Merge tag 'irqchip-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

Pull irqchip updates for 5.11 from Marc Zyngier:

  - Preliminary support for managed interrupts on platform devices
  - Correctly identify allocation of MSIs proxyied by another device
  - Remove the fasteoi IPI flow which has been proved useless
  - Generalise the Ocelot support to new SoCs
  - Improve GICv4.1 vcpu entry, matching the corresponding KVM optimisation
  - Work around spurious interrupts on Qualcomm PDC
  - Random fixes and cleanups

Link: https://lore.kernel.org/r/20201212135626.1479884-1-maz@kernel.org

23 files changed, 2252 insertions, 277 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d2c2d6205008..7a2c242b7152 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,10 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0-only
+/aarch64/get-reg-list
+/aarch64/get-reg-list-sve
 /s390x/memop
 /s390x/resets
 /s390x/sync_regs_test
 /x86_64/cr4_cpuid_sync_test
 /x86_64/debug_regs
 /x86_64/evmcs_test
+/x86_64/kvm_pv_test
 /x86_64/hyperv_cpuid
 /x86_64/mmio_warning_test
 /x86_64/platform_info_test
@@ -24,6 +27,7 @@
 /clear_dirty_log_test
 /demand_paging_test
 /dirty_log_test
+/dirty_log_perf_test
 /kvm_create_max_vcpus
 /set_memory_region_test
 /steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 30afbad36cd5..3d14ef77755e 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -34,13 +34,14 @@ ifeq ($(ARCH),s390)
 endif
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
-LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
+LIBKVM_x86_64 = 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
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
+TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
@@ -58,14 +59,15 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
 TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test
-TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
-TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
@@ -111,14 +113,21 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
 include ../lib.mk
 
 STATIC_LIBS := $(OUTPUT)/libkvm.a
-LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
+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.*
+
+x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
+$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
-$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
+$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
 	$(AR) crs $@ $^
 
