1 files changed, 92 insertions, 52 deletions

diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index e7bece4..d3efef7 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -15,20 +15,27 @@
 #include <linux/vfio.h>
 #include <linux/iommufd.h>
 
-#include "hw/vfio/vfio-common.h"
+#include "hw/vfio/vfio-device.h"
 #include "qemu/error-report.h"
 #include "trace.h"
 #include "qapi/error.h"
-#include "sysemu/iommufd.h"
+#include "system/iommufd.h"
 #include "hw/qdev-core.h"
-#include "sysemu/reset.h"
+#include "hw/vfio/vfio-cpr.h"
+#include "system/reset.h"
 #include "qemu/cutils.h"
 #include "qemu/chardev_open.h"
 #include "pci.h"
-#include "exec/ram_addr.h"
+#include "vfio-iommufd.h"
+#include "vfio-helpers.h"
+#include "vfio-listener.h"
+
+#define TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO             \
+            TYPE_HOST_IOMMU_DEVICE_IOMMUFD "-vfio"
 
 static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
-                            ram_addr_t size, void *vaddr, bool readonly)
+                            ram_addr_t size, void *vaddr, bool readonly,
+                            MemoryRegion *mr)
 {
     const VFIOIOMMUFDContainer *container =
         container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
@@ -40,11 +47,28 @@ static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
 
 static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
                               hwaddr iova, ram_addr_t size,
-                              IOMMUTLBEntry *iotlb)
+                              IOMMUTLBEntry *iotlb, bool unmap_all)
 {
     const VFIOIOMMUFDContainer *container =
         container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
 
+    /* unmap in halves */
+    if (unmap_all) {
+        Int128 llsize = int128_rshift(int128_2_64(), 1);
+        int ret;
+
+        ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
+                                        0, int128_get64(llsize));
+
+        if (ret == 0) {
+            ret = iommufd_backend_unmap_dma(container->be, container->ioas_id,
+                                            int128_get64(llsize),
+                                            int128_get64(llsize));
+        }
+
+        return ret;
+    }
+
     /* TODO: Handle dma_unmap_bitmap with iotlb args (migration) */
     return iommufd_backend_unmap_dma(container->be,
                                      container->ioas_id, iova, size);
@@ -281,7 +305,8 @@ static bool iommufd_cdev_autodomains_get(VFIODevice *vbasedev,
 {
     ERRP_GUARD();
     IOMMUFDBackend *iommufd = vbasedev->iommufd;
-    uint32_t flags = 0;
+    uint32_t type, flags = 0;
+    uint64_t hw_caps;
     VFIOIOASHwpt *hwpt;
     uint32_t hwpt_id;
     int ret;
@@ -318,7 +343,12 @@ static bool iommufd_cdev_autodomains_get(VFIODevice *vbasedev,
      * vfio_migration_realize() may decide to use VF dirty tracking
      * instead.
      */
-    if (vbasedev->hiod->caps.hw_caps & IOMMU_HW_CAP_DIRTY_TRACKING) {
+    if (!iommufd_backend_get_device_info(vbasedev->iommufd, vbasedev->devid,
+                                         &type, NULL, 0, &hw_caps, errp)) {
+        return false;
+    }
+
+    if (hw_caps & IOMMU_HW_CAP_DIRTY_TRACKING) {
         flags = IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
     }
 
@@ -404,7 +434,8 @@ static void iommufd_cdev_container_destroy(VFIOIOMMUFDContainer *container)
     if (!QLIST_EMPTY(&bcontainer->device_list)) {
         return;
     }
-    memory_listener_unregister(&bcontainer->listener);
+    vfio_cpr_unregister_container(bcontainer);
+    vfio_listener_unregister(bcontainer);
     iommufd_backend_free_id(container->be, container->ioas_id);
     object_unref(container);
 }
@@ -486,18 +517,7 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         goto err_connect_bind;
     }
 
