Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:3 as permitted sender) client-ip=2620:137:e000::3:3;
From:   Si-Wei Liu <si-wei.liu@oracle.com>
To:     jasowang@redhat.com, mst@redhat.com, eperezma@redhat.com,
        sgarzare@redhat.com, dtatulea@nvidia.com
Cc:     virtualization@lists.linux-foundation.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH v4 7/7] vdpa_sim: implement .reset_map support
Date:   Sat, 21 Oct 2023 02:25:19 -0700
Message-Id: <1697880319-4937-8-git-send-email-si-wei.liu@oracle.com>
In-Reply-To: <1697880319-4937-1-git-send-email-si-wei.liu@oracle.com>
References: <1697880319-4937-1-git-send-email-si-wei.liu@oracle.com>
Precedence: bulk

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.

Additionally, implement .compat_reset 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 | 52 ++++++++++++++++++++++++++------
 1 file changed, 43 insertions(+), 9 deletions(-)

diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 76d41058add9..be2925d0d283 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -139,7 +139,7 @@ static void vdpasim_vq_reset(struct vdpasim *vdpasim,
 	vq->vring.notify = NULL;
 }
 
-static void vdpasim_do_reset(struct vdpasim *vdpasim)
+static void vdpasim_do_reset(struct vdpasim *vdpasim, u32 flags)
 {
 	int i;
 
@@ -151,11 +151,13 @@ 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 (flags & VDPA_RESET_F_CLEAN_MAP) {
+		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;
@@ -259,8 +261,12 @@ 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);
+		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],
@@ -480,18 +486,23 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status)
 	mutex_unlock(&vdpasim->mutex);
 }
 
-static int vdpasim_reset(struct vdpa_device *vdpa)
+static int vdpasim_compat_reset(struct vdpa_device *vdpa, u32 flags)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
 	mutex_lock(&vdpasim->mutex);
 	vdpasim->status = 0;
-	vdpasim_do_reset(vdpasim);
+	vdpasim_do_reset(vdpasim, flags);
 	mutex_unlock(&vdpasim->mutex);
 
 	return 0;
 }
 
+static int vdpasim_reset(struct vdpa_device *vdpa)
+{
+	return vdpasim_compat_reset(vdpa, 0);
+}
+
 static int vdpasim_suspend(struct vdpa_device *vdpa)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -637,6 +648,25 @@ 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);
@@ -749,6 +779,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
 	.reset			= vdpasim_reset,
+	.compat_reset		= vdpasim_compat_reset,
 	.suspend		= vdpasim_suspend,
 	.resume			= vdpasim_resume,
 	.get_config_size        = vdpasim_get_config_size,
@@ -759,6 +790,7 @@ 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,
@@ -787,6 +819,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
 	.reset			= vdpasim_reset,
+	.compat_reset		= vdpasim_compat_reset,
 	.suspend		= vdpasim_suspend,
 	.resume			= vdpasim_resume,
 	.get_config_size        = vdpasim_get_config_size,
@@ -796,6 +829,7 @@ 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