vhost-vdpa: Add support for vIOMMU.
1. The vIOMMU support will make vDPA can work in IOMMU mode. This
will fix security issues while using the no-IOMMU mode.
To support this feature we need to add new functions for IOMMU MR adds and
deletes.
Also since the SVQ does not support vIOMMU yet, add the check for IOMMU
in vhost_vdpa_dev_start, if the SVQ and IOMMU enable at the same time
the function will return fail.
2. Skip the iova_max check vhost_vdpa_listener_skipped_section(). While
MR is IOMMU, move this check to vhost_vdpa_iommu_map_notify()
Verified in vp_vdpa and vdpa_sim_net driver
Signed-off-by: Cindy Lu <lulu@redhat.com>
Message-Id: <20230510054631.2951812-5-lulu@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 0c8c37e..b3094e8 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -26,6 +26,7 @@
#include "cpu.h"
#include "trace.h"
#include "qapi/error.h"
+#include "hw/virtio/virtio-access.h"
/*
* Return one past the end of the end of section. Be careful with uint64_t
@@ -60,13 +61,21 @@
iova_min, section->offset_within_address_space);
return true;
}
+ /*
+ * While using vIOMMU, sometimes the section will be larger than iova_max,
+ * but the memory that actually maps is smaller, so move the check to
+ * function vhost_vdpa_iommu_map_notify(). That function will use the actual
+ * size that maps to the kernel
+ */
- llend = vhost_vdpa_section_end(section);
- if (int128_gt(llend, int128_make64(iova_max))) {
- error_report("RAM section out of device range (max=0x%" PRIx64
- ", end addr=0x%" PRIx64 ")",
- iova_max, int128_get64(llend));
- return true;
+ if (!memory_region_is_iommu(section->mr)) {
+ llend = vhost_vdpa_section_end(section);
+ if (int128_gt(llend, int128_make64(iova_max))) {
+ error_report("RAM section out of device range (max=0x%" PRIx64
+ ", end addr=0x%" PRIx64 ")",
+ iova_max, int128_get64(llend));
+ return true;
+ }
}
return false;
@@ -185,6 +194,115 @@
v->iotlb_batch_begin_sent = false;
}
+static void vhost_vdpa_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+ struct vdpa_iommu *iommu = container_of(n, struct vdpa_iommu, n);
+
+ hwaddr iova = iotlb->iova + iommu->iommu_offset;
+ struct vhost_vdpa *v = iommu->dev;
+ void *vaddr;
+ int ret;
+ Int128 llend;
+
+ if (iotlb->target_as != &address_space_memory) {
+ error_report("Wrong target AS \"%s\", only system memory is allowed",
+ iotlb->target_as->name ? iotlb->target_as->name : "none");
+ return;
+ }
+ RCU_READ_LOCK_GUARD();
+ /* check if RAM section out of device range */
+ llend = int128_add(int128_makes64(iotlb->addr_mask), int128_makes64(iova));
+ if (int128_gt(llend, int128_make64(v->iova_range.last))) {
+ error_report("RAM section out of device range (max=0x%" PRIx64
+ ", end addr=0x%" PRIx64 ")",
+ v->iova_range.last, int128_get64(llend));
+ return;
+ }
+
+ if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
+ bool read_only;
+
+ if (!memory_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, NULL)) {
+ return;
+ }
+ ret = vhost_vdpa_dma_map(v, VHOST_VDPA_GUEST_PA_ASID, iova,
+ iotlb->addr_mask + 1, vaddr, read_only);
+ if (ret) {
+ error_report("vhost_vdpa_dma_map(%p, 0x%" HWADDR_PRIx ", "
+ "0x%" HWADDR_PRIx ", %p) = %d (%m)",
+ v, iova, iotlb->addr_mask + 1, vaddr, ret);
+ }
+ } else {
+ ret = vhost_vdpa_dma_unmap(v, VHOST_VDPA_GUEST_PA_ASID, iova,
+ iotlb->addr_mask + 1);
+ if (ret) {
