[PATCH 5/24] Introduce vmcs12: a VMCS structure for L1

["Nadav Har'El" <nyh@il.ibm.com>]

An implementation of VMX needs to define a VMCS structure. This structure
is kept in guest memory, but is opaque to the guest (who can only read or
write it with VMX instructions).

This patch starts to define the VMCS structure which our nested VMX
implementation will present to L1. We call it "vmcs12", as it is the VMCS
that L1 keeps for its L2 guests.

This patch also adds the notion (as required by the VMX spec) of the "current
VMCS", and finally includes utility functions for mapping the guest-allocated
VMCSs in host memory.

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
---
--- .before/arch/x86/kvm/vmx.c	2010-06-13 15:01:28.000000000 +0300
+++ .after/arch/x86/kvm/vmx.c	2010-06-13 15:01:28.000000000 +0300
@@ -117,6 +117,29 @@ struct shared_msr_entry {
 	u64 mask;
 };
 
+#define VMCS12_REVISION 0x11e57ed0
+
+/*
+ * struct vmcs12 describes the state that our guest hypervisor (L1) keeps for a
+ * single nested guest (L2), hence the name vmcs12. Any VMX implementation has
+ * a VMCS structure (which is opaque to the guest), and vmcs12 is our emulated
+ * VMX's VMCS. This structure is stored in guest memory specified by VMPTRLD,
+ * and accessed by the guest using VMREAD/VMWRITE/VMCLEAR instructions. More
+ * than one of these structures may exist, if L1 runs multiple L2 guests.
+ * nested_vmx_run() will use the data here to build a VMCS for the underlying
+ * hardware which will be used to run L2.
+ * This structure is packed in order to preseve the binary content after live
+ * migration. If there are changes in the content or layout, VMCS12_REVISION
+ * must be changed.
+ */
+struct __attribute__ ((__packed__)) vmcs12 {
+	/* According to the Intel spec, a VMCS region must start with the
+	 * following two fields. Then follow implementation-specific data.
+	 */
+	u32 revision_id;
+	u32 abort;
+};
+
 /* 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,
  * the current VMCS set by L1, a list of the VMCSs used to run the active
@@ -125,6 +148,11 @@ struct shared_msr_entry {
 struct nested_vmx {
 	/* Has the level1 guest done vmxon? */
 	bool vmxon;
+
+	/* The guest-physical address of the current VMCS L1 keeps for L2 */
+	gpa_t current_vmptr;
+	/* The host-usable pointer to the above. Set by nested_map_current() */
+	struct vmcs12 *current_l2_page;
 };
 
 struct vcpu_vmx {
@@ -188,6 +216,61 @@ static inline struct vcpu_vmx *to_vmx(st
 	return container_of(vcpu, struct vcpu_vmx, vcpu);
 }
 
+static struct page *nested_get_page(struct kvm_vcpu *vcpu, u64 vmcs_addr)
+{
+	struct page *vmcs_page =
+		gfn_to_page(vcpu->kvm, vmcs_addr >> PAGE_SHIFT);
+
+	if (is_error_page(vmcs_page)) {
+		printk(KERN_ERR "%s error allocating page 0x%llx\n",
+		       __func__, vmcs_addr);
+		kvm_release_page_clean(vmcs_page);
+		return NULL;
+	}
+	return vmcs_page;
+}
+
+static int nested_map_current(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct page *vmcs_page =
+		nested_get_page(vcpu, vmx->nested.current_vmptr);
+
+	if (vmcs_page == NULL) {
+		printk(KERN_INFO "%s: failure in nested_get_page\n", __func__);
+		return 0;
+	}
+
+	if (vmx->nested.current_l2_page) {
+		printk(KERN_INFO "Shadow vmcs already mapped\n");
+		BUG_ON(1);
+		return 0;
+	}
+
+	vmx->nested.current_l2_page = kmap_atomic(vmcs_page, KM_USER0);
+	return 1;
+}
+
+static void nested_unmap_current(struct kvm_vcpu *vcpu)
+{
+	struct page *page;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!vmx->nested.current_l2_page) {
+		printk(KERN_INFO "Shadow vmcs already unmapped\n");
+		BUG_ON(1);
+		return;
+	}
+
+	page = kmap_atomic_to_page(vmx->nested.current_l2_page);
+
+	kunmap_atomic(vmx->nested.current_l2_page, KM_USER0);
+
+	kvm_release_page_dirty(page);
+
+	vmx->nested.current_l2_page = NULL;
+}
+
 static int init_rmode(struct kvm *kvm);
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
@@ -4186,6 +4269,9 @@ static struct kvm_vcpu *vmx_create_vcpu(
 			goto free_vmcs;
 	}
 
+	vmx->nested.current_vmptr = -1ull;
+	vmx->nested.current_l2_page = NULL;
+
 	return &vmx->vcpu;
 
 free_vmcs: