Re: [Qemu-devel] [PATCH v3 6/8] intel_iommu: reject broken EIM

[Igor Mammedov <imammedo@redhat.com>]

On Fri, 30 Sep 2016 18:10:11 +0200
Radim Krčmář <rkrcmar@redhat.com> wrote:

> Cluster x2APIC cannot work without KVM's x2apic API when the maximal
> APIC ID is greater than 8 and only KVM's LAPIC can support x2APIC, so we
> forbid other APICs and also the old KVM case with less than 9, to
> simplify the code.
> 
> There is no point in enabling EIM in forbidden APICs, so we keep it
> enabled only for the KVM APIC;  unconditionally, because making the
> option depend on KVM version would be a maintanance burden.
Probably it would be good to mention here that x2APIC API is enabled
if KVM's apic is used and kernel supports x2APIC API + DISABLE_BROADCAST_QUIRK,
and doing that enabling fixes error:

   KVM: injection failed, MSI lost (Operation not permitted)

when guest is started with: kernel-irqchip=split + intremap=on,[eim=on]

> 
> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
> ---
> v3:
>  * use error_setg [Paolo]
>  * shorten the code [Peter]
> v2:
>  * adapt to new intr_eim parameter
>  * provide first linux version that has x2apic api
>  * disable QEMU's LAPIC
> ---
>  hw/i386/intel_iommu.c  | 15 ++++++++++++++-
>  target-i386/kvm-stub.c |  5 +++++
>  target-i386/kvm.c      | 13 +++++++++++++
>  target-i386/kvm_i386.h |  1 +
>  4 files changed, 33 insertions(+), 1 deletion(-)
> 
> diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
> index 17892b8c336b..efb018b85544 100644
> --- a/hw/i386/intel_iommu.c
> +++ b/hw/i386/intel_iommu.c
> @@ -33,6 +33,7 @@
>  #include "hw/pci-host/q35.h"
>  #include "sysemu/kvm.h"
>  #include "hw/i386/apic_internal.h"
> +#include "kvm_i386.h"
>  
>  /*#define DEBUG_INTEL_IOMMU*/
>  #ifdef DEBUG_INTEL_IOMMU
> @@ -2472,10 +2473,22 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp)
>      }
>  
>      if (s->intr_eim == ON_OFF_AUTO_AUTO) {
> -        s->intr_eim = x86_iommu->intr_supported ?
> +        s->intr_eim = x86_iommu->intr_supported && kvm_irqchip_in_kernel() ?
>                                                ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
>      }
>  
> +    if (s->intr_eim == ON_OFF_AUTO_ON) {
> +        if (kvm_irqchip_in_kernel() && !kvm_enable_x2apic()) {
> +            error_setg(errp, "eim=on requires support on the KVM side"
> +                             "(X2APIC_API, first shipped in v4.7)");
> +            return false;
> +        }
> +        if (!kvm_irqchip_in_kernel()) {
> +            error_setg(errp, "eim=on requires accel=kvm,kernel-irqchip=split");
> +            return false;
> +        }
> +    }
> +
>      return true;
>  }
>  
> diff --git a/target-i386/kvm-stub.c b/target-i386/kvm-stub.c
> index cdf15061091d..bda4dc2f0c57 100644
> --- a/target-i386/kvm-stub.c
> +++ b/target-i386/kvm-stub.c
> @@ -25,6 +25,11 @@ bool kvm_has_smm(void)
>      return 1;
>  }
>  
> +bool kvm_enable_x2apic(void)
> +{
> +    return false;
> +}
> +
>  /* This function is only called inside conditionals which we
>   * rely on the compiler to optimize out when CONFIG_KVM is not
>   * defined.
> diff --git a/target-i386/kvm.c b/target-i386/kvm.c
> index ee1f53e56953..0fd664648665 100644
> --- a/target-i386/kvm.c
> +++ b/target-i386/kvm.c
> @@ -122,6 +122,19 @@ bool kvm_allows_irq0_override(void)
>      return !kvm_irqchip_in_kernel() || kvm_has_gsi_routing();
>  }
>  
> +static bool kvm_x2apic_api_set_flags(uint64_t flags)
> +{
> +    KVMState *s = KVM_STATE(current_machine->accelerator);
> +
> +    return !kvm_vm_enable_cap(s, KVM_CAP_X2APIC_API, 0, flags);
> +}
> +
> +bool kvm_enable_x2apic(void)
> +{
> +    return kvm_x2apic_api_set_flags(KVM_X2APIC_API_USE_32BIT_IDS |
> +                                    KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK);
> +}
> +
>  static int kvm_get_tsc(CPUState *cs)
>  {
>      X86CPU *cpu = X86_CPU(cs);
> diff --git a/target-i386/kvm_i386.h b/target-i386/kvm_i386.h
> index 36407e0a5dc7..5c369b1c5b40 100644
> --- a/target-i386/kvm_i386.h
> +++ b/target-i386/kvm_i386.h
> @@ -43,4 +43,5 @@ int kvm_device_msix_deassign(KVMState *s, uint32_t dev_id);
>  
>  void kvm_put_apicbase(X86CPU *cpu, uint64_t value);
>  
> +bool kvm_enable_x2apic(void);
>  #endif