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
new file mode 100644
index 000000000000..efba76682b4b
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+#define REG_LIST_SVE
+#include "get-reg-list.c"
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
new file mode 100644
index 000000000000..33218a395d9f
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -0,0 +1,841 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check for KVM_GET_REG_LIST regressions.
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ *
+ * When attempting to migrate from a host with an older kernel to a host
+ * with a newer kernel we allow the newer kernel on the destination to
+ * list new registers with get-reg-list. We assume they'll be unused, at
+ * least until the guest reboots, and so they're relatively harmless.
+ * However, if the destination host with the newer kernel is missing
+ * registers which the source host with the older kernel has, then that's
+ * a regression in get-reg-list. This test checks for that regression by
+ * checking the current list against a blessed list. We should never have
+ * missing registers, but if new ones appear then they can probably be
+ * added to the blessed list. A completely new blessed list can be created
+ * by running the test with the --list command line argument.
+ *
+ * Note, the blessed list should be created from the oldest possible
+ * kernel. We can't go older than v4.15, though, because that's the first
+ * release to expose the ID system registers in KVM_GET_REG_LIST, see
+ * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features
+ * from guests"). Also, one must use the --core-reg-fixup command line
+ * option when running on an older kernel that doesn't include df205b5c6328
+ * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST")
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "kvm_util.h"
+#include "test_util.h"
+#include "processor.h"
+
+#ifdef REG_LIST_SVE
+#define reg_list_sve() (true)
+#else
+#define reg_list_sve() (false)
+#endif
+
+#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
+
+#define for_each_reg(i)								\
+	for ((i) = 0; (i) < reg_list->n; ++(i))
+
+#define for_each_missing_reg(i)							\
+	for ((i) = 0; (i) < blessed_n; ++(i))					\
+		if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i]))
+
+#define for_each_new_reg(i)							\
+	for ((i) = 0; (i) < reg_list->n; ++(i))					\
+		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
+
+
+static struct kvm_reg_list *reg_list;
+
+static __u64 base_regs[], vregs[], sve_regs[], rejects_set[];
+static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n;
+static __u64 *blessed_reg, blessed_n;
+
+static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg)
+{
+	int i;
+
+	for (i = 0; i < nr_regs; ++i)
+		if (reg == regs[i])
+			return true;
+	return false;
+}
+
+static const char *str_with_index(const char *template, __u64 index)
+{
+	char *str, *p;
+	int n;
+
+	str = strdup(template);
+	p = strstr(str, "##");
+	n = sprintf(p, "%lld", index);
+	strcat(p + n, strstr(template, "##") + 2);
+
+	return (const char *)str;
+}
+
+#define CORE_REGS_XX_NR_WORDS	2
+#define CORE_SPSR_XX_NR_WORDS	2
+#define CORE_FPREGS_XX_NR_WORDS	4
+
+static const char *core_id_to_str(__u64 id)
+{
+	__u64 core_off = id & ~REG_MASK, idx;
+
+	/*
+	 * core_off is the offset into struct kvm_regs
+	 */
+	switch (core_off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+		idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS;
+		TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx);
+		return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx);
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+		return "KVM_REG_ARM_CORE_REG(regs.sp)";
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+		return "KVM_REG_ARM_CORE_REG(regs.pc)";
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+		return "KVM_REG_ARM_CORE_REG(regs.pstate)";
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+		return "KVM_REG_ARM_CORE_REG(sp_el1)";
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+		return "KVM_REG_ARM_CORE_REG(elr_el1)";
+	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+		idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS;
+		TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx);
+		return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx);
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS;
+		TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx);
+		return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx);
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)";
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)";
+	}
+
+	TEST_FAIL("Unknown core reg id: 0x%llx", id);
+	return NULL;
+}
+
+static const char *sve_id_to_str(__u64 id)
+{
+	__u64 sve_off, n, i;
+
+	if (id == KVM_REG_ARM64_SVE_VLS)
+		return "KVM_REG_ARM64_SVE_VLS";
+
+	sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1));
+	i = id & (KVM_ARM64_SVE_MAX_SLICES - 1);
+
+	TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id);
+
+	switch (sve_off) {
+	case KVM_REG_ARM64_SVE_ZREG_BASE ...
+	     KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1:
+		n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1);
+		TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0),
+			    "Unexpected bits set in SVE ZREG id: 0x%llx", id);
+		return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n);
+	case KVM_REG_ARM64_SVE_PREG_BASE ...
+	     KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1:
+		n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1);
+		TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0),
+			    "Unexpected bits set in SVE PREG id: 0x%llx", id);
+		return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n);
+	case KVM_REG_ARM64_SVE_FFR_BASE:
+		TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0),
+			    "Unexpected bits set in SVE FFR id: 0x%llx", id);
+		return "KVM_REG_ARM64_SVE_FFR(0)";
+	}
+
+	return NULL;
+}
+
+static void print_reg(__u64 id)
+{
+	unsigned op0, op1, crn, crm, op2;
+	const char *reg_size = NULL;
+
+	TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64,
+		    "KVM_REG_ARM64 missing in reg id: 0x%llx", id);
+
+	switch (id & KVM_REG_SIZE_MASK) {
+	case KVM_REG_SIZE_U8:
+		reg_size = "KVM_REG_SIZE_U8";
+		break;
+	case KVM_REG_SIZE_U16:
+		reg_size = "KVM_REG_SIZE_U16";
+		break;
+	case KVM_REG_SIZE_U32:
+		reg_size = "KVM_REG_SIZE_U32";
+		break;
+	case KVM_REG_SIZE_U64:
+		reg_size = "KVM_REG_SIZE_U64";
+		break;
+	case KVM_REG_SIZE_U128:
+		reg_size = "KVM_REG_SIZE_U128";
+		break;
+	case KVM_REG_SIZE_U256:
+		reg_size = "KVM_REG_SIZE_U256";
+		break;
+	case KVM_REG_SIZE_U512:
+		reg_size = "KVM_REG_SIZE_U512";
+		break;
+	case KVM_REG_SIZE_U1024:
+		reg_size = "KVM_REG_SIZE_U1024";
+		break;
+	case KVM_REG_SIZE_U2048:
+		reg_size = "KVM_REG_SIZE_U2048";
+		break;
+	default:
+		TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx",
+			  (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
+	}
+
+	switch (id & KVM_REG_ARM_COPROC_MASK) {
+	case KVM_REG_ARM_CORE:
+		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id));
+		break;
+	case KVM_REG_ARM_DEMUX:
+		TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)),
+			    "Unexpected bits set in DEMUX reg id: 0x%llx", id);
+		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n",
+		       reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK);
+		break;
+	case KVM_REG_ARM64_SYSREG:
+		op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT;
+		op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT;
+		crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT;
+		crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT;
+		op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT;
+		TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2),
+			    "Unexpected bits set in SYSREG reg id: 0x%llx", id);
+		printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2);
+		break;
+	case KVM_REG_ARM_FW:
+		TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff),
+			    "Unexpected bits set in FW reg id: 0x%llx", id);
+		printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff);
+		break;
+	case KVM_REG_ARM64_SVE:
+		if (reg_list_sve())
+			printf("\t%s,\n", sve_id_to_str(id));
+		else
+			TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id);
+		break;
+	default:
+		TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx",
+			  (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
+	}
+}
+
+/*
+ * Older kernels listed each 32-bit word of CORE registers separately.
+ * For 64 and 128-bit registers we need to ignore the extra words. We
+ * also need to fixup the sizes, because the older kernels stated all
+ * registers were 64-bit, even when they weren't.
+ */
+static void core_reg_fixup(void)
+{
+	struct kvm_reg_list *tmp;
+	__u64 id, core_off;
+	int i;
+
+	tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64));
+
+	for (i = 0; i < reg_list->n; ++i) {
+		id = reg_list->reg[i];
+
+		if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) {
+			tmp->reg[tmp->n++] = id;
+			continue;
+		}
+
+		core_off = id & ~REG_MASK;
+
+		switch (core_off) {
+		case 0x52: case 0xd2: case 0xd6:
+			/*
+			 * These offsets are pointing at padding.
+			 * We need to ignore them too.
+			 */
+			continue;
+		case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+		     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+			if (core_off & 3)
+				continue;
+			id &= ~KVM_REG_SIZE_MASK;
+			id |= KVM_REG_SIZE_U128;
+			tmp->reg[tmp->n++] = id;
+			continue;
+		case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+			id &= ~KVM_REG_SIZE_MASK;
+			id |= KVM_REG_SIZE_U32;
+			tmp->reg[tmp->n++] = id;
+			continue;
+		default:
+			if (core_off & 1)
+				continue;
+			tmp->reg[tmp->n++] = id;
+			break;
+		}
+	}
+
+	free(reg_list);
+	reg_list = tmp;
+}
+
+static void prepare_vcpu_init(struct kvm_vcpu_init *init)
+{
+	if (reg_list_sve())
+		init->features[0] |= 1 << KVM_ARM_VCPU_SVE;
+}
+
+static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	int feature;
+
+	if (reg_list_sve()) {
+		feature = KVM_ARM_VCPU_SVE;
+		vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature);
+	}
+}
+
+static void check_supported(void)
+{
+	if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) {
+		fprintf(stderr, "SVE not available, skipping tests\n");
+		exit(KSFT_SKIP);
+	}
+}
+
+int main(int ac, char **av)
+{
+	struct kvm_vcpu_init init = { .target = -1, };
+	int new_regs = 0, missing_regs = 0, i;
+	int failed_get = 0, failed_set = 0, failed_reject = 0;
+	bool print_list = false, fixup_core_regs = false;
+	struct kvm_vm *vm;
+	__u64 *vec_regs;
+
+	check_supported();
+
+	for (i = 1; i < ac; ++i) {
+		if (strcmp(av[i], "--core-reg-fixup") == 0)
+			fixup_core_regs = true;
+		else if (strcmp(av[i], "--list") == 0)
+			print_list = true;
+		else
+			fprintf(stderr, "Ignoring unknown option: %s\n", av[i]);
+	}
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	prepare_vcpu_init(&init);
+	aarch64_vcpu_add_default(vm, 0, &init, NULL);
+	finalize_vcpu(vm, 0);
+
+	reg_list = vcpu_get_reg_list(vm, 0);
+
+	if (fixup_core_regs)
+		core_reg_fixup();
+
+	if (print_list) {
+		putchar('\n');
+		for_each_reg(i)
+			print_reg(reg_list->reg[i]);
+		putchar('\n');
+		return 0;
+	}
+
+	/*
+	 * We only test that we can get the register and then write back the
+	 * same value. Some registers may allow other values to be written
+	 * back, but others only allow some bits to be changed, and at least
+	 * for ID registers set will fail if the value does not exactly match
+	 * what was returned by get. If registers that allow other values to
+	 * be written need to have the other values tested, then we should
+	 * create a new set of tests for those in a new independent test
+	 * executable.
+	 */
+	for_each_reg(i) {
+		uint8_t addr[2048 / 8];
+		struct kvm_one_reg reg = {
+			.id = reg_list->reg[i],
+			.addr = (__u64)&addr,
+		};
+		int ret;
+
+		ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, &reg);
+		if (ret) {
+			puts("Failed to get ");
+			print_reg(reg.id);
+			putchar('\n');
+			++failed_get;
+		}
+
+		/* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
+		if (find_reg(rejects_set, rejects_set_n, reg.id)) {
+			ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
+			if (ret != -1 || errno != EPERM) {
+				printf("Failed to reject (ret=%d, errno=%d) ", ret, errno);
+				print_reg(reg.id);
+				putchar('\n');
+				++failed_reject;
+			}
+			continue;
+		}
+
+		ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
+		if (ret) {
+			puts("Failed to set ");
+			print_reg(reg.id);
+			putchar('\n');
+			++failed_set;
+		}
+	}
+
+	if (reg_list_sve()) {
+		blessed_n = base_regs_n + sve_regs_n;
+		vec_regs = sve_regs;
+	} else {
+		blessed_n = base_regs_n + vregs_n;
+		vec_regs = vregs;
+	}
+
+	blessed_reg = calloc(blessed_n, sizeof(__u64));
+	for (i = 0; i < base_regs_n; ++i)
+		blessed_reg[i] = base_regs[i];
+	for (i = 0; i < blessed_n - base_regs_n; ++i)
+		blessed_reg[base_regs_n + i] = vec_regs[i];
+
+	for_each_new_reg(i)
+		++new_regs;
+
+	for_each_missing_reg(i)
+		++missing_regs;
+
+	if (new_regs || missing_regs) {
+		printf("Number blessed registers: %5lld\n", blessed_n);
+		printf("Number registers:         %5lld\n", reg_list->n);
+	}
+
+	if (new_regs) {
+		printf("\nThere are %d new registers.\n"
+		       "Consider adding them to the blessed reg "
+		       "list with the following lines:\n\n", new_regs);
+		for_each_new_reg(i)
+			print_reg(reg_list->reg[i]);
+		putchar('\n');
+	}
