Re: [PATCH 2/2] intel_iommu: Simplify caching mode check with VFIO device

["Cédric Le Goater" <clg@redhat.com>]

On 9/19/25 09:06, Zhenzhong Duan wrote:
> In early days, we have different tricks to ensure caching-mode=on with VFIO
> device:
> 
> 28cf553afe ("intel_iommu: Sanity check vfio-pci config on machine init done")
> c6cbc29d36 ("pc/q35: Disallow vfio-pci hotplug without VT-d caching mode")
> b8d78277c0 ("intel-iommu: fail MAP notifier without caching mode")
> 
> Because without caching mode, MAP notifier won't work correctly since guest
> won't send IOTLB update event when it establishes new mappings in the I/O page
> tables.
> 
> Now with host IOMMU device interface between VFIO and vIOMMU, we can simplify
> it with a small check in set_iommu_device(). This also works for future VDPA
> implementation which may also need caching mode on.
> 
> For coldplug VFIO device:
> 
> qemu-system-x86_64: -device vfio-pci,host=0000:3b:00.0,id=hostdev3,bus=root0,iommufd=iommufd0: vfio 0000:3b:00.0: Failed to set vIOMMU: Device assignment is not allowed without enabling caching-mode=on for Intel IOMMU.
> 
> For hotplug VFIO device:
> 
> Error: vfio 0000:3b:00.0: Failed to set vIOMMU: Device assignment is not allowed without enabling caching-mode=on for Intel IOMMU.
> 
> Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
> ---
>   hw/i386/intel_iommu.c | 47 ++++++-------------------------------------
>   hw/i386/pc.c          | 20 ------------------
>   2 files changed, 6 insertions(+), 61 deletions(-)

This is a nice cleanup.

Acked-by: Cédric Le Goater <clg@redhat.com>

Thanks,

C.



> 
> diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
> index f04300022e..5c67b42dde 100644
> --- a/hw/i386/intel_iommu.c
> +++ b/hw/i386/intel_iommu.c
> @@ -85,13 +85,6 @@ struct vtd_iotlb_key {
>   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)
>   {
> @@ -3731,13 +3724,6 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
>                            "Snoop Control with vhost or VFIO is not supported");
>           return -ENOTSUP;
>       }
> -    if (!s->caching_mode && (new & IOMMU_NOTIFIER_MAP)) {
> -        error_setg_errno(errp, ENOTSUP,
> -                         "device %02x.%02x.%x requires caching mode",
> -                         pci_bus_num(vtd_as->bus), PCI_SLOT(vtd_as->devfn),
> -                         PCI_FUNC(vtd_as->devfn));
> -        return -ENOTSUP;
> -    }
>       if (!x86_iommu->dt_supported && (new & IOMMU_NOTIFIER_DEVIOTLB_UNMAP)) {
>           error_setg_errno(errp, ENOTSUP,
>                            "device %02x.%02x.%x requires device IOTLB mode",
> @@ -4378,6 +4364,12 @@ static bool vtd_dev_set_iommu_device(PCIBus *bus, void *opaque, int devfn,
>   
>       assert(hiod);
>   
> +    if (!s->caching_mode) {
> +        error_setg(errp, "Device assignment is not allowed without enabling "
> +                   "caching-mode=on for Intel IOMMU.");
> +        return false;
> +    }
> +
>       vtd_iommu_lock(s);
>   
>       if (g_hash_table_lookup(s->vtd_host_iommu_dev, &key)) {
> @@ -4910,32 +4902,6 @@ 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());
> @@ -4990,7 +4956,6 @@ static void vtd_realize(DeviceState *dev, Error **errp)
>       pci_setup_iommu(bus, &vtd_iommu_ops, dev);
>       /* Pseudo address space under root PCI bus. */
>       x86ms->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, const void *data)
> diff --git a/hw/i386/pc.c b/hw/i386/pc.c
> index bc048a6d13..01cd9a67db 100644
> --- a/hw/i386/pc.c
> +++ b/hw/i386/pc.c
> @@ -1720,25 +1720,6 @@ static void pc_machine_wakeup(MachineState *machine)
>       cpu_synchronize_all_post_reset();
>   }
>   
> -static bool pc_hotplug_allowed(MachineState *ms, DeviceState *dev, Error **errp)
> -{
> -    X86IOMMUState *iommu = x86_iommu_get_default();
> -    IntelIOMMUState *intel_iommu;
> -
> -    if (iommu &&
> -        object_dynamic_cast((Object *)iommu, TYPE_INTEL_IOMMU_DEVICE) &&
> -        object_dynamic_cast((Object *)dev, "vfio-pci")) {
> -        intel_iommu = INTEL_IOMMU_DEVICE(iommu);
> -        if (!intel_iommu->caching_mode) {
> -            error_setg(errp, "Device assignment is not allowed without "
> -                       "enabling caching-mode=on for Intel IOMMU.");
> -            return false;
> -        }
> -    }
> -
> -    return true;
> -}
> -
>   static void pc_machine_class_init(ObjectClass *oc, const void *data)
>   {
>       MachineClass *mc = MACHINE_CLASS(oc);
> @@ -1758,7 +1739,6 @@ static void pc_machine_class_init(ObjectClass *oc, const void *data)
>       x86mc->apic_xrupt_override = true;
>       assert(!mc->get_hotplug_handler);
>       mc->get_hotplug_handler = pc_get_hotplug_handler;
> -    mc->hotplug_allowed = pc_hotplug_allowed;
>       mc->auto_enable_numa_with_memhp = true;
>       mc->auto_enable_numa_with_memdev = true;
>       mc->has_hotpluggable_cpus = true;