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

Pull kvm updates from Paolo Bonzini:
 "This is a large update by KVM standards, including AMD PSP (Platform
  Security Processor, aka "AMD Secure Technology") and ARM CoreSight
  (debug and trace) changes.

  ARM:

   - CoreSight: Add support for ETE and TRBE

   - Stage-2 isolation for the host kernel when running in protected
     mode

   - Guest SVE support when running in nVHE mode

   - Force W^X hypervisor mappings in nVHE mode

   - ITS save/restore for guests using direct injection with GICv4.1

   - nVHE panics now produce readable backtraces

   - Guest support for PTP using the ptp_kvm driver

   - Performance improvements in the S2 fault handler

  x86:

   - AMD PSP driver changes

   - Optimizations and cleanup of nested SVM code

   - AMD: Support for virtual SPEC_CTRL

   - Optimizations of the new MMU code: fast invalidation, zap under
     read lock, enable/disably dirty page logging under read lock

   - /dev/kvm API for AMD SEV live migration (guest API coming soon)

   - support SEV virtual machines sharing the same encryption context

   - support SGX in virtual machines

   - add a few more statistics

   - improved directed yield heuristics

   - Lots and lots of cleanups

  Generic:

   - Rework of MMU notifier interface, simplifying and optimizing the
     architecture-specific code

   - a handful of "Get rid of oprofile leftovers" patches

   - Some selftests improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (379 commits)
  KVM: selftests: Speed up set_memory_region_test
  selftests: kvm: Fix the check of return value
  KVM: x86: Take advantage of kvm_arch_dy_has_pending_interrupt()
  KVM: SVM: Skip SEV cache flush if no ASIDs have been used
  KVM: SVM: Remove an unnecessary prototype declaration of sev_flush_asids()
  KVM: SVM: Drop redundant svm_sev_enabled() helper
  KVM: SVM: Move SEV VMCB tracking allocation to sev.c
  KVM: SVM: Explicitly check max SEV ASID during sev_hardware_setup()
  KVM: SVM: Unconditionally invoke sev_hardware_teardown()
  KVM: SVM: Enable SEV/SEV-ES functionality by default (when supported)
  KVM: SVM: Condition sev_enabled and sev_es_enabled on CONFIG_KVM_AMD_SEV=y
  KVM: SVM: Append "_enabled" to module-scoped SEV/SEV-ES control variables
  KVM: SEV: Mask CPUID[0x8000001F].eax according to supported features
  KVM: SVM: Move SEV module params/variables to sev.c
  KVM: SVM: Disable SEV/SEV-ES if NPT is disabled
  KVM: SVM: Free sev_asid_bitmap during init if SEV setup fails
  KVM: SVM: Zero out the VMCB array used to track SEV ASID association
  x86/sev: Drop redundant and potentially misleading 'sev_enabled'
  KVM: x86: Move reverse CPUID helpers to separate header file
  KVM: x86: Rename GPR accessors to make mode-aware variants the defaults
  ...

13 files changed, 1459 insertions, 78 deletions

diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h
index e4732d3c2998..4f3d5aaa11f5 100644
--- a/tools/include/asm-generic/hugetlb_encode.h
+++ b/tools/include/asm-generic/hugetlb_encode.h
@@ -20,13 +20,16 @@
 #define HUGETLB_FLAG_ENCODE_SHIFT	26
 #define HUGETLB_FLAG_ENCODE_MASK	0x3f
 
+#define HUGETLB_FLAG_ENCODE_16KB	(14 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_64KB	(16 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_512KB	(19 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_1MB		(20 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_2MB		(21 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_8MB		(23 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_16MB	(24 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_32MB	(25 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_256MB	(28 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512MB	(29 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_1GB		(30 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_2GB		(31 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_16GB	(34 << HUGETLB_FLAG_ENCODE_SHIFT)
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 7bd7e776c266..bd83158e0e0b 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /aarch64/get-reg-list
 /aarch64/get-reg-list-sve
+/aarch64/vgic_init
 /s390x/memop
 /s390x/resets
 /s390x/sync_regs_test
@@ -38,6 +39,7 @@
 /dirty_log_perf_test
 /hardware_disable_test
 /kvm_create_max_vcpus
+/kvm_page_table_test
 /memslot_modification_stress_test
 /set_memory_region_test
 /steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index cb95b5bace7b..e439d027939d 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -72,16 +72,19 @@ TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
 TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_x86_64 += kvm_page_table_test
 TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
+TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_aarch64 += kvm_page_table_test
 TEST_GEN_PROGS_aarch64 += set_memory_region_test
 TEST_GEN_PROGS_aarch64 += steal_time
 
@@ -91,6 +94,7 @@ TEST_GEN_PROGS_s390x += s390x/sync_regs_test
 TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
+TEST_GEN_PROGS_s390x += kvm_page_table_test
 TEST_GEN_PROGS_s390x += set_memory_region_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c
new file mode 100644
index 000000000000..623f31a14326
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c
@@ -0,0 +1,551 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * vgic init sequence tests
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#define _GNU_SOURCE
+#include <linux/kernel.h>
+#include <sys/syscall.h>
+#include <asm/kvm.h>
+#include <asm/kvm_para.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define NR_VCPUS		4
+
+#define REDIST_REGION_ATTR_ADDR(count, base, flags, index) (((uint64_t)(count) << 52) | \
+	((uint64_t)((base) >> 16) << 16) | ((uint64_t)(flags) << 12) | index)
+#define REG_OFFSET(vcpu, offset) (((uint64_t)vcpu << 32) | offset)
+
+#define GICR_TYPER 0x8
+
+struct vm_gic {
+	struct kvm_vm *vm;
+	int gic_fd;
+};
+
+static int max_ipa_bits;
+
+/* helper to access a redistributor register */
+static int access_redist_reg(int gicv3_fd, int vcpu, int offset,
+			     uint32_t *val, bool write)
+{
+	uint64_t attr = REG_OFFSET(vcpu, offset);
+
+	return _kvm_device_access(gicv3_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS,
+				  attr, val, write);
+}
+
+/* dummy guest code */
+static void guest_code(void)
+{
+	GUEST_SYNC(0);
+	GUEST_SYNC(1);
+	GUEST_SYNC(2);
+	GUEST_DONE();
+}
+
+/* we don't want to assert on run execution, hence that helper */
+static int run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	ucall_init(vm, NULL);
+	int ret = _vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL);
+	if (ret)
+		return -errno;
+	return 0;
+}
+
+static struct vm_gic vm_gic_create(void)
+{
+	struct vm_gic v;
+
+	v.vm = vm_create_default_with_vcpus(NR_VCPUS, 0, 0, guest_code, NULL);
+	v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+
+	return v;
+}
+
+static void vm_gic_destroy(struct vm_gic *v)
+{
+	close(v->gic_fd);
+	kvm_vm_free(v->vm);
+}
+
+/**
+ * Helper routine that performs KVM device tests in general and
+ * especially ARM_VGIC_V3 ones. Eventually the ARM_VGIC_V3
+ * device gets created, a legacy RDIST region is set at @0x0
+ * and a DIST region is set @0x60000
+ */
+static void subtest_dist_rdist(struct vm_gic *v)
+{
+	int ret;
+	uint64_t addr;
+
+	/* Check existing group/attributes */
+	kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			      KVM_VGIC_V3_ADDR_TYPE_DIST);
+
+	kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			      KVM_VGIC_V3_ADDR_TYPE_REDIST);
+
+	/* check non existing attribute */
+	ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, 0);
+	TEST_ASSERT(ret && errno == ENXIO, "attribute not supported");
+
+	/* misaligned DIST and REDIST address settings */
+	addr = 0x1000;
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "GICv3 dist base not 64kB aligned");
+
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "GICv3 redist base not 64kB aligned");
+
+	/* out of range address */
+	if (max_ipa_bits) {
+		addr = 1ULL << max_ipa_bits;
+		ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+					 KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true);
+		TEST_ASSERT(ret && errno == E2BIG, "dist address beyond IPA limit");
+
+		ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+					 KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+		TEST_ASSERT(ret && errno == E2BIG, "redist address beyond IPA limit");
+	}
+
+	/* set REDIST base address @0x0*/
+	addr = 0x00000;
+	kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+
+	/* Attempt to create a second legacy redistributor region */
+	addr = 0xE0000;
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+	TEST_ASSERT(ret && errno == EEXIST, "GICv3 redist base set again");
+
+	/* Attempt to mix legacy and new redistributor regions */
+	addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 0, 0);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "attempt to mix GICv3 REDIST and REDIST_REGION");
+
+	/*
+	 * Set overlapping DIST / REDIST, cannot be detected here. Will be detected
+	 * on first vcpu run instead.
+	 */
+	addr = 3 * 2 * 0x10000;
+	kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_DIST,
+			  &addr, true);
+}
+
+/* Test the new REDIST region API */
+static void subtest_redist_regions(struct vm_gic *v)
+{
+	uint64_t addr, expected_addr;
+	int ret;
+
+	ret = kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				     KVM_VGIC_V3_ADDR_TYPE_REDIST);
+	TEST_ASSERT(!ret, "Multiple redist regions advertised");
+
+	addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 2, 0);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "redist region attr value with flags != 0");
+
+	addr = REDIST_REGION_ATTR_ADDR(0, 0x100000, 0, 0);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "redist region attr value with count== 0");
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 1);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL,
+		    "attempt to register the first rdist region with index != 0");
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x201000, 0, 1);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "rdist region with misaligned address");
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 0);
+	kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 1);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "register an rdist region with already used index");
+
+	addr = REDIST_REGION_ATTR_ADDR(1, 0x210000, 0, 2);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL,
+		    "register an rdist region overlapping with another one");
+
+	addr = REDIST_REGION_ATTR_ADDR(1, 0x240000, 0, 2);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "register redist region with index not +1");
+
+	addr = REDIST_REGION_ATTR_ADDR(1, 0x240000, 0, 1);
+	kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	addr = REDIST_REGION_ATTR_ADDR(1, 1ULL << max_ipa_bits, 0, 2);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == E2BIG,
+		    "register redist region with base address beyond IPA range");
+
+	addr = 0x260000;
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL,
+		    "Mix KVM_VGIC_V3_ADDR_TYPE_REDIST and REDIST_REGION");
+
+	/*
+	 * Now there are 2 redist regions:
+	 * region 0 @ 0x200000 2 redists
+	 * region 1 @ 0x240000 1 redist
+	 * Attempt to read their characteristics
+	 */
+
+	addr = REDIST_REGION_ATTR_ADDR(0, 0, 0, 0);
+	expected_addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 0);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, false);
+	TEST_ASSERT(!ret && addr == expected_addr, "read characteristics of region #0");
+
+	addr = REDIST_REGION_ATTR_ADDR(0, 0, 0, 1);
+	expected_addr = REDIST_REGION_ATTR_ADDR(1, 0x240000, 0, 1);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, false);
+	TEST_ASSERT(!ret && addr == expected_addr, "read characteristics of region #1");
+
+	addr = REDIST_REGION_ATTR_ADDR(0, 0, 0, 2);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, false);
+	TEST_ASSERT(ret && errno == ENOENT, "read characteristics of non existing region");
+
+	addr = 0x260000;
+	kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true);
+
+	addr = REDIST_REGION_ATTR_ADDR(1, 0x260000, 0, 2);
+	ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "register redist region colliding with dist");
+}
+
+/*
+ * VGIC KVM device is created and initialized before the secondary CPUs
+ * get created
+ */
+static void test_vgic_then_vcpus(void)
+{
+	struct vm_gic v;
+	int ret, i;
+
+	v.vm = vm_create_default(0, 0, guest_code);
+	v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+
+	subtest_dist_rdist(&v);
+
+	/* Add the rest of the VCPUs */
+	for (i = 1; i < NR_VCPUS; ++i)
+		vm_vcpu_add_default(v.vm, i, guest_code);
+
+	ret = run_vcpu(v.vm, 3);
+	TEST_ASSERT(ret == -EINVAL, "dist/rdist overlap detected on 1st vcpu run");
+
+	vm_gic_destroy(&v);
+}
+
+/* All the VCPUs are created before the VGIC KVM device gets initialized */
+static void test_vcpus_then_vgic(void)
+{
+	struct vm_gic v;
+	int ret;
+
+	v = vm_gic_create();
+
+	subtest_dist_rdist(&v);
+
+	ret = run_vcpu(v.vm, 3);
+	TEST_ASSERT(ret == -EINVAL, "dist/rdist overlap detected on 1st vcpu run");
+
+	vm_gic_destroy(&v);
+}
+
+static void test_new_redist_regions(void)
+{
+	void *dummy = NULL;
+	struct vm_gic v;
+	uint64_t addr;
+	int ret;
+
+	v = vm_gic_create();
+	subtest_redist_regions(&v);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			  KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
+	ret = run_vcpu(v.vm, 3);
+	TEST_ASSERT(ret == -ENXIO, "running without sufficient number of rdists");
+	vm_gic_destroy(&v);
+
+	/* step2 */
+
+	v = vm_gic_create();
+	subtest_redist_regions(&v);
+
+	addr = REDIST_REGION_ATTR_ADDR(1, 0x280000, 0, 2);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	ret = run_vcpu(v.vm, 3);
+	TEST_ASSERT(ret == -EBUSY, "running without vgic explicit init");
+
+	vm_gic_destroy(&v);
+
+	/* step 3 */
+
+	v = vm_gic_create();
+	subtest_redist_regions(&v);
+
+	_kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, dummy, true);
+	TEST_ASSERT(ret && errno == EFAULT,
+		    "register a third region allowing to cover the 4 vcpus");
+
+	addr = REDIST_REGION_ATTR_ADDR(1, 0x280000, 0, 2);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			  KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
+	ret = run_vcpu(v.vm, 3);
+	TEST_ASSERT(!ret, "vcpu run");
+
+	vm_gic_destroy(&v);
+}
+
+static void test_typer_accesses(void)
+{
+	struct vm_gic v;
+	uint64_t addr;
+	uint32_t val;
+	int ret, i;
+
+	v.vm = vm_create_default(0, 0, guest_code);
+
+	v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+
+	vm_vcpu_add_default(v.vm, 3, guest_code);
+
+	ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+	TEST_ASSERT(ret && errno == EINVAL, "attempting to read GICR_TYPER of non created vcpu");
+
+	vm_vcpu_add_default(v.vm, 1, guest_code);
+
+	ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+	TEST_ASSERT(ret && errno == EBUSY, "read GICR_TYPER before GIC initialized");
+
+	vm_vcpu_add_default(v.vm, 2, guest_code);
+
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			  KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
+	for (i = 0; i < NR_VCPUS ; i++) {
+		ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+		TEST_ASSERT(!ret && !val, "read GICR_TYPER before rdist region setting");
+	}
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 0);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	/* The 2 first rdists should be put there (vcpu 0 and 3) */
+	ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && !val, "read typer of rdist #0");
+
+	ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #1");
+
+	addr = REDIST_REGION_ATTR_ADDR(10, 0x100000, 0, 1);
+	ret = _kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+				 KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+	TEST_ASSERT(ret && errno == EINVAL, "collision with previous rdist region");
+
+	ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x100,
+		    "no redist region attached to vcpu #1 yet, last cannot be returned");
+
+	ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x200,
+		    "no redist region attached to vcpu #2, last cannot be returned");
+
+	addr = REDIST_REGION_ATTR_ADDR(10, 0x20000, 0, 1);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1");
+
+	ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x210,
+		    "read typer of rdist #1, last properly returned");
+
+	vm_gic_destroy(&v);
+}
+
+/**
+ * Test GICR_TYPER last bit with new redist regions
+ * rdist regions #1 and #2 are contiguous
+ * rdist region #0 @0x100000 2 rdist capacity
+ *     rdists: 0, 3 (Last)
+ * rdist region #1 @0x240000 2 rdist capacity
+ *     rdists:  5, 4 (Last)
+ * rdist region #2 @0x200000 2 rdist capacity
+ *     rdists: 1, 2
+ */
+static void test_last_bit_redist_regions(void)
+{
+	uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 };
+	struct vm_gic v;
+	uint64_t addr;
+	uint32_t val;
+	int ret;
+
+	v.vm = vm_create_default_with_vcpus(6, 0, 0, guest_code, vcpuids);
+
+	v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			  KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x100000, 0, 0);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x240000, 0, 1);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	addr = REDIST_REGION_ATTR_ADDR(2, 0x200000, 0, 2);
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+
+	ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0");
+
+	ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1");
+
+	ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x200, "read typer of rdist #2");
+
+	ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #3");
+
+	ret = access_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #5");
+
+	ret = access_redist_reg(v.gic_fd, 4, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x410, "read typer of rdist #4");
+
+	vm_gic_destroy(&v);
+}
+
+/* Test last bit with legacy region */
+static void test_last_bit_single_rdist(void)
+{
+	uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 };
+	struct vm_gic v;
+	uint64_t addr;
+	uint32_t val;
+	int ret;
+
+	v.vm = vm_create_default_with_vcpus(6, 0, 0, guest_code, vcpuids);
+
+	v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			  KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
+	addr = 0x10000;
+	kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			  KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+
+	ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0");
+
+	ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x300, "read typer of rdist #1");
+
+	ret = access_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #2");
+
+	ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #3");
+
+	ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+	TEST_ASSERT(!ret && val == 0x210, "read typer of rdist #3");
+
+	vm_gic_destroy(&v);
+}
+
+void test_kvm_device(void)
+{
+	struct vm_gic v;
+	int ret, fd;
+
+	v.vm = vm_create_default_with_vcpus(NR_VCPUS, 0, 0, guest_code, NULL);
+
+	/* try to create a non existing KVM device */
+	ret = _kvm_create_device(v.vm, 0, true, &fd);
+	TEST_ASSERT(ret && errno == ENODEV, "unsupported device");
+
+	/* trial mode with VGIC_V3 device */
+	ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, true, &fd);
+	if (ret) {
+		print_skip("GICv3 not supported");
+		exit(KSFT_SKIP);
+	}
+	v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+
+	ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false, &fd);
+	TEST_ASSERT(ret && errno == EEXIST, "create GICv3 device twice");
+
+	kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, true);
+
+	if (!_kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V2, true, &fd)) {
+		ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V2, false, &fd);
+		TEST_ASSERT(ret && errno == EINVAL, "create GICv2 while v3 exists");
+	}
+
+	vm_gic_destroy(&v);
+}
+
+int main(int ac, char **av)
+{
+	max_ipa_bits = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+	test_kvm_device();
+	test_vcpus_then_vgic();
+	test_vgic_then_vcpus();
+	test_new_redist_regions();
+	test_typer_accesses();
+	test_last_bit_redist_regions();
+	test_last_bit_single_rdist();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index bb2752d78fe3..81edbd23d371 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -17,6 +17,7 @@
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <asm/barrier.h>
+#include <linux/atomic.h>
 
 #include "kvm_util.h"
 #include "test_util.h"
@@ -137,12 +138,20 @@ static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
 /* Whether dirty ring reset is requested, or finished */
-static sem_t dirty_ring_vcpu_stop;
-static sem_t dirty_ring_vcpu_cont;
+static sem_t sem_vcpu_stop;
+static sem_t sem_vcpu_cont;
+/*
+ * This is only set by main thread, and only cleared by vcpu thread.  It is
+ * used to request vcpu thread to stop at the next GUEST_SYNC, since GUEST_SYNC
+ * is the only place that we'll guarantee both "dirty bit" and "dirty data"
+ * will match.  E.g., SIG_IPI won't guarantee that if the vcpu is interrupted
+ * after setting dirty bit but before the data is written.
+ */
+static atomic_t vcpu_sync_stop_requested;
 /*
  * This is updated by the vcpu thread to tell the host whether it's a
  * ring-full event.  It should only be read until a sem_wait() of
- * dirty_ring_vcpu_stop and before vcpu continues to run.
+ * sem_vcpu_stop and before vcpu continues to run.
  */
 static bool dirty_ring_vcpu_ring_full;
 /*
@@ -234,6 +243,17 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
 }
 
+/* Should only be called after a GUEST_SYNC */
+static void vcpu_handle_sync_stop(void)
+{
+	if (atomic_read(&vcpu_sync_stop_requested)) {
+		/* It means main thread is sleeping waiting */
+		atomic_set(&vcpu_sync_stop_requested, false);
+		sem_post(&sem_vcpu_stop);
+		sem_wait_until(&sem_vcpu_cont);
+	}
+}
+
 static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 {
 	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
@@ -244,6 +264,8 @@ static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
 		    "Invalid guest sync status: exit_reason=%s\n",
 		    exit_reason_str(run->exit_reason));
+
+	vcpu_handle_sync_stop();
 }
 
 static bool dirty_ring_supported(void)
@@ -301,13 +323,13 @@ static void dirty_ring_wait_vcpu(void)
 {
 	/* This makes sure that hardware PML cache flushed */
 	vcpu_kick();
-	sem_wait_until(&dirty_ring_vcpu_stop);
+	sem_wait_until(&sem_vcpu_stop);
 }
 
 static void dirty_ring_continue_vcpu(void)
 {
 	pr_info("Notifying vcpu to continue\n");
-	sem_post(&dirty_ring_vcpu_cont);
+	sem_post(&sem_vcpu_cont);
 }
 
 static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
@@ -361,11 +383,11 @@ static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 		/* Update the flag first before pause */
 		WRITE_ONCE(dirty_ring_vcpu_ring_full,
 			   run->exit_reason == KVM_EXIT_DIRTY_RING_FULL);
-		sem_post(&dirty_ring_vcpu_stop);
+		sem_post(&sem_vcpu_stop);
 		pr_info("vcpu stops because %s...\n",
 			dirty_ring_vcpu_ring_full ?
 			"dirty ring is full" : "vcpu is kicked out");
-		sem_wait_until(&dirty_ring_vcpu_cont);
+		sem_wait_until(&sem_vcpu_cont);
 		pr_info("vcpu continues now.\n");
 	} else {
 		TEST_ASSERT(false, "Invalid guest sync status: "
@@ -377,7 +399,7 @@ static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 static void dirty_ring_before_vcpu_join(void)
 {
 	/* Kick another round of vcpu just to make sure it will quit */
-	sem_post(&dirty_ring_vcpu_cont);
+	sem_post(&sem_vcpu_cont);
 }
 
 struct log_mode {
@@ -505,9 +527,8 @@ static void *vcpu_worker(void *data)
 	 */
 	sigmask->len = 8;
 	pthread_sigmask(0, NULL, sigset);
+	sigdelset(sigset, SIG_IPI);
 	vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask);
-	sigaddset(sigset, SIG_IPI);
-	pthread_sigmask(SIG_BLOCK, sigset, NULL);
 
 	sigemptyset(sigset);
 	sigaddset(sigset, SIG_IPI);
@@ -768,7 +789,25 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		usleep(p->interval * 1000);
 		log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
 					     bmap, host_num_pages);
+
+		/*
+		 * See vcpu_sync_stop_requested definition for details on why
+		 * we need to stop vcpu when verify data.
+		 */
+		atomic_set(&vcpu_sync_stop_requested, true);
+		sem_wait_until(&sem_vcpu_stop);
+		/*
+		 * NOTE: for dirty ring, it's possible that we didn't stop at
+		 * GUEST_SYNC but instead we stopped because ring is full;
+		 * that's okay too because ring full means we're only missing
+		 * the flush of the last page, and since we handle the last
+		 * page specially verification will succeed anyway.
+		 */
+		assert(host_log_mode == LOG_MODE_DIRTY_RING ||
+		       atomic_read(&vcpu_sync_stop_requested) == false);
 		vm_dirty_log_verify(mode, bmap);
+		sem_post(&sem_vcpu_cont);
+
 		iteration++;
 		sync_global_to_guest(vm, iteration);
 	}
@@ -818,9 +857,10 @@ int main(int argc, char *argv[])
 		.interval = TEST_HOST_LOOP_INTERVAL,
 	};
 	int opt, i;
+	sigset_t sigset;
 
-	sem_init(&dirty_ring_vcpu_stop, 0, 0);
-	sem_init(&dirty_ring_vcpu_cont, 0, 0);
+	sem_init(&sem_vcpu_stop, 0, 0);
+	sem_init(&sem_vcpu_cont, 0, 0);
 
 	guest_modes_append_default();
 
@@ -876,6 +916,11 @@ int main(int argc, char *argv[])
 
 	srandom(time(0));
 
+	/* Ensure that vCPU threads start with SIG_IPI blocked.  */
+	sigemptyset(&sigset);
+	sigaddset(&sigset, SIG_IPI);
+	pthread_sigmask(SIG_BLOCK, &sigset, NULL);
+
 	if (host_log_mode_option == LOG_MODE_ALL) {
 		/* Run each log mode */
 		for (i = 0; i < LOG_MODE_NUM; i++) {
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 0f4258eaa629..a8f022794ce3 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -69,9 +69,6 @@ enum vm_guest_mode {
 #define MIN_PAGE_SIZE		(1U << MIN_PAGE_SHIFT)
 #define PTES_PER_MIN_PAGE	ptes_per_page(MIN_PAGE_SIZE)
 
-#define vm_guest_mode_string(m) vm_guest_mode_string[m]
-extern const char * const vm_guest_mode_string[];
-
 struct vm_guest_mode_params {
 	unsigned int pa_bits;
 	unsigned int va_bits;
@@ -85,6 +82,7 @@ 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);
+const char *vm_guest_mode_string(uint32_t i);
 
 struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
 void kvm_vm_free(struct kvm_vm *vmp);
@@ -225,6 +223,15 @@ int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
 #endif
 void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
 
+int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
+int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
+int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd);
+int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test);
+int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+		       void *val, bool write);
+int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+		      void *val, bool write);
+
 const char *exit_reason_str(unsigned int exit_reason);
 
 void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index b7f41399f22c..fade3130eb01 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -71,13 +71,32 @@ enum vm_mem_backing_src_type {
 	VM_MEM_SRC_ANONYMOUS,
 	VM_MEM_SRC_ANONYMOUS_THP,
 	VM_MEM_SRC_ANONYMOUS_HUGETLB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB,
+	VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB,
+	NUM_SRC_TYPES,
 };
 
 struct vm_mem_backing_src_alias {
 	const char *name;
-	enum vm_mem_backing_src_type type;
+	uint32_t flag;
 };
 
+bool thp_configured(void);
+size_t get_trans_hugepagesz(void);
+size_t get_def_hugetlb_pagesz(void);
+const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
+size_t get_backing_src_pagesz(uint32_t i);
 void backing_src_help(void);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
new file mode 100644
index 000000000000..1c4753fff19e
--- /dev/null
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM page table test
+ *
+ * Copyright (C) 2021, Huawei, Inc.
+ *
+ * Make sure that THP has been enabled or enough HUGETLB pages with specific
+ * page size have been pre-allocated on your system, if you are planning to
+ * use hugepages to back the guest memory for testing.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <pthread.h>
+#include <semaphore.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "guest_modes.h"
+
+#define TEST_MEM_SLOT_INDEX             1
+
+/* Default size(1GB) of the memory for testing */
+#define DEFAULT_TEST_MEM_SIZE		(1 << 30)
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM		0xc0000000
+
+/* Different guest memory accessing stages */
+enum test_stage {
+	KVM_BEFORE_MAPPINGS,
+	KVM_CREATE_MAPPINGS,
+	KVM_UPDATE_MAPPINGS,
+	KVM_ADJUST_MAPPINGS,
+	NUM_TEST_STAGES,
+};
+
+static const char * const test_stage_string[] = {
+	"KVM_BEFORE_MAPPINGS",
+	"KVM_CREATE_MAPPINGS",
+	"KVM_UPDATE_MAPPINGS",
+	"KVM_ADJUST_MAPPINGS",
+};
+
+struct vcpu_args {
+	int vcpu_id;
+	bool vcpu_write;
+};
+
+struct test_args {
+	struct kvm_vm *vm;
+	uint64_t guest_test_virt_mem;
+	uint64_t host_page_size;
+	uint64_t host_num_pages;
+	uint64_t large_page_size;
+	uint64_t large_num_pages;
+	uint64_t host_pages_per_lpage;
+	enum vm_mem_backing_src_type src_type;
+	struct vcpu_args vcpu_args[KVM_MAX_VCPUS];
+};
+
+/*
+ * Guest variables. Use addr_gva2hva() if these variables need
+ * to be changed in host.
+ */
+static enum test_stage guest_test_stage;
+
+/* Host variables */
+static uint32_t nr_vcpus = 1;
+static struct test_args test_args;
+static enum test_stage *current_stage;
+static bool host_quit;
+
+/* Whether the test stage is updated, or completed */
+static sem_t test_stage_updated;
+static sem_t test_stage_completed;
+
+/*
+ * 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 void guest_code(int vcpu_id)
+{
+	struct test_args *p = &test_args;
+	struct vcpu_args *vcpu_args = &p->vcpu_args[vcpu_id];
+	enum test_stage *current_stage = &guest_test_stage;
+	uint64_t addr;
+	int i, j;
+
+	/* Make sure vCPU args data structure is not corrupt */
+	GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+	while (true) {
+		addr = p->guest_test_virt_mem;
+
+		switch (READ_ONCE(*current_stage)) {
+		/*
+		 * All vCPU threads will be started in this stage,
+		 * where guest code of each vCPU will do nothing.
+		 */
+		case KVM_BEFORE_MAPPINGS:
+			break;
+
+		/*
+		 * Before dirty logging, vCPUs concurrently access the first
+		 * 8 bytes of each page (host page/large page) within the same
+		 * memory region with different accessing types (read/write).
+		 * Then KVM will create normal page mappings or huge block
+		 * mappings for them.
+		 */
+		case KVM_CREATE_MAPPINGS:
+			for (i = 0; i < p->large_num_pages; i++) {
+				if (vcpu_args->vcpu_write)
+					*(uint64_t *)addr = 0x0123456789ABCDEF;
+				else
+					READ_ONCE(*(uint64_t *)addr);
+
+				addr += p->large_page_size;
+			}
+			break;
+
+		/*
+		 * During dirty logging, KVM will only update attributes of the
+		 * normal page mappings from RO to RW if memory backing src type
+		 * is anonymous. In other cases, KVM will split the huge block
+		 * mappings into normal page mappings if memory backing src type
+		 * is THP or HUGETLB.
+		 */
+		case KVM_UPDATE_MAPPINGS:
+			if (p->src_type == VM_MEM_SRC_ANONYMOUS) {
+				for (i = 0; i < p->host_num_pages; i++) {
+					*(uint64_t *)addr = 0x0123456789ABCDEF;
+					addr += p->host_page_size;
+				}
+				break;
+			}
+
+			for (i = 0; i < p->large_num_pages; i++) {
+				/*
+				 * Write to the first host page in each large
+				 * page region, and triger break of large pages.
+				 */
+				*(uint64_t *)addr = 0x0123456789ABCDEF;
+
+				/*
+				 * Access the middle host pages in each large
+				 * page region. Since dirty logging is enabled,
+				 * this will create new mappings at the smallest
+				 * granularity.
+				 */
+				addr += p->large_page_size / 2;
+				for (j = 0; j < p->host_pages_per_lpage / 2; j++) {
+					READ_ONCE(*(uint64_t *)addr);
+					addr += p->host_page_size;
+				}
+			}
+			break;
+
+		/*
+		 * After dirty logging is stopped, vCPUs concurrently read
+		 * from every single host page. Then KVM will coalesce the
+		 * split page mappings back to block mappings. And a TLB
+		 * conflict abort could occur here if TLB entries of the
+		 * page mappings are not fully invalidated.
+		 */
+		case KVM_ADJUST_MAPPINGS:
+			for (i = 0; i < p->host_num_pages; i++) {
+				READ_ONCE(*(uint64_t *)addr);
+				addr += p->host_page_size;
+			}
+			break;
+
+		default:
+			GUEST_ASSERT(0);
+		}
+
+		GUEST_SYNC(1);
+	}
+}
+
+static void *vcpu_worker(void *data)
+{
+	int ret;
+	struct vcpu_args *vcpu_args = data;
+	struct kvm_vm *vm = test_args.vm;
+	int vcpu_id = vcpu_args->vcpu_id;
+	struct kvm_run *run;
+	struct timespec start;
+	struct timespec ts_diff;
+	enum test_stage stage;
+
+	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+	run = vcpu_state(vm, vcpu_id);
+
+	while (!READ_ONCE(host_quit)) {
+		ret = sem_wait(&test_stage_updated);
+		TEST_ASSERT(ret == 0, "Error in sem_wait");
+
+		if (READ_ONCE(host_quit))
+			return NULL;
+
+		clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+		ret = _vcpu_run(vm, vcpu_id);
+		ts_diff = timespec_elapsed(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);
+		stage = READ_ONCE(*current_stage);
+
+		/*
+		 * Here we can know the execution time of every
+		 * single vcpu running in different test stages.
+		 */
+		pr_debug("vCPU %d has completed stage %s\n"
+			 "execution time is: %ld.%.9lds\n\n",
+			 vcpu_id, test_stage_string[stage],
+			 ts_diff.tv_sec, ts_diff.tv_nsec);
+
+		ret = sem_post(&test_stage_completed);
+		TEST_ASSERT(ret == 0, "Error in sem_post");
+	}
+
+	return NULL;
+}
+
+struct test_params {
+	uint64_t phys_offset;
+	uint64_t test_mem_size;
+	enum vm_mem_backing_src_type src_type;
+};
+
+static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
+{
+	int ret;
+	struct test_params *p = arg;
+	struct vcpu_args *vcpu_args;
+	enum vm_mem_backing_src_type src_type = p->src_type;
+	uint64_t large_page_size = get_backing_src_pagesz(src_type);
+	uint64_t guest_page_size = vm_guest_mode_params[mode].page_size;
+	uint64_t host_page_size = getpagesize();
+	uint64_t test_mem_size = p->test_mem_size;
+	uint64_t guest_num_pages;
+	uint64_t alignment;
+	void *host_test_mem;
+	struct kvm_vm *vm;
+	int vcpu_id;
+
+	/* Align up the test memory size */
+	alignment = max(large_page_size, guest_page_size);
+	test_mem_size = (test_mem_size + alignment - 1) & ~(alignment - 1);
+
+	/* Create a VM with enough guest pages */
+	guest_num_pages = test_mem_size / guest_page_size;
+	vm = vm_create_with_vcpus(mode, nr_vcpus,
+				  guest_num_pages, 0, guest_code, NULL);
+
+	/* Align down GPA of the testing memslot */
+	if (!p->phys_offset)
+		guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+				       guest_page_size;
+	else
+		guest_test_phys_mem = p->phys_offset;
+#ifdef __s390x__
+	alignment = max(0x100000, alignment);
+#endif
+	guest_test_phys_mem &= ~(alignment - 1);
+
+	/* Set up the shared data structure test_args */
+	test_args.vm = vm;
+	test_args.guest_test_virt_mem = guest_test_virt_mem;
+	test_args.host_page_size = host_page_size;
+	test_args.host_num_pages = test_mem_size / host_page_size;
+	test_args.large_page_size = large_page_size;
+	test_args.large_num_pages = test_mem_size / large_page_size;
+	test_args.host_pages_per_lpage = large_page_size / host_page_size;
+	test_args.src_type = src_type;
+
+	for (vcpu_id = 0; vcpu_id < KVM_MAX_VCPUS; vcpu_id++) {
+		vcpu_args = &test_args.vcpu_args[vcpu_id];
+		vcpu_args->vcpu_id = vcpu_id;
+		vcpu_args->vcpu_write = !(vcpu_id % 2);
+	}
+
+	/* Add an extra memory slot with specified backing src type */
+	vm_userspace_mem_region_add(vm, src_type, guest_test_phys_mem,
+				    TEST_MEM_SLOT_INDEX, guest_num_pages, 0);
+
+	/* Do mapping(GVA->GPA) for the testing memory slot */
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+	/* Cache the HVA pointer of the region */
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
+
+	/* Export shared structure test_args to guest */
+	ucall_init(vm, NULL);
+	sync_global_to_guest(vm, test_args);
+
+	ret = sem_init(&test_stage_updated, 0, 0);
+	TEST_ASSERT(ret == 0, "Error in sem_init");
+
+	ret = sem_init(&test_stage_completed, 0, 0);
+	TEST_ASSERT(ret == 0, "Error in sem_init");
+
+	current_stage = addr_gva2hva(vm, (vm_vaddr_t)(&guest_test_stage));
+	*current_stage = NUM_TEST_STAGES;
+
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+	pr_info("Testing memory backing src type: %s\n",
+		vm_mem_backing_src_alias(src_type)->name);
+	pr_info("Testing memory backing src granularity: 0x%lx\n",
+		large_page_size);
+	pr_info("Testing memory size(aligned): 0x%lx\n", test_mem_size);
+	pr_info("Guest physical test memory offset: 0x%lx\n",
+		guest_test_phys_mem);
+	pr_info("Host  virtual  test memory offset: 0x%lx\n",
+		(uint64_t)host_test_mem);
+	pr_info("Number of testing vCPUs: %d\n", nr_vcpus);
+
+	return vm;
+}
+
+static void vcpus_complete_new_stage(enum test_stage stage)
+{
+	int ret;
+	int vcpus;
+
+	/* Wake up all the vcpus to run new test stage */
+	for (vcpus = 0; vcpus < nr_vcpus; vcpus++) {
+		ret = sem_post(&test_stage_updated);
+		TEST_ASSERT(ret == 0, "Error in sem_post");
+	}
+	pr_debug("All vcpus have been notified to continue\n");
+
+	/* Wait for all the vcpus to complete new test stage */
+	for (vcpus = 0; vcpus < nr_vcpus; vcpus++) {
+		ret = sem_wait(&test_stage_completed);
+		TEST_ASSERT(ret == 0, "Error in sem_wait");
+
+		pr_debug("%d vcpus have completed stage %s\n",
+			 vcpus + 1, test_stage_string[stage]);
+	}
+
+	pr_debug("All vcpus have completed stage %s\n",
+		 test_stage_string[stage]);
+}
+
+static void run_test(enum vm_guest_mode mode, void *arg)
+{
+	int ret;
+	pthread_t *vcpu_threads;
+	struct kvm_vm *vm;
+	int vcpu_id;
+	struct timespec start;
+	struct timespec ts_diff;
+
+	/* Create VM with vCPUs and make some pre-initialization */
+	vm = pre_init_before_test(mode, arg);
+
+	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
+	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+
+	host_quit = false;
+	*current_stage = KVM_BEFORE_MAPPINGS;
+
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
+			       &test_args.vcpu_args[vcpu_id]);
+	}
+
+	vcpus_complete_new_stage(*current_stage);
+	pr_info("Started all vCPUs successfully\n");
+
+	/* Test the stage of KVM creating mappings */
+	*current_stage = KVM_CREATE_MAPPINGS;
+
+	clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+	vcpus_complete_new_stage(*current_stage);
+	ts_diff = timespec_elapsed(start);
+
+	pr_info("KVM_CREATE_MAPPINGS: total execution time: %ld.%.9lds\n\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	/* Test the stage of KVM updating mappings */
+	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+				KVM_MEM_LOG_DIRTY_PAGES);
+
+	*current_stage = KVM_UPDATE_MAPPINGS;
+
+	clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+	vcpus_complete_new_stage(*current_stage);
+	ts_diff = timespec_elapsed(start);
+
+	pr_info("KVM_UPDATE_MAPPINGS: total execution time: %ld.%.9lds\n\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	/* Test the stage of KVM adjusting mappings */
+	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+
+	*current_stage = KVM_ADJUST_MAPPINGS;
+
+	clock_gettime(CLOCK_MONOTONIC_RAW, &start);
+	vcpus_complete_new_stage(*current_stage);
+	ts_diff = timespec_elapsed(start);
+
+	pr_info("KVM_ADJUST_MAPPINGS: total execution time: %ld.%.9lds\n\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		ret = sem_post(&test_stage_updated);
+		TEST_ASSERT(ret == 0, "Error in sem_post");
+	}
+
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id], NULL);
+
+	ret = sem_destroy(&test_stage_updated);
+	TEST_ASSERT(ret == 0, "Error in sem_destroy");
+
+	ret = sem_destroy(&test_stage_completed);
+	TEST_ASSERT(ret == 0, "Error in sem_destroy");
+
+	free(vcpu_threads);
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+}
+
+static void help(char *name)
+{
+	puts("");
+	printf("usage: %s [-h] [-p offset] [-m mode] "
+	       "[-b mem-size] [-v vcpus] [-s mem-type]\n", name);
+	puts("");
+	printf(" -p: specify guest physical test memory offset\n"
+	       "     Warning: a low offset can conflict with the loaded test code.\n");
+	guest_modes_help();
+	printf(" -b: specify size of the memory region for testing. e.g. 10M or 3G.\n"
+	       "     (default: 1G)\n");
+	printf(" -v: specify the number of vCPUs to run\n"
+	       "     (default: 1)\n");
+	printf(" -s: specify the type of memory that should be used to\n"
+	       "     back the guest data region.\n"
+	       "     (default: anonymous)\n\n");
+	backing_src_help();
+	puts("");
+}
+
+int main(int argc, char *argv[])
+{
+	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+	struct test_params p = {
+		.test_mem_size = DEFAULT_TEST_MEM_SIZE,
+		.src_type = VM_MEM_SRC_ANONYMOUS,
+	};
+	int opt;
+
+	guest_modes_append_default();
+
+	while ((opt = getopt(argc, argv, "hp:m:b:v:s:")) != -1) {
+		switch (opt) {
+		case 'p':
+			p.phys_offset = strtoull(optarg, NULL, 0);
+			break;
+		case 'm':
+			guest_modes_cmdline(optarg);
+			break;
+		case 'b':
+			p.test_mem_size = parse_size(optarg);
+			break;
+		case 'v':
+			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 's':
+			p.src_type = parse_backing_src_type(optarg);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			exit(0);
+		}
+	}
+
+	for_each_guest_mode(run_test, &p);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index 5ebbd0d6b472..71ade6100fd3 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -71,9 +71,9 @@ test_assert(bool exp, const char *exp_str,
 
 		fprintf(stderr, "==== Test Assertion Failure ====\n"
 			"  %s:%u: %s\n"
-			"  pid=%d tid=%d - %s\n",
+			"  pid=%d tid=%d errno=%d - %s\n",
 			file, line, exp_str, getpid(), _gettid(),
-			strerror(errno));
+			errno, strerror(errno));
 		test_dump_stack();
 		if (fmt) {
 			fputs("  ", stderr);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b8849a1aca79..fc83f6c5902d 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -18,7 +18,6 @@
 #include <unistd.h>
 #include <linux/kernel.h>
 
-#define KVM_UTIL_PGS_PER_HUGEPG 512
 #define KVM_UTIL_MIN_PFN	2
 
 static int vcpu_mmap_sz(void);
@@ -143,17 +142,24 @@ static void vm_open(struct kvm_vm *vm, int perm)
 		"rc: %i errno: %i", vm->fd, errno);
 }
 
-const char * const vm_guest_mode_string[] = {
-	"PA-bits:52,  VA-bits:48,  4K pages",
-	"PA-bits:52,  VA-bits:48, 64K pages",
-	"PA-bits:48,  VA-bits:48,  4K pages",
-	"PA-bits:48,  VA-bits:48, 64K pages",
-	"PA-bits:40,  VA-bits:48,  4K pages",
-	"PA-bits:40,  VA-bits:48, 64K pages",
-	"PA-bits:ANY, VA-bits:48,  4K pages",
-};
-_Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
-	       "Missing new mode strings?");
+const char *vm_guest_mode_string(uint32_t i)
+{
+	static const char * const strings[] = {
+		[VM_MODE_P52V48_4K]	= "PA-bits:52,  VA-bits:48,  4K pages",
+		[VM_MODE_P52V48_64K]	= "PA-bits:52,  VA-bits:48, 64K pages",
+		[VM_MODE_P48V48_4K]	= "PA-bits:48,  VA-bits:48,  4K pages",
+		[VM_MODE_P48V48_64K]	= "PA-bits:48,  VA-bits:48, 64K pages",
+		[VM_MODE_P40V48_4K]	= "PA-bits:40,  VA-bits:48,  4K pages",
+		[VM_MODE_P40V48_64K]	= "PA-bits:40,  VA-bits:48, 64K pages",
+		[VM_MODE_PXXV48_4K]	= "PA-bits:ANY, VA-bits:48,  4K pages",
+	};
+	_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
+		       "Missing new mode strings?");
+
+	TEST_ASSERT(i < NUM_VM_MODES, "Guest mode ID %d too big", i);
+
+	return strings[i];
+}
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	{ 52, 48,  0x1000, 12 },
@@ -514,7 +520,7 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu)
 	ret = munmap(vcpu->state, vcpu_mmap_sz());
 	TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i "
 		"errno: %i", ret, errno);
-	close(vcpu->fd);
+	ret = close(vcpu->fd);
 	TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i "
 		"errno: %i", ret, errno);
 
@@ -534,7 +540,7 @@ void kvm_vm_release(struct kvm_vm *vmp)
 	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
 		"  vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno);
 
-	close(vmp->kvm_fd);
+	ret = close(vmp->kvm_fd);
 	TEST_ASSERT(ret == 0, "Close of /dev/kvm fd failed,\n"
 		"  vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno);
 }
@@ -681,7 +687,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 {
 	int ret;
 	struct userspace_mem_region *region;
-	size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size;
+	size_t backing_src_pagesz = get_backing_src_pagesz(src_type);
 	size_t alignment;
 
 	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
@@ -743,7 +749,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 #endif
 
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
-		alignment = max(huge_page_size, alignment);
+		alignment = max(backing_src_pagesz, alignment);
 
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
@@ -752,7 +758,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	region->mmap_start = mmap(NULL, region->mmap_size,
 				  PROT_READ | PROT_WRITE,
 				  MAP_PRIVATE | MAP_ANONYMOUS
-				  | (src_type == VM_MEM_SRC_ANONYMOUS_HUGETLB ? MAP_HUGETLB : 0),
+				  | vm_mem_backing_src_alias(src_type)->flag,
 				  -1, 0);
 	TEST_ASSERT(region->mmap_start != MAP_FAILED,
 		    "test_malloc failed, mmap_start: %p errno: %i",
@@ -762,22 +768,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	region->host_mem = align(region->mmap_start, alignment);
 
 	/* As needed perform madvise */
-	if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) {
-		struct stat statbuf;
-
-		ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
-		TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
-			    "stat /sys/kernel/mm/transparent_hugepage");
-
-		TEST_ASSERT(ret == 0 || src_type != VM_MEM_SRC_ANONYMOUS_THP,
-			    "VM_MEM_SRC_ANONYMOUS_THP requires THP to be configured in the host kernel");
-
-		if (ret == 0) {
-			ret = madvise(region->host_mem, npages * vm->page_size,
-				      src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
-			TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %x",
-				    region->host_mem, npages * vm->page_size, src_type);
-		}
+	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
+	     src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) {
+		ret = madvise(region->host_mem, npages * vm->page_size,
+			      src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
+		TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s",
+			    region->host_mem, npages * vm->page_size,
+			    vm_mem_backing_src_alias(src_type)->name);
 	}
 
 	region->unused_phy_pages = sparsebit_alloc();
@@ -1734,6 +1731,81 @@ int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
 }
 
 /*
+ * Device Ioctl
+ */
+
+int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr)
+{
+	struct kvm_device_attr attribute = {
+		.group = group,
+		.attr = attr,
+		.flags = 0,
+	};
+
+	return ioctl(dev_fd, KVM_HAS_DEVICE_ATTR, &attribute);
+}
+
+int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr)
+{
+	int ret = _kvm_device_check_attr(dev_fd, group, attr);
+
+	TEST_ASSERT(ret >= 0, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno);
+	return ret;
+}
+
+int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd)
+{
+	struct kvm_create_device create_dev;
+	int ret;
+
+	create_dev.type = type;
+	create_dev.fd = -1;
+	create_dev.flags = test ? KVM_CREATE_DEVICE_TEST : 0;
+	ret = ioctl(vm_get_fd(vm), KVM_CREATE_DEVICE, &create_dev);
+	*fd = create_dev.fd;
+	return ret;
+}
+
+int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test)
+{
+	int fd, ret;
+
+	ret = _kvm_create_device(vm, type, test, &fd);
+
+	if (!test) {
+		TEST_ASSERT(ret >= 0,
+			    "KVM_CREATE_DEVICE IOCTL failed, rc: %i errno: %i", ret, errno);
+		return fd;
+	}
+	return ret;
+}
+
+int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+		      void *val, bool write)
+{
+	struct kvm_device_attr kvmattr = {
+		.group = group,
+		.attr = attr,
+		.flags = 0,
+		.addr = (uintptr_t)val,
+	};
+	int ret;
+
+	ret = ioctl(dev_fd, write ? KVM_SET_DEVICE_ATTR : KVM_GET_DEVICE_ATTR,
+		    &kvmattr);
+	return ret;
+}
+
+int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+		      void *val, bool write)
+{
+	int ret = _kvm_device_access(dev_fd, group, attr, val, write);
+
+	TEST_ASSERT(ret >= 0, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno);
+	return ret;
+}
+
+/*
  * VM Dump
  *
  * Input Args:
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 906c955384e2..63d2bc7d757b 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -10,6 +10,8 @@
 #include <limits.h>
 #include <stdlib.h>
 #include <time.h>
+#include <sys/stat.h>
+#include <linux/mman.h>
 #include "linux/kernel.h"
 
 #include "test_util.h"
@@ -111,28 +113,169 @@ void print_skip(const char *fmt, ...)
 	puts(", skipping test");
 }
 