+
+	if (missing_regs) {
+		printf("\nThere are %d missing registers.\n"
+		       "The following lines are missing registers:\n\n", missing_regs);
+		for_each_missing_reg(i)
+			print_reg(blessed_reg[i]);
+		putchar('\n');
+	}
+
+	TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
+		    "There are %d missing registers; "
+		    "%d registers failed get; %d registers failed set; %d registers failed reject",
+		    missing_regs, failed_get, failed_set, failed_reject);
+
+	return 0;
+}
+
+/*
+ * The current blessed list was primed with the output of kernel version
+ * v4.15 with --core-reg-fixup and then later updated with new registers.
+ */
+static __u64 base_regs[] = {
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
+	KVM_REG_ARM_FW_REG(0),
+	KVM_REG_ARM_FW_REG(1),
+	KVM_REG_ARM_FW_REG(2),
+	ARM64_SYS_REG(3, 3, 14, 3, 1),	/* CNTV_CTL_EL0 */
+	ARM64_SYS_REG(3, 3, 14, 3, 2),	/* CNTV_CVAL_EL0 */
+	ARM64_SYS_REG(3, 3, 14, 0, 2),
+	ARM64_SYS_REG(3, 0, 0, 0, 0),	/* MIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 0, 6),	/* REVIDR_EL1 */
+	ARM64_SYS_REG(3, 1, 0, 0, 1),	/* CLIDR_EL1 */
+	ARM64_SYS_REG(3, 1, 0, 0, 7),	/* AIDR_EL1 */
+	ARM64_SYS_REG(3, 3, 0, 0, 1),	/* CTR_EL0 */
+	ARM64_SYS_REG(2, 0, 0, 0, 4),
+	ARM64_SYS_REG(2, 0, 0, 0, 5),
+	ARM64_SYS_REG(2, 0, 0, 0, 6),
+	ARM64_SYS_REG(2, 0, 0, 0, 7),
+	ARM64_SYS_REG(2, 0, 0, 1, 4),
+	ARM64_SYS_REG(2, 0, 0, 1, 5),
+	ARM64_SYS_REG(2, 0, 0, 1, 6),
+	ARM64_SYS_REG(2, 0, 0, 1, 7),
+	ARM64_SYS_REG(2, 0, 0, 2, 0),	/* MDCCINT_EL1 */
+	ARM64_SYS_REG(2, 0, 0, 2, 2),	/* MDSCR_EL1 */
+	ARM64_SYS_REG(2, 0, 0, 2, 4),
+	ARM64_SYS_REG(2, 0, 0, 2, 5),
+	ARM64_SYS_REG(2, 0, 0, 2, 6),
+	ARM64_SYS_REG(2, 0, 0, 2, 7),
+	ARM64_SYS_REG(2, 0, 0, 3, 4),
+	ARM64_SYS_REG(2, 0, 0, 3, 5),
+	ARM64_SYS_REG(2, 0, 0, 3, 6),
+	ARM64_SYS_REG(2, 0, 0, 3, 7),
+	ARM64_SYS_REG(2, 0, 0, 4, 4),
+	ARM64_SYS_REG(2, 0, 0, 4, 5),
+	ARM64_SYS_REG(2, 0, 0, 4, 6),
+	ARM64_SYS_REG(2, 0, 0, 4, 7),
+	ARM64_SYS_REG(2, 0, 0, 5, 4),
+	ARM64_SYS_REG(2, 0, 0, 5, 5),
+	ARM64_SYS_REG(2, 0, 0, 5, 6),
+	ARM64_SYS_REG(2, 0, 0, 5, 7),
+	ARM64_SYS_REG(2, 0, 0, 6, 4),
+	ARM64_SYS_REG(2, 0, 0, 6, 5),
+	ARM64_SYS_REG(2, 0, 0, 6, 6),
+	ARM64_SYS_REG(2, 0, 0, 6, 7),
+	ARM64_SYS_REG(2, 0, 0, 7, 4),
+	ARM64_SYS_REG(2, 0, 0, 7, 5),
+	ARM64_SYS_REG(2, 0, 0, 7, 6),
+	ARM64_SYS_REG(2, 0, 0, 7, 7),
+	ARM64_SYS_REG(2, 0, 0, 8, 4),
+	ARM64_SYS_REG(2, 0, 0, 8, 5),
+	ARM64_SYS_REG(2, 0, 0, 8, 6),
+	ARM64_SYS_REG(2, 0, 0, 8, 7),
+	ARM64_SYS_REG(2, 0, 0, 9, 4),
+	ARM64_SYS_REG(2, 0, 0, 9, 5),
+	ARM64_SYS_REG(2, 0, 0, 9, 6),
+	ARM64_SYS_REG(2, 0, 0, 9, 7),
+	ARM64_SYS_REG(2, 0, 0, 10, 4),
+	ARM64_SYS_REG(2, 0, 0, 10, 5),
+	ARM64_SYS_REG(2, 0, 0, 10, 6),
+	ARM64_SYS_REG(2, 0, 0, 10, 7),
+	ARM64_SYS_REG(2, 0, 0, 11, 4),
+	ARM64_SYS_REG(2, 0, 0, 11, 5),
+	ARM64_SYS_REG(2, 0, 0, 11, 6),
+	ARM64_SYS_REG(2, 0, 0, 11, 7),
+	ARM64_SYS_REG(2, 0, 0, 12, 4),
+	ARM64_SYS_REG(2, 0, 0, 12, 5),
+	ARM64_SYS_REG(2, 0, 0, 12, 6),
+	ARM64_SYS_REG(2, 0, 0, 12, 7),
+	ARM64_SYS_REG(2, 0, 0, 13, 4),
+	ARM64_SYS_REG(2, 0, 0, 13, 5),
+	ARM64_SYS_REG(2, 0, 0, 13, 6),
+	ARM64_SYS_REG(2, 0, 0, 13, 7),
+	ARM64_SYS_REG(2, 0, 0, 14, 4),
+	ARM64_SYS_REG(2, 0, 0, 14, 5),
+	ARM64_SYS_REG(2, 0, 0, 14, 6),
+	ARM64_SYS_REG(2, 0, 0, 14, 7),
+	ARM64_SYS_REG(2, 0, 0, 15, 4),
+	ARM64_SYS_REG(2, 0, 0, 15, 5),
+	ARM64_SYS_REG(2, 0, 0, 15, 6),
+	ARM64_SYS_REG(2, 0, 0, 15, 7),
+	ARM64_SYS_REG(2, 4, 0, 7, 0),	/* DBGVCR32_EL2 */
+	ARM64_SYS_REG(3, 0, 0, 0, 5),	/* MPIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 0),	/* ID_PFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 1),	/* ID_PFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 2),	/* ID_DFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 3),	/* ID_AFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 4),	/* ID_MMFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 5),	/* ID_MMFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 6),	/* ID_MMFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 7),	/* ID_MMFR3_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 0),	/* ID_ISAR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 1),	/* ID_ISAR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 2),	/* ID_ISAR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 3),	/* ID_ISAR3_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 4),	/* ID_ISAR4_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 5),	/* ID_ISAR5_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 6),	/* ID_MMFR4_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 7),	/* ID_ISAR6_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 0),	/* MVFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 1),	/* MVFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 2),	/* MVFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 3),
+	ARM64_SYS_REG(3, 0, 0, 3, 4),	/* ID_PFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 5),	/* ID_DFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 6),	/* ID_MMFR5_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 7),
+	ARM64_SYS_REG(3, 0, 0, 4, 0),	/* ID_AA64PFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 4, 1),	/* ID_AA64PFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 4, 2),
+	ARM64_SYS_REG(3, 0, 0, 4, 3),
+	ARM64_SYS_REG(3, 0, 0, 4, 4),	/* ID_AA64ZFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 4, 5),
+	ARM64_SYS_REG(3, 0, 0, 4, 6),
+	ARM64_SYS_REG(3, 0, 0, 4, 7),
+	ARM64_SYS_REG(3, 0, 0, 5, 0),	/* ID_AA64DFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 1),	/* ID_AA64DFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 2),
+	ARM64_SYS_REG(3, 0, 0, 5, 3),
+	ARM64_SYS_REG(3, 0, 0, 5, 4),	/* ID_AA64AFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 5),	/* ID_AA64AFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 6),
+	ARM64_SYS_REG(3, 0, 0, 5, 7),
+	ARM64_SYS_REG(3, 0, 0, 6, 0),	/* ID_AA64ISAR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 6, 1),	/* ID_AA64ISAR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 6, 2),
+	ARM64_SYS_REG(3, 0, 0, 6, 3),
+	ARM64_SYS_REG(3, 0, 0, 6, 4),
+	ARM64_SYS_REG(3, 0, 0, 6, 5),
+	ARM64_SYS_REG(3, 0, 0, 6, 6),
+	ARM64_SYS_REG(3, 0, 0, 6, 7),
+	ARM64_SYS_REG(3, 0, 0, 7, 0),	/* ID_AA64MMFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 7, 1),	/* ID_AA64MMFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 7, 2),	/* ID_AA64MMFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 7, 3),
+	ARM64_SYS_REG(3, 0, 0, 7, 4),
+	ARM64_SYS_REG(3, 0, 0, 7, 5),
+	ARM64_SYS_REG(3, 0, 0, 7, 6),
+	ARM64_SYS_REG(3, 0, 0, 7, 7),
+	ARM64_SYS_REG(3, 0, 1, 0, 0),	/* SCTLR_EL1 */
+	ARM64_SYS_REG(3, 0, 1, 0, 1),	/* ACTLR_EL1 */
+	ARM64_SYS_REG(3, 0, 1, 0, 2),	/* CPACR_EL1 */
+	ARM64_SYS_REG(3, 0, 2, 0, 0),	/* TTBR0_EL1 */
+	ARM64_SYS_REG(3, 0, 2, 0, 1),	/* TTBR1_EL1 */
+	ARM64_SYS_REG(3, 0, 2, 0, 2),	/* TCR_EL1 */
+	ARM64_SYS_REG(3, 0, 5, 1, 0),	/* AFSR0_EL1 */
+	ARM64_SYS_REG(3, 0, 5, 1, 1),	/* AFSR1_EL1 */
+	ARM64_SYS_REG(3, 0, 5, 2, 0),	/* ESR_EL1 */
+	ARM64_SYS_REG(3, 0, 6, 0, 0),	/* FAR_EL1 */
+	ARM64_SYS_REG(3, 0, 7, 4, 0),	/* PAR_EL1 */
+	ARM64_SYS_REG(3, 0, 9, 14, 1),	/* PMINTENSET_EL1 */
+	ARM64_SYS_REG(3, 0, 9, 14, 2),	/* PMINTENCLR_EL1 */
+	ARM64_SYS_REG(3, 0, 10, 2, 0),	/* MAIR_EL1 */
+	ARM64_SYS_REG(3, 0, 10, 3, 0),	/* AMAIR_EL1 */
+	ARM64_SYS_REG(3, 0, 12, 0, 0),	/* VBAR_EL1 */
+	ARM64_SYS_REG(3, 0, 12, 1, 1),	/* DISR_EL1 */
+	ARM64_SYS_REG(3, 0, 13, 0, 1),	/* CONTEXTIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 13, 0, 4),	/* TPIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 14, 1, 0),	/* CNTKCTL_EL1 */
+	ARM64_SYS_REG(3, 2, 0, 0, 0),	/* CSSELR_EL1 */
+	ARM64_SYS_REG(3, 3, 9, 12, 0),	/* PMCR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 1),	/* PMCNTENSET_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 2),	/* PMCNTENCLR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 3),	/* PMOVSCLR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 4),	/* PMSWINC_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 5),	/* PMSELR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 13, 0),	/* PMCCNTR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 14, 0),	/* PMUSERENR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 14, 3),	/* PMOVSSET_EL0 */
+	ARM64_SYS_REG(3, 3, 13, 0, 2),	/* TPIDR_EL0 */
+	ARM64_SYS_REG(3, 3, 13, 0, 3),	/* TPIDRRO_EL0 */
+	ARM64_SYS_REG(3, 3, 14, 8, 0),
+	ARM64_SYS_REG(3, 3, 14, 8, 1),
+	ARM64_SYS_REG(3, 3, 14, 8, 2),
+	ARM64_SYS_REG(3, 3, 14, 8, 3),
+	ARM64_SYS_REG(3, 3, 14, 8, 4),
+	ARM64_SYS_REG(3, 3, 14, 8, 5),
+	ARM64_SYS_REG(3, 3, 14, 8, 6),
+	ARM64_SYS_REG(3, 3, 14, 8, 7),
+	ARM64_SYS_REG(3, 3, 14, 9, 0),
+	ARM64_SYS_REG(3, 3, 14, 9, 1),
+	ARM64_SYS_REG(3, 3, 14, 9, 2),
+	ARM64_SYS_REG(3, 3, 14, 9, 3),
+	ARM64_SYS_REG(3, 3, 14, 9, 4),
+	ARM64_SYS_REG(3, 3, 14, 9, 5),
+	ARM64_SYS_REG(3, 3, 14, 9, 6),
+	ARM64_SYS_REG(3, 3, 14, 9, 7),
+	ARM64_SYS_REG(3, 3, 14, 10, 0),
+	ARM64_SYS_REG(3, 3, 14, 10, 1),
+	ARM64_SYS_REG(3, 3, 14, 10, 2),
+	ARM64_SYS_REG(3, 3, 14, 10, 3),
+	ARM64_SYS_REG(3, 3, 14, 10, 4),
+	ARM64_SYS_REG(3, 3, 14, 10, 5),
+	ARM64_SYS_REG(3, 3, 14, 10, 6),
+	ARM64_SYS_REG(3, 3, 14, 10, 7),
+	ARM64_SYS_REG(3, 3, 14, 11, 0),
+	ARM64_SYS_REG(3, 3, 14, 11, 1),
+	ARM64_SYS_REG(3, 3, 14, 11, 2),
+	ARM64_SYS_REG(3, 3, 14, 11, 3),
+	ARM64_SYS_REG(3, 3, 14, 11, 4),
+	ARM64_SYS_REG(3, 3, 14, 11, 5),
+	ARM64_SYS_REG(3, 3, 14, 11, 6),
+	ARM64_SYS_REG(3, 3, 14, 12, 0),
+	ARM64_SYS_REG(3, 3, 14, 12, 1),
+	ARM64_SYS_REG(3, 3, 14, 12, 2),
+	ARM64_SYS_REG(3, 3, 14, 12, 3),
+	ARM64_SYS_REG(3, 3, 14, 12, 4),
+	ARM64_SYS_REG(3, 3, 14, 12, 5),
+	ARM64_SYS_REG(3, 3, 14, 12, 6),
+	ARM64_SYS_REG(3, 3, 14, 12, 7),
+	ARM64_SYS_REG(3, 3, 14, 13, 0),
+	ARM64_SYS_REG(3, 3, 14, 13, 1),
+	ARM64_SYS_REG(3, 3, 14, 13, 2),
+	ARM64_SYS_REG(3, 3, 14, 13, 3),
+	ARM64_SYS_REG(3, 3, 14, 13, 4),
+	ARM64_SYS_REG(3, 3, 14, 13, 5),
+	ARM64_SYS_REG(3, 3, 14, 13, 6),
+	ARM64_SYS_REG(3, 3, 14, 13, 7),
+	ARM64_SYS_REG(3, 3, 14, 14, 0),
+	ARM64_SYS_REG(3, 3, 14, 14, 1),
+	ARM64_SYS_REG(3, 3, 14, 14, 2),
+	ARM64_SYS_REG(3, 3, 14, 14, 3),
+	ARM64_SYS_REG(3, 3, 14, 14, 4),
+	ARM64_SYS_REG(3, 3, 14, 14, 5),
+	ARM64_SYS_REG(3, 3, 14, 14, 6),
+	ARM64_SYS_REG(3, 3, 14, 14, 7),
+	ARM64_SYS_REG(3, 3, 14, 15, 0),
+	ARM64_SYS_REG(3, 3, 14, 15, 1),
+	ARM64_SYS_REG(3, 3, 14, 15, 2),
+	ARM64_SYS_REG(3, 3, 14, 15, 3),
+	ARM64_SYS_REG(3, 3, 14, 15, 4),
+	ARM64_SYS_REG(3, 3, 14, 15, 5),
+	ARM64_SYS_REG(3, 3, 14, 15, 6),
+	ARM64_SYS_REG(3, 3, 14, 15, 7),	/* PMCCFILTR_EL0 */
+	ARM64_SYS_REG(3, 4, 3, 0, 0),	/* DACR32_EL2 */
+	ARM64_SYS_REG(3, 4, 5, 0, 1),	/* IFSR32_EL2 */
+	ARM64_SYS_REG(3, 4, 5, 3, 0),	/* FPEXC32_EL2 */
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0,
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1,
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2,
+};
+static __u64 base_regs_n = ARRAY_SIZE(base_regs);
+
+static __u64 vregs[] = {
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]),
+};
+static __u64 vregs_n = ARRAY_SIZE(vregs);
+
+static __u64 sve_regs[] = {
+	KVM_REG_ARM64_SVE_VLS,
+	KVM_REG_ARM64_SVE_ZREG(0, 0),
+	KVM_REG_ARM64_SVE_ZREG(1, 0),
+	KVM_REG_ARM64_SVE_ZREG(2, 0),
+	KVM_REG_ARM64_SVE_ZREG(3, 0),
+	KVM_REG_ARM64_SVE_ZREG(4, 0),
+	KVM_REG_ARM64_SVE_ZREG(5, 0),
+	KVM_REG_ARM64_SVE_ZREG(6, 0),
+	KVM_REG_ARM64_SVE_ZREG(7, 0),
+	KVM_REG_ARM64_SVE_ZREG(8, 0),
+	KVM_REG_ARM64_SVE_ZREG(9, 0),
+	KVM_REG_ARM64_SVE_ZREG(10, 0),
+	KVM_REG_ARM64_SVE_ZREG(11, 0),
+	KVM_REG_ARM64_SVE_ZREG(12, 0),
+	KVM_REG_ARM64_SVE_ZREG(13, 0),
+	KVM_REG_ARM64_SVE_ZREG(14, 0),
+	KVM_REG_ARM64_SVE_ZREG(15, 0),
+	KVM_REG_ARM64_SVE_ZREG(16, 0),
+	KVM_REG_ARM64_SVE_ZREG(17, 0),
+	KVM_REG_ARM64_SVE_ZREG(18, 0),
+	KVM_REG_ARM64_SVE_ZREG(19, 0),
+	KVM_REG_ARM64_SVE_ZREG(20, 0),
+	KVM_REG_ARM64_SVE_ZREG(21, 0),
+	KVM_REG_ARM64_SVE_ZREG(22, 0),
+	KVM_REG_ARM64_SVE_ZREG(23, 0),
+	KVM_REG_ARM64_SVE_ZREG(24, 0),
+	KVM_REG_ARM64_SVE_ZREG(25, 0),
+	KVM_REG_ARM64_SVE_ZREG(26, 0),
+	KVM_REG_ARM64_SVE_ZREG(27, 0),
+	KVM_REG_ARM64_SVE_ZREG(28, 0),
+	KVM_REG_ARM64_SVE_ZREG(29, 0),
+	KVM_REG_ARM64_SVE_ZREG(30, 0),
+	KVM_REG_ARM64_SVE_ZREG(31, 0),
+	KVM_REG_ARM64_SVE_PREG(0, 0),
+	KVM_REG_ARM64_SVE_PREG(1, 0),
+	KVM_REG_ARM64_SVE_PREG(2, 0),
+	KVM_REG_ARM64_SVE_PREG(3, 0),
+	KVM_REG_ARM64_SVE_PREG(4, 0),
+	KVM_REG_ARM64_SVE_PREG(5, 0),
+	KVM_REG_ARM64_SVE_PREG(6, 0),
+	KVM_REG_ARM64_SVE_PREG(7, 0),
+	KVM_REG_ARM64_SVE_PREG(8, 0),
+	KVM_REG_ARM64_SVE_PREG(9, 0),
+	KVM_REG_ARM64_SVE_PREG(10, 0),
+	KVM_REG_ARM64_SVE_PREG(11, 0),
+	KVM_REG_ARM64_SVE_PREG(12, 0),
+	KVM_REG_ARM64_SVE_PREG(13, 0),
+	KVM_REG_ARM64_SVE_PREG(14, 0),
+	KVM_REG_ARM64_SVE_PREG(15, 0),
+	KVM_REG_ARM64_SVE_FFR(0),
+	ARM64_SYS_REG(3, 0, 1, 2, 0),   /* ZCR_EL1 */
+};
+static __u64 sve_regs_n = ARRAY_SIZE(sve_regs);
+
+static __u64 rejects_set[] = {
+#ifdef REG_LIST_SVE
+	KVM_REG_ARM64_SVE_VLS,
+#endif
+};
+static __u64 rejects_set_n = ARRAY_SIZE(rejects_set);
diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c
deleted file mode 100644
index 11672ec6f74e..000000000000
--- a/tools/testing/selftests/kvm/clear_dirty_log_test.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#define USE_CLEAR_DIRTY_LOG
-#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
-#define KVM_DIRTY_LOG_INITIALLY_SET         (1 << 1)
-#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
-		KVM_DIRTY_LOG_INITIALLY_SET)
-#include "dirty_log_test.c"
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 360cd3ea4cd6..3d96a7bfaff3 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -21,20 +21,12 @@
 #include <linux/bitops.h>
 #include <linux/userfaultfd.h>
 
