[PATCH v5 2/4] vfio: add 'fd' and 'fd_offset' to VFIOMmap

[Naman Gulati <namangulati@google.com>]

Allow each sparse mmap subregion to specify its own file descriptor and
file offset for the mmap call.

Add 'fd' (set to -1 when the region fd should be used) and 'fd_offset'
to VFIOMmap, and update vfio_region_mmap() to use them.

Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
Signed-off-by: Naman Gulati <namangulati@google.com>
---
 hw/vfio/vfio-region.h |  4 +++-
 hw/vfio/pci.c         |  2 ++
 hw/vfio/region.c      | 26 +++++++++++++++++++-------
 3 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/hw/vfio/vfio-region.h b/hw/vfio/vfio-region.h
index 58b236f113..9f6a5cf7d5 100644
--- a/hw/vfio/vfio-region.h
+++ b/hw/vfio/vfio-region.h
@@ -14,8 +14,10 @@
 typedef struct VFIOMmap {
     MemoryRegion mem;
     void *mmap;
-    off_t offset;
+    off_t offset;       /* offset within the region */
     size_t size;
+    int fd;             /* per-mmap fd, or -1 to use the region fd */
+    uint64_t fd_offset; /* offset within fd for the mmap call */
 } VFIOMmap;
 
 typedef struct VFIODevice VFIODevice;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 428ab2f069..f851082114 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1623,6 +1623,7 @@ static void vfio_pci_fixup_msix_region(VFIOPCIDevice *vdev)
                                   vdev->msix->table_bar, 0, 0);
         } else {
             region->mmaps[0].offset = end;
+            region->mmaps[0].fd_offset += end;
             region->mmaps[0].size = region->size - end;
             trace_vfio_msix_fixup(vdev->vbasedev.name,
                               vdev->msix->table_bar, region->mmaps[0].offset,
@@ -1649,6 +1650,7 @@ static void vfio_pci_fixup_msix_region(VFIOPCIDevice *vdev)
                               region->mmaps[0].offset + region->mmaps[0].size);
 
         region->mmaps[1].offset = end;
+        region->mmaps[1].fd_offset += end;
         region->mmaps[1].size = region->size - end;
         trace_vfio_msix_fixup(vdev->vbasedev.name,
                               vdev->msix->table_bar, region->mmaps[1].offset,
diff --git a/hw/vfio/region.c b/hw/vfio/region.c
index 54ad11a6c8..16efed2fce 100644
--- a/hw/vfio/region.c
+++ b/hw/vfio/region.c
@@ -189,6 +189,9 @@ static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
                                             sparse->areas[i].size - 1);
             region->mmaps[j].offset = sparse->areas[i].offset;
             region->mmaps[j].size = sparse->areas[i].size;
+            region->mmaps[j].fd = -1;
+            region->mmaps[j].fd_offset = region->fd_offset +
+                                         sparse->areas[i].offset;
             j++;
         }
     }
@@ -262,6 +265,8 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
                 region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
                 region->mmaps[0].offset = 0;
                 region->mmaps[0].size = region->size;
+                region->mmaps[0].fd = -1;
+                region->mmaps[0].fd_offset = region->fd_offset;
             } else if (ret) {
                 return ret;
             }
@@ -354,7 +359,6 @@ int vfio_region_mmap(VFIORegion *region)
     off_t map_offset = 0;
     size_t align;
     char *name;
-    int fd;
 
     if (!region->mem || !region->nr_mmaps) {
         return 0;
@@ -391,8 +395,6 @@ int vfio_region_mmap(VFIORegion *region)
         return ret;
     }
 
-    fd = vfio_device_get_region_fd(region->vbasedev, region->nr);
-
     map_align = (void *)ROUND_UP((uintptr_t)map_base, (uintptr_t)align);
     munmap(map_base, map_align - map_base);
     munmap(map_align + region->size,
@@ -404,12 +406,22 @@ int vfio_region_mmap(VFIORegion *region)
      * offsets being in ascending order.
      */
     for (i = 0; i < region->nr_mmaps; i++) {
+        int fd = region->mmaps[i].fd;
+
+        if (fd < 0) {
+            fd = vfio_device_get_region_fd(region->vbasedev, region->nr);
+        }
+        if (fd < 0) {
+            ret = -EINVAL;
+            munmap(map_align + map_offset, region->size - map_offset);
+            goto no_mmap;
+        }
+
         munmap(map_align + map_offset, region->mmaps[i].offset - map_offset);
         region->mmaps[i].mmap = mmap(map_align + region->mmaps[i].offset,
                                      region->mmaps[i].size, prot,
                                      MAP_SHARED | MAP_FIXED, fd,
-                                     region->fd_offset +
-                                     region->mmaps[i].offset);
+                                     region->mmaps[i].fd_offset);
         if (region->mmaps[i].mmap == MAP_FAILED) {
             ret = -errno;
             /*
@@ -454,8 +466,8 @@ int vfio_region_mmap(VFIORegion *region)
 
 no_mmap:
     trace_vfio_region_mmap_fault(memory_region_name(region->mem), i,
-                                 region->fd_offset + region->mmaps[i].offset,
-                                 region->fd_offset + region->mmaps[i].offset +
+                                 region->mmaps[i].fd_offset,
+                                 region->mmaps[i].fd_offset +
                                  region->mmaps[i].size - 1, ret);
 
     region->mmaps[i].mmap = NULL;
-- 
2.56.0.385.gd3acb90ef8-goog