-    space = vfio_get_address_space(as);
-
-    /*
-     * The HostIOMMUDevice data from legacy backend is static and doesn't need
-     * any information from the (type1-iommu) backend to be initialized. In
-     * contrast however, the IOMMUFD HostIOMMUDevice data requires the iommufd
-     * FD to be connected and having a devid to be able to successfully call
-     * iommufd_backend_get_device_info().
-     */
-    if (!vfio_device_hiod_realize(vbasedev, errp)) {
-        goto err_alloc_ioas;
-    }
+    space = vfio_address_space_get(as);
 
     /* try to attach to an existing container in this space */
     QLIST_FOREACH(bcontainer, &space->containers, next) {
@@ -515,8 +535,8 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         } else {
             ret = iommufd_cdev_ram_block_discard_disable(true);
             if (ret) {
-                error_setg(errp,
-                              "Cannot set discarding of RAM broken (%d)", ret);
+                error_setg_errno(errp, -ret,
+                                 "Cannot set discarding of RAM broken");
                 goto err_discard_disable;
             }
             goto found_container;
@@ -544,6 +564,7 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
 
     ret = iommufd_cdev_ram_block_discard_disable(true);
     if (ret) {
+        error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
         goto err_discard_disable;
     }
 
@@ -555,12 +576,11 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         bcontainer->pgsizes = qemu_real_host_page_size();
     }
 
-    bcontainer->listener = vfio_memory_listener;
-    memory_listener_register(&bcontainer->listener, bcontainer->space->as);
+    if (!vfio_listener_register(bcontainer, errp)) {
+        goto err_listener_register;
+    }
 
-    if (bcontainer->error) {
-        error_propagate_prepend(errp, bcontainer->error,
-                                "memory listener initialization failed: ");
+    if (!vfio_cpr_register_container(bcontainer, errp)) {
         goto err_listener_register;
     }
 
@@ -573,7 +593,12 @@ found_container:
         goto err_listener_register;
     }
 
-    if (!vfio_cpr_register_container(bcontainer, errp)) {
+    /*
+     * Do not move this code before attachment! The nested IOMMU support
+     * needs device and hwpt id which are generated only after attachment.
+     */
+    if (!vfio_device_hiod_create_and_realize(vbasedev,
+                     TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO, errp)) {
         goto err_listener_register;
     }
 
@@ -585,14 +610,7 @@ found_container:
         iommufd_cdev_ram_block_discard_disable(false);
     }
 
-    vbasedev->group = 0;
-    vbasedev->num_irqs = dev_info.num_irqs;
-    vbasedev->num_regions = dev_info.num_regions;
-    vbasedev->flags = dev_info.flags;
-    vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);
-    vbasedev->bcontainer = bcontainer;
-    QLIST_INSERT_HEAD(&bcontainer->device_list, vbasedev, container_next);
-    QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+    vfio_device_prepare(vbasedev, bcontainer, &dev_info);
 
     trace_iommufd_cdev_device_info(vbasedev->name, devfd, vbasedev->num_irqs,
                                    vbasedev->num_regions, vbasedev->flags);
@@ -605,7 +623,7 @@ err_discard_disable:
 err_attach_container:
     iommufd_cdev_container_destroy(container);
 err_alloc_ioas:
-    vfio_put_address_space(space);
+    vfio_address_space_put(space);
     iommufd_cdev_unbind_and_disconnect(vbasedev);
 err_connect_bind:
     close(vbasedev->fd);
@@ -619,18 +637,16 @@ static void iommufd_cdev_detach(VFIODevice *vbasedev)
     VFIOIOMMUFDContainer *container = container_of(bcontainer,
                                                    VFIOIOMMUFDContainer,
                                                    bcontainer);
-    QLIST_REMOVE(vbasedev, global_next);
-    QLIST_REMOVE(vbasedev, container_next);
-    vbasedev->bcontainer = NULL;
+    vfio_device_unprepare(vbasedev);
 
     if (!vbasedev->ram_block_discard_allowed) {
         iommufd_cdev_ram_block_discard_disable(false);
     }
 
-    vfio_cpr_unregister_container(bcontainer);
+    object_unref(vbasedev->hiod);
     iommufd_cdev_detach_container(vbasedev, container);
     iommufd_cdev_container_destroy(container);
-    vfio_put_address_space(space);
+    vfio_address_space_put(space);
 
     iommufd_cdev_unbind_and_disconnect(vbasedev);
     close(vbasedev->fd);
@@ -786,12 +802,10 @@ out_single:
     return ret;
 }
 
