Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "While last week's pull request contained miscellaneous fixes for x86,
  this one covers other architectures, selftests changes, and a bigger
  series for APIC virtualization bugs that were discovered during 5.20
  development. The idea is to base 5.20 development for KVM on top of
  this tag.

  ARM64:

   - Properly reset the SVE/SME flags on vcpu load

   - Fix a vgic-v2 regression regarding accessing the pending state of a
     HW interrupt from userspace (and make the code common with vgic-v3)

   - Fix access to the idreg range for protected guests

   - Ignore 'kvm-arm.mode=protected' when using VHE

   - Return an error from kvm_arch_init_vm() on allocation failure

   - A bunch of small cleanups (comments, annotations, indentation)

  RISC-V:

   - Typo fix in arch/riscv/kvm/vmid.c

   - Remove broken reference pattern from MAINTAINERS entry

  x86-64:

   - Fix error in page tables with MKTME enabled

   - Dirty page tracking performance test extended to running a nested
     guest

   - Disable APICv/AVIC in cases that it cannot implement correctly"

[ This merge also fixes a misplaced end parenthesis bug introduced in
  commit 3743c2f02517 ("KVM: x86: inhibit APICv/AVIC on changes to APIC
  ID or APIC base") pointed out by Sean Christopherson ]

Link: https://lore.kernel.org/all/20220610191813.371682-1-seanjc@google.com/

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (34 commits)
  KVM: selftests: Restrict test region to 48-bit physical addresses when using nested
  KVM: selftests: Add option to run dirty_log_perf_test vCPUs in L2
  KVM: selftests: Clean up LIBKVM files in Makefile
  KVM: selftests: Link selftests directly with lib object files
  KVM: selftests: Drop unnecessary rule for STATIC_LIBS
  KVM: selftests: Add a helper to check EPT/VPID capabilities
  KVM: selftests: Move VMX_EPT_VPID_CAP_AD_BITS to vmx.h
  KVM: selftests: Refactor nested_map() to specify target level
  KVM: selftests: Drop stale function parameter comment for nested_map()
  KVM: selftests: Add option to create 2M and 1G EPT mappings
  KVM: selftests: Replace x86_page_size with PG_LEVEL_XX
  KVM: x86: SVM: fix nested PAUSE filtering when L0 intercepts PAUSE
  KVM: x86: SVM: drop preempt-safe wrappers for avic_vcpu_load/put
  KVM: x86: disable preemption around the call to kvm_arch_vcpu_{un|}blocking
  KVM: x86: disable preemption while updating apicv inhibition
  KVM: x86: SVM: fix avic_kick_target_vcpus_fast
  KVM: x86: SVM: remove avic's broken code that updated APIC ID
  KVM: x86: inhibit APICv/AVIC on changes to APIC ID or APIC base
  KVM: x86: document AVIC/APICv inhibit reasons
  KVM: x86/mmu: Set memory encryption "value", not "mask", in shadow PDPTRs
  ...

