[RFC,00/13] Introducing AMD x2APIC Virtualization (x2AVIC) support.

Message

Suthikulpanit, Suravee Feb. 21, 2022, 2:19 a.m. UTC

Previously, with AVIC, guest needs to disable x2APIC capability and
can only run in APIC mode to activate hardware-accelerated interrupt
virtualization.  With x2AVIC, guest can run in x2APIC mode.
This feature is indicated by the CPUID Fn8000_000A EDX[14],
and it can be activated by setting bit 31 (enable AVIC) and
bit 30 (x2APIC mode) of VMCB offset 60h.

The mode of interrupt virtualization can dynamically change during runtime.
For example, when AVIC is enabled, the hypervisor currently keeps track of
the AVIC activation and set the VMCB bit 31 accordingly. With x2AVIC,
the guest OS can also switch between APIC and x2APIC modes during runtime.
The kvm_amd driver needs to also keep track and set the VMCB
bit 30 accordingly. 

Besides, for x2AVIC, kvm_amd driver needs to disable interception for the
x2APIC MSR range to allow AVIC hardware to virtualize register accesses.

Testing:
  * This series has been tested booting a Linux VM with x2APIC physical
    and logical modes upto 511 vCPUs.

Regards,
Suravee


Suravee Suthikulpanit (13):
  KVM: SVM: Add warning when encounter invalid APIC ID
  x86/cpufeatures: Introduce x2AVIC CPUID bit
  KVM: SVM: Detect X2APIC virtualization (x2AVIC) support
  KVM: SVM: Only call vcpu_(un)blocking when AVIC is enabled.
  KVM: SVM: Update max number of vCPUs supported for x2AVIC mode
  KVM: SVM: Add logic to determine x2APIC mode
  KVM: SVM: Update avic_kick_target_vcpus to support 32-bit APIC ID
  KVM: SVM: Do not update logical APIC ID table when in x2APIC mode
  KVM: SVM: Introduce helper function avic_get_apic_id
  KVM: SVM: Adding support for configuring x2APIC MSRs interception
  KVM: SVM: Add logic to switch between APIC and x2APIC virtualization
    mode
  KVM: SVM: Remove APICv inhibit reasone due to x2APIC
  KVM: SVM: Use fastpath x2apic IPI emulation when #vmexit with x2AVIC

 arch/x86/include/asm/cpufeatures.h |   1 +
 arch/x86/include/asm/svm.h         |  15 +-
 arch/x86/kvm/svm/avic.c            | 216 ++++++++++++++++++++++++++---
 arch/x86/kvm/svm/svm.c             | 102 ++++++++------
 arch/x86/kvm/svm/svm.h             |  13 +-
 arch/x86/kvm/x86.c                 |   3 +-
 arch/x86/kvm/x86.h                 |   1 +
 7 files changed, 281 insertions(+), 70 deletions(-)

Comments

Suthikulpanit, Suravee Feb. 22, 2022, 5:37 a.m. UTC | #1

On 2/21/2022 9:19 AM, Suravee Suthikulpanit wrote:
> Testing:
>    * This series has been tested booting a Linux VM with x2APIC physical
>      and logical modes upto 511 vCPUs.

Update:
   * This series has been tested booting a Linux VM with x2APIC physical
     and logical modes upto 512 vCPUs with the following change in QEMU:

diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 797e09500b..282036df98 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -352,7 +352,7 @@ static void pc_q35_machine_options(MachineClass *m)
      machine_class_allow_dynamic_sysbus_dev(m, TYPE_INTEL_IOMMU_DEVICE);
      machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE);
      machine_class_allow_dynamic_sysbus_dev(m, TYPE_VMBUS_BRIDGE);
-    m->max_cpus = 288;
+    m->max_cpus = 512;
  }

Regards,
Suravee