[Qemu-devel] [PATCH v2] vfio: Handle zero-length sparse mmap ranges

[Alex Williamson]

As reported in the link below, user has a PCI device with a 4KB BAR
which contains the MSI-X table.  This seems to hit a corner case in
the kernel where the region reports being mmap capable, but the sparse
mmap information reports a zero sized range.  It's not entirely clear
that the kernel is incorrect in doing this, but regardless, we need
to handle it.  To do this, fill our mmap array only with non-zero
sized sparse mmap entries and add an error return from the function
so we can tell the difference between nr_mmaps being zero based on
sparse mmap info vs lack of sparse mmap info.

NB, this doesn't actually change the behavior of the device, it only
removes the scary "Failed to mmap ... Performance may be slow" error
message.  We cannot currently create an mmap over the MSI-X table.

Link: http://lists.nongnu.org/archive/html/qemu-discuss/2016-10/msg00009.html
Signed-off-by: Alex Williamson <address@hidden>
---
v2: Fixed my stray tab, re-posting in case the automated testing
    finds more reasons to whine at me ;)

 hw/vfio/common.c |   36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index c764cb3..f528309 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -610,16 +610,16 @@ vfio_get_region_info_cap(struct vfio_region_info *info, 
uint16_t id)
     return NULL;
 }
 
-static void vfio_setup_region_sparse_mmaps(VFIORegion *region,
-                                           struct vfio_region_info *info)
+static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
+                                          struct vfio_region_info *info)
 {
     struct vfio_info_cap_header *hdr;
     struct vfio_region_info_cap_sparse_mmap *sparse;
-    int i;
+    int i, j;
 
     hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
     if (!hdr) {
-        return;
+        return -ENODEV;
     }
 
     sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, 
header);
@@ -627,16 +627,24 @@ static void vfio_setup_region_sparse_mmaps(VFIORegion 
*region,
     trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
                                          region->nr, sparse->nr_areas);
 
-    region->nr_mmaps = sparse->nr_areas;
-    region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
+    region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);
 
-    for (i = 0; i < region->nr_mmaps; i++) {
-        region->mmaps[i].offset = sparse->areas[i].offset;
-        region->mmaps[i].size = sparse->areas[i].size;
-        trace_vfio_region_sparse_mmap_entry(i, region->mmaps[i].offset,
-                                            region->mmaps[i].offset +
-                                            region->mmaps[i].size);
+    for (i = 0, j = 0; i < sparse->nr_areas; i++) {
+        trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
+                                            sparse->areas[i].offset +
+                                            sparse->areas[i].size);
+
+        if (sparse->areas[i].size) {
+            region->mmaps[j].offset = sparse->areas[i].offset;
+            region->mmaps[j].size = sparse->areas[i].size;
+            j++;
+        }
     }
+
+    region->nr_mmaps = j;
+    region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));
+
+    return 0;
 }
 
 int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
@@ -665,9 +673,9 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, 
VFIORegion *region,
             region->flags & VFIO_REGION_INFO_FLAG_MMAP &&
             !(region->size & ~qemu_real_host_page_mask)) {
 
-            vfio_setup_region_sparse_mmaps(region, info);
+            ret = vfio_setup_region_sparse_mmaps(region, info);
 
-            if (!region->nr_mmaps) {
+            if (ret) {
                 region->nr_mmaps = 1;
                 region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
                 region->mmaps[0].offset = 0;