KVM: nVMX: Introduce vmcs02: VMCS used to run L2

We saw in a previous patch that L1 controls its L2 guest with a vcms12.
L0 needs to create a real VMCS for running L2. We call that "vmcs02".
A later patch will contain the code, prepare_vmcs02(), for filling the vmcs02
fields. This patch only contains code for allocating vmcs02.

In this version, prepare_vmcs02() sets *all* of vmcs02's fields each time we
enter from L1 to L2, so keeping just one vmcs02 for the vcpu is enough: It can
be reused even when L1 runs multiple L2 guests. However, in future versions
we'll probably want to add an optimization where vmcs02 fields that rarely
change will not be set each time. For that, we may want to keep around several
vmcs02s of L2 guests that have recently run, so that potentially we could run
these L2s again more quickly because less vmwrites to vmcs02 will be needed.

This patch adds to each vcpu a vmcs02 pool, vmx->nested.vmcs02_pool,
which remembers the vmcs02s last used to run up to VMCS02_POOL_SIZE L2s.
As explained above, in the current version we choose VMCS02_POOL_SIZE=1,
I.e., one vmcs02 is allocated (and loaded onto the processor), and it is
reused to enter any L2 guest. In the future, when prepare_vmcs02() is
optimized not to set all fields every time, VMCS02_POOL_SIZE should be
increased.

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/kvm/vmx.c

@@ -119,6 +119,7 @@ static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
 module_param(ple_window, int, S_IRUGO);
 
 #define NR_AUTOLOAD_MSRS 1
+#define VMCS02_POOL_SIZE 1
 
 struct vmcs {
 	u32 revision_id;
@@ -179,6 +180,13 @@ struct __packed vmcs12 {
  */
 #define VMCS12_SIZE 0x1000
 
+/* Used to remember the last vmcs02 used for some recently used vmcs12s */
+struct vmcs02_list {
+	struct list_head list;
+	gpa_t vmptr;
+	struct loaded_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.
@@ -192,6 +200,10 @@ struct nested_vmx {
 	/* The host-usable pointer to the above */
 	struct page *current_vmcs12_page;
 	struct vmcs12 *current_vmcs12;
+
+	/* vmcs02_list cache of VMCSs recently used to run L2 guests */
+	struct list_head vmcs02_pool;
+	int vmcs02_num;
 };
 
 struct vcpu_vmx {
@@ -4243,6 +4255,89 @@ static int handle_invalid_op(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/*
+ * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
+ * We could reuse a single VMCS for all the L2 guests, but we also want the
+ * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this
+ * allows keeping them loaded on the processor, and in the future will allow
+ * optimizations where prepare_vmcs02 doesn't need to set all the fields on
+ * every entry if they never change.
+ * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE
+ * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first.
+ *
+ * The following functions allocate and free a vmcs02 in this pool.
+ */
+
+/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */
+static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
+{
+	struct vmcs02_list *item;
+	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
+		if (item->vmptr == vmx->nested.current_vmptr) {
+			list_move(&item->list, &vmx->nested.vmcs02_pool);
+			return &item->vmcs02;
+		}
+
+	if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
+		/* Recycle the least recently used VMCS. */
+		item = list_entry(vmx->nested.vmcs02_pool.prev,
+			struct vmcs02_list, list);
+		item->vmptr = vmx->nested.current_vmptr;
+		list_move(&item->list, &vmx->nested.vmcs02_pool);
+		return &item->vmcs02;
+	}
+
+	/* Create a new VMCS */
+	item = (struct vmcs02_list *)
+		kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
+	if (!item)
+		return NULL;
+	item->vmcs02.vmcs = alloc_vmcs();
+	if (!item->vmcs02.vmcs) {
+		kfree(item);
+		return NULL;
+	}
+	loaded_vmcs_init(&item->vmcs02);
+	item->vmptr = vmx->nested.current_vmptr;
+	list_add(&(item->list), &(vmx->nested.vmcs02_pool));
+	vmx->nested.vmcs02_num++;
+	return &item->vmcs02;
+}
+
+/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */
+static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr)
+{
+	struct vmcs02_list *item;
+	list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
+		if (item->vmptr == vmptr) {
+			free_loaded_vmcs(&item->vmcs02);
+			list_del(&item->list);
+			kfree(item);
+			vmx->nested.vmcs02_num--;
+			return;
+		}
+}
+
+/*
+ * Free all VMCSs saved for this vcpu, except the one pointed by
+ * vmx->loaded_vmcs. These include the VMCSs in vmcs02_pool (except the one
+ * currently used, if running L2), and vmcs01 when running L2.
+ */
+static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
+{
+	struct vmcs02_list *item, *n;
+	list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) {
+		if (vmx->loaded_vmcs != &item->vmcs02)
+			free_loaded_vmcs(&item->vmcs02);
+		list_del(&item->list);
+		kfree(item);
+	}
+	vmx->nested.vmcs02_num = 0;
+
+	if (vmx->loaded_vmcs != &vmx->vmcs01)
+		free_loaded_vmcs(&vmx->vmcs01);
+}
+
 /*
  * Emulate the VMXON instruction.
  * Currently, we just remember that VMX is active, and do not save or even
@@ -4279,6 +4374,9 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
+	INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
+	vmx->nested.vmcs02_num = 0;
+
 	vmx->nested.vmxon = true;
 
 	skip_emulated_instruction(vcpu);
@@ -4330,6 +4428,8 @@ static void free_nested(struct vcpu_vmx *vmx)
 		vmx->nested.current_vmptr = -1ull;
 		vmx->nested.current_vmcs12 = NULL;
 	}
+
+	nested_free_all_saved_vmcss(vmx);
 }
 
 /* Emulate the VMXOFF instruction */