KVM: xen: allow vcpu_info to be mapped by fixed HVA

If the guest does not explicitly set the GPA of vcpu_info structure in
memory then, for guests with 32 vCPUs or fewer, the vcpu_info embedded
in the shared_info page may be used. As described in a previous commit,
the shared_info page is an overlay at a fixed HVA within the VMM, so in
this case it also more optimal to activate the vcpu_info cache with a
fixed HVA to avoid unnecessary invalidation if the guest memory layout
is modified.

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
---
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
v8:
 - Re-base.

v5:
 - New in this version.

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 25ac75b6d8c5b3070c6319290c49fc1e7bf13329..2c9d6bbba051cb1683205f029a5bb146bda65351 100644 (file)
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5516,11 +5516,12 @@ KVM_XEN_ATTR_TYPE_SHARED_INFO
   Sets the guest physical frame number at which the Xen shared_info
   page resides. Note that although Xen places vcpu_info for the first
   32 vCPUs in the shared_info page, KVM does not automatically do so
-  and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used
-  explicitly even when the vcpu_info for a given vCPU resides at the
-  "default" location in the shared_info page. This is because KVM may
-  not be aware of the Xen CPU id which is used as the index into the
-  vcpu_info[] array, so may know the correct default location.
+  and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO or
+  KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA be used explicitly even when
+  the vcpu_info for a given vCPU resides at the "default" location
+  in the shared_info page. This is because KVM may not be aware of
+  the Xen CPU id which is used as the index into the vcpu_info[]
+  array, so may know the correct default location.
 
   Note that the shared_info page may be constantly written to by KVM;
   it contains the event channel bitmap used to deliver interrupts to
@@ -5642,6 +5643,21 @@ KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO
   on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable
   the vcpu_info.
 
+KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA
+  If the KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA flag is also set in the
+  Xen capabilities, then this attribute may be used to set the
+  userspace address of the vcpu_info for a given vCPU. It should
+  only be used when the vcpu_info resides at the "default" location
+  in the shared_info page. In this case it is safe to assume the
+  userspace address will not change, because the shared_info page is
+  an overlay on guest memory and remains at a fixed host address
+  regardless of where it is mapped in guest physical address space
+  and hence unnecessary invalidation of an internal cache may be
+  avoided if the guest memory layout is modified.
+  If the vcpu_info does not reside at the "default" location then
+  it is not guaranteed to remain at the same host address and
+  hence the aforementioned cache invalidation is required.
+
 KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO
   Sets the guest physical address of an additional pvclock structure
   for a given vCPU. This is typically used for guest vsyscall support.

diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 62d8ea73a744e314876004f0a0877a68e926d0e2..7b662fd9bd01d4504bd5646dc9ff8003e19e53d5 100644 (file)
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -775,20 +775,33 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 
        switch (data->type) {
        case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
+       case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA:
                /* No compat necessary here. */
                BUILD_BUG_ON(sizeof(struct vcpu_info) !=
                             sizeof(struct compat_vcpu_info));
                BUILD_BUG_ON(offsetof(struct vcpu_info, time) !=
                             offsetof(struct compat_vcpu_info, time));
 
-               if (data->u.gpa == KVM_XEN_INVALID_GPA) {
-                       kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
-                       r = 0;
-                       break;
+               if (data->type == KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO) {
+                       if (data->u.gpa == KVM_XEN_INVALID_GPA) {
+                               kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
+                               r = 0;
+                               break;
+                       }
+
+                       r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_info_cache,
+                                            data->u.gpa, sizeof(struct vcpu_info));
+               } else {
+                       if (data->u.hva == 0) {
+                               kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
+                               r = 0;
+                               break;
+                       }
+
+                       r = kvm_gpc_activate_hva(&vcpu->arch.xen.vcpu_info_cache,
+                                                data->u.hva, sizeof(struct vcpu_info));
                }
 
-               r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_info_cache,
-                                    data->u.gpa, sizeof(struct vcpu_info));
                if (!r)
                        kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 
@@ -1017,6 +1030,15 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
                r = 0;
                break;
 
+       case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA:
+               if (vcpu->arch.xen.vcpu_info_cache.active &&
+                   vcpu->arch.xen.vcpu_info_cache.gpa == KVM_XEN_INVALID_GPA)
+                       data->u.hva = vcpu->arch.xen.vcpu_info_cache.uhva;
+               else
+                       data->u.hva = 0;
+               r = 0;
+               break;
+
        case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
                if (vcpu->arch.xen.vcpu_time_info_cache.active)
                        data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa;

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 769361b91f95083d2ea20592e9fd4afdd47f80eb..bb9d40b5e613243dcbf16a7e6e1a43c1a6691137 100644 (file)
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1869,6 +1869,7 @@ struct kvm_xen_vcpu_attr {
        union {
                __u64 gpa;
 #define KVM_XEN_INVALID_GPA ((__u64)-1)
+               __u64 hva;
                __u64 pad[8];
                struct {
                        __u64 state;
@@ -1899,6 +1900,8 @@ struct kvm_xen_vcpu_attr {
 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID         0x6
 #define KVM_XEN_VCPU_ATTR_TYPE_TIMER           0x7
 #define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR   0x8
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA   0x9
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {