[Qemu-devel] [PULL 05/10] intel_iommu: Sanity check vfio-pci config on machine init done

["Michael S. Tsirkin" <mst@redhat.com>]

From: Peter Xu <peterx@redhat.com>

This check was previously only happened when the IOMMU is enabled in
the guest.  It was always too late because the enabling of IOMMU
normally only happens during the boot of guest OS.  It means that we
can bail out and exit directly during the guest OS boots if the
configuration of devices are not supported.  Or, if the guest didn't
enable vIOMMU at all, then the user can use the guest normally but as
long as it reconfigure the guest OS to enable the vIOMMU then reboot,
the user will see the panic right after the reset when the next boot
starts.

Let's make this failure even earlier so that we force the user to use
caching-mode for vfio-pci devices when with the vIOMMU.  So the user
won't get surprise at least during execution of the guest, which seems
a bit nicer.

This will affect some user who didn't enable vIOMMU in the guest OS
but was using vfio-pci and the vtd device in the past.  However I hope
it's not a majority because not enabling vIOMMU with the device
attached is actually meaningless.

We still keep the old assertion for safety so far because the hotplug
path could still reach it, so far.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20190916080718.3299-2-peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 hw/i386/intel_iommu.c | 39 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 75ca6f9c70..bed8ffe446 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -35,6 +35,7 @@
 #include "hw/i386/x86-iommu.h"
 #include "hw/pci-host/q35.h"
 #include "sysemu/kvm.h"
+#include "sysemu/sysemu.h"
 #include "hw/i386/apic_internal.h"
 #include "kvm_i386.h"
 #include "migration/vmstate.h"
@@ -64,6 +65,13 @@
 static void vtd_address_space_refresh_all(IntelIOMMUState *s);
 static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n);
 
+static void vtd_panic_require_caching_mode(void)
+{
+    error_report("We need to set caching-mode=on for intel-iommu to enable "
+                 "device assignment with IOMMU protection.");
+    exit(1);
+}
+
 static void vtd_define_quad(IntelIOMMUState *s, hwaddr addr, uint64_t val,
                             uint64_t wmask, uint64_t w1cmask)
 {
@@ -2929,9 +2937,7 @@ static void vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
     IntelIOMMUState *s = vtd_as->iommu_state;
 
     if (!s->caching_mode && new & IOMMU_NOTIFIER_MAP) {
-        error_report("We need to set caching-mode=on for intel-iommu to enable "
-                     "device assignment with IOMMU protection.");
-        exit(1);
+        vtd_panic_require_caching_mode();
     }
 
     /* Update per-address-space notifier flags */
@@ -3699,6 +3705,32 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp)
     return true;
 }
 
+static int vtd_machine_done_notify_one(Object *child, void *unused)
+{
+    IntelIOMMUState *iommu = INTEL_IOMMU_DEVICE(x86_iommu_get_default());
+
+    /*
+     * We hard-coded here because vfio-pci is the only special case
+     * here.  Let's be more elegant in the future when we can, but so
+     * far there seems to be no better way.
+     */
+    if (object_dynamic_cast(child, "vfio-pci") && !iommu->caching_mode) {
+        vtd_panic_require_caching_mode();
+    }
+
+    return 0;
+}
+
+static void vtd_machine_done_hook(Notifier *notifier, void *unused)
+{
+    object_child_foreach_recursive(object_get_root(),
+                                   vtd_machine_done_notify_one, NULL);
+}
+
+static Notifier vtd_machine_done_notify = {
+    .notify = vtd_machine_done_hook,
+};
+
 static void vtd_realize(DeviceState *dev, Error **errp)
 {
     MachineState *ms = MACHINE(qdev_get_machine());
@@ -3744,6 +3776,7 @@ static void vtd_realize(DeviceState *dev, Error **errp)
     pci_setup_iommu(bus, vtd_host_dma_iommu, dev);
     /* Pseudo address space under root PCI bus. */
     pcms->ioapic_as = vtd_host_dma_iommu(bus, s, Q35_PSEUDO_DEVFN_IOAPIC);
+    qemu_add_machine_init_done_notifier(&vtd_machine_done_notify);
 }
 
 static void vtd_class_init(ObjectClass *klass, void *data)
-- 
MST