From fc49c9cbf2deba53370f48ad9db2adc5f6ceb3ba Mon Sep 17 00:00:00 2001
From: Kirti Wankhede <kwankhede@nvidia.com>
Date: Mon, 26 Oct 2020 15:06:21 +0530
Subject: [PATCH] vfio: Get migration capability flags for container

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 4c32b1bb99..35168b8f3e 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1210,6 +1210,75 @@ 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)
 {
@@ -1273,6 +1342,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
     container = g_malloc0(sizeof(*container));
     container->space = space;
     container->fd = fd;
+    container->dirty_pages_supported = false;
     QLIST_INIT(&container->giommu_list);
     QLIST_INIT(&container->hostwin_list);
 
@@ -1285,7 +1355,7 @@ 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
@@ -1294,15 +1364,19 @@ 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 954c064435..0d2bd9e5cd 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 c825524606..8fd0212264 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;
     int 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;
-- 
2.27.0