11 files changed, 341 insertions, 107 deletions

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 81470a99ed1c..22423c871ed6 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -37,11 +37,38 @@ ifeq ($(ARCH),riscv)
 	UNAME_M := riscv
 endif
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
-LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
-LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
-LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
-LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
+LIBKVM += lib/assert.c
+LIBKVM += lib/elf.c
+LIBKVM += lib/guest_modes.c
+LIBKVM += lib/io.c
+LIBKVM += lib/kvm_util.c
+LIBKVM += lib/perf_test_util.c
+LIBKVM += lib/rbtree.c
+LIBKVM += lib/sparsebit.c
+LIBKVM += lib/test_util.c
+
+LIBKVM_x86_64 += lib/x86_64/apic.c
+LIBKVM_x86_64 += lib/x86_64/handlers.S
+LIBKVM_x86_64 += lib/x86_64/perf_test_util.c
+LIBKVM_x86_64 += lib/x86_64/processor.c
+LIBKVM_x86_64 += lib/x86_64/svm.c
+LIBKVM_x86_64 += lib/x86_64/ucall.c
+LIBKVM_x86_64 += lib/x86_64/vmx.c
+
+LIBKVM_aarch64 += lib/aarch64/gic.c
+LIBKVM_aarch64 += lib/aarch64/gic_v3.c
+LIBKVM_aarch64 += lib/aarch64/handlers.S
+LIBKVM_aarch64 += lib/aarch64/processor.c
+LIBKVM_aarch64 += lib/aarch64/spinlock.c
+LIBKVM_aarch64 += lib/aarch64/ucall.c
+LIBKVM_aarch64 += lib/aarch64/vgic.c
+
+LIBKVM_s390x += lib/s390x/diag318_test_handler.c
+LIBKVM_s390x += lib/s390x/processor.c
+LIBKVM_s390x += lib/s390x/ucall.c
+
+LIBKVM_riscv += lib/riscv/processor.c
+LIBKVM_riscv += lib/riscv/ucall.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
@@ -173,12 +200,13 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
 include ../lib.mk
 
-STATIC_LIBS := $(OUTPUT)/libkvm.a
 LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
-EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+
+EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
 $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
@@ -187,13 +215,8 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
 $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
-	$(AR) crs $@ $^
-
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
-all: $(STATIC_LIBS)
-$(TEST_GEN_PROGS): $(STATIC_LIBS)
+$(TEST_GEN_PROGS): $(LIBKVM_OBJS)
 
 cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
 cscope:
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 7b47ae4f952e..d60a34cdfaee 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -336,8 +336,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-i iterations] [-p offset] [-g]"
-	       "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
+	printf("usage: %s [-h] [-i iterations] [-p offset] [-g] "
+	       "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
 	       "[-x memslots]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
@@ -351,6 +351,7 @@ static void help(char *name)
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
 	guest_modes_help();
+	printf(" -n: Run the vCPUs in nested mode (L2)\n");
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     dirtied by each vCPU. e.g. 10M or 3G.\n"
 	       "     (default: 1G)\n");
@@ -387,7 +388,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "ghi:p:m:b:f:v:os:x:")) != -1) {
+	while ((opt = getopt(argc, argv, "ghi:p:m:nb:f:v:os:x:")) != -1) {
 		switch (opt) {
 		case 'g':
 			dirty_log_manual_caps = 0;
@@ -401,6 +402,9 @@ int main(int argc, char *argv[])
 		case 'm':
 			guest_modes_cmdline(optarg);
 			break;
+		case 'n':
+			perf_test_args.nested = true;
+			break;
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
 			break;
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index a86f953d8d36..d822cb670f1c 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -30,10 +30,15 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
+	/* The starting address and size of the guest test region. */
 	uint64_t gpa;
+	uint64_t size;
 	uint64_t guest_page_size;
 	int wr_fract;
 
+	/* Run vCPUs in L2 instead of L1, if the architecture supports it. */
+	bool nested;
+
 	struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
 };
 
@@ -49,5 +54,9 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
 
 void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
 void perf_test_join_vcpu_threads(int vcpus);
+void perf_test_guest_code(uint32_t vcpu_id);
+
+uint64_t perf_test_nested_pages(int nr_vcpus);
+void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index d0d51adec76e..6ce185449259 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -482,13 +482,23 @@ void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
 struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
 void vm_xsave_req_perm(int bit);
 
-enum x86_page_size {
-	X86_PAGE_SIZE_4K = 0,
-	X86_PAGE_SIZE_2M,
-	X86_PAGE_SIZE_1G,
+enum pg_level {
+	PG_LEVEL_NONE,
+	PG_LEVEL_4K,
+	PG_LEVEL_2M,
+	PG_LEVEL_1G,
+	PG_LEVEL_512G,
+	PG_LEVEL_NUM
 };
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-		   enum x86_page_size page_size);
+
+#define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
+#define PG_LEVEL_SIZE(_level) (1ull << PG_LEVEL_SHIFT(_level))
+
+#define PG_SIZE_4K PG_LEVEL_SIZE(PG_LEVEL_4K)
+#define PG_SIZE_2M PG_LEVEL_SIZE(PG_LEVEL_2M)
+#define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G)
+
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
 