-#include "test_util.h"
-#include "kvm_util.h"
+#include "perf_test_util.h"
 #include "processor.h"
+#include "test_util.h"
 
 #ifdef __NR_userfaultfd
 
-/* The memory slot index demand page */
-#define TEST_MEM_SLOT_INDEX		1
-
-/* Default guest test virtual memory offset */
-#define DEFAULT_GUEST_TEST_MEM		0xc0000000
-
-#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */
-
 #ifdef PRINT_PER_PAGE_UPDATES
 #define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
 #else
@@ -47,77 +39,17 @@
 #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
 #endif
 
-#define MAX_VCPUS 512
-
-/*
- * Guest/Host shared variables. Ensure addr_gva2hva() and/or
- * sync_global_to/from_guest() are used when accessing from
- * the host. READ/WRITE_ONCE() should also be used with anything
- * that may change.
- */
-static uint64_t host_page_size;
-static uint64_t guest_page_size;
-
 static char *guest_data_prototype;
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-static uint64_t guest_test_phys_mem;
-
-/*
- * Guest virtual memory offset of the testing memory slot.
- * Must not conflict with identity mapped test code.
- */
-static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
-
-struct vcpu_args {
-	uint64_t gva;
-	uint64_t pages;
-
-	/* Only used by the host userspace part of the vCPU thread */
-	int vcpu_id;
-	struct kvm_vm *vm;
-};
-
-static struct vcpu_args vcpu_args[MAX_VCPUS];
-
-/*
- * Continuously write to the first 8 bytes of each page in the demand paging
- * memory region.
- */
-static void guest_code(uint32_t vcpu_id)
-{
-	uint64_t gva;
-	uint64_t pages;
-	int i;
-
-	/* Make sure vCPU args data structure is not corrupt. */
-	GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id);
-
-	gva = vcpu_args[vcpu_id].gva;
-	pages = vcpu_args[vcpu_id].pages;
-
-	for (i = 0; i < pages; i++) {
-		uint64_t addr = gva + (i * guest_page_size);
-
-		addr &= ~(host_page_size - 1);
-		*(uint64_t *)addr = 0x0123456789ABCDEF;
-	}
-
-	GUEST_SYNC(1);
-}
-
 static void *vcpu_worker(void *data)
 {
 	int ret;
-	struct vcpu_args *args = (struct vcpu_args *)data;
-	struct kvm_vm *vm = args->vm;
-	int vcpu_id = args->vcpu_id;
+	struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+	int vcpu_id = vcpu_args->vcpu_id;
+	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
-	struct timespec start, end, ts_diff;
+	struct timespec start;
+	struct timespec ts_diff;
 
 	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
 	run = vcpu_state(vm, vcpu_id);
@@ -133,52 +65,18 @@ static void *vcpu_worker(void *data)
 			    exit_reason_str(run->exit_reason));
 	}
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
-	ts_diff = timespec_sub(end, start);
+	ts_diff = timespec_diff_now(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
 
 	return NULL;
 }
 
-#define PAGE_SHIFT_4K  12
-#define PTES_PER_4K_PT 512
-
-static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
-				uint64_t vcpu_memory_bytes)
-{
-	struct kvm_vm *vm;
-	uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
-
-	/* Account for a few pages per-vCPU for stacks */
-	pages += DEFAULT_STACK_PGS * vcpus;
-
-	/*
-	 * Reserve twice the ammount of memory needed to map the test region and
-	 * the page table / stacks region, at 4k, for page tables. Do the
-	 * calculation with 4K page size: the smallest of all archs. (e.g., 64K
-	 * page size guest will need even less memory for page tables).
-	 */
-	pages += (2 * pages) / PTES_PER_4K_PT;
-	pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
-		 PTES_PER_4K_PT;
-	pages = vm_adjust_num_guest_pages(mode, pages);
-
-	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
-
-	vm = _vm_create(mode, pages, O_RDWR);
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-#ifdef __x86_64__
-	vm_create_irqchip(vm);
-#endif
-	return vm;
-}
-
 static int handle_uffd_page_request(int uffd, uint64_t addr)
 {
 	pid_t tid;
 	struct timespec start;
-	struct timespec end;
+	struct timespec ts_diff;
 	struct uffdio_copy copy;
 	int r;
 
@@ -186,7 +84,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr)
 
 	copy.src = (uint64_t)guest_data_prototype;
 	copy.dst = addr;
-	copy.len = host_page_size;
+	copy.len = perf_test_args.host_page_size;
 	copy.mode = 0;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
@@ -198,12 +96,12 @@ static int handle_uffd_page_request(int uffd, uint64_t addr)
 		return r;
 	}
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
+	ts_diff = timespec_diff_now(start);
 
 	PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
-		       timespec_to_ns(timespec_sub(end, start)));
+		       timespec_to_ns(ts_diff));
 	PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
-		       host_page_size, addr, tid);
+		       perf_test_args.host_page_size, addr, tid);
 
 	return 0;
 }
@@ -223,7 +121,8 @@ static void *uffd_handler_thread_fn(void *arg)
 	int pipefd = uffd_args->pipefd;
 	useconds_t delay = uffd_args->delay;
 	int64_t pages = 0;
-	struct timespec start, end, ts_diff;
+	struct timespec start;
+	struct timespec ts_diff;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 	while (!quit_uffd_thread) {
@@ -292,8 +191,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		pages++;
 	}
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
-	ts_diff = timespec_sub(end, start);
+	ts_diff = timespec_diff_now(start);
 	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
 		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
 		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
@@ -351,99 +249,54 @@ static int setup_demand_paging(struct kvm_vm *vm,
 }
 
 static void run_test(enum vm_guest_mode mode, bool use_uffd,
-		     useconds_t uffd_delay, int vcpus,
-		     uint64_t vcpu_memory_bytes)
+		     useconds_t uffd_delay)
 {
 	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
-	struct timespec start, end, ts_diff;
+	struct timespec start;
+	struct timespec ts_diff;
 	int *pipefds = NULL;
 	struct kvm_vm *vm;
-	uint64_t guest_num_pages;
 	int vcpu_id;
 	int r;
 
-	vm = create_vm(mode, vcpus, vcpu_memory_bytes);
-
-	guest_page_size = vm_get_page_size(vm);
-
-	TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0,
-		    "Guest memory size is not guest page size aligned.");
-
-	guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size;
-	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
-
-	/*
-	 * 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),
-		    "Requested more guest memory than address space allows.\n"
-		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
-		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
-		    vcpu_memory_bytes);
-
-	host_page_size = getpagesize();
-	TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0,
-		    "Guest memory size is not host page size aligned.");
+	vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
 
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      guest_page_size;
-	guest_test_phys_mem &= ~(host_page_size - 1);
+	perf_test_args.wr_fract = 1;
 
-#ifdef __s390x__
-	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
-#endif
-
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
-
-	/* Add an extra memory slot for testing demand paging */
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    guest_test_phys_mem,
-				    TEST_MEM_SLOT_INDEX,
-				    guest_num_pages, 0);
-
-	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
-
-	ucall_init(vm, NULL);
-
-	guest_data_prototype = malloc(host_page_size);
+	guest_data_prototype = malloc(perf_test_args.host_page_size);
 	TEST_ASSERT(guest_data_prototype,
 		    "Failed to allocate buffer for guest data pattern");
-	memset(guest_data_prototype, 0xAB, host_page_size);
+	memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size);
 
-	vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads));
+	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
+	add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
 	if (use_uffd) {
 		uffd_handler_threads =
-			malloc(vcpus * sizeof(*uffd_handler_threads));
+			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
 		TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
 
