[Qemu-devel] [PATCH 3/3] vhost: iommu: cache static mapping if there is

[Peter Xu <peterx@redhat.com>]

This patch pre-heat vhost iotlb cache when passthrough mode enabled.

Sometimes, even if user specified iommu_platform for vhost devices,
IOMMU might still be disabled. One case is passthrough mode in VT-d
implementation. We can detect this by observing iommu_list. If it's
empty, it means IOMMU translation is disabled, then we can actually
pre-heat the translation (it'll be static mapping then) by first
invalidating all IOTLB, then cache existing memory ranges into vhost
backend iotlb using 1:1 mapping.

Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 hw/virtio/trace-events |  4 +++
 hw/virtio/vhost.c      | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 1f7a7c1..54dcbb3 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -24,3 +24,7 @@ virtio_balloon_handle_output(const char *name, uint64_t gpa) "section name: %s g
 virtio_balloon_get_config(uint32_t num_pages, uint32_t actual) "num_pages: %d actual: %d"
 virtio_balloon_set_config(uint32_t actual, uint32_t oldactual) "actual: %d oldactual: %d"
 virtio_balloon_to_target(uint64_t target, uint32_t num_pages) "balloon target: %"PRIx64" num_pages: %d"
+
+# hw/virtio/vhost.c
+vhost_iommu_commit(void) ""
+vhost_iommu_static_preheat(void) ""
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 03a46a7..d03d720 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -27,6 +27,7 @@
 #include "hw/virtio/virtio-access.h"
 #include "migration/blocker.h"
 #include "sysemu/dma.h"
+#include "trace.h"
 
 /* enabled until disconnected backend stabilizes */
 #define _VHOST_DEBUG 1
@@ -730,6 +731,11 @@ static void vhost_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
     }
 }
 
+static bool vhost_iommu_mr_enabled(struct vhost_dev *dev)
+{
+    return !QLIST_EMPTY(&dev->iommu_list);
+}
+
 static void vhost_iommu_region_add(MemoryListener *listener,
                                    MemoryRegionSection *section)
 {
@@ -782,6 +788,65 @@ static void vhost_iommu_region_del(MemoryListener *listener,
     }
 }
 
+static void vhost_iommu_commit(MemoryListener *listener)
+{
+    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
+                                         iommu_listener);
+    struct vhost_memory_region *r;
+    int i;
+
+    trace_vhost_iommu_commit();
+
+    if (!vhost_iommu_mr_enabled(dev)) {
+        /*
+        * This means iommu_platform is enabled, however iommu memory
+        * region is disabled, e.g., when device passthrough is setup.
+        * Then, no translation is needed any more.
+        *
+        * Let's first invalidate the whole IOTLB, then pre-heat the
+        * static mapping by looping over vhost memory ranges.
+        */
+
+        if (dev->vhost_ops->vhost_invalidate_device_iotlb(dev, 0,
+                                                          UINT64_MAX)) {
+            error_report("%s: flush existing IOTLB failed", __func__);
+            return;
+        }
+
+        /*
+         * Current VHOST_IOTLB_INVALIDATE API has a small defect that
+         * the invalidation for (start=0, size=UINT64_MAX) cannot
+         * really invalidate an cached range of (start=UINT64_MAX-1,
+         * size=1). We send this 2nd invalidation to workaround this.
+         * But, frankly speaking for QEMU we don't have a problem with
+         * this since we will never have a vhost cache with range
+         * (start=UINT64_MAX-1, size=1) - if you see
+         * address_space_get_iotlb_entry() all IOTLBs are page
+         * aligned.
+         */
+        if (dev->vhost_ops->vhost_invalidate_device_iotlb(dev, UINT64_MAX,
+                                                          1)) {
+            error_report("%s: flush existing IOTLB failed", __func__);
+            return;
+        }
+
+        for (i = 0; i < dev->mem->nregions; i++) {
+            r = &dev->mem->regions[i];
+            /* Vhost regions are writable RAM, so IOMMU_RW suites. */
+            if (dev->vhost_ops->vhost_update_device_iotlb(dev,
+                                                          r->guest_phys_addr,
+                                                          r->userspace_addr,
+                                                          r->memory_size,
+                                                          IOMMU_RW)) {
+                error_report("%s: pre-heat static mapping failed", __func__);
+                return;
+            }
+        }
+
+        trace_vhost_iommu_static_preheat();
+    }
+}
+
 static void vhost_region_nop(MemoryListener *listener,
                              MemoryRegionSection *section)
 {
@@ -1298,6 +1363,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
     hdev->iommu_listener = (MemoryListener) {
         .region_add = vhost_iommu_region_add,
         .region_del = vhost_iommu_region_del,
+        .commit = vhost_iommu_commit,
     };
 
     if (hdev->migration_blocker == NULL) {
-- 
2.7.4