 /*
  * Basic CPU control in CR0
@@ -505,9 +515,6 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 #define X86_CR0_CD          (1UL<<30) /* Cache Disable */
 #define X86_CR0_PG          (1UL<<31) /* Paging */
 
-/* VMX_EPT_VPID_CAP bits */
-#define VMX_EPT_VPID_CAP_AD_BITS       (1ULL << 21)
-
 #define XSTATE_XTILE_CFG_BIT		17
 #define XSTATE_XTILE_DATA_BIT		18
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 583ceb0d1457..cc3604f8f1d3 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -96,6 +96,9 @@
 #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 
+#define VMX_EPT_VPID_CAP_1G_PAGES		0x00020000
+#define VMX_EPT_VPID_CAP_AD_BITS		0x00200000
+
 #define EXIT_REASON_FAILED_VMENTRY	0x80000000
 #define EXIT_REASON_EXCEPTION_NMI	0
 #define EXIT_REASON_EXTERNAL_INTERRUPT	1
@@ -606,6 +609,7 @@ bool load_vmcs(struct vmx_pages *vmx);
 
 bool nested_vmx_supported(void);
 void nested_vmx_check_supported(void);
+bool ept_1g_pages_supported(void);
 
 void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		   uint64_t nested_paddr, uint64_t paddr);
@@ -613,6 +617,8 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		 uint64_t nested_paddr, uint64_t paddr, uint64_t size);
 void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 			uint32_t memslot);
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+			    uint64_t addr, uint64_t size);
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot);
 void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 722df3a28791..f989ff91f022 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -40,7 +40,7 @@ static bool all_vcpu_threads_running;
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
  */
-static void guest_code(uint32_t vcpu_id)
+void perf_test_guest_code(uint32_t vcpu_id)
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
@@ -108,8 +108,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
-	uint64_t guest_num_pages;
+	uint64_t guest_num_pages, slot0_pages = DEFAULT_GUEST_PHY_PAGES;
 	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
+	uint64_t region_end_gfn;
 	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
@@ -135,33 +136,53 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    slots);
 
 	/*
+	 * If using nested, allocate extra pages for the nested page tables and
+	 * in-memory data structures.
+	 */
+	if (pta->nested)
+		slot0_pages += perf_test_nested_pages(vcpus);
+
+	/*
 	 * Pass guest_num_pages to populate the page tables for test memory.
 	 * The memory is also added to memslot 0, but that's a benign side
 	 * effect as KVM allows aliasing HVAs in meslots.
 	 */
-	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  guest_num_pages, 0, guest_code, NULL);
+	vm = vm_create_with_vcpus(mode, vcpus, slot0_pages, guest_num_pages, 0,
+				  perf_test_guest_code, NULL);
 
 	pta->vm = vm;
 
+	/* Put the test region at the top guest physical memory. */
+	region_end_gfn = vm_get_max_gfn(vm) + 1;
+
+#ifdef __x86_64__
+	/*
+	 * When running vCPUs in L2, restrict the test region to 48 bits to
+	 * avoid needing 5-level page tables to identity map L2.
+	 */
+	if (pta->nested)
+		region_end_gfn = min(region_end_gfn, (1UL << 48) / pta->guest_page_size);
+#endif
 	/*
 	 * If there should be more memory in the guest test region than there
 	 * can be pages in the guest, it will definitely cause problems.
 	 */
-	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+	TEST_ASSERT(guest_num_pages < region_end_gfn,
 		    "Requested more guest memory than address space allows.\n"
 		    "    guest pages: %" PRIx64 " max gfn: %" PRIx64
 		    " vcpus: %d wss: %" PRIx64 "]\n",
-		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
+		    guest_num_pages, region_end_gfn - 1, vcpus,
 		    vcpu_memory_bytes);
 