-		uffd_args = malloc(vcpus * sizeof(*uffd_args));
+		uffd_args = malloc(nr_vcpus * sizeof(*uffd_args));
 		TEST_ASSERT(uffd_args, "Memory allocation failed");
 
-		pipefds = malloc(sizeof(int) * vcpus * 2);
+		pipefds = malloc(sizeof(int) * nr_vcpus * 2);
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
-	}
-
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vm_paddr_t vcpu_gpa;
-		void *vcpu_hva;
 
-		vm_vcpu_add_default(vm, vcpu_id, guest_code);
+		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+			vm_paddr_t vcpu_gpa;
+			void *vcpu_hva;
 
-		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
-		PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+			vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size);
+			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+				       vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size);
 
-		/* Cache the HVA pointer of the region */
-		vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
+			/* Cache the HVA pointer of the region */
+			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
 
-		if (use_uffd) {
 			/*
 			 * Set up user fault fd to handle demand paging
 			 * requests.
@@ -456,53 +309,41 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
 						&uffd_handler_threads[vcpu_id],
 						pipefds[vcpu_id * 2],
 						uffd_delay, &uffd_args[vcpu_id],
-						vcpu_hva, vcpu_memory_bytes);
+						vcpu_hva, guest_percpu_mem_size);
 			if (r < 0)
 				exit(-r);
 		}
-
-#ifdef __x86_64__
-		vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
-#endif
-
-		vcpu_args[vcpu_id].vm = vm;
-		vcpu_args[vcpu_id].vcpu_id = vcpu_id;
-		vcpu_args[vcpu_id].gva = guest_test_virt_mem +
-					 (vcpu_id * vcpu_memory_bytes);
-		vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size;
 	}
 
 	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, host_page_size);
-	sync_global_to_guest(vm, guest_page_size);
-	sync_global_to_guest(vm, vcpu_args);
+	sync_global_to_guest(vm, perf_test_args);
 
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &vcpu_args[vcpu_id]);
+			       &perf_test_args.vcpu_args[vcpu_id]);
 	}
 
 	pr_info("Started all vCPUs\n");
 
 	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 		pthread_join(vcpu_threads[vcpu_id], NULL);
 		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
 	}
 
-	pr_info("All vCPU threads joined\n");
+	ts_diff = timespec_diff_now(start);
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
+	pr_info("All vCPU threads joined\n");
 
 	if (use_uffd) {
 		char c;
 
 		/* Tell the user fault fd handler threads to quit */
-		for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 			r = write(pipefds[vcpu_id * 2 + 1], &c, 1);
 			TEST_ASSERT(r == 1, "Unable to write to pipefd");
 
@@ -510,11 +351,11 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
 		}
 	}
 
-	ts_diff = timespec_sub(end, start);
 	pr_info("Total guest execution time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 	pr_info("Overall demand paging rate: %f pgs/sec\n",
-		guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+		perf_test_args.vcpu_args[0].pages * nr_vcpus /
+		((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
 
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
@@ -568,9 +409,8 @@ static void help(char *name)
 
 int main(int argc, char *argv[])
 {
+	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
 	bool mode_selected = false;
-	uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE;
-	int vcpus = 1;
 	unsigned int mode;
 	int opt, i;
 	bool use_uffd = false;
@@ -619,15 +459,12 @@ int main(int argc, char *argv[])
 				    "A negative UFFD delay is not supported.");
 			break;
 		case 'b':
-			vcpu_memory_bytes = parse_size(optarg);
+			guest_percpu_mem_size = parse_size(optarg);
 			break;
 		case 'v':
-			vcpus = atoi(optarg);
-			TEST_ASSERT(vcpus > 0,
-				    "Must have a positive number of vCPUs");
-			TEST_ASSERT(vcpus <= MAX_VCPUS,
-				    "This test does not currently support\n"
-				    "more than %d vCPUs.", MAX_VCPUS);
+			nr_vcpus = atoi(optarg);
+			TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
 			break;
 		case 'h':
 		default:
@@ -642,7 +479,7 @@ int main(int argc, char *argv[])
 		TEST_ASSERT(guest_modes[i].supported,
 			    "Guest mode ID %d (%s) not supported.",
 			    i, vm_guest_mode_string(i));
-		run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes);
+		run_test(i, use_uffd, uffd_delay);
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
new file mode 100644
index 000000000000..85c9b8f73142
--- /dev/null
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging performance test
+ *
+ * Based on dirty_log_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2020, Google, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
+#define TEST_HOST_LOOP_N		2UL
+
+/* Host variables */
+static bool host_quit;
+static uint64_t iteration;
+static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
+
+static void *vcpu_worker(void *data)
+{
+	int ret;
+	struct kvm_vm *vm = perf_test_args.vm;
+	uint64_t pages_count = 0;
+	struct kvm_run *run;
+	struct timespec start;
+	struct timespec ts_diff;
+	struct timespec total = (struct timespec){0};
+	struct timespec avg;
+	struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+	int vcpu_id = vcpu_args->vcpu_id;
+
+	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+	run = vcpu_state(vm, vcpu_id);
+
+	while (!READ_ONCE(host_quit)) {
+		uint64_t current_iteration = READ_ONCE(iteration);
+
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		ret = _vcpu_run(vm, vcpu_id);
+		ts_diff = timespec_diff_now(start);
+
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC,
+			    "Invalid guest sync status: exit_reason=%s\n",
+			    exit_reason_str(run->exit_reason));
+
+		pr_debug("Got sync event from vCPU %d\n", vcpu_id);
+		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+		pr_debug("vCPU %d updated last completed iteration to %lu\n",
+			 vcpu_id, vcpu_last_completed_iteration[vcpu_id]);
+
+		if (current_iteration) {
+			pages_count += vcpu_args->pages;
+			total = timespec_add(total, ts_diff);
+			pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n",
+				vcpu_id, current_iteration, ts_diff.tv_sec,
+				ts_diff.tv_nsec);
+		} else {
+			pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n",
+				vcpu_id, current_iteration, ts_diff.tv_sec,
+				ts_diff.tv_nsec);
+		}
+
+		while (current_iteration == READ_ONCE(iteration) &&
+		       !READ_ONCE(host_quit)) {}
+	}
+
+	avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]);
+	pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
+		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+	return NULL;
+}
+
+#ifdef USE_CLEAR_DIRTY_LOG
+static u64 dirty_log_manual_caps;
+#endif
+
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+		     uint64_t phys_offset, int wr_fract)
+{
+	pthread_t *vcpu_threads;
+	struct kvm_vm *vm;
+	unsigned long *bmap;
+	uint64_t guest_num_pages;
+	uint64_t host_num_pages;
+	int vcpu_id;
+	struct timespec start;
+	struct timespec ts_diff;
+	struct timespec get_dirty_log_total = (struct timespec){0};
+	struct timespec vcpu_dirty_total = (struct timespec){0};
+	struct timespec avg;
+#ifdef USE_CLEAR_DIRTY_LOG
+	struct kvm_enable_cap cap = {};
+	struct timespec clear_dirty_log_total = (struct timespec){0};
+#endif
+
+	vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+
+	perf_test_args.wr_fract = wr_fract;
+
+	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
+	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
+	bmap = bitmap_alloc(host_num_pages);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+	cap.args[0] = dirty_log_manual_caps;
+	vm_enable_cap(vm, &cap);
+#endif
+
+	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
+	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+
+	add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
+	sync_global_to_guest(vm, perf_test_args);
+
+	/* Start the iterations */
+	iteration = 0;
+	host_quit = false;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
+			       &perf_test_args.vcpu_args[vcpu_id]);
+	}
+
+	/* Allow the vCPU to populate memory */
+	pr_debug("Starting iteration %lu - Populating\n", iteration);
+	while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+		pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n",
+			iteration);
+
+	ts_diff = timespec_diff_now(start);
+	pr_info("Populate memory time: %ld.%.9lds\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	/* Enable dirty logging */
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+				KVM_MEM_LOG_DIRTY_PAGES);
+	ts_diff = timespec_diff_now(start);
+	pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	while (iteration < iterations) {
+		/*
+		 * Incrementing the iteration number will start the vCPUs
+		 * dirtying memory again.
+		 */
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		iteration++;
+
+		pr_debug("Starting iteration %lu\n", iteration);
+		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+			while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+				pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n",
+					 vcpu_id, iteration);
+		}
+
+		ts_diff = timespec_diff_now(start);
+		vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff);
+		pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n",
+			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+
+		ts_diff = timespec_diff_now(start);
+		get_dirty_log_total = timespec_add(get_dirty_log_total,
+						   ts_diff);
+		pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n",
+			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+				       host_num_pages);
+
+		ts_diff = timespec_diff_now(start);
+		clear_dirty_log_total = timespec_add(clear_dirty_log_total,
+						     ts_diff);
+		pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
+			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+#endif
+	}
+
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id], NULL);
+
+	/* Disable dirty logging */
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+	ts_diff = timespec_diff_now(start);
+	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	avg = timespec_div(get_dirty_log_total, iterations);
+	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+		iterations, get_dirty_log_total.tv_sec,
+		get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+	avg = timespec_div(clear_dirty_log_total, iterations);
+	pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+		iterations, clear_dirty_log_total.tv_sec,
+		clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+#endif
+
+	free(bmap);
+	free(vcpu_threads);
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+}
+
+struct guest_mode {
+	bool supported;
+	bool enabled;
+};
+static struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_init(mode, supported, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+static void help(char *name)
+{
+	int i;
+
+	puts("");
+	printf("usage: %s [-h] [-i iterations] [-p offset] "
+	       "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -p: specify guest physical test memory offset\n"
+	       "     Warning: a low offset can conflict with the loaded test code.\n");
+	printf(" -m: specify the guest mode ID to test "
+	       "(default: test all supported modes)\n"
+	       "     This option may be used multiple times.\n"
+	       "     Guest mode IDs:\n");
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
+		       guest_modes[i].supported ? " (supported)" : "");
+	}
+	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");
+	printf(" -f: specify the fraction of pages which should be written to\n"
+	       "     as opposed to simply read, in the form\n"
+	       "     1/<fraction of pages to write>.\n"
+	       "     (default: 1 i.e. all pages are written to.)\n");
+	printf(" -v: specify the number of vCPUs to run.\n");
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long iterations = TEST_HOST_LOOP_N;
+	bool mode_selected = false;
+	uint64_t phys_offset = 0;
+	unsigned int mode;
+	int opt, i;
+	int wr_fract = 1;
+
+#ifdef USE_CLEAR_DIRTY_LOG
+	dirty_log_manual_caps =
+		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+	if (!dirty_log_manual_caps) {
+		print_skip("KVM_CLEAR_DIRTY_LOG not available");
+		exit(KSFT_SKIP);
+	}
+	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+				  KVM_DIRTY_LOG_INITIALLY_SET);
+#endif
+
+#ifdef __x86_64__
+	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
+#endif
+#ifdef __aarch64__
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
+	guest_mode_init(VM_MODE_P40V48_64K, true, true);
+
+	{
+		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+		if (limit >= 52)
+			guest_mode_init(VM_MODE_P52V48_64K, true, true);
+		if (limit >= 48) {
+			guest_mode_init(VM_MODE_P48V48_4K, true, true);
+			guest_mode_init(VM_MODE_P48V48_64K, true, true);
+		}
+	}
+#endif
+#ifdef __s390x__
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
+#endif
+
+	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'p':
+			phys_offset = strtoull(optarg, NULL, 0);
+			break;
+		case 'm':
+			if (!mode_selected) {
+				for (i = 0; i < NUM_VM_MODES; ++i)
+					guest_modes[i].enabled = false;
+				mode_selected = true;
+			}
+			mode = strtoul(optarg, NULL, 10);
+			TEST_ASSERT(mode < NUM_VM_MODES,
+				    "Guest mode ID %d too big", mode);
+			guest_modes[mode].enabled = true;
+			break;
+		case 'b':
+			guest_percpu_mem_size = parse_size(optarg);
+			break;
+		case 'f':
+			wr_fract = atoi(optarg);
+			TEST_ASSERT(wr_fract >= 1,
+				    "Write fraction cannot be less than one");
+			break;
+		case 'v':
+			nr_vcpus = atoi(optarg);
+			TEST_ASSERT(nr_vcpus > 0,
+				    "Must have a positive number of vCPUs");
+			TEST_ASSERT(nr_vcpus <= MAX_VCPUS,
+				    "This test does not currently support\n"
+				    "more than %d vCPUs.", MAX_VCPUS);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations >= 2, "The test should have at least two iterations");
+
+	pr_info("Test iterations: %"PRIu64"\n",	iterations);
+
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		if (!guest_modes[i].enabled)
+			continue;
+		TEST_ASSERT(guest_modes[i].supported,
+			    "Guest mode ID %d (%s) not supported.",
+			    i, vm_guest_mode_string(i));
+		run_test(i, iterations, phys_offset, wr_fract);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 752ec158ac59..54da9cc20db4 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -128,6 +128,78 @@ static uint64_t host_dirty_count;
 static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
+enum log_mode_t {
+	/* Only use KVM_GET_DIRTY_LOG for logging */
+	LOG_MODE_DIRTY_LOG = 0,
+
+	/* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
+	LOG_MODE_CLEAR_LOG = 1,
+
+	LOG_MODE_NUM,
+
+	/* Run all supported modes */
+	LOG_MODE_ALL = LOG_MODE_NUM,
+};
+
+/* Mode of logging to test.  Default is to run all supported modes */
+static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
+/* Logging mode for current run */
+static enum log_mode_t host_log_mode;
+
+static bool clear_log_supported(void)
+{
+	return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+}
+
+static void clear_log_create_vm_done(struct kvm_vm *vm)
+{
+	struct kvm_enable_cap cap = {};
+	u64 manual_caps;
+
+	manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+	TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!");
+	manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+			KVM_DIRTY_LOG_INITIALLY_SET);
+	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+	cap.args[0] = manual_caps;
+	vm_enable_cap(vm, &cap);
+}
+
+static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					  void *bitmap, uint32_t num_pages)
+{
+	kvm_vm_get_dirty_log(vm, slot, bitmap);
+}
+
+static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					  void *bitmap, uint32_t num_pages)
+{
+	kvm_vm_get_dirty_log(vm, slot, bitmap);
+	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
+}
+
+struct log_mode {
+	const char *name;
+	/* Return true if this mode is supported, otherwise false */
+	bool (*supported)(void);
+	/* Hook when the vm creation is done (before vcpu creation) */
+	void (*create_vm_done)(struct kvm_vm *vm);
+	/* Hook to collect the dirty pages into the bitmap provided */
+	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
+				     void *bitmap, uint32_t num_pages);
+} log_modes[LOG_MODE_NUM] = {
+	{
+		.name = "dirty-log",
+		.collect_dirty_pages = dirty_log_collect_dirty_pages,
+	},
+	{
+		.name = "clear-log",
+		.supported = clear_log_supported,
+		.create_vm_done = clear_log_create_vm_done,
+		.collect_dirty_pages = clear_log_collect_dirty_pages,
+	},
+};
+
 /*
  * We use this bitmap to track some pages that should have its dirty
  * bit set in the _next_ iteration.  For example, if we detected the
@@ -137,6 +209,44 @@ static uint64_t host_track_next_count;
  */
 static unsigned long *host_bmap_track;
 
+static void log_modes_dump(void)
+{
+	int i;
+
+	printf("all");
+	for (i = 0; i < LOG_MODE_NUM; i++)
+		printf(", %s", log_modes[i].name);
+	printf("\n");
+}
+
+static bool log_mode_supported(void)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->supported)
+		return mode->supported();
+
+	return true;
+}
+
+static void log_mode_create_vm_done(struct kvm_vm *vm)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->create_vm_done)
+		mode->create_vm_done(vm);
+}
+
+static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					 void *bitmap, uint32_t num_pages)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	TEST_ASSERT(mode->collect_dirty_pages != NULL,
+		    "collect_dirty_pages() is required for any log mode!");
+	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
+}
+
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
@@ -195,7 +305,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 				    page);
 		}
 
-		if (test_bit_le(page, bmap)) {
+		if (test_and_clear_bit_le(page, bmap)) {
 			host_dirty_count++;
 			/*
 			 * If the bit is set, the value written onto
@@ -252,11 +362,12 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 #ifdef __x86_64__
 	vm_create_irqchip(vm);
 #endif
+	log_mode_create_vm_done(vm);
 	vm_vcpu_add_default(vm, vcpuid, guest_code);
 	return vm;
 }
@@ -264,10 +375,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 #define DIRTY_MEM_BITS 30 /* 1G */
 #define PAGE_SHIFT_4K  12
 
-#ifdef USE_CLEAR_DIRTY_LOG
-static u64 dirty_log_manual_caps;
-#endif
-
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		     unsigned long interval, uint64_t phys_offset)
 {
@@ -275,6 +382,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 
+	if (!log_mode_supported()) {
+		print_skip("Log mode '%s' not supported",
+			   log_modes[host_log_mode].name);
+		return;
+	}
+
 	/*
 	 * We reserve page table for 2 times of extra dirty mem which
 	 * will definitely cover the original (1G+) test range.  Here
@@ -317,14 +430,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-	struct kvm_enable_cap cap = {};
-
-	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
-	cap.args[0] = dirty_log_manual_caps;
-	vm_enable_cap(vm, &cap);
-#endif
-
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
 				    guest_test_phys_mem,
@@ -362,11 +467,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	while (iteration < iterations) {
 		/* Give the vcpu thread some time to dirty some pages */
 		usleep(interval * 1000);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-#ifdef USE_CLEAR_DIRTY_LOG
-		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
-				       host_num_pages);
-#endif
+		log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
+					     bmap, host_num_pages);
 		vm_dirty_log_verify(mode, bmap);
 		iteration++;
 		sync_global_to_guest(vm, iteration);
@@ -410,6 +512,9 @@ static void help(char *name)
 	       TEST_HOST_LOOP_INTERVAL);
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
+	printf(" -M: specify the host logging mode "
+	       "(default: run all log modes).  Supported modes: \n\t");
+	log_modes_dump();
 	printf(" -m: specify the guest mode ID to test "
 	       "(default: test all supported modes)\n"
 	       "     This option may be used multiple times.\n"
@@ -429,18 +534,7 @@ int main(int argc, char *argv[])
 	bool mode_selected = false;
 	uint64_t phys_offset = 0;
 	unsigned int mode;
-	int opt, i;
-
-#ifdef USE_CLEAR_DIRTY_LOG
-	dirty_log_manual_caps =
-		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
-	if (!dirty_log_manual_caps) {
-		print_skip("KVM_CLEAR_DIRTY_LOG not available");
-		exit(KSFT_SKIP);
-	}
-	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
-				  KVM_DIRTY_LOG_INITIALLY_SET);
-#endif
+	int opt, i, j;
 
 #ifdef __x86_64__
 	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
@@ -464,7 +558,7 @@ int main(int argc, char *argv[])
 	guest_mode_init(VM_MODE_P40V48_4K, true, true);
 #endif
 
-	while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
+	while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
 		switch (opt) {
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
@@ -486,6 +580,26 @@ int main(int argc, char *argv[])
 				    "Guest mode ID %d too big", mode);
 			guest_modes[mode].enabled = true;
 			break;
+		case 'M':
+			if (!strcmp(optarg, "all")) {
+				host_log_mode_option = LOG_MODE_ALL;
+				break;
+			}
+			for (i = 0; i < LOG_MODE_NUM; i++) {
+				if (!strcmp(optarg, log_modes[i].name)) {
+					pr_info("Setting log mode to: '%s'\n",
+						optarg);
+					host_log_mode_option = i;
+					break;
+				}
+			}
+			if (i == LOG_MODE_NUM) {
+				printf("Log mode '%s' invalid. Please choose "
+				       "from: ", optarg);
+				log_modes_dump();
+				exit(1);
+			}
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
@@ -507,7 +621,18 @@ int main(int argc, char *argv[])
 		TEST_ASSERT(guest_modes[i].supported,
 			    "Guest mode ID %d (%s) not supported.",
 			    i, vm_guest_mode_string(i));
-		run_test(i, iterations, interval, phys_offset);
+		if (host_log_mode_option == LOG_MODE_ALL) {
+			/* Run each log mode */
+			for (j = 0; j < LOG_MODE_NUM; j++) {
+				pr_info("Testing Log Mode '%s'\n",
+					log_modes[j].name);
+				host_log_mode = j;
+				run_test(i, iterations, interval, phys_offset);
+			}
+		} else {
+			host_log_mode = host_log_mode_option;
+			run_test(i, iterations, interval, phys_offset);
+		}
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 919e161dd289..7d29aa786959 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -63,9 +63,11 @@ enum vm_mem_backing_src_type {
 
 int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+		    struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
 
 struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
 void kvm_vm_free(struct kvm_vm *vmp);
 void kvm_vm_restart(struct kvm_vm *vmp, int perm);
 void kvm_vm_release(struct kvm_vm *vmp);
@@ -149,6 +151,7 @@ void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_guest_debug *debug);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 
@@ -294,6 +297,8 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
 	memcpy(&(g), _p, sizeof(g));				\
 })
 
