[PATCH v2 1/2] vhost-vdpa: introduce module parameter for no-IOMMU mode

[Srujana Challa <schalla@xxxxxxxxxxx>]

This commit introduces module parameter
"enable_vhost_vdpa_unsafe_noiommu_mode" to enable an UNSAFE, no-IOMMU
mode in the vhost-vdpa driver. When enabled, this mode provides no
device isolation, no DMA translation, no host kernel protection, and
cannot be used for device assignment to virtual machines.
It requires RAWIO permissions and will taint the kernel.

Signed-off-by: Srujana Challa <schalla@xxxxxxxxxxx>
---
 drivers/vhost/vdpa.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 5a49b5a6d496..b3085189ea4a 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -36,6 +36,11 @@ enum {
 
 #define VHOST_VDPA_IOTLB_BUCKETS 16
 
+bool vhost_vdpa_noiommu;
+module_param_named(enable_vhost_vdpa_unsafe_noiommu_mode,
+		   vhost_vdpa_noiommu, bool, 0644);
+MODULE_PARM_DESC(enable_vhost_vdpa_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode.  This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel.  If you do not know what this is for, step away. (default: false)");
+
 struct vhost_vdpa_as {
 	struct hlist_node hash_link;
 	struct vhost_iotlb iotlb;
@@ -60,6 +65,7 @@ struct vhost_vdpa {
 	struct vdpa_iova_range range;
 	u32 batch_asid;
 	bool suspended;
+	bool noiommu_en;
 };
 
 static DEFINE_IDA(vhost_vdpa_ida);
@@ -910,6 +916,10 @@ static void vhost_vdpa_general_unmap(struct vhost_vdpa *v,
 {
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (v->noiommu_en)
+		return;
+
 	if (ops->dma_map) {
 		ops->dma_unmap(vdpa, asid, map->start, map->size);
 	} else if (ops->set_map == NULL) {
@@ -1003,6 +1013,9 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
 	if (r)
 		return r;
 
+	if (v->noiommu_en)
+		goto skip_map;
+
 	if (ops->dma_map) {
 		r = ops->dma_map(vdpa, asid, iova, size, pa, perm, opaque);
 	} else if (ops->set_map) {
@@ -1018,6 +1031,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
 		return r;
 	}
 
+skip_map:
 	if (!vdpa->use_va)
 		atomic64_add(PFN_DOWN(size), &dev->mm->pinned_vm);
 
@@ -1321,12 +1335,26 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
 	struct device *dma_dev = vdpa_get_dma_dev(vdpa);
+	struct iommu_domain *domain;
 	int ret;
 
 	/* Device want to do DMA by itself */
 	if (ops->set_map || ops->dma_map)
 		return 0;
 
+	domain = iommu_get_domain_for_dev(dma_dev);
+	if (!domain && vhost_vdpa_noiommu) {
+		if (!capable(CAP_SYS_RAWIO)) {
+			dev_warn_once(&v->dev, "No RAWIO permissions, couldn't support NOIOMMU\n");
+			return -ENOTSUPP;
+		}
+		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+		dev_warn(&v->dev, "Adding kernel taint for noiommu on device\n");
+		v->noiommu_en = true;
+		return 0;
+	}
+	v->noiommu_en = false;
+
 	if (!device_iommu_capable(dma_dev, IOMMU_CAP_CACHE_COHERENCY)) {
 		dev_warn_once(&v->dev,
 			      "Failed to allocate domain, device is not IOMMU cache coherent capable\n");
-- 
2.25.1