-	pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+	pta->gpa = (region_end_gfn - guest_num_pages) * pta->guest_page_size;
 	pta->gpa = align_down(pta->gpa, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
 	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
+	pta->size = guest_num_pages * pta->guest_page_size;
+	pr_info("guest physical test memory: [0x%lx, 0x%lx)\n",
+		pta->gpa, pta->gpa + pta->size);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
@@ -178,6 +199,11 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
 
+	if (pta->nested) {
+		pr_info("Configuring vCPUs to run in L2 (nested).\n");
+		perf_test_setup_nested(vm, vcpus);
+	}
+
 	ucall_init(vm, NULL);
 
 	/* Export the shared variables to the guest. */
@@ -198,6 +224,17 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
 	sync_global_to_guest(vm, perf_test_args);
 }
 
+uint64_t __weak perf_test_nested_pages(int nr_vcpus)
+{
+	return 0;
+}
+
+void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus)
+{
+	pr_info("%s() not support on this architecture, skipping.\n", __func__);
+	exit(KSFT_SKIP);
+}
+
 static void *vcpu_thread_main(void *data)
 {
 	struct vcpu_thread *vcpu = data;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
new file mode 100644
index 000000000000..e258524435a0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * x86_64-specific extensions to perf_test_util.c.
+ *
+ * Copyright (C) 2022, Google, Inc.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+#include "vmx.h"
+
+void perf_test_l2_guest_code(uint64_t vcpu_id)
+{
+	perf_test_guest_code(vcpu_id);
+	vmcall();
+}
+
+extern char perf_test_l2_guest_entry[];
+__asm__(
+"perf_test_l2_guest_entry:"
+"	mov (%rsp), %rdi;"
+"	call perf_test_l2_guest_code;"
+"	ud2;"
+);
+
+static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	unsigned long *rsp;
+
+	GUEST_ASSERT(vmx->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
+	GUEST_ASSERT(load_vmcs(vmx));
+	GUEST_ASSERT(ept_1g_pages_supported());
+
+	rsp = &l2_guest_stack[L2_GUEST_STACK_SIZE - 1];
+	*rsp = vcpu_id;
+	prepare_vmcs(vmx, perf_test_l2_guest_entry, rsp);
+
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	GUEST_DONE();
+}
+
+uint64_t perf_test_nested_pages(int nr_vcpus)
+{
+	/*
+	 * 513 page tables is enough to identity-map 256 TiB of L2 with 1G
+	 * pages and 4-level paging, plus a few pages per-vCPU for data
+	 * structures such as the VMCS.
+	 */
+	return 513 + 10 * nr_vcpus;
+}
+
+void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
+{
+	uint64_t start, end;
+
+	prepare_eptp(vmx, vm, 0);
+
+	/*
+	 * Identity map the first 4G and the test region with 1G pages so that
+	 * KVM can shadow the EPT12 with the maximum huge page size supported
+	 * by the backing source.
+	 */
+	nested_identity_map_1g(vmx, vm, 0, 0x100000000ULL);
+
+	start = align_down(perf_test_args.gpa, PG_SIZE_1G);
+	end = align_up(perf_test_args.gpa + perf_test_args.size, PG_SIZE_1G);
+	nested_identity_map_1g(vmx, vm, start, end - start);
+}
+
+void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus)
+{
+	struct vmx_pages *vmx, *vmx0 = NULL;
+	struct kvm_regs regs;
+	vm_vaddr_t vmx_gva;
+	int vcpu_id;
+
+	nested_vmx_check_supported();
+
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		vmx = vcpu_alloc_vmx(vm, &vmx_gva);
+
+		if (vcpu_id == 0) {
+			perf_test_setup_ept(vmx, vm);
+			vmx0 = vmx;
+		} else {
+			/* Share the same EPT table across all vCPUs. */
+			vmx->eptp = vmx0->eptp;
+			vmx->eptp_hva = vmx0->eptp_hva;
+			vmx->eptp_gpa = vmx0->eptp_gpa;
+		}
+
+		/*
+		 * Override the vCPU to run perf_test_l1_guest_code() which will
+		 * bounce it into L2 before calling perf_test_guest_code().
+		 */
+		vcpu_regs_get(vm, vcpu_id, &regs);
+		regs.rip = (unsigned long) perf_test_l1_guest_code;
+		vcpu_regs_set(vm, vcpu_id, &regs);
+		vcpu_args_set(vm, vcpu_id, 2, vmx_gva, vcpu_id);
+	}
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 33ea5e9955d9..ead7011ee8f6 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -158,7 +158,7 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
 			  int level)
 {
 	uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift);
-	int index = vaddr >> (vm->page_shift + level * 9) & 0x1ffu;
+	int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
 