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
+
 /* Common ucalls */
 enum {
 	UCALL_NONE,
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
new file mode 100644
index 000000000000..2618052057b1
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tools/testing/selftests/kvm/include/perf_test_util.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
+#define SELFTEST_KVM_PERF_TEST_UTIL_H
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define MAX_VCPUS 512
+
+#define PAGE_SHIFT_4K  12
+#define PTES_PER_4K_PT 512
+
+#define TEST_MEM_SLOT_INDEX		1
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM		0xc0000000
+
+#define DEFAULT_PER_VCPU_MEM_SIZE	(1 << 30) /* 1G */
+
+/*
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
+ */
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
+/* Number of VCPUs for the test */
+static int nr_vcpus = 1;
+
+struct vcpu_args {
+	uint64_t gva;
+	uint64_t pages;
+
+	/* Only used by the host userspace part of the vCPU thread */
+	int vcpu_id;
+};
+
+struct perf_test_args {
+	struct kvm_vm *vm;
+	uint64_t host_page_size;
+	uint64_t guest_page_size;
+	int wr_fract;
+
+	struct vcpu_args vcpu_args[MAX_VCPUS];
+};
+
+static struct perf_test_args perf_test_args;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+	struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	uint64_t gva;
+	uint64_t pages;
+	int i;
+
+	/* Make sure vCPU args data structure is not corrupt. */
+	GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+	gva = vcpu_args->gva;
+	pages = vcpu_args->pages;
+
+	while (true) {
+		for (i = 0; i < pages; i++) {
+			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+
+			if (i % perf_test_args.wr_fract == 0)
+				*(uint64_t *)addr = 0x0123456789ABCDEF;
+			else
+				READ_ONCE(*(uint64_t *)addr);
+		}
+
+		GUEST_SYNC(1);
+	}
+}
+
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
+				uint64_t vcpu_memory_bytes)
+{
+	struct kvm_vm *vm;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
+	uint64_t guest_num_pages;
+
+	/* Account for a few pages per-vCPU for stacks */
+	pages += DEFAULT_STACK_PGS * vcpus;
+
+	/*
+	 * Reserve twice the ammount of memory needed to map the test region and
+	 * the page table / stacks region, at 4k, for page tables. Do the
+	 * calculation with 4K page size: the smallest of all archs. (e.g., 64K
+	 * page size guest will need even less memory for page tables).
+	 */
+	pages += (2 * pages) / PTES_PER_4K_PT;
+	pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
+		 PTES_PER_4K_PT;
+	pages = vm_adjust_num_guest_pages(mode, pages);
+
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+	vm = vm_create(mode, pages, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+
+	perf_test_args.vm = vm;
+	perf_test_args.guest_page_size = vm_get_page_size(vm);
+	perf_test_args.host_page_size = getpagesize();
+
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+		    "Guest memory size is not guest page size aligned.");
+
+	guest_num_pages = (vcpus * vcpu_memory_bytes) /
+			  perf_test_args.guest_page_size;
+	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
+	/*
+	 * 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),
+		    "Requested more guest memory than address space allows.\n"
+		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
+		    vcpu_memory_bytes);
+
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+		    "Guest memory size is not host page size aligned.");
+
+	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+			      perf_test_args.guest_page_size;
+	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+
+#ifdef __s390x__
+	/* Align to 1M (segment size) */
+	guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+
+	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+	/* Add an extra memory slot for testing */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    guest_test_phys_mem,
+				    TEST_MEM_SLOT_INDEX,
+				    guest_num_pages, 0);
+
+	/* Do mapping for the demand paging memory slot */
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+	ucall_init(vm, NULL);
+
+	return vm;
+}
+
+static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+	vm_paddr_t vcpu_gpa;
+	struct vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+
+		vm_vcpu_add_default(vm, vcpu_id, guest_code);
+
+#ifdef __x86_64__
+		vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
+#endif
+
+		vcpu_args->vcpu_id = vcpu_id;
+		vcpu_args->gva = guest_test_virt_mem +
+				 (vcpu_id * vcpu_memory_bytes);
+		vcpu_args->pages = vcpu_memory_bytes /
+				   perf_test_args.guest_page_size;
+
+		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+	}
+}
+
+#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 5eb01bf51b86..ffffa560436b 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -64,5 +64,7 @@ int64_t timespec_to_ns(struct timespec ts);
 struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
 struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
 struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_diff_now(struct timespec start);
+struct timespec timespec_div(struct timespec ts, int divisor);
 
 #endif /* SELFTEST_KVM_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 82b7fe16a824..8e61340b3911 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -36,6 +36,8 @@
 #define X86_CR4_SMAP		(1ul << 21)
 #define X86_CR4_PKE		(1ul << 22)
 
+#define UNEXPECTED_VECTOR_PORT 0xfff0u
+
 /* General Registers in 64-Bit Mode */
 struct gpr64_regs {
 	u64 rax;
@@ -59,7 +61,7 @@ struct gpr64_regs {
 struct desc64 {
 	uint16_t limit0;
 	uint16_t base0;
-	unsigned base1:8, s:1, type:4, dpl:2, p:1;
+	unsigned base1:8, type:4, s:1, dpl:2, p:1;
 	unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
 	uint32_t base3;
 	uint32_t zero1;
@@ -239,6 +241,11 @@ static inline struct desc_ptr get_idt(void)
 	return idt;
 }
 
+static inline void outl(uint16_t port, uint32_t value)
+{
+	__asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value));
+}
+
 #define SET_XMM(__var, __xmm) \
 	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
 
@@ -338,6 +345,35 @@ uint32_t kvm_get_cpuid_max_basic(void);
 uint32_t kvm_get_cpuid_max_extended(void);
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
 
+struct ex_regs {
+	uint64_t rax, rcx, rdx, rbx;
+	uint64_t rbp, rsi, rdi;
+	uint64_t r8, r9, r10, r11;
+	uint64_t r12, r13, r14, r15;
+	uint64_t vector;
+	uint64_t error_code;
+	uint64_t rip;
+	uint64_t cs;
+	uint64_t rflags;
+};
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+			void (*handler)(struct ex_regs *));
+
+/*
+ * set_cpuid() - overwrites a matching cpuid entry with the provided value.
+ *		 matches based on ent->function && ent->index. returns true
+ *		 if a match was found and successfully overwritten.
+ * @cpuid: the kvm cpuid list to modify.
+ * @ent: cpuid entry to insert
+ */
+bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent);
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+		       uint64_t a3);
+
 /*
  * Basic CPU control in CR0
  */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 2afa6618b396..d6c32c328e9a 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -350,3 +350,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
 
 	va_end(ap);
 }
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index c8e0ec20d3bf..2f37b90ee1a9 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -94,6 +94,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_MMIO &&
 	    run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
 		vm_vaddr_t gva;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 3327cebc1095..126c6727a6b0 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -86,6 +86,34 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap)
 	return ret;
 }
 
+/* VCPU Enable Capability
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpu_id - VCPU
+ *   cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
+ *
+ * Enables a capability (KVM_CAP_*) on the VCPU.
+ */
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+		    struct kvm_enable_cap *cap)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpu_id);
+	int r;
+
+	TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id);
+
+	r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap);
+	TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n"
+			"  rc: %i, errno: %i", r, errno);
+
+	return r;
+}
+
 static void vm_open(struct kvm_vm *vm, int perm)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -152,7 +180,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params)
  * descriptor to control the created VM is created with the permissions
  * given by perm (e.g. O_RDWR).
  */
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 {
 	struct kvm_vm *vm;
 
@@ -243,11 +271,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
-{
-	return _vm_create(mode, phy_pages, perm);
-}
-
 /*
  * VM Restart
  *
@@ -1204,6 +1227,9 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	do {
 		rc = ioctl(vcpu->fd, KVM_RUN, NULL);
 	} while (rc == -1 && errno == EINTR);
+
+	assert_on_unhandled_exception(vm, vcpuid);
+
 	return rc;
 }
 
@@ -1261,6 +1287,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 }
 
 /*
+ * VM VCPU Get Reg List
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *
+ * Output Args:
+ *   None
+ *
+ * Return:
+ *   A pointer to an allocated struct kvm_reg_list
+ *
+ * Get the list of guest registers which are supported for
+ * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls
+ */
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list;
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, &reg_list_n);
+	TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0");
+	reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64));
+	reg_list->n = reg_list_n.n;
+	vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list);
+	return reg_list;
+}
+
+/*
  * VM VCPU Regs Get
  *
  * Input Args:
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 2ef446520748..f07d383d03a1 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -50,6 +50,8 @@ struct kvm_vm {
 	vm_paddr_t pgd;
 	vm_vaddr_t gdt;
 	vm_vaddr_t tss;
+	vm_vaddr_t idt;
+	vm_vaddr_t handlers;
 };
 
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index a88c5d665725..7349bb2e1a24 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -241,3 +241,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 	fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
 		indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);
 }
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c
index fd589dc9bfab..9d3b0f15249a 100644
--- a/tools/testing/selftests/kvm/lib/s390x/ucall.c
+++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c
@@ -38,6 +38,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_S390_SIEIC &&
 	    run->s390_sieic.icptcode == 4 &&
 	    (run->s390_sieic.ipa >> 8) == 0x83 &&    /* 0x83 means DIAGNOSE */
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 689e97c27ee2..8e04c0b1608e 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -4,10 +4,13 @@
  *
  * Copyright (C) 2020, Google LLC.
  */
-#include <stdlib.h>
+
+#include <assert.h>
 #include <ctype.h>
 #include <limits.h>
-#include <assert.h>
+#include <stdlib.h>
+#include <time.h>
+
 #include "test_util.h"
 
 /*
@@ -81,6 +84,21 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2)
 	return timespec_add_ns((struct timespec){0}, ns1 - ns2);
 }
 
+struct timespec timespec_diff_now(struct timespec start)
+{
+	struct timespec end;
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	return timespec_sub(end, start);
+}
+
+struct timespec timespec_div(struct timespec ts, int divisor)
+{
+	int64_t ns = timespec_to_ns(ts) / divisor;
+
+	return timespec_add_ns((struct timespec){0}, ns);
+}
+
 void print_skip(const char *fmt, ...)
 {
 	va_list ap;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
new file mode 100644
index 000000000000..aaf7bc7d2ce1
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
@@ -0,0 +1,81 @@
+handle_exception:
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+	push %r11
+	push %r10
+	push %r9
+	push %r8
+
+	push %rdi
+	push %rsi
+	push %rbp
+	push %rbx
+	push %rdx
+	push %rcx
+	push %rax
+	mov %rsp, %rdi
+
+	call route_exception
+
+	pop %rax
+	pop %rcx
+	pop %rdx
+	pop %rbx
+	pop %rbp
+	pop %rsi
+	pop %rdi
+	pop %r8
+	pop %r9
+	pop %r10
+	pop %r11
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+
+	/* Discard vector and error code. */
+	add $16, %rsp
+	iretq
+
+/*
+ * Build the handle_exception wrappers which push the vector/error code on the
+ * stack and an array of pointers to those wrappers.
+ */
+.pushsection .rodata
+.globl idt_handlers
+idt_handlers:
+.popsection
+
+.macro HANDLERS has_error from to
+	vector = \from
+	.rept \to - \from + 1
+	.align 8
+
+	/* Fetch current address and append it to idt_handlers. */
+	current_handler = .
+.pushsection .rodata
+.quad current_handler
+.popsection
+
+	.if ! \has_error
+	pushq $0
+	.endif
+	pushq $vector
+	jmp handle_exception
+	vector = vector + 1
+	.endr
+.endm
+
+.global idt_handler_code
+idt_handler_code:
+	HANDLERS has_error=0 from=0  to=7
+	HANDLERS has_error=1 from=8  to=8
+	HANDLERS has_error=0 from=9  to=9
+	HANDLERS has_error=1 from=10 to=14
+	HANDLERS has_error=0 from=15 to=16
+	HANDLERS has_error=1 from=17 to=17
+	HANDLERS has_error=0 from=18 to=255
+
+.section        .note.GNU-stack, "", %progbits
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index f6eb34eaa0d2..d10c5c05bdf0 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -12,9 +12,18 @@
 #include "../kvm_util_internal.h"
 #include "processor.h"
 
