2 files changed, 46 insertions, 21 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 801578b4b9..f3ba9b9007 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -294,53 +294,78 @@ static bool vfio_listener_skipped_section(MemoryRegionSection *section)
            section->offset_within_address_space & (1ULL << 63);
 }
 
-static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+/* Called with rcu_read_lock held.  */
+static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr,
+                           bool *read_only)
 {
-    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
-    VFIOContainer *container = giommu->container;
-    hwaddr iova = iotlb->iova + giommu->iommu_offset;
     MemoryRegion *mr;
     hwaddr xlat;
     hwaddr len = iotlb->addr_mask + 1;
-    void *vaddr;
-    int ret;
-
-    trace_vfio_iommu_map_notify(iova, iova + iotlb->addr_mask);
-
-    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;
-    }
+    bool writable = iotlb->perm & IOMMU_WO;
 
     /*
      * The IOMMU TLB entry we have just covers translation through
      * this IOMMU to its immediate target.  We need to translate
      * it the rest of the way through to memory.
      */
-    rcu_read_lock();
     mr = address_space_translate(&address_space_memory,
                                  iotlb->translated_addr,
-                                 &xlat, &len, iotlb->perm & IOMMU_WO);
+                                 &xlat, &len, writable);
     if (!memory_region_is_ram(mr)) {
         error_report("iommu map to non memory area %"HWADDR_PRIx"",
                      xlat);
-        goto out;
+        return false;
     }
+
     /*
      * Translation truncates length to the IOMMU page size,
      * check that it did not truncate too much.
      */
     if (len & iotlb->addr_mask) {
         error_report("iommu has granularity incompatible with target AS");
-        goto out;
+        return false;
     }
 
+    *vaddr = memory_region_get_ram_ptr(mr) + xlat;
+    *read_only = !writable || mr->readonly;
+
+    return true;
+}
+
+static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
+    VFIOContainer *container = giommu->container;
+    hwaddr iova = iotlb->iova + giommu->iommu_offset;
+    bool read_only;
+    void *vaddr;
+    int ret;
+
+    trace_vfio_iommu_map_notify(iotlb->perm == IOMMU_NONE ? "UNMAP" : "MAP",
+                                iova, iova + iotlb->addr_mask);
+
+    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();
+
     if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
-        vaddr = memory_region_get_ram_ptr(mr) + xlat;
+        if (!vfio_get_vaddr(iotlb, &vaddr, &read_only)) {
+            goto out;
+        }
+        /*
+         * vaddr is only valid until rcu_read_unlock(). But after
+         * vfio_dma_map has set up the mapping the pages will be
+         * pinned by the kernel. This makes sure that the RAM backend
+         * of vaddr will always be there, even if the memory object is
+         * destroyed and its backing memory munmap-ed.
+         */
         ret = vfio_dma_map(container, iova,
                            iotlb->addr_mask + 1, vaddr,
-                           !(iotlb->perm & IOMMU_WO) || mr->readonly);
+                           read_only);
         if (ret) {
             error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                          "0x%"HWADDR_PRIx", %p) = %d (%m)",
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 8de8281357..2561c6d31a 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -84,7 +84,7 @@ vfio_pci_igd_lpc_bridge_enabled(const char *name) "%s"
 # hw/vfio/common.c
 vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)"
 vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64
-vfio_iommu_map_notify(uint64_t iova_start, uint64_t iova_end) "iommu map @ %"PRIx64" - %"PRIx64
+vfio_iommu_map_notify(const char *op, uint64_t iova_start, uint64_t iova_end) "iommu %s @ %"PRIx64" - %"PRIx64
 vfio_listener_region_add_skip(uint64_t start, uint64_t end) "SKIPPING region_add %"PRIx64" - %"PRIx64
 vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] %"PRIx64" - %"PRIx64
 vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] %"PRIx64" - %"PRIx64" [%p]"