 	return &page_table[index];
 }
@@ -167,14 +167,14 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 				       uint64_t pt_pfn,
 				       uint64_t vaddr,
 				       uint64_t paddr,
-				       int level,
-				       enum x86_page_size page_size)
+				       int current_level,
+				       int target_level)
 {
-	uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+	uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level);
 
 	if (!(*pte & PTE_PRESENT_MASK)) {
 		*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
-		if (level == page_size)
+		if (current_level == target_level)
 			*pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 		else
 			*pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK;
@@ -184,20 +184,19 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 		 * a hugepage at this level, and that there isn't a hugepage at
 		 * this level.
 		 */
-		TEST_ASSERT(level != page_size,
+		TEST_ASSERT(current_level != target_level,
 			    "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
-			    page_size, vaddr);
+			    current_level, vaddr);
 		TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
 			    "Cannot create page table at level: %u, vaddr: 0x%lx\n",
-			    level, vaddr);
+			    current_level, vaddr);
 	}
 	return pte;
 }
 
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-		   enum x86_page_size page_size)
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 {
-	const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
+	const uint64_t pg_size = PG_LEVEL_SIZE(level);
 	uint64_t *pml4e, *pdpe, *pde;
 	uint64_t *pte;
 
@@ -222,20 +221,20 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	 * early if a hugepage was created.
 	 */
 	pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
-				      vaddr, paddr, 3, page_size);
+				      vaddr, paddr, PG_LEVEL_512G, level);
 	if (*pml4e & PTE_LARGE_MASK)
 		return;
 
-	pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size);
+	pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, PG_LEVEL_1G, level);
 	if (*pdpe & PTE_LARGE_MASK)
 		return;
 
-	pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size);
+	pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, PG_LEVEL_2M, level);
 	if (*pde & PTE_LARGE_MASK)
 		return;
 
 	/* Fill in page table entry. */
-	pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0);
+	pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, PG_LEVEL_4K);
 	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
 		    "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
 	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
@@ -243,7 +242,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 {
-	__virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
+	__virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K);
 }
 
 static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index d089d8b850b5..b77a01d0a271 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -198,6 +198,16 @@ bool load_vmcs(struct vmx_pages *vmx)
 	return true;
 }
 
+static bool ept_vpid_cap_supported(uint64_t mask)
+{
+	return rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & mask;
+}
+
+bool ept_1g_pages_supported(void)
+{
+	return ept_vpid_cap_supported(VMX_EPT_VPID_CAP_1G_PAGES);
+}
+
 /*
  * Initialize the control fields to the most basic settings possible.
  */
@@ -215,7 +225,7 @@ static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
 		struct eptPageTablePointer eptp = {
 			.memory_type = VMX_BASIC_MEM_TYPE_WB,
 			.page_walk_length = 3, /* + 1 */
-			.ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS),
+			.ad_enabled = ept_vpid_cap_supported(VMX_EPT_VPID_CAP_AD_BITS),
 			.address = vmx->eptp_gpa >> PAGE_SHIFT_4K,
 		};
 
