[PULL 11/32] vfio: Get migration capability flags for container

[Alex Williamson <alex.williamson@redhat.com>]

From: Kirti Wankhede <kwankhede@nvidia.com>

Added helper functions to get IOMMU info capability chain.
Added function to get migration capability information from that
capability chain for IOMMU container.

Similar change was proposed earlier:
https://lists.gnu.org/archive/html/qemu-devel/2018-05/msg03759.html

Disable migration for devices if IOMMU module doesn't support migration
capability.

Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Cc: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Cc: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 hw/vfio/common.c              |   90 +++++++++++++++++++++++++++++++++++++----
 hw/vfio/migration.c           |    7 +++
 include/hw/vfio/vfio-common.h |    3 +
 3 files changed, 91 insertions(+), 9 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index c6e98b8d61be..d4959c036dd1 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1228,6 +1228,75 @@ static int vfio_init_container(VFIOContainer *container, int group_fd,
     return 0;
 }
 
+static int vfio_get_iommu_info(VFIOContainer *container,
+                               struct vfio_iommu_type1_info **info)
+{
+
+    size_t argsz = sizeof(struct vfio_iommu_type1_info);
+
+    *info = g_new0(struct vfio_iommu_type1_info, 1);
+again:
+    (*info)->argsz = argsz;
+
+    if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) {
+        g_free(*info);
+        *info = NULL;
+        return -errno;
+    }
+
+    if (((*info)->argsz > argsz)) {
+        argsz = (*info)->argsz;
+        *info = g_realloc(*info, argsz);
+        goto again;
+    }
+
+    return 0;
+}
+
+static struct vfio_info_cap_header *
+vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id)
+{
+    struct vfio_info_cap_header *hdr;
+    void *ptr = info;
+
+    if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) {
+        return NULL;
+    }
+
+    for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
+        if (hdr->id == id) {
+            return hdr;
+        }
+    }
+
+    return NULL;
+}
+
+static void vfio_get_iommu_info_migration(VFIOContainer *container,
+                                         struct vfio_iommu_type1_info *info)
+{
+    struct vfio_info_cap_header *hdr;
+    struct vfio_iommu_type1_info_cap_migration *cap_mig;
+
+    hdr = vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION);
+    if (!hdr) {
+        return;
+    }
+
+    cap_mig = container_of(hdr, struct vfio_iommu_type1_info_cap_migration,
+                            header);
+
+    /*
+     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
+     * TARGET_PAGE_SIZE to mark those dirty.
+     */
+    if (cap_mig->pgsize_bitmap & TARGET_PAGE_SIZE) {
+        container->dirty_pages_supported = true;
+        container->max_dirty_bitmap_size = cap_mig->max_dirty_bitmap_size;
+        container->dirty_pgsizes = cap_mig->pgsize_bitmap;
+    }
+}
+
 static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
                                   Error **errp)
 {
@@ -1297,6 +1366,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
     container->space = space;
     container->fd = fd;
     container->error = NULL;
+    container->dirty_pages_supported = false;
     QLIST_INIT(&container->giommu_list);
     QLIST_INIT(&container->hostwin_list);
 
@@ -1309,7 +1379,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
     case VFIO_TYPE1v2_IOMMU:
     case VFIO_TYPE1_IOMMU:
     {
-        struct vfio_iommu_type1_info info;
+        struct vfio_iommu_type1_info *info;
 
         /*
          * FIXME: This assumes that a Type1 IOMMU can map any 64-bit
@@ -1318,15 +1388,19 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
          * existing Type1 IOMMUs generally support any IOVA we're
          * going to actually try in practice.
          */
-        info.argsz = sizeof(info);
-        ret = ioctl(fd, VFIO_IOMMU_GET_INFO, &info);
-        /* Ignore errors */
-        if (ret || !(info.flags & VFIO_IOMMU_INFO_PGSIZES)) {
+        ret = vfio_get_iommu_info(container, &info);
+
+        if (ret || !(info->flags & VFIO_IOMMU_INFO_PGSIZES)) {
             /* Assume 4k IOVA page size */
-            info.iova_pgsizes = 4096;
+            info->iova_pgsizes = 4096;
         }
-        vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
-        container->pgsizes = info.iova_pgsizes;
+        vfio_host_win_add(container, 0, (hwaddr)-1, info->iova_pgsizes);
+        container->pgsizes = info->iova_pgsizes;
+
+        if (!ret) {
+            vfio_get_iommu_info_migration(container, info);
+        }
+        g_free(info);
         break;
     }
     case VFIO_SPAPR_TCE_v2_IOMMU:
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 6ac72b46a88b..93f8fe7bd869 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -832,9 +832,14 @@ err:
 
 int vfio_migration_probe(VFIODevice *vbasedev, Error **errp)
 {
+    VFIOContainer *container = vbasedev->group->container;
     struct vfio_region_info *info = NULL;
     Error *local_err = NULL;
-    int ret;
+    int ret = -ENOTSUP;
+
+    if (!container->dirty_pages_supported) {
+        goto add_blocker;
+    }
 
     ret = vfio_get_dev_region_info(vbasedev, VFIO_REGION_TYPE_MIGRATION,
                                    VFIO_REGION_SUBTYPE_MIGRATION, &info);
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index f4ebdae013ad..b1c1b18fd228 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -84,6 +84,9 @@ typedef struct VFIOContainer {
     unsigned iommu_type;
     Error *error;
     bool initialized;
+    bool dirty_pages_supported;
+    uint64_t dirty_pgsizes;
+    uint64_t max_dirty_bitmap_size;
     unsigned long pgsizes;
     QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
     QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;