In this patch we add a list of L0 (hardware) VMCSs, which we'll use to hold a
hardware VMCS for each active vmcs12 (i.e., for each L2 guest).
We call each of these L0 VMCSs a "vmcs02", as it is the VMCS that L0 uses
to run its nested guest L2.
Signed-off-by: Nadav Har'El
---
arch/x86/kvm/vmx.c | 96 +++
1 file changed, 96 insertions(+)
--- .before/arch/x86/kvm/vmx.c 2010-12-08 18:56:49.0 +0200
+++ .after/arch/x86/kvm/vmx.c 2010-12-08 18:56:49.0 +0200
@@ -155,6 +155,12 @@ struct __packed vmcs12 {
*/
#define VMCS12_REVISION 0x11e57ed0
+struct vmcs_list {
+ struct list_head list;
+ gpa_t vmcs12_addr;
+ struct vmcs *vmcs02;
+};
+
/*
* The nested_vmx structure is part of vcpu_vmx, and holds information we need
* for correct emulation of VMX (i.e., nested VMX) on this vcpu. For example,
@@ -170,6 +176,10 @@ struct nested_vmx {
/* The host-usable pointer to the above */
struct page *current_vmcs12_page;
struct vmcs12 *current_vmcs12;
+
+ /* list of real (hardware) VMCS, one for each L2 guest of L1 */
+ struct list_head vmcs02_list; /* a vmcs_list */
+ int vmcs02_num;
};
struct vcpu_vmx {
@@ -1736,6 +1746,85 @@ static void free_vmcs(struct vmcs *vmcs)
free_pages((unsigned long)vmcs, vmcs_config.order);
}
+static struct vmcs *nested_get_current_vmcs(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs_list *list_item, *n;
+
+ list_for_each_entry_safe(list_item, n, &vmx->nested.vmcs02_list, list)
+ if (list_item->vmcs12_addr == vmx->nested.current_vmptr)
+ return list_item->vmcs02;
+
+ return NULL;
+}
+
+/*
+ * Allocate an L0 VMCS (vmcs02) for the current L1 VMCS (vmcs12), if one
+ * does not already exist. The allocation is done in L0 memory, so to avoid
+ * denial-of-service attack by guests, we limit the number of concurrently-
+ * allocated vmcss. A well-behaving L1 will VMCLEAR unused vmcs12s and not
+ * trigger this limit.
+ */
+static const int NESTED_MAX_VMCS = 256;
+static int nested_create_current_vmcs(struct kvm_vcpu *vcpu)
+{
+ struct vmcs_list *new_l2_guest;
+ struct vmcs *vmcs02;
+
+ if (nested_get_current_vmcs(vcpu))
+ return 0; /* nothing to do - we already have a VMCS */
+
+ if (to_vmx(vcpu)->nested.vmcs02_num >= NESTED_MAX_VMCS)
+ return -ENOMEM;
+
+ new_l2_guest = (struct vmcs_list *)
+ kmalloc(sizeof(struct vmcs_list), GFP_KERNEL);
+ if (!new_l2_guest)
+ return -ENOMEM;
+
+ vmcs02 = alloc_vmcs();
+ if (!vmcs02) {
+ kfree(new_l2_guest);
+ return -ENOMEM;
+ }
+
+ new_l2_guest->vmcs12_addr = to_vmx(vcpu)->nested.current_vmptr;
+ new_l2_guest->vmcs02 = vmcs02;
+ list_add(&(new_l2_guest->list), &(to_vmx(vcpu)->nested.vmcs02_list));
+ to_vmx(vcpu)->nested.vmcs02_num++;
+ return 0;
+}
+
+/* Free a vmcs12's associated vmcs02, and remove it from vmcs02_list */
+static void nested_free_vmcs(struct kvm_vcpu *vcpu, gpa_t vmptr)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs_list *list_item, *n;
+
+ list_for_each_entry_safe(list_item, n, &vmx->nested.vmcs02_list, list)
+ if (list_item->vmcs12_addr == vmptr) {
+ free_vmcs(list_item->vmcs02);
+ list_del(&(list_item->list));
+ kfree(list_item);
+ vmx->nested.vmcs02_num--;
+ return;
+ }
+}
+
+static void free_l1_state(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs_list *list_item, *n;
+
+ list_for_each_entry_safe(list_item, n,
+ &vmx->nested.vmcs02_list, list) {
+ free_vmcs(list_item->vmcs02);
+ list_del(&(list_item->list));
+ kfree(list_item);
+ }
+ vmx->nested.vmcs02_num = 0;
+}
+
static void free_kvm_area(void)
{
int cpu;
@@ -3884,6 +3973,9 @@ static int handle_vmon(struct kvm_vcpu *
return 1;
}
+ INIT_LIST_HEAD(&(vmx->nested.vmcs02_list));
+ vmx->nested.vmcs02_num = 0;
+
vmx->nested.vmxon = true;
skip_emulated_instruction(vcpu);
@@ -3931,6 +4023,8 @@ static int handle_vmoff(struct kvm_vcpu
if (to_vmx(vcpu)->nested.current_vmptr != -1ull)
nested_release_page(to_vmx(vcpu)->nested.current_vmcs12_page);
+ free_l1_state(vcpu);
+
skip_emulated_instruction(vcpu);
return 1;
}
@@ -4420,6 +4514,8 @@ static void vmx_free_vcpu(struct kvm_vcp
free_vpid(vmx);
if (vmx->nested.vmxon && to_vmx(vcpu)->nested.current_vmptr != -1ull)
nested_release_page(to_vmx(vcpu)->nested.current_vmcs12_page);
+ if (vmx->nested.vmxon)
+ free_l1_