+#ifndef NUM_INTERRUPTS
+#define NUM_INTERRUPTS 256
+#endif
+
+#define DEFAULT_CODE_SELECTOR 0x8
+#define DEFAULT_DATA_SELECTOR 0x10
+
 /* Minimum physical address used for virtual translation tables. */
 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
 
+vm_vaddr_t exception_handlers;
+
 /* Virtual translation table structure declarations */
 struct pageMapL4Entry {
 	uint64_t present:1;
@@ -392,11 +401,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
 	desc->limit0 = segp->limit & 0xFFFF;
 	desc->base0 = segp->base & 0xFFFF;
 	desc->base1 = segp->base >> 16;
-	desc->s = segp->s;
 	desc->type = segp->type;
+	desc->s = segp->s;
 	desc->dpl = segp->dpl;
 	desc->p = segp->present;
 	desc->limit1 = segp->limit >> 16;
+	desc->avl = segp->avl;
 	desc->l = segp->l;
 	desc->db = segp->db;
 	desc->g = segp->g;
@@ -556,9 +566,9 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m
 		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
 
 		kvm_seg_set_unusable(&sregs.ldt);
-		kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
+		kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs);
+		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds);
+		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es);
 		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
 		break;
 
@@ -1118,3 +1128,131 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 		*va_bits = (entry->eax >> 8) & 0xff;
 	}
 }
+
+struct idt_entry {
+	uint16_t offset0;
+	uint16_t selector;
+	uint16_t ist : 3;
+	uint16_t : 5;
+	uint16_t type : 4;
+	uint16_t : 1;
+	uint16_t dpl : 2;
+	uint16_t p : 1;
+	uint16_t offset1;
+	uint32_t offset2; uint32_t reserved;
+};
+
+static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
+			  int dpl, unsigned short selector)
+{
+	struct idt_entry *base =
+		(struct idt_entry *)addr_gva2hva(vm, vm->idt);
+	struct idt_entry *e = &base[vector];
+
+	memset(e, 0, sizeof(*e));
+	e->offset0 = addr;
+	e->selector = selector;
+	e->ist = 0;
+	e->type = 14;
+	e->dpl = dpl;
+	e->p = 1;
+	e->offset1 = addr >> 16;
+	e->offset2 = addr >> 32;
+}
+
+void kvm_exit_unexpected_vector(uint32_t value)
+{
+	outl(UNEXPECTED_VECTOR_PORT, value);
+}
+
+void route_exception(struct ex_regs *regs)
+{
+	typedef void(*handler)(struct ex_regs *);
+	handler *handlers = (handler *)exception_handlers;
+
+	if (handlers && handlers[regs->vector]) {
+		handlers[regs->vector](regs);
+		return;
+	}
+
+	kvm_exit_unexpected_vector(regs->vector);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+	extern void *idt_handlers;
+	int i;
+
+	vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0);
+	vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0);
+	/* Handlers have the same address in both address spaces.*/
+	for (i = 0; i < NUM_INTERRUPTS; i++)
+		set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0,
+			DEFAULT_CODE_SELECTOR);
+}
+
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_sregs sregs;
+
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+	sregs.idt.base = vm->idt;
+	sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+	sregs.gdt.base = vm->gdt;
+	sregs.gdt.limit = getpagesize() - 1;
+	kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs);
+	vcpu_sregs_set(vm, vcpuid, &sregs);
+	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+			 void (*handler)(struct ex_regs *))
+{
+	vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
+
+	handlers[vector] = (vm_vaddr_t)handler;
+}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO
+		&& vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT
+		&& vcpu_state(vm, vcpuid)->io.size == 4) {
+		/* Grab pointer to io data */
+		uint32_t *data = (void *)vcpu_state(vm, vcpuid)
+			+ vcpu_state(vm, vcpuid)->io.data_offset;
+
+		TEST_ASSERT(false,
+			    "Unexpected vectored event in guest (vector:0x%x)",
+			    *data);
+	}
+}
+
+bool set_cpuid(struct kvm_cpuid2 *cpuid,
+	       struct kvm_cpuid_entry2 *ent)
+{
+	int i;
+
+	for (i = 0; i < cpuid->nent; i++) {
+		struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+		if (cur->function != ent->function || cur->index != ent->index)
+			continue;
+
+		memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2));
+		return true;
+	}
+
+	return false;
+}
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+		       uint64_t a3)
+{
+	uint64_t r;
+
+	asm volatile("vmcall"
+		     : "=a"(r)
+		     : "b"(a0), "c"(a1), "d"(a2), "S"(a3));
+	return r;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
index da4d89ad5419..a3489973e290 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
@@ -40,6 +40,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
 		struct kvm_regs regs;
 
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
new file mode 100644
index 000000000000..b10a27485bad
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM paravirtual feature disablement
+ */
+#include <asm/kvm_para.h>
+#include <linux/kvm_para.h>
+#include <stdint.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+extern unsigned char rdmsr_start;
+extern unsigned char rdmsr_end;
+
+static u64 do_rdmsr(u32 idx)
+{
+	u32 lo, hi;
+
+	asm volatile("rdmsr_start: rdmsr;"
+		     "rdmsr_end:"
+		     : "=a"(lo), "=c"(hi)
+		     : "c"(idx));
+
+	return (((u64) hi) << 32) | lo;
+}
+
+extern unsigned char wrmsr_start;
+extern unsigned char wrmsr_end;
+
+static void do_wrmsr(u32 idx, u64 val)
+{
+	u32 lo, hi;
+
+	lo = val;
+	hi = val >> 32;
+
+	asm volatile("wrmsr_start: wrmsr;"
+		     "wrmsr_end:"
+		     : : "a"(lo), "c"(idx), "d"(hi));
+}
+
+static int nr_gp;
+
+static void guest_gp_handler(struct ex_regs *regs)
+{
+	unsigned char *rip = (unsigned char *)regs->rip;
+	bool r, w;
+
+	r = rip == &rdmsr_start;
+	w = rip == &wrmsr_start;
+	GUEST_ASSERT(r || w);
+
+	nr_gp++;
+
+	if (r)
+		regs->rip = (uint64_t)&rdmsr_end;
+	else
+		regs->rip = (uint64_t)&wrmsr_end;
+}
+
+struct msr_data {
+	uint32_t idx;
+	const char *name;
+};
+
+#define TEST_MSR(msr) { .idx = msr, .name = #msr }
+#define UCALL_PR_MSR 0xdeadbeef
+#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr)
+
+/*
+ * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or
+ * written, as the KVM_CPUID_FEATURES leaf is cleared.
+ */
+static struct msr_data msrs_to_test[] = {
+	TEST_MSR(MSR_KVM_SYSTEM_TIME),
+	TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW),
+	TEST_MSR(MSR_KVM_WALL_CLOCK),
+	TEST_MSR(MSR_KVM_WALL_CLOCK_NEW),
+	TEST_MSR(MSR_KVM_ASYNC_PF_EN),
+	TEST_MSR(MSR_KVM_STEAL_TIME),
+	TEST_MSR(MSR_KVM_PV_EOI_EN),
+	TEST_MSR(MSR_KVM_POLL_CONTROL),
+	TEST_MSR(MSR_KVM_ASYNC_PF_INT),
+	TEST_MSR(MSR_KVM_ASYNC_PF_ACK),
+};
+
+static void test_msr(struct msr_data *msr)
+{
+	PR_MSR(msr);
+	do_rdmsr(msr->idx);
+	GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+
+	nr_gp = 0;
+	do_wrmsr(msr->idx, 0);
+	GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+	nr_gp = 0;
+}
+
+struct hcall_data {
+	uint64_t nr;
+	const char *name;
+};
+
+#define TEST_HCALL(hc) { .nr = hc, .name = #hc }
+#define UCALL_PR_HCALL 0xdeadc0de
+#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc)
+
+/*
+ * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding
+ * features have been cleared in KVM_CPUID_FEATURES.
+ */
+static struct hcall_data hcalls_to_test[] = {
+	TEST_HCALL(KVM_HC_KICK_CPU),
+	TEST_HCALL(KVM_HC_SEND_IPI),
+	TEST_HCALL(KVM_HC_SCHED_YIELD),
+};
+
+static void test_hcall(struct hcall_data *hc)
+{
+	uint64_t r;
+
+	PR_HCALL(hc);
+	r = kvm_hypercall(hc->nr, 0, 0, 0, 0);
+	GUEST_ASSERT(r == -KVM_ENOSYS);
+}
+
+static void guest_main(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) {
+		test_msr(&msrs_to_test[i]);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) {
+		test_hcall(&hcalls_to_test[i]);
+	}
+
+	GUEST_DONE();
+}
+
+static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid)
+{
+	struct kvm_cpuid_entry2 ent = {0};
+
+	ent.function = KVM_CPUID_FEATURES;
+	TEST_ASSERT(set_cpuid(cpuid, &ent),
+		    "failed to clear KVM_CPUID_FEATURES leaf");
+}
+
+static void pr_msr(struct ucall *uc)
+{
+	struct msr_data *msr = (struct msr_data *)uc->args[0];
+
+	pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx);
+}
+
+static void pr_hcall(struct ucall *uc)
+{
+	struct hcall_data *hc = (struct hcall_data *)uc->args[0];
+
+	pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr);
+}
+
+static void handle_abort(struct ucall *uc)
+{
+	TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0],
+		  __FILE__, uc->args[1]);
+}
+
+#define VCPU_ID 0
+
+static void enter_guest(struct kvm_vm *vm)
+{
+	struct kvm_run *run;
+	struct ucall uc;
+	int r;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	while (true) {
+		r = _vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(!r, "vcpu_run failed: %d\n", r);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "unexpected exit reason: %u (%s)",
+			    run->exit_reason, exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_PR_MSR:
+			pr_msr(&uc);
+			break;
+		case UCALL_PR_HCALL:
+			pr_hcall(&uc);
+			break;
+		case UCALL_ABORT:
+			handle_abort(&uc);
+			return;
+		case UCALL_DONE:
+			return;
+		}
+	}
+}
+
+int main(void)
+{
+	struct kvm_enable_cap cap = {0};
+	struct kvm_cpuid2 *best;
+	struct kvm_vm *vm;
+
+	if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) {
+		pr_info("will skip kvm paravirt restriction tests.\n");
+		return 0;
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+
+	cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID;
+	cap.args[0] = 1;
+	vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+	best = kvm_get_supported_cpuid();
+	clear_kvm_cpuid_features(best);
+	vcpu_set_cpuid(vm, VCPU_ID, best);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+
+	enter_guest(vm);
+	kvm_vm_free(vm);
+}