+	if (use_va && vdpasim->mm_bound) {
+		vringh_init_iotlb_va(&vq->vring, vdpasim->features, vq->num,
+				     true, desc, avail, used);
+	} else {
+		vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num,
+				  true, desc, avail, used);
+	}
 
 	vq->vring.last_avail_idx = last_avail_idx;
 
@@ -130,8 +171,20 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops;
 static void vdpasim_work_fn(struct kthread_work *work)
 {
 	struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
+	struct mm_struct *mm = vdpasim->mm_bound;
+
+	if (use_va && mm) {
+		if (!mmget_not_zero(mm))
+			return;
+		kthread_use_mm(mm);
+	}
 
 	vdpasim->dev_attr.work_fn(vdpasim);
+
+	if (use_va && mm) {
+		kthread_unuse_mm(mm);
+		mmput(mm);
+	}
 }
 
 struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
@@ -162,7 +215,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	vdpa = __vdpa_alloc_device(NULL, ops,
 				   dev_attr->ngroups, dev_attr->nas,
 				   dev_attr->alloc_size,
-				   dev_attr->name, false);
+				   dev_attr->name, use_va);
 	if (IS_ERR(vdpa)) {
 		ret = PTR_ERR(vdpa);
 		goto err_alloc;
@@ -582,6 +635,30 @@ err:
 	return ret;
 }
 
+static int vdpasim_bind_mm(struct vdpa_device *vdpa, struct mm_struct *mm)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_mm_work mm_work;
+
+	mm_work.vdpasim = vdpasim;
+	mm_work.mm_to_bind = mm;
+
+	vdpasim_worker_change_mm_sync(vdpasim, &mm_work);
+
+	return mm_work.ret;
+}
+
+static void vdpasim_unbind_mm(struct vdpa_device *vdpa)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_mm_work mm_work;
+
+	mm_work.vdpasim = vdpasim;
+	mm_work.mm_to_bind = NULL;
+
+	vdpasim_worker_change_mm_sync(vdpasim, &mm_work);
+}
+
 static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,
 			   u64 iova, u64 size,
 			   u64 pa, u32 perm, void *opaque)
@@ -678,6 +755,8 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.set_group_asid         = vdpasim_set_group_asid,
 	.dma_map                = vdpasim_dma_map,
 	.dma_unmap              = vdpasim_dma_unmap,
+	.bind_mm		= vdpasim_bind_mm,
+	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
 };
 
@@ -712,6 +791,8 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.get_iova_range         = vdpasim_get_iova_range,
 	.set_group_asid         = vdpasim_set_group_asid,
 	.set_map                = vdpasim_set_map,
+	.bind_mm		= vdpasim_bind_mm,
+	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
 };
 
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h
index 4774292fba8c..3a42887d05d9 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.h
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h
@@ -59,6 +59,7 @@ struct vdpasim {
 	struct vdpasim_virtqueue *vqs;
 	struct kthread_worker *worker;
 	struct kthread_work work;
+	struct mm_struct *mm_bound;
 	struct vdpasim_dev_attr dev_attr;
 	/* mutex to synchronize virtqueue state */
 	struct mutex mutex;