kvm: vmx: Add memcg accounting to KVM allocations

There are many KVM kernel memory allocations which are tied to the life of
the VM process and should be charged to the VM process's cgroup. If the
allocations aren't tied to the process, the OOM killer will not know
that killing the process will free the associated kernel memory.
Add __GFP_ACCOUNT flags to many of the allocations which are not yet being
charged to the VM process's cgroup.

Tested:
	Ran all kvm-unit-tests on a 64 bit Haswell machine, the patch
	introduced no new failures.
	Ran a kernel memory accounting test which creates a VM to touch
	memory and then checks that the kernel memory allocated for the
	process is within certain bounds.
	With this patch we account for much more of the vmalloc and slab memory
	allocated for the VM.

Signed-off-by: Ben Gardon <bgardon@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 18 insertions, 9 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index de6a9e7c6471..4950bb20e06a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -246,6 +246,10 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 
 	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
 	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		/*
+		 * This allocation for vmx_l1d_flush_pages is not tied to a VM
+		 * lifetime and so should not be charged to a memcg.
+		 */
 		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
 		if (!page)
 			return -ENOMEM;
@@ -2386,13 +2390,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	return 0;
 }
 
-struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu)
+struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags)
 {
 	int node = cpu_to_node(cpu);
 	struct page *pages;
 	struct vmcs *vmcs;
 
-	pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order);
+	pages = __alloc_pages_node(node, flags, vmcs_config.order);
 	if (!pages)
 		return NULL;
 	vmcs = page_address(pages);
@@ -2439,7 +2443,8 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 	loaded_vmcs_init(loaded_vmcs);
 
 	if (cpu_has_vmx_msr_bitmap()) {
-		loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
+		loaded_vmcs->msr_bitmap = (unsigned long *)
+				__get_free_page(GFP_KERNEL_ACCOUNT);
 		if (!loaded_vmcs->msr_bitmap)
 			goto out_vmcs;
 		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
@@ -2480,7 +2485,7 @@ static __init int alloc_kvm_area(void)
 	for_each_possible_cpu(cpu) {
 		struct vmcs *vmcs;
 
-		vmcs = alloc_vmcs_cpu(false, cpu);
+		vmcs = alloc_vmcs_cpu(false, cpu, GFP_KERNEL);
 		if (!vmcs) {
 			free_kvm_area();
 			return -ENOMEM;
@@ -6530,7 +6535,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 static struct kvm *vmx_vm_alloc(void)
 {
-	struct kvm_vmx *kvm_vmx = vzalloc(sizeof(struct kvm_vmx));
+	struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx),
+					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
+					    PAGE_KERNEL);
 	return &kvm_vmx->kvm;
 }
 
@@ -6557,14 +6564,16 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 {
 	int err;
-	struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	struct vcpu_vmx *vmx;
 	unsigned long *msr_bitmap;
 	int cpu;
 
+	vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
 
-	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL);
+	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
+			GFP_KERNEL_ACCOUNT);
 	if (!vmx->vcpu.arch.guest_fpu) {
 		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
 		err = -ENOMEM;
@@ -6586,12 +6595,12 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	 * for the guest, etc.
 	 */
 	if (enable_pml) {
-		vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 		if (!vmx->pml_pg)
 			goto uninit_vcpu;
 	}
 
-	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
 	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
 		     > PAGE_SIZE);