+ error_report("vhost_vdpa_dma_unmap(%p, 0x%" HWADDR_PRIx ", "
+ "0x%" HWADDR_PRIx ") = %d (%m)",
+ v, iova, iotlb->addr_mask + 1, ret);
+ }
+ }
+}
+
+static void vhost_vdpa_iommu_region_add(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener);
+
+ struct vdpa_iommu *iommu;
+ Int128 end;
+ int iommu_idx;
+ IOMMUMemoryRegion *iommu_mr;
+ int ret;
+
+ iommu_mr = IOMMU_MEMORY_REGION(section->mr);
+
+ iommu = g_malloc0(sizeof(*iommu));
+ end = int128_add(int128_make64(section->offset_within_region),
+ section->size);
+ end = int128_sub(end, int128_one());
+ iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
+ MEMTXATTRS_UNSPECIFIED);
+ iommu->iommu_mr = iommu_mr;
+ iommu_notifier_init(&iommu->n, vhost_vdpa_iommu_map_notify,
+ IOMMU_NOTIFIER_IOTLB_EVENTS,
+ section->offset_within_region,
+ int128_get64(end),
+ iommu_idx);
+ iommu->iommu_offset = section->offset_within_address_space -
+ section->offset_within_region;
+ iommu->dev = v;
+
+ ret = memory_region_register_iommu_notifier(section->mr, &iommu->n, NULL);
+ if (ret) {
+ g_free(iommu);
+ return;
+ }
+
+ QLIST_INSERT_HEAD(&v->iommu_list, iommu, iommu_next);
+ memory_region_iommu_replay(iommu->iommu_mr, &iommu->n);
+
+ return;
+}
+
+static void vhost_vdpa_iommu_region_del(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener);
+
+ struct vdpa_iommu *iommu;
+
+ QLIST_FOREACH(iommu, &v->iommu_list, iommu_next)
+ {
+ if (MEMORY_REGION(iommu->iommu_mr) == section->mr &&
+ iommu->n.start == section->offset_within_region) {
+ memory_region_unregister_iommu_notifier(section->mr, &iommu->n);
+ QLIST_REMOVE(iommu, iommu_next);
+ g_free(iommu);
+ break;
+ }
+ }
+}
+
static void vhost_vdpa_listener_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
@@ -199,6 +317,10 @@
v->iova_range.last)) {
return;
}
+ if (memory_region_is_iommu(section->mr)) {
+ vhost_vdpa_iommu_region_add(listener, section);
+ return;
+ }
if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
(section->offset_within_region & ~TARGET_PAGE_MASK))) {
@@ -278,6 +400,9 @@
v->iova_range.last)) {
return;
}
+ if (memory_region_is_iommu(section->mr)) {
+ vhost_vdpa_iommu_region_del(listener, section);
+ }
if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
(section->offset_within_region & ~TARGET_PAGE_MASK))) {
@@ -1182,7 +1307,13 @@
}
if (started) {
- memory_listener_register(&v->listener, &address_space_memory);
+ if (vhost_dev_has_iommu(dev) && (v->shadow_vqs_enabled)) {
+ error_report("SVQ can not work while IOMMU enable, please disable"
+ "IOMMU and try again");
+ return -1;
+ }
+ memory_listener_register(&v->listener, dev->vdev->dma_as);
+
return vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
}
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index c278a2a..e64bfc7 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -52,6 +52,8 @@
struct vhost_dev *dev;
Error *migration_blocker;
VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX];
+ QLIST_HEAD(, vdpa_iommu) iommu_list;
+ IOMMUNotifier n;
} VhostVDPA;
int vhost_vdpa_get_iova_range(int fd, struct vhost_vdpa_iova_range *iova_range);
@@ -61,4 +63,13 @@
int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
hwaddr size);
+typedef struct vdpa_iommu {
+ struct vhost_vdpa *dev;
+ IOMMUMemoryRegion *iommu_mr;
+ hwaddr iommu_offset;
+ IOMMUNotifier n;
+ QLIST_ENTRY(vdpa_iommu) iommu_next;
+} VDPAIOMMUState;
+
+
#endif
