[PATCH v3 5/5] vdpa_sim: implement .reset_map support

[Si-Wei Liu <si-wei.liu@oracle.com>]

In order to reduce excessive memory mapping cost in live migration and
VM reboot, it is desirable to decouple the vhost-vdpa IOTLB abstraction
from the virtio device life cycle, i.e. mappings can be kept intact
across virtio device reset. Leverage the .reset_map callback, which is
meant to destroy the iotlb on the given ASID and recreate the 1:1
passthrough/identity mapping. To be consistent, the mapping on device
creation is initiailized to passthrough/identity with PA 1:1 mapped
as IOVA. With this the device .reset op doesn't have to maintain and
clean up memory mappings by itself.

Add a module paramemter, iotlb_persist, to cater for older userspace
which may wish to see mapping to be cleared during reset.

Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Tested-by: Stefano Garzarella <sgarzare@redhat.com>
---
 drivers/vdpa/vdpa_sim/vdpa_sim.c | 58 ++++++++++++++++++++++++++------
 1 file changed, 47 insertions(+), 11 deletions(-)

diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 76d41058add9..74506636375f 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -40,6 +40,10 @@ 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");
 
+static bool iotlb_persist = true;
+module_param(iotlb_persist, bool, 0444);
+MODULE_PARM_DESC(iotlb_persist, "Enable/disable persistent iotlb across reset: 1 to keep maps, 0 to clear");
+
 #define VDPASIM_QUEUE_ALIGN PAGE_SIZE
 #define VDPASIM_QUEUE_MAX 256
 #define VDPASIM_VENDOR_ID 0
@@ -151,11 +155,13 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim)
 				 &vdpasim->iommu_lock);
 	}
 
-	for (i = 0; i < vdpasim->dev_attr.nas; i++) {
-		vhost_iotlb_reset(&vdpasim->iommu[i]);
-		vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
-				      0, VHOST_MAP_RW);
-		vdpasim->iommu_pt[i] = true;
+	if (unlikely(!iotlb_persist)) {
+		for (i = 0; i < vdpasim->dev_attr.nas; i++) {
+			vhost_iotlb_reset(&vdpasim->iommu[i]);
+			vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX,
+					      0, VHOST_MAP_RW);
+			vdpasim->iommu_pt[i] = true;
+		}
 	}
 
 	vdpasim->running = true;
@@ -166,8 +172,8 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim)
 	++vdpasim->generation;
 }
 
-static const struct vdpa_config_ops vdpasim_config_ops;
-static const struct vdpa_config_ops vdpasim_batch_config_ops;
+static struct vdpa_config_ops vdpasim_config_ops;
+static struct vdpa_config_ops vdpasim_batch_config_ops;
 
 static void vdpasim_work_fn(struct kthread_work *work)
 {
@@ -191,7 +197,7 @@ static void vdpasim_work_fn(struct kthread_work *work)
 struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 			       const struct vdpa_dev_set_config *config)
 {
-	const struct vdpa_config_ops *ops;
+	struct vdpa_config_ops *ops;
 	struct vdpa_device *vdpa;
 	struct vdpasim *vdpasim;
 	struct device *dev;
@@ -213,6 +219,9 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	else
 		ops = &vdpasim_config_ops;
 
+	if (unlikely(!iotlb_persist))
+		ops->reset_map = NULL;
+
 	vdpa = __vdpa_alloc_device(NULL, ops,
 				   dev_attr->ngroups, dev_attr->nas,
 				   dev_attr->alloc_size,
@@ -259,8 +268,14 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	if (!vdpasim->iommu_pt)
 		goto err_iommu;
 
-	for (i = 0; i < vdpasim->dev_attr.nas; i++)
+	for (i = 0; i < vdpasim->dev_attr.nas; i++) {
 		vhost_iotlb_init(&vdpasim->iommu[i], max_iotlb_entries, 0);
+		if (likely(iotlb_persist)) {
+			vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX, 0,
+					      VHOST_MAP_RW);
+			vdpasim->iommu_pt[i] = true;
+		}
+	}
 
 	for (i = 0; i < dev_attr->nvqs; i++)
 		vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0],
@@ -637,6 +652,25 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,
 	return ret;
 }
 
+static int vdpasim_reset_map(struct vdpa_device *vdpa, unsigned int asid)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	if (asid >= vdpasim->dev_attr.nas)
+		return -EINVAL;
+
+	spin_lock(&vdpasim->iommu_lock);
+	if (vdpasim->iommu_pt[asid])
+		goto out;
+	vhost_iotlb_reset(&vdpasim->iommu[asid]);
+	vhost_iotlb_add_range(&vdpasim->iommu[asid], 0, ULONG_MAX,
+			      0, VHOST_MAP_RW);
+	vdpasim->iommu_pt[asid] = true;
+out:
+	spin_unlock(&vdpasim->iommu_lock);
+	return 0;
+}
+
 static int vdpasim_bind_mm(struct vdpa_device *vdpa, struct mm_struct *mm)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -726,7 +760,7 @@ static void vdpasim_free(struct vdpa_device *vdpa)
 	kfree(vdpasim->config);
 }
 
-static const struct vdpa_config_ops vdpasim_config_ops = {
+static struct vdpa_config_ops vdpasim_config_ops = {
 	.set_vq_address         = vdpasim_set_vq_address,
 	.set_vq_num             = vdpasim_set_vq_num,
 	.kick_vq                = vdpasim_kick_vq,
@@ -759,12 +793,13 @@ 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,
+	.reset_map              = vdpasim_reset_map,
 	.bind_mm		= vdpasim_bind_mm,
 	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
 };
 
-static const struct vdpa_config_ops vdpasim_batch_config_ops = {
+static struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.set_vq_address         = vdpasim_set_vq_address,
 	.set_vq_num             = vdpasim_set_vq_num,
 	.kick_vq                = vdpasim_kick_vq,
@@ -796,6 +831,7 @@ 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,
+	.reset_map              = vdpasim_reset_map,
 	.bind_mm		= vdpasim_bind_mm,
 	.unbind_mm		= vdpasim_unbind_mm,
 	.free                   = vdpasim_free,
-- 
2.39.3