vfio/iommufd: use IOMMU_IOAS_MAP_FILE

Use IOMMU_IOAS_MAP_FILE when the mapped region is backed by a file.
Such a mapping can be preserved without modification during CPR,
because it depends on the file's address space, which does not change,
rather than on the process's address space, which does change.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/qemu-devel/1751493538-202042-9-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index d834bd482290a8b195f94c07832b7f8020504c3a..56304978e1e8ec456e0eb5f13e8bddc091e76208 100644 (file)
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -78,7 +78,16 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
                            void *vaddr, bool readonly, MemoryRegion *mr)
 {
     VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+    RAMBlock *rb = mr->ram_block;
+    int mfd = rb ? qemu_ram_get_fd(rb) : -1;
 
+    if (mfd >= 0 && vioc->dma_map_file) {
+        unsigned long start = vaddr - qemu_ram_get_host_addr(rb);
+        unsigned long offset = qemu_ram_get_fd_offset(rb);
+
+        return vioc->dma_map_file(bcontainer, iova, size, mfd, start + offset,
+                                  readonly);
+    }
     g_assert(vioc->dma_map);
     return vioc->dma_map(bcontainer, iova, size, vaddr, readonly, mr);
 }

diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index d3efef71afd4fd9e68455cefe7666c9f70e8c61e..962a1e2b1f28b297cc876fffa2677bd525479c8c 100644 (file)
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -45,6 +45,18 @@ static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
                                    iova, size, vaddr, readonly);
 }
 
+static int iommufd_cdev_map_file(const VFIOContainerBase *bcontainer,
+                                 hwaddr iova, ram_addr_t size,
+                                 int fd, unsigned long start, bool readonly)
+{
+    const VFIOIOMMUFDContainer *container =
+        container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
+
+    return iommufd_backend_map_file_dma(container->be,
+                                        container->ioas_id,
+                                        iova, size, fd, start, readonly);
+}
+
 static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
                               hwaddr iova, ram_addr_t size,
                               IOMMUTLBEntry *iotlb, bool unmap_all)
@@ -807,6 +819,7 @@ static void vfio_iommu_iommufd_class_init(ObjectClass *klass, const void *data)
     VFIOIOMMUClass *vioc = VFIO_IOMMU_CLASS(klass);
 
     vioc->dma_map = iommufd_cdev_map;
+    vioc->dma_map_file = iommufd_cdev_map_file;
     vioc->dma_unmap = iommufd_cdev_unmap;
     vioc->attach_device = iommufd_cdev_attach;
     vioc->detach_device = iommufd_cdev_detach;

diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 3cd86ec59e1a4605dea92fadeca5816145ae409b..bded6e993ffd34910f5583bf8e94c81c41f4885f 100644 (file)
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -167,6 +167,21 @@ struct VFIOIOMMUClass {
     int (*dma_map)(const VFIOContainerBase *bcontainer,
                    hwaddr iova, ram_addr_t size,
                    void *vaddr, bool readonly, MemoryRegion *mr);
+    /**
+     * @dma_map_file
+     *
+     * Map a file range for the container.
+     *
+     * @bcontainer: #VFIOContainerBase to use for map
+     * @iova: start address to map
+     * @size: size of the range to map
+     * @fd: descriptor of the file to map
+     * @start: starting file offset of the range to map
+     * @readonly: map read only if true
+     */
+    int (*dma_map_file)(const VFIOContainerBase *bcontainer,
+                        hwaddr iova, ram_addr_t size,
+                        int fd, unsigned long start, bool readonly);
     /**
      * @dma_unmap
      *