vfio: spapr: Add DMA memory preregistering (SPAPR IOMMU v2)

This makes use of the new "memory registering" feature. The idea is
to provide the userspace ability to notify the host kernel about pages
which are going to be used for DMA. Having this information, the host
kernel can pin them all once per user process, do locked pages
accounting (once) and not spent time on doing that in real time with
possible failures which cannot be handled nicely in some cases.

This adds a prereg memory listener which listens on address_space_memory
and notifies a VFIO container about memory which needs to be
pinned/unpinned. VFIO MMIO regions (i.e. "skip dump" regions) are skipped.

The feature is only enabled for SPAPR IOMMU v2. The host kernel changes
are required. Since v2 does not need/support VFIO_IOMMU_ENABLE, this does
not call it when v2 is detected and enabled.

This enforces guest RAM blocks to be host page size aligned; however
this is not new as KVM already requires memory slots to be host page
size aligned.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[dwg: Fix compile error on 32-bit host]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

1 files changed, 31 insertions, 9 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 7be638e..46381e6 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -503,6 +503,9 @@ static const MemoryListener vfio_memory_listener = {
 static void vfio_listener_release(VFIOContainer *container)
 {
     memory_listener_unregister(&container->listener);
+    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+        memory_listener_unregister(&container->prereg_listener);
+    }
 }
 
 static struct vfio_info_cap_header *
@@ -861,8 +864,8 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
             goto free_container_exit;
         }
 
-        ret = ioctl(fd, VFIO_SET_IOMMU,
-                    v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU);
+        container->iommu_type = v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU;
+        ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
         if (ret) {
             error_report("vfio: failed to set iommu for container: %m");
             ret = -errno;
@@ -887,8 +890,10 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
         if ((ret == 0) && (info.flags & VFIO_IOMMU_INFO_PGSIZES)) {
             container->iova_pgsizes = info.iova_pgsizes;
         }
-    } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) {
+    } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU) ||
+               ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU)) {
         struct vfio_iommu_spapr_tce_info info;
+        bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU);
 
         ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
         if (ret) {
@@ -896,7 +901,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
             ret = -errno;
             goto free_container_exit;
         }
-        ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU);
+        container->iommu_type =
+            v2 ? VFIO_SPAPR_TCE_v2_IOMMU : VFIO_SPAPR_TCE_IOMMU;
+        ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
         if (ret) {
             error_report("vfio: failed to set iommu for container: %m");
             ret = -errno;
@@ -908,11 +915,23 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
          * when container fd is closed so we do not call it explicitly
          * in this file.
          */
-        ret = ioctl(fd, VFIO_IOMMU_ENABLE);
-        if (ret) {
-            error_report("vfio: failed to enable container: %m");
-            ret = -errno;
-            goto free_container_exit;
+        if (!v2) {
+            ret = ioctl(fd, VFIO_IOMMU_ENABLE);
+            if (ret) {
+                error_report("vfio: failed to enable container: %m");
+                ret = -errno;
+                goto free_container_exit;
+            }
+        } else {
+            container->prereg_listener = vfio_prereg_listener;
+
+            memory_listener_register(&container->prereg_listener,
+                                     &address_space_memory);
+            if (container->error) {
+                memory_listener_unregister(&container->prereg_listener);
+                error_report("vfio: RAM memory listener initialization failed for container");
+                goto free_container_exit;
+            }
         }
 
         /*
@@ -925,6 +944,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
         if (ret) {
             error_report("vfio: VFIO_IOMMU_SPAPR_TCE_GET_INFO failed: %m");
             ret = -errno;
+            if (v2) {
+                memory_listener_unregister(&container->prereg_listener);
+            }
             goto free_container_exit;
         }
         container->min_iova = info.dma32_window_start;