-const struct vm_mem_backing_src_alias backing_src_aliases[] = {
-	{"anonymous", VM_MEM_SRC_ANONYMOUS,},
-	{"anonymous_thp", VM_MEM_SRC_ANONYMOUS_THP,},
-	{"anonymous_hugetlb", VM_MEM_SRC_ANONYMOUS_HUGETLB,},
-};
+bool thp_configured(void)
+{
+	int ret;
+	struct stat statbuf;
+
+	ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
+	TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
+		    "Error in stating /sys/kernel/mm/transparent_hugepage");
+
+	return ret == 0;
+}
+
+size_t get_trans_hugepagesz(void)
+{
+	size_t size;
+	FILE *f;
+
+	TEST_ASSERT(thp_configured(), "THP is not configured in host kernel");
+
+	f = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r");
+	TEST_ASSERT(f != NULL, "Error in opening transparent_hugepage/hpage_pmd_size");
+
+	fscanf(f, "%ld", &size);
+	fclose(f);
+
+	return size;
+}
+
+size_t get_def_hugetlb_pagesz(void)
+{
+	char buf[64];
+	const char *tag = "Hugepagesize:";
+	FILE *f;
+
+	f = fopen("/proc/meminfo", "r");
+	TEST_ASSERT(f != NULL, "Error in opening /proc/meminfo");
+
+	while (fgets(buf, sizeof(buf), f) != NULL) {
+		if (strstr(buf, tag) == buf) {
+			fclose(f);
+			return strtoull(buf + strlen(tag), NULL, 10) << 10;
+		}
+	}
+
+	if (feof(f))
+		TEST_FAIL("HUGETLB is not configured in host kernel");
+	else
+		TEST_FAIL("Error in reading /proc/meminfo");
+
+	fclose(f);
+	return 0;
+}
+
+const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i)
+{
+	static const struct vm_mem_backing_src_alias aliases[] = {
+		[VM_MEM_SRC_ANONYMOUS] = {
+			.name = "anonymous",
+			.flag = 0,
+		},
+		[VM_MEM_SRC_ANONYMOUS_THP] = {
+			.name = "anonymous_thp",
+			.flag = 0,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB] = {
+			.name = "anonymous_hugetlb",
+			.flag = MAP_HUGETLB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = {
+			.name = "anonymous_hugetlb_16kb",
+			.flag = MAP_HUGETLB | MAP_HUGE_16KB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = {
+			.name = "anonymous_hugetlb_64kb",
+			.flag = MAP_HUGETLB | MAP_HUGE_64KB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = {
+			.name = "anonymous_hugetlb_512kb",
+			.flag = MAP_HUGETLB | MAP_HUGE_512KB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = {
+			.name = "anonymous_hugetlb_1mb",
+			.flag = MAP_HUGETLB | MAP_HUGE_1MB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = {
+			.name = "anonymous_hugetlb_2mb",
+			.flag = MAP_HUGETLB | MAP_HUGE_2MB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = {
+			.name = "anonymous_hugetlb_8mb",
+			.flag = MAP_HUGETLB | MAP_HUGE_8MB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = {
+			.name = "anonymous_hugetlb_16mb",
+			.flag = MAP_HUGETLB | MAP_HUGE_16MB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = {
+			.name = "anonymous_hugetlb_32mb",
+			.flag = MAP_HUGETLB | MAP_HUGE_32MB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = {
+			.name = "anonymous_hugetlb_256mb",
+			.flag = MAP_HUGETLB | MAP_HUGE_256MB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = {
+			.name = "anonymous_hugetlb_512mb",
+			.flag = MAP_HUGETLB | MAP_HUGE_512MB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = {
+			.name = "anonymous_hugetlb_1gb",
+			.flag = MAP_HUGETLB | MAP_HUGE_1GB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = {
+			.name = "anonymous_hugetlb_2gb",
+			.flag = MAP_HUGETLB | MAP_HUGE_2GB,
+		},
+		[VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = {
+			.name = "anonymous_hugetlb_16gb",
+			.flag = MAP_HUGETLB | MAP_HUGE_16GB,
+		},
+	};
+	_Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES,
+		       "Missing new backing src types?");
+
+	TEST_ASSERT(i < NUM_SRC_TYPES, "Backing src type ID %d too big", i);
+
+	return &aliases[i];
+}
+
+#define MAP_HUGE_PAGE_SIZE(x) (1ULL << ((x >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK))
+
+size_t get_backing_src_pagesz(uint32_t i)
+{
+	uint32_t flag = vm_mem_backing_src_alias(i)->flag;
+
+	switch (i) {
+	case VM_MEM_SRC_ANONYMOUS:
+		return getpagesize();
+	case VM_MEM_SRC_ANONYMOUS_THP:
+		return get_trans_hugepagesz();
+	case VM_MEM_SRC_ANONYMOUS_HUGETLB:
+		return get_def_hugetlb_pagesz();
+	default:
+		return MAP_HUGE_PAGE_SIZE(flag);
+	}
+}
 
 void backing_src_help(void)
 {
 	int i;
 
 	printf("Available backing src types:\n");
-	for (i = 0; i < ARRAY_SIZE(backing_src_aliases); i++)
-		printf("\t%s\n", backing_src_aliases[i].name);
+	for (i = 0; i < NUM_SRC_TYPES; i++)
+		printf("\t%s\n", vm_mem_backing_src_alias(i)->name);
 }
 
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(backing_src_aliases); i++)
-		if (!strcmp(type_name, backing_src_aliases[i].name))
-			return backing_src_aliases[i].type;
+	for (i = 0; i < NUM_SRC_TYPES; i++)
+		if (!strcmp(type_name, vm_mem_backing_src_alias(i)->name))
+			return i;
 
 	backing_src_help();
 	TEST_FAIL("Unknown backing src type: %s", type_name);
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index f127ed31dba7..978f5b5f4dc0 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -329,6 +329,22 @@ static void test_zero_memory_regions(void)
 }
 #endif /* __x86_64__ */
 
+static int test_memory_region_add(struct kvm_vm *vm, void *mem, uint32_t slot,
+				   uint32_t size, uint64_t guest_addr)
+{
+	struct kvm_userspace_memory_region region;
+	int ret;
+
+	region.slot = slot;
+	region.flags = 0;
+	region.guest_phys_addr = guest_addr;
+	region.memory_size = size;
+	region.userspace_addr = (uintptr_t) mem;
+	ret = ioctl(vm_get_fd(vm), KVM_SET_USER_MEMORY_REGION, &region);
+
+	return ret;
+}
+
 /*
  * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any
  * tentative to add further slots should fail.
@@ -339,9 +355,15 @@ static void test_add_max_memory_regions(void)
 	struct kvm_vm *vm;
 	uint32_t max_mem_slots;
 	uint32_t slot;
-	uint64_t guest_addr = 0x0;
-	uint64_t mem_reg_npages;
-	void *mem;
+	void *mem, *mem_aligned, *mem_extra;
+	size_t alignment;
+
+#ifdef __s390x__
+	/* On s390x, the host address must be aligned to 1M (due to PGSTEs) */
+	alignment = 0x100000;
+#else
+	alignment = 1;
+#endif
 
 	max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS);
 	TEST_ASSERT(max_mem_slots > 0,
@@ -350,30 +372,37 @@ static void test_add_max_memory_regions(void)
 
 	vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
 
-	mem_reg_npages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, MEM_REGION_SIZE);
-
 	/* Check it can be added memory slots up to the maximum allowed */
 	pr_info("Adding slots 0..%i, each memory region with %dK size\n",
 		(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
+
+	mem = mmap(NULL, MEM_REGION_SIZE * max_mem_slots + alignment,
+		   PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
+	mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
+
 	for (slot = 0; slot < max_mem_slots; slot++) {
-		vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-					    guest_addr, slot, mem_reg_npages,
-					    0);
-		guest_addr += MEM_REGION_SIZE;
+		ret = test_memory_region_add(vm, mem_aligned +
+					     ((uint64_t)slot * MEM_REGION_SIZE),
+					     slot, MEM_REGION_SIZE,
+					     (uint64_t)slot * MEM_REGION_SIZE);
+		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+			    "  rc: %i errno: %i slot: %i\n",
+			    ret, errno, slot);
 	}
 
 	/* Check it cannot be added memory slots beyond the limit */
-	mem = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE,
-		   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
-	TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
+	mem_extra = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE,
+			 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	TEST_ASSERT(mem_extra != MAP_FAILED, "Failed to mmap() host");
 
-	ret = ioctl(vm_get_fd(vm), KVM_SET_USER_MEMORY_REGION,
-		    &(struct kvm_userspace_memory_region) {slot, 0, guest_addr,
-		    MEM_REGION_SIZE, (uint64_t) mem});
+	ret = test_memory_region_add(vm, mem_extra, max_mem_slots, MEM_REGION_SIZE,
+				     (uint64_t)max_mem_slots * MEM_REGION_SIZE);
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
 		    "Adding one more memory slot should fail with EINVAL");
 
-	munmap(mem, MEM_REGION_SIZE);
+	munmap(mem, MEM_REGION_SIZE * max_mem_slots + alignment);
+	munmap(mem_extra, MEM_REGION_SIZE);
 	kvm_vm_free(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 804ff5ff022d..1f4a0599683c 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -186,7 +186,7 @@ int main(int argc, char *argv[])
 		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
 	}
 
-	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);;
+	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
 	rs->state = 0x5a;
 
 	for (;;) {