vfio-pci: Allow mmap of MSIX BAR

At the moment we unconditionally avoid mapping MSIX data of a BAR and
emulate MSIX table in QEMU. However it is 1) not always necessary as
a platform may provide a paravirt interface for MSIX configuration;
2) can affect the speed of MMIO access by emulating them in QEMU when
frequently accessed registers share same system page with MSIX data,
this is particularly a problem for systems with the page size bigger
than 4KB.

A new capability - VFIO_REGION_INFO_CAP_MSIX_MAPPABLE - has been added
to the kernel [1] which tells the userspace that mapping of the MSIX data
is possible now. This makes use of it so from now on QEMU tries mapping
the entire BAR as a whole and emulate MSIX on top of that.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=a32295c612c57990d17fb0f41e7134394b2f35f6

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 07c03d78b666f06b7d09a74df849bb64b4cd3a00..5e8471621800011b7c3fecb5081f6beddb8a3135 100644 (file)
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1471,6 +1471,21 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
     return -ENODEV;
 }
 
+bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
+{
+    struct vfio_region_info *info = NULL;
+    bool ret = false;
+
+    if (!vfio_get_region_info(vbasedev, region, &info)) {
+        if (vfio_get_region_info_cap(info, cap_type)) {
+            ret = true;
+        }
+        g_free(info);
+    }
+
+    return ret;
+}
+
 /*
  * Interfaces for IBM EEH (Enhanced Error Handling)
  */

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index b9d2c12b8273fbd70f89093abaed6be128c49498..02974f4eb976a6c838826f0dbc104b148dcf0895 100644 (file)
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1294,6 +1294,15 @@ static void vfio_pci_fixup_msix_region(VFIOPCIDevice *vdev)
     off_t start, end;
     VFIORegion *region = &vdev->bars[vdev->msix->table_bar].region;
 
+    /*
+     * If the host driver allows mapping of a MSIX data, we are going to
+     * do map the entire BAR and emulate MSIX table on top of that.
+     */
+    if (vfio_has_region_cap(&vdev->vbasedev, region->nr,
+                            VFIO_REGION_INFO_CAP_MSIX_MAPPABLE)) {
+        return;
+    }
+
     /*
      * We expect to find a single mmap covering the whole BAR, anything else
      * means it's either unsupported or already setup.

diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index c5efa32750e72c5bea5922f9b9b3c332af75a848..d9360148e6a70bd5e11ca45bef6ff7a506edf684 100644 (file)
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -193,6 +193,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
                          struct vfio_region_info **info);
 int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
                              uint32_t subtype, struct vfio_region_info **info);
+bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type);
 #endif
 extern const MemoryListener vfio_prereg_listener;