We use cap_frozen to mark cap/ecap read/writable or read-only,
At init stage, we allow to update cap/ecap based on host IOMMU
cap/ecap, but when machine create done, cap_frozen is set and
we only allow checking cap/ecap for compatibility.

Currently only stage-2 translation is supported which is backed by
shadow page table on host side. So we don't need exact matching of
each bit of cap/ecap between vIOMMU and host. However, we can still
ensure compatibility of host and vIOMMU's address width at least,
i.e., vIOMMU's mgaw <= host IOMMU mgaw, which is missed before.

When stage-1 translation is supported in future, a.k.a. scalable
modern mode, this mechanism will be further extended to check more
bits.

Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
---
 hw/i386/intel_iommu_internal.h |  1 +
 include/hw/i386/intel_iommu.h  |  1 +
 hw/i386/intel_iommu.c          | 29 +++++++++++++++++++++++++++++
 3 files changed, 31 insertions(+)

diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 3301f54b35..33d2298dce 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -206,6 +206,7 @@
 #define VTD_DOMAIN_ID_MASK          ((1UL << VTD_DOMAIN_ID_SHIFT) - 1)
 #define VTD_CAP_ND                  (((VTD_DOMAIN_ID_SHIFT - 4) / 2) & 7ULL)
 #define VTD_ADDRESS_SIZE(aw)        (1ULL << (aw))
+#define VTD_CAP_MGAW_MASK           (0x3fULL << 16)
 #define VTD_CAP_MGAW(aw)            ((((aw) - 1) & 0x3fULL) << 16)
 #define VTD_MAMV                    18ULL
 #define VTD_CAP_MAMV                (VTD_MAMV << 48)
diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index c71a133820..a0b530ebc6 100644
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -47,6 +47,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(IntelIOMMUState, INTEL_IOMMU_DEVICE)
 #define VTD_HOST_AW_48BIT           48
 #define VTD_HOST_ADDRESS_WIDTH      VTD_HOST_AW_39BIT
 #define VTD_HAW_MASK(aw)            ((1ULL << (aw)) - 1)
+#define VTD_MGAW_FROM_CAP(cap)      (((cap >> 16) & 0x3fULL) + 1)
 
 #define DMAR_REPORT_F_INTR          (1)
 
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 7ed2b79669..409f8a59c3 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -35,6 +35,7 @@
 #include "sysemu/kvm.h"
 #include "sysemu/dma.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/iommufd.h"
 #include "hw/i386/apic_internal.h"
 #include "kvm/kvm_i386.h"
 #include "migration/vmstate.h"
@@ -3830,6 +3831,34 @@ static int vtd_check_iommufd_hdev(IntelIOMMUState *s,
                                   IOMMUFDDevice *idev,
                                   Error **errp)
 {
+    struct iommu_hw_info_vtd vtd;
+    enum iommu_hw_info_type type = IOMMU_HW_INFO_TYPE_INTEL_VTD;
+    long host_mgaw, viommu_mgaw = VTD_MGAW_FROM_CAP(s->cap);
+    uint64_t tmp_cap = s->cap;
+    int ret;
+
+    ret = iommufd_device_get_info(idev, &type, sizeof(vtd), &vtd, errp);
+    if (ret) {
+        return ret;
+    }
+
+    if (type != IOMMU_HW_INFO_TYPE_INTEL_VTD) {
+        error_setg(errp, "IOMMU hardware is not compatible");
+        return -EINVAL;
+    }
+
+    host_mgaw = VTD_MGAW_FROM_CAP(vtd.cap_reg);
+    if (viommu_mgaw > host_mgaw) {
+        if (s->cap_frozen) {
+            error_setg(errp, "mgaw %" PRId64 " > host mgaw %" PRId64,
+                       viommu_mgaw, host_mgaw);
+            return -EINVAL;
+        }
+        tmp_cap &= ~VTD_CAP_MGAW_MASK;
+        tmp_cap |= VTD_CAP_MGAW(host_mgaw + 1);
+    }
+
+    s->cap = tmp_cap;
     return 0;
 }
 
-- 
2.34.1