1 files changed, 71 insertions, 6 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index f895e3c335..5e84716218 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -544,18 +544,40 @@ static void vfio_listener_region_add(MemoryListener *listener,
 
     llsize = int128_sub(llend, int128_make64(iova));
 
+    if (memory_region_is_ram_device(section->mr)) {
+        hwaddr pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1;
+
+        if ((iova & pgmask) || (int128_get64(llsize) & pgmask)) {
+            error_report("Region 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx
+                         " is not aligned to 0x%"HWADDR_PRIx
+                         " and cannot be mapped for DMA",
+                         section->offset_within_region,
+                         int128_getlo(section->size),
+                         pgmask + 1);
+            return;
+        }
+    }
+
     ret = vfio_dma_map(container, iova, int128_get64(llsize),
                        vaddr, section->readonly);
     if (ret) {
         error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                      "0x%"HWADDR_PRIx", %p) = %d (%m)",
                      container, iova, int128_get64(llsize), vaddr, ret);
+        if (memory_region_is_ram_device(section->mr)) {
+            /* Allow unexpected mappings not to be fatal for RAM devices */
+            return;
+        }
         goto fail;
     }
 
     return;
 
 fail:
+    if (memory_region_is_ram_device(section->mr)) {
+        error_report("failed to vfio_dma_map. pci p2p may not work");
+        return;
+    }
     /*
      * On the initfn path, store the first error in the container so we
      * can gracefully fail.  Runtime, there's not much we can do other
@@ -577,6 +599,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
     hwaddr iova, end;
     Int128 llend, llsize;
     int ret;
+    bool try_unmap = true;
 
     if (vfio_listener_skipped_section(section)) {
         trace_vfio_listener_region_del_skip(
@@ -629,14 +652,34 @@ static void vfio_listener_region_del(MemoryListener *listener,
 
     trace_vfio_listener_region_del(iova, end);
 
-    ret = vfio_dma_unmap(container, iova, int128_get64(llsize));
-    memory_region_unref(section->mr);
-    if (ret) {
-        error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
-                     "0x%"HWADDR_PRIx") = %d (%m)",
-                     container, iova, int128_get64(llsize), ret);
+    if (memory_region_is_ram_device(section->mr)) {
+        hwaddr pgmask;
+        VFIOHostDMAWindow *hostwin;
+        bool hostwin_found = false;
+
+        QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
+            if (hostwin->min_iova <= iova && end <= hostwin->max_iova) {
+                hostwin_found = true;
+                break;
+            }
+        }
+        assert(hostwin_found); /* or region_add() would have failed */
+
+        pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1;
+        try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask));
     }
 
+    if (try_unmap) {
+        ret = vfio_dma_unmap(container, iova, int128_get64(llsize));
+        if (ret) {
+            error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
+                         "0x%"HWADDR_PRIx") = %d (%m)",
+                         container, iova, int128_get64(llsize), ret);
+        }
+    }
+
+    memory_region_unref(section->mr);
+
     if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
         vfio_spapr_remove_window(container,
                                  section->offset_within_address_space);
@@ -858,6 +901,13 @@ void vfio_region_finalize(VFIORegion *region)
     g_free(region->mmaps);
 
     trace_vfio_region_finalize(region->vbasedev->name, region->nr);
+
+    region->mem = NULL;
+    region->mmaps = NULL;
+    region->nr_mmaps = 0;
+    region->size = 0;
+    region->flags = 0;
+    region->nr = 0;
 }
 
 void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled)
@@ -1421,6 +1471,21 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
     return -ENODEV;
 }
 
+bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
+{
+    struct vfio_region_info *info = NULL;
+    bool ret = false;
+
+    if (!vfio_get_region_info(vbasedev, region, &info)) {
+        if (vfio_get_region_info_cap(info, cap_type)) {
+            ret = true;
+        }
+        g_free(info);
+    }
+
+    return ret;
+}
+
 /*
  * Interfaces for IBM EEH (Enhanced Error Handling)
  */