@@ -392,80 +402,93 @@ void nested_vmx_check_supported(void)
 	}
 }
 
-void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
-		   uint64_t nested_paddr, uint64_t paddr)
+static void nested_create_pte(struct kvm_vm *vm,
+			      struct eptPageTableEntry *pte,
+			      uint64_t nested_paddr,
+			      uint64_t paddr,
+			      int current_level,
+			      int target_level)
+{
+	if (!pte->readable) {
+		pte->writable = true;
+		pte->readable = true;
+		pte->executable = true;
+		pte->page_size = (current_level == target_level);
+		if (pte->page_size)
+			pte->address = paddr >> vm->page_shift;
+		else
+			pte->address = vm_alloc_page_table(vm) >> vm->page_shift;
+	} else {
+		/*
+		 * Entry already present.  Assert that the caller doesn't want
+		 * a hugepage at this level, and that there isn't a hugepage at
+		 * this level.
+		 */
+		TEST_ASSERT(current_level != target_level,
+			    "Cannot create hugepage at level: %u, nested_paddr: 0x%lx\n",
+			    current_level, nested_paddr);
+		TEST_ASSERT(!pte->page_size,
+			    "Cannot create page table at level: %u, nested_paddr: 0x%lx\n",
+			    current_level, nested_paddr);
+	}
+}
+
+
+void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		     uint64_t nested_paddr, uint64_t paddr, int target_level)
 {
-	uint16_t index[4];
-	struct eptPageTableEntry *pml4e;
+	const uint64_t page_size = PG_LEVEL_SIZE(target_level);
+	struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
+	uint16_t index;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
 		    "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
-	TEST_ASSERT((nested_paddr % vm->page_size) == 0,
+	TEST_ASSERT((nested_paddr >> 48) == 0,
+		    "Nested physical address 0x%lx requires 5-level paging",
+		    nested_paddr);
+	TEST_ASSERT((nested_paddr % page_size) == 0,
 		    "Nested physical address not on page boundary,\n"
-		    "  nested_paddr: 0x%lx vm->page_size: 0x%x",
-		    nested_paddr, vm->page_size);
+		    "  nested_paddr: 0x%lx page_size: 0x%lx",
+		    nested_paddr, page_size);
 	TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn,
 		    "Physical address beyond beyond maximum supported,\n"
 		    "  nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
-	TEST_ASSERT((paddr % vm->page_size) == 0,
+	TEST_ASSERT((paddr % page_size) == 0,
 		    "Physical address not on page boundary,\n"
-		    "  paddr: 0x%lx vm->page_size: 0x%x",
-		    paddr, vm->page_size);
+		    "  paddr: 0x%lx page_size: 0x%lx",
+		    paddr, page_size);
 	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
 		    "Physical address beyond beyond maximum supported,\n"
 		    "  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
 
-	index[0] = (nested_paddr >> 12) & 0x1ffu;
-	index[1] = (nested_paddr >> 21) & 0x1ffu;
-	index[2] = (nested_paddr >> 30) & 0x1ffu;
-	index[3] = (nested_paddr >> 39) & 0x1ffu;
-
-	/* Allocate page directory pointer table if not present. */
-	pml4e = vmx->eptp_hva;
-	if (!pml4e[index[3]].readable) {
-		pml4e[index[3]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pml4e[index[3]].writable = true;
-		pml4e[index[3]].readable = true;
-		pml4e[index[3]].executable = true;
-	}
+	for (int level = PG_LEVEL_512G; level >= PG_LEVEL_4K; level--) {
+		index = (nested_paddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
+		pte = &pt[index];
 
