summary refs log tree commit diff stats
diff options
context:
space:
mode:
-rw-r--r--hw/vfio/common.c39
-rw-r--r--hw/virtio/virtio-mem.c1
-rw-r--r--include/migration/vmstate.h1
3 files changed, 41 insertions, 0 deletions
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index f8a2fe8441..8a9bbf2791 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -36,6 +36,7 @@
 #include "qemu/range.h"
 #include "sysemu/kvm.h"
 #include "sysemu/reset.h"
+#include "sysemu/runstate.h"
 #include "trace.h"
 #include "qapi/error.h"
 #include "migration/migration.h"
@@ -569,6 +570,44 @@ static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
         error_report("iommu map to non memory area %"HWADDR_PRIx"",
                      xlat);
         return false;
+    } else if (memory_region_has_ram_discard_manager(mr)) {
+        RamDiscardManager *rdm = memory_region_get_ram_discard_manager(mr);
+        MemoryRegionSection tmp = {
+            .mr = mr,
+            .offset_within_region = xlat,
+            .size = int128_make64(len),
+        };
+
+        /*
+         * Malicious VMs can map memory into the IOMMU, which is expected
+         * to remain discarded. vfio will pin all pages, populating memory.
+         * Disallow that. vmstate priorities make sure any RamDiscardManager
+         * were already restored before IOMMUs are restored.
+         */
+        if (!ram_discard_manager_is_populated(rdm, &tmp)) {
+            error_report("iommu map to discarded memory (e.g., unplugged via"
+                         " virtio-mem): %"HWADDR_PRIx"",
+                         iotlb->translated_addr);
+            return false;
+        }
+
+        /*
+         * Malicious VMs might trigger discarding of IOMMU-mapped memory. The
+         * pages will remain pinned inside vfio until unmapped, resulting in a
+         * higher memory consumption than expected. If memory would get
+         * populated again later, there would be an inconsistency between pages
+         * pinned by vfio and pages seen by QEMU. This is the case until
+         * unmapped from the IOMMU (e.g., during device reset).
+         *
+         * With malicious guests, we really only care about pinning more memory
+         * than expected. RLIMIT_MEMLOCK set for the user/process can never be
+         * exceeded and can be used to mitigate this problem.
+         */
+        warn_report_once("Using vfio with vIOMMUs and coordinated discarding of"
+                         " RAM (e.g., virtio-mem) works, however, malicious"
+                         " guests can trigger pinning of more memory than"
+                         " intended via an IOMMU. It's possible to mitigate "
+                         " by setting/adjusting RLIMIT_MEMLOCK.");
     }
 
     /*
diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index f60cb8a3fc..368ae1db90 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -886,6 +886,7 @@ static const VMStateDescription vmstate_virtio_mem_device = {
     .name = "virtio-mem-device",
     .minimum_version_id = 1,
     .version_id = 1,
+    .priority = MIG_PRI_VIRTIO_MEM,
     .post_load = virtio_mem_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_WITH_TMP(VirtIOMEM, VirtIOMEMMigSanityChecks,
diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h
index 8df7b69f38..017c03675c 100644
--- a/include/migration/vmstate.h
+++ b/include/migration/vmstate.h
@@ -153,6 +153,7 @@ typedef enum {
     MIG_PRI_DEFAULT = 0,
     MIG_PRI_IOMMU,              /* Must happen before PCI devices */
     MIG_PRI_PCI_BUS,            /* Must happen before IOMMU */
+    MIG_PRI_VIRTIO_MEM,         /* Must happen before IOMMU */
     MIG_PRI_GICV3_ITS,          /* Must happen before PCI devices */
     MIG_PRI_GICV3,              /* Must happen before the ITS */
     MIG_PRI_MAX,