-static void vfio_iommu_iommufd_class_init(ObjectClass *klass, void *data)
+static void vfio_iommu_iommufd_class_init(ObjectClass *klass, const void *data)
 {
     VFIOIOMMUClass *vioc = VFIO_IOMMU_CLASS(klass);
 
-    vioc->hiod_typename = TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO;
-
     vioc->dma_map = iommufd_cdev_map;
     vioc->dma_unmap = iommufd_cdev_unmap;
     vioc->attach_device = iommufd_cdev_attach;
@@ -801,21 +815,38 @@ static void vfio_iommu_iommufd_class_init(ObjectClass *klass, void *data)
     vioc->query_dirty_bitmap = iommufd_query_dirty_bitmap;
 };
 
+static bool
+host_iommu_device_iommufd_vfio_attach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+                                           uint32_t hwpt_id, Error **errp)
+{
+    VFIODevice *vbasedev = HOST_IOMMU_DEVICE(idev)->agent;
+
+    return !iommufd_cdev_attach_ioas_hwpt(vbasedev, hwpt_id, errp);
+}
+
+static bool
+host_iommu_device_iommufd_vfio_detach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+                                           Error **errp)
+{
+    VFIODevice *vbasedev = HOST_IOMMU_DEVICE(idev)->agent;
+
+    return iommufd_cdev_detach_ioas_hwpt(vbasedev, errp);
+}
+
 static bool hiod_iommufd_vfio_realize(HostIOMMUDevice *hiod, void *opaque,
                                       Error **errp)
 {
     VFIODevice *vdev = opaque;
+    HostIOMMUDeviceIOMMUFD *idev;
     HostIOMMUDeviceCaps *caps = &hiod->caps;
+    VendorCaps *vendor_caps = &caps->vendor_caps;
     enum iommu_hw_info_type type;
-    union {
-        struct iommu_hw_info_vtd vtd;
-    } data;
     uint64_t hw_caps;
 
     hiod->agent = opaque;
 
-    if (!iommufd_backend_get_device_info(vdev->iommufd, vdev->devid,
-                                         &type, &data, sizeof(data),
+    if (!iommufd_backend_get_device_info(vdev->iommufd, vdev->devid, &type,
+                                         vendor_caps, sizeof(*vendor_caps),
                                          &hw_caps, errp)) {
         return false;
     }
@@ -824,6 +855,11 @@ static bool hiod_iommufd_vfio_realize(HostIOMMUDevice *hiod, void *opaque,
     caps->type = type;
     caps->hw_caps = hw_caps;
 
+    idev = HOST_IOMMU_DEVICE_IOMMUFD(hiod);
+    idev->iommufd = vdev->iommufd;
+    idev->devid = vdev->devid;
+    idev->hwpt_id = vdev->hwpt->hwpt_id;
+
     return true;
 }
 
@@ -846,13 +882,17 @@ hiod_iommufd_vfio_get_page_size_mask(HostIOMMUDevice *hiod)
 }
 
 
-static void hiod_iommufd_vfio_class_init(ObjectClass *oc, void *data)
+static void hiod_iommufd_vfio_class_init(ObjectClass *oc, const void *data)
 {
     HostIOMMUDeviceClass *hiodc = HOST_IOMMU_DEVICE_CLASS(oc);
+    HostIOMMUDeviceIOMMUFDClass *idevc = HOST_IOMMU_DEVICE_IOMMUFD_CLASS(oc);
 
     hiodc->realize = hiod_iommufd_vfio_realize;
     hiodc->get_iova_ranges = hiod_iommufd_vfio_get_iova_ranges;
     hiodc->get_page_size_mask = hiod_iommufd_vfio_get_page_size_mask;
+
+    idevc->attach_hwpt = host_iommu_device_iommufd_vfio_attach_hwpt;
+    idevc->detach_hwpt = host_iommu_device_iommufd_vfio_detach_hwpt;
 };
 
 static const TypeInfo types[] = {