vfio/pci: Add support for opregion v2.1+

Before opregion version 2.0 VBT data is stored in opregion mailbox #4,
but when VBT data exceeds 6KB size and cannot be within mailbox #4
then from opregion v2.0+, Extended VBT region, next to opregion is
used to hold the VBT data, so the total size will be opregion size plus
extended VBT region size.

Since opregion v2.0 with physical host VBT address would not be
practically available for end user and guest can not directly access
host physical address, so it is not supported.

Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Swee Yee Fonn <swee.yee.fonn@intel.com>
Signed-off-by: Fred Gao <fred.gao@intel.com>
Message-Id: <20210325170953.24549-1-fred.gao@intel.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c
index e66dfb0178ed9770c2ef21d3f0d6dc4009164040..228df565e9bc40d0e0ed0608dd14012cb09bce84 100644 (file)
--- a/drivers/vfio/pci/vfio_pci_igd.c
+++ b/drivers/vfio/pci/vfio_pci_igd.c
@@ -21,6 +21,10 @@
 #define OPREGION_SIZE          (8 * 1024)
 #define OPREGION_PCI_ADDR      0xfc
 
+#define OPREGION_RVDA          0x3ba
+#define OPREGION_RVDS          0x3c2
+#define OPREGION_VERSION       0x16
+
 static size_t vfio_pci_igd_rw(struct vfio_pci_device *vdev, char __user *buf,
                              size_t count, loff_t *ppos, bool iswrite)
 {
@@ -58,6 +62,7 @@ static int vfio_pci_igd_opregion_init(struct vfio_pci_device *vdev)
        u32 addr, size;
        void *base;
        int ret;
+       u16 version;
 
        ret = pci_read_config_dword(vdev->pdev, OPREGION_PCI_ADDR, &addr);
        if (ret)
@@ -83,6 +88,54 @@ static int vfio_pci_igd_opregion_init(struct vfio_pci_device *vdev)
 
        size *= 1024; /* In KB */
 
+       /*
+        * Support opregion v2.1+
+        * When VBT data exceeds 6KB size and cannot be within mailbox #4, then
+        * the Extended VBT region next to opregion is used to hold the VBT data.
+        * RVDA (Relative Address of VBT Data from Opregion Base) and RVDS
+        * (Raw VBT Data Size) from opregion structure member are used to hold the
+        * address from region base and size of VBT data. RVDA/RVDS are not
+        * defined before opregion 2.0.
+        *
+        * opregion 2.1+: RVDA is unsigned, relative offset from
+        * opregion base, and should point to the end of opregion.
+        * otherwise, exposing to userspace to allow read access to everything between
+        * the OpRegion and VBT is not safe.
+        * RVDS is defined as size in bytes.
+        *
+        * opregion 2.0: rvda is the physical VBT address.
+        * Since rvda is HPA it cannot be directly used in guest.
+        * And it should not be practically available for end user,so it is not supported.
+        */
+       version = le16_to_cpu(*(__le16 *)(base + OPREGION_VERSION));
+       if (version >= 0x0200) {
+               u64 rvda;
+               u32 rvds;
+
+               rvda = le64_to_cpu(*(__le64 *)(base + OPREGION_RVDA));
+               rvds = le32_to_cpu(*(__le32 *)(base + OPREGION_RVDS));
+               if (rvda && rvds) {
+                       /* no support for opregion v2.0 with physical VBT address */
+                       if (version == 0x0200) {
+                               memunmap(base);
+                               pci_err(vdev->pdev,
+                                       "IGD assignment does not support opregion v2.0 with an extended VBT region\n");
+                               return -EINVAL;
+                       }
+
+                       if (rvda != size) {
+                               memunmap(base);
+                               pci_err(vdev->pdev,
+                                       "Extended VBT does not follow opregion on version 0x%04x\n",
+                                       version);
+                               return -EINVAL;
+                       }
+
+                       /* region size for opregion v2.0+: opregion and VBT size. */
+                       size += rvds;
+               }
+       }
+
        if (size != OPREGION_SIZE) {
                memunmap(base);
                base = memremap(addr, size, MEMREMAP_WB);