vfio: add per-region fd support

For vfio-user, each region has its own fd rather than sharing
vbasedev's. Add the necessary plumbing to support this, and use the
correct fd in vfio_region_mmap().

Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250607001056.335310-4-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

3 files changed, 37 insertions, 8 deletions

diff --git a/hw/vfio/device.c b/hw/vfio/device.c
index 9fba2c7..a4bdde8 100644
--- a/hw/vfio/device.c
+++ b/hw/vfio/device.c
@@ -200,6 +200,7 @@ int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
                                 struct vfio_region_info **info)
 {
     size_t argsz = sizeof(struct vfio_region_info);
+    int fd = -1;
     int ret;
 
     /* check cache */
@@ -214,7 +215,7 @@ int vfio_device_get_region_info(VFIODevice *vbasedev, int index,
 retry:
     (*info)->argsz = argsz;
 
-    ret = vbasedev->io_ops->get_region_info(vbasedev, *info);
+    ret = vbasedev->io_ops->get_region_info(vbasedev, *info, &fd);
     if (ret != 0) {
         g_free(*info);
         *info = NULL;
@@ -225,11 +226,19 @@ retry:
         argsz = (*info)->argsz;
         *info = g_realloc(*info, argsz);
 
+        if (fd != -1) {
+            close(fd);
+            fd = -1;
+        }
+
         goto retry;
     }
 
     /* fill cache */
     vbasedev->reginfo[index] = *info;
+    if (vbasedev->region_fds != NULL) {
+        vbasedev->region_fds[index] = fd;
+    }
 
     return 0;
 }
@@ -334,6 +343,7 @@ void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
     vbasedev->io_ops = &vfio_device_io_ops_ioctl;
     vbasedev->dev = dev;
     vbasedev->fd = -1;
+    vbasedev->use_region_fds = false;
 
     vbasedev->ram_block_discard_allowed = ram_discard;
 }
@@ -444,6 +454,9 @@ void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer,
 
     vbasedev->reginfo = g_new0(struct vfio_region_info *,
                                vbasedev->num_regions);
+    if (vbasedev->use_region_fds) {
+        vbasedev->region_fds = g_new0(int, vbasedev->num_regions);
+    }
 }
 
 void vfio_device_unprepare(VFIODevice *vbasedev)
@@ -452,9 +465,14 @@ void vfio_device_unprepare(VFIODevice *vbasedev)
 
     for (i = 0; i < vbasedev->num_regions; i++) {
         g_free(vbasedev->reginfo[i]);
+        if (vbasedev->region_fds != NULL && vbasedev->region_fds[i] != -1) {
+            close(vbasedev->region_fds[i]);
+        }
+
     }
-    g_free(vbasedev->reginfo);
-    vbasedev->reginfo = NULL;
+
+    g_clear_pointer(&vbasedev->reginfo, g_free);
+    g_clear_pointer(&vbasedev->region_fds, g_free);
 
     QLIST_REMOVE(vbasedev, container_next);
     QLIST_REMOVE(vbasedev, global_next);
@@ -476,10 +494,13 @@ static int vfio_device_io_device_feature(VFIODevice *vbasedev,
 }
 
 static int vfio_device_io_get_region_info(VFIODevice *vbasedev,
-                                          struct vfio_region_info *info)
+                                          struct vfio_region_info *info,
+                                          int *fd)
 {
     int ret;
 
+    *fd = -1;
+
     ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
 
     return ret < 0 ? -errno : ret;
diff --git a/hw/vfio/region.c b/hw/vfio/region.c
index 34752c3..cb172f2 100644
--- a/hw/vfio/region.c
+++ b/hw/vfio/region.c
@@ -241,6 +241,7 @@ int vfio_region_mmap(VFIORegion *region)
 {
     int i, ret, prot = 0;
     char *name;
+    int fd;
 
     if (!region->mem) {
         return 0;
@@ -271,14 +272,18 @@ int vfio_region_mmap(VFIORegion *region)
             goto no_mmap;
         }
 
+        /* Use the per-region fd if set, or the shared fd. */
+        fd = region->vbasedev->region_fds ?
+             region->vbasedev->region_fds[region->nr] :
+             region->vbasedev->fd,
+
         map_align = (void *)ROUND_UP((uintptr_t)map_base, (uintptr_t)align);
         munmap(map_base, map_align - map_base);
         munmap(map_align + region->mmaps[i].size,
                align - (map_align - map_base));
 
         region->mmaps[i].mmap = mmap(map_align, region->mmaps[i].size, prot,
-                                     MAP_SHARED | MAP_FIXED,
-                                     region->vbasedev->fd,
+                                     MAP_SHARED | MAP_FIXED, fd,
                                      region->fd_offset +
                                      region->mmaps[i].offset);
         if (region->mmaps[i].mmap == MAP_FAILED) {
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 8bcb3c1..bf54fc6 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -66,6 +66,7 @@ typedef struct VFIODevice {
     OnOffAuto enable_migration;
     OnOffAuto migration_multifd_transfer;
     bool migration_events;
+    bool use_region_fds;
     VFIODeviceOps *ops;
     VFIODeviceIOOps *io_ops;
     unsigned int num_irqs;
@@ -84,6 +85,7 @@ typedef struct VFIODevice {
     VFIOIOASHwpt *hwpt;
     QLIST_ENTRY(VFIODevice) hwpt_next;
     struct vfio_region_info **reginfo;
+    int *region_fds;
 } VFIODevice;
 
 struct VFIODeviceOps {
@@ -170,10 +172,11 @@ struct VFIODeviceIOOps {
     /**
      * @get_region_info
      *
-     * Fill in @info with information on the region given by @info->index.
+     * Fill in @info (and optionally @fd) with information on the region given
+     * by @info->index.
      */
     int (*get_region_info)(VFIODevice *vdev,
-                           struct vfio_region_info *info);
+                           struct vfio_region_info *info, int *fd);
 
     /**
      * @get_irq_info