-	/* Allocate page directory table if not present. */
-	struct eptPageTableEntry *pdpe;
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
-	if (!pdpe[index[2]].readable) {
-		pdpe[index[2]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pdpe[index[2]].writable = true;
-		pdpe[index[2]].readable = true;
-		pdpe[index[2]].executable = true;
-	}
+		nested_create_pte(vm, pte, nested_paddr, paddr, level, target_level);
 
-	/* Allocate page table if not present. */
-	struct eptPageTableEntry *pde;
-	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
-	if (!pde[index[1]].readable) {
-		pde[index[1]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pde[index[1]].writable = true;
-		pde[index[1]].readable = true;
-		pde[index[1]].executable = true;
-	}
+		if (pte->page_size)
+			break;
 
-	/* Fill in page table entry. */
-	struct eptPageTableEntry *pte;
-	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
-	pte[index[0]].address = paddr >> vm->page_shift;
-	pte[index[0]].writable = true;
-	pte[index[0]].readable = true;
-	pte[index[0]].executable = true;
+		pt = addr_gpa2hva(vm, pte->address * vm->page_size);
+	}
 
 	/*
 	 * For now mark these as accessed and dirty because the only
 	 * testcase we have needs that.  Can be reconsidered later.
 	 */
-	pte[index[0]].accessed = true;
-	pte[index[0]].dirty = true;
+	pte->accessed = true;
+	pte->dirty = true;
+
+}
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		   uint64_t nested_paddr, uint64_t paddr)
+{
+	__nested_pg_map(vmx, vm, nested_paddr, paddr, PG_LEVEL_4K);
 }
 
 /*
@@ -476,7 +499,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
  *   nested_paddr - Nested guest physical address to map
  *   paddr - VM Physical Address
  *   size - The size of the range to map
- *   eptp_memslot - Memory region slot for new virtual translation tables
+ *   level - The level at which to map the range
  *
  * Output Args: None
  *
@@ -485,22 +508,29 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
  * Within the VM given by vm, creates a nested guest translation for the
  * page range starting at nested_paddr to the page range starting at paddr.
  */
-void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
-		uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+void __nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		  uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+		  int level)
 {
-	size_t page_size = vm->page_size;
+	size_t page_size = PG_LEVEL_SIZE(level);
 	size_t npages = size / page_size;
 
 	TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow");
 	TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
 
 	while (npages--) {
-		nested_pg_map(vmx, vm, nested_paddr, paddr);
+		__nested_pg_map(vmx, vm, nested_paddr, paddr, level);
 		nested_paddr += page_size;
 		paddr += page_size;
 	}
 }
 
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+{
+	__nested_map(vmx, vm, nested_paddr, paddr, size, PG_LEVEL_4K);
+}
+
 /* Prepare an identity extended page table that maps all the
  * physical pages in VM.
  */
@@ -525,6 +555,13 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 	}
 }
 
+/* Identity map a region with 1GiB Pages. */
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+			    uint64_t addr, uint64_t size)
+{
+	__nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G);
+}
+
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot)
 {
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 3875c4b23a04..15f046e19cb2 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -244,7 +244,7 @@ int main(int argc, char *argv[])
 #ifdef __x86_64__
 		/* Identity map memory in the guest using 1gb pages. */
 		for (i = 0; i < slot_size; i += size_1gb)
-			__virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G);
+			__virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
 #else
 		for (i = 0; i < slot_size; i += vm_get_page_size(vm))
 			virt_pg_map(vm, gpa + i, gpa + i);
diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
index da2325fcad87..bdecd532f935 100644
--- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
@@ -35,7 +35,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
 	run = vcpu_state(vm, VCPU_ID);
 
 	/* Map 1gb page without a backing memlot. */
-	__virt_pg_map(vm, MMIO_GPA, MMIO_GPA, X86_PAGE_SIZE_1G);
+	__virt_pg_map(vm, MMIO_GPA, MMIO_GPA, PG_LEVEL_1G);
 
 	r = _vcpu_run(